CN110084481A - Monitor the method, apparatus and server of vehicle-state - Google Patents
Monitor the method, apparatus and server of vehicle-state Download PDFInfo
- Publication number
- CN110084481A CN110084481A CN201910251192.6A CN201910251192A CN110084481A CN 110084481 A CN110084481 A CN 110084481A CN 201910251192 A CN201910251192 A CN 201910251192A CN 110084481 A CN110084481 A CN 110084481A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- state
- training sample
- server
- monitored
- 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.)
- Pending
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of method, apparatus and server for monitoring vehicle-state, this method comprises: obtaining vehicle to be monitored for the vector value of described eigenvector according to the feature vector of the reflection vehicle-state of setting；According to the mapping relations between the vector value and described eigenvector and the vehicle-state, the vehicle-state of the vehicle to be monitored is obtained；When the vehicle-state of the vehicle to be monitored meets the condition wait intervene, marking the vehicle is vehicle to be intervened.
Description
Technical field
The present invention relates to vehicle state monitoring technical fields, more particularly, to a kind of method for monitoring vehicle-state, one
The device and a kind of server of kind monitoring vehicle-state.
Background technique
Currently, having become trip mode emerging in city by shared vehicle driving, urban human can be effectively solved
The trip requirements of group.And as the userbase of shared vehicle is increasingly huge, the injected volume of shared vehicle is also being continuously increased, from
And can not the vehicle-state to each vehicle to be monitored accurately monitored.
Currently, the platform side of shared vehicle is mainly the vehicle-state of the vehicle to be monitored fed back according to personnel under line, uses
Vehicle-state of vehicle to be monitored that family reports etc. obtains the vehicle-state of vehicle to be monitored, however, this kind of monitoring vehicle shape
Therefore the method for state, has dependent on human factor to can not accurately obtain the vehicle-state of each vehicle to be monitored
Necessity provides a kind of technical solution for monitoring vehicle-state.
Summary of the invention
One purpose of the embodiment of the present invention is to provide a kind of for monitoring the new solution of vehicle-state.
According to the first aspect of the invention, a kind of method for monitoring vehicle-state is provided, comprising:
According to the feature vector of the reflection vehicle-state of setting, vehicle to be monitored is obtained for described eigenvector
Vector value；
According to the mapping relations between the vector value and described eigenvector and the vehicle-state, obtain described to be monitored
The vehicle-state of vehicle；
When the vehicle-state of the vehicle to be monitored meets the condition wait intervene, marking the vehicle is vehicle to be intervened
?.
Optionally, described eigenvector includes the interaction feature and vehicle between vehicle parameter feature, vehicle and user
An at least category feature in stand feature.
Optionally, the vehicle-state includes the health status of vehicle, and the condition to be intervened includes the healthy shape
State is malfunction.
Optionally, the method also includes:
In response to the monitor event of setting, the feature vector of the reflection vehicle-state according to setting is executed, is obtained
Take the operation of the vector value of the corresponding described eigenvector of vehicle to be monitored.
Optionally, the method also includes:
Obtain selected target area；
Search is located at the vehicle in the target area as the vehicle to be monitored.
Optionally, the method also includes:
Obtain the quantity for the vehicle to be intervened that the target area has；
According to the quantity, vehicle scheduling is carried out to the target area.
Optionally, the method also includes:
For the vehicle to be intervened, intervention instruction is sent to terminal is intervened；Wherein, the intervention prompt carries described
The stand of the car number of vehicle to be intervened and the vehicle to be intervened.
Optionally, the mapping relations are mapping function, the step of the mapping function described the method also includes training, packet
It includes:
The accurate vehicle of the vehicle-state is obtained as training sample；
According to the training sample for the vector value and the corresponding vehicle-state of the training sample of described eigenvector,
Obtain the mapping function.
It is optionally, described to obtain the step of accurate vehicle of vehicle-state is as training sample, comprising:
The accurate vehicle of vehicle-state for obtaining the first setting quantity, as the first training sample；
The vehicle for obtaining the second setting quantity, as the second training sample；
Second training sample is clustered according to first training sample, is obtained in second training sample
The vehicle-state of each vehicle；
Using second training sample after first training sample and cluster as the training sample.
Optionally, the method also includes:
The accurate vehicle of vehicle-state is obtained, as verifying sample；
According to the mapping relations, the vehicle-state of each vehicle in the verifying sample is obtained as prediction vehicle shape
State；
The prediction vehicle-state of each vehicle in the verifying sample is compared with the actual vehicle state of corresponding vehicle,
Obtain the judge value of the mapping relations；
According to the judge value, judge whether the mapping relations are effective；
In the effective situation of the mapping relations, then execute described according to the vector value and described eigenvector and institute
The step of stating the mapping relations between vehicle-state, obtaining the vehicle-state of the vehicle to be monitored.
Optionally, the method also includes:
In the case where the mapping relations are invalid, the mapping is obtained by adjusting described eigenvector and for training
At least one of in the sample size of the training sample of relationship, re -training obtains the mapping relations, wherein the training sample
For the accurate vehicle of the vehicle-state.
According to the second aspect of the invention, a kind of device for monitoring vehicle-state is additionally provided comprising:
First obtains module, for the feature vector for reflecting the vehicle-state according to setting, obtains vehicle to be monitored
For the vector value of described eigenvector；
Second obtains module, for being closed according to the mapping between the vector value and described eigenvector and the vehicle-state
System obtains the vehicle-state of the vehicle to be monitored；
Mark module, for marking the vehicle when the vehicle-state of the vehicle to be monitored meets the condition wait intervene
Be vehicle to be intervened.
According to the third aspect of the invention we, a kind of server is additionally provided comprising described according to a second aspect of the present invention
Device；Alternatively,
The server includes: memory, for storing executable instruction；Processor, for according to described instruction
Control runs the method that the server executes the monitoring vehicle-state described according to a first aspect of the present invention.
A beneficial effect of the invention is, according to the method for the embodiment of the present invention, device and server, on the one hand,
It can according to reflection vehicle-state feature vector vector value and this feature vector and vehicle-state between mapping function,
The vehicle-state of vehicle to be monitored is obtained, so that the accuracy and validity of vehicle state monitoring are effectively improved, on the other hand,
Can be when the vehicle-state of vehicle to be monitored meet the condition wait intervene, direct marked vehicle is vehicle to be intervened, to indicate
The vehicle needs to carry out intervention processing, realizes the purpose of monitoring.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Detailed description of the invention
It is combined in the description and the attached drawing for constituting part of specification shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.
Fig. 1 is the principle frame for showing the hardware configuration of system for the monitoring vehicle-state that can be used for realizing the embodiment of the present invention
Figure；
Fig. 2 is the flow chart of the method for monitoring vehicle-state according to an embodiment of the present invention；
Fig. 3 is the flow chart of the method for monitoring vehicle-state according to another embodiment of the present invention；
Fig. 4 is the flow chart of the method for monitoring vehicle-state according to a third embodiment of the present invention；
Fig. 5 is the flow chart of the method for monitoring vehicle-state according to a fourth embodiment of the present invention；
Fig. 6 is the flow chart of the method for the monitoring vehicle-state of an example according to the present invention；
Fig. 7 is the flow chart of the method for the monitoring vehicle-state of another example according to the present invention；
Fig. 8 is the functional block diagram of the device of monitoring vehicle-state according to an embodiment of the present invention；
Fig. 9 is the functional block diagram of server according to an embodiment of the present invention.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
<hardware configuration>
Fig. 1 is the block diagram that can be used for realizing the hardware configuration of the system 100 of monitoring vehicle-state of the embodiment of the present invention.
As shown in Figure 1, the system 100 of monitoring vehicle-state includes server 1000, mobile terminal 2000 and vehicle 3000.
1000 offer processing of server, database, communications service service point.Server 1000 can be monoblock type service
Device or decentralized service device across multicomputer or computer data center.Server can be it is various types of, such as but
It is not limited to, network server, NEWS SERVER, mail server, message server, Advertisement Server, file server, applies
Server, interactive server, database server or proxy server.In some embodiments, each server may include
Hardware, software, or the embedded logic module of proper function supporting or realize for execute server or it is two or more this
The combination of class component.For example, server such as blade server, cloud server etc., or can be by multiple servers group
At server farm, may include one of server of the above-mentioned type or a variety of etc..
In one embodiment, server 1000 can be as shown in Figure 1, include processor 1100, memory 1200, interface
Device 1300, communication device 1400, display device 1500, input unit 1600.
In a further embodiment, server 1000 can also be including loudspeaker, microphone etc., it is not limited here.
Processor 1100 can be dedicated processor-server, be also possible to meet the desktop computer processing of performance requirement
Device, mobile edition processor etc., it is not limited here.Memory 1200 is for example including ROM (read-only memory), RAM (arbitrary access
Memory), the nonvolatile memory of hard disk etc..Interface arrangement 1300 is for example including various bus interface, such as serially
Bus interface (including USB interface), parallel bus interface etc..Communication device 1400 is for example able to carry out wired or wireless communication.
Display device 1150 is, for example, liquid crystal display, LED display touch display screen etc..Input unit 1160 for example may include touching
Touch screen, keyboard etc..
In the present embodiment, for storing instruction, which is used for control processor to the memory 1200 of server 1000
1100 methods operated to execute monitoring vehicle-state.Technical staff disclosed conceptual design can refer to according to the present invention
It enables.How control processor is operated for instruction, this is it is known in the art that therefore being not described in detail herein.
Although multiple devices of server 1000 are shown in FIG. 1, the present invention can only relate to part therein
Device, for example, server 1000 pertains only to memory 1200 and processor 1100.
In the present embodiment, mobile terminal 2000 is, for example, mobile phone, portable computer, tablet computer, palm PC, wearable
Equipment etc..
The mobile terminal 2000 can install vehicle using the user terminal of application, be also possible to install vehicle intervention application
Intervention terminal, the intervention terminal for operation personnel use.
As shown in Figure 1, mobile terminal 2000 may include processor 2100, memory 2200, interface arrangement 2300, communication
Device 2400, display device 2500, input unit 2600, loudspeaker 2700, microphone 2800 etc..
Processor 2100 can be mobile edition processor.Memory 2200 for example including ROM (read-only memory), RAM (with
Machine accesses memory), the nonvolatile memory of hard disk etc..Interface arrangement 2300 is for example including USB interface, earphone interface
Deng.Communication device 2400 is for example able to carry out wired or wireless communication, and communication device 2400 may include short-range communication device,
E.g. based on Hilink agreement, WiFi (802.11 agreement of IEEE), Mesh, bluetooth, ZigBee, Thread, Z-Wave,
The short-range wireless communication protocols such as NFC, UWB, LiFi carry out any device of short-distance wireless communication, and communication device 2400 can also
To include remote communication devices, any device of WLAN, GPRS, 2G/3G/4G/5G telecommunication is e.g. carried out.Display device
2500 be, for example, liquid crystal display, touch display screen etc..Input unit 2600 is such as may include touch screen, keyboard.User
2800 inputting/outputting voice information of loudspeaker 2700 and microphone can be passed through.
In one example, mobile terminal 2000 is user terminal, and the memory 2200 of mobile terminal 2000 is for storing
Instruction, the instruction are operated for control processor 2100 to execute the method for using vehicle 3000, for example, at least include: to obtain
The identity of pick-up 3000, the unlocking request formed for particular vehicle are sent to server；And it is sent out according to server
The disbursement and sattlement notice sent carries out bill resolving etc..Technical staff can disclosed conceptual design instruction according to the present invention.Refer to
Enable how control processor is operated, this is it is known in the art that therefore being not described in detail herein.
In another example, mobile terminal 2000 is the intervention terminal used for operation personnel, mobile terminal 2000
For storing instruction, which is operated the method to execute vehicle intervention for control processor 2100 to memory 2200,
For example, at least include: acquisition and the mark and location information for showing the vehicle to be intervened that server is sent, and will find
The vehicle-state of vehicle to be intervened and intervention result etc. are uploaded to server etc..Technical staff can be disclosed according to the present invention
Conceptual design instruction.How control processor is operated for instruction, this is it is known in the art that therefore being not described in detail herein.
Although multiple devices of mobile terminal 2000 are shown in FIG. 1, the present invention can only relate to portion therein
Separating device, for example, mobile terminal 2000 pertains only to memory 2200 and processor 2100, communication device 2400 and display device
2500。
Vehicle 3000 can be bicycle shown in Fig. 1, be also possible to tricycle, Moped Scooter, motorcycle and
The various forms such as fourth wheel passenger car, it is not limited here.
As shown in Figure 1, vehicle 3000 may include processor 3100, memory 3200, interface arrangement 3300, communication device
3400, output device 3500, input unit 3600, etc..Wherein, processor 3100 can be Micro-processor MCV etc..Memory
3200 for example including ROM (read-only memory), RAM (random access memory), nonvolatile memory of hard disk etc..It connects
Mouth device 3300 is for example including USB interface, earphone interface etc..Communication device 3400 is for example able to carry out wired or wireless communication,
In another example being able to carry out short distance and telecommunication.Output device 3500 for example can be the device of output signal, can show
Device, such as liquid crystal display, touch display screen etc. are also possible to output voice messaging such as loudspeaker etc..Input unit 3600
Such as may include touch screen, keyboard etc., it is also possible to microphone input voice messaging.
Although multiple devices of vehicle 3000 are shown in FIG. 1, the present invention can only relate to part dress therein
It sets, for example, vehicle 3000 pertains only to communication device 3400, memory 3200 and processor 3100.Alternatively, can also include Fig. 1
In the unshowned latch mechanism for being controlled by processor 3100 and the sensor device etc. for detecting latch mechanism state.
In the present embodiment, vehicle 3000 can report the location information of itself to server 1000, and, to server
1000 report use state information of itself etc., for example, reporting when detecting that user completes lock operation to server 1000
It is latched notification signal.
In the present embodiment, for storing instruction, which is used for control processor 3100 to the memory 3200 of vehicle 3000
It is operated to execute the information exchange between server 1000.Technical staff can disclosed conceptual design according to the present invention
Instruction.How control processor is operated for instruction, this is it is known in the art that therefore being not described in detail herein.
Network 4000 can be cordless communication network and be also possible to wireline communication network, can be local area network and is also possible to extensively
Domain net.In the system 100 of monitoring vehicle-state shown in Fig. 1, vehicle 3000 and server 1000, mobile terminal 2000 and clothes
Business device 1000, can be communicated by network 4000.In addition, vehicle 3000 and server 1000, mobile terminal 2000 and clothes
Business device 1000 communicates the network 4000 that is based on and can be same, is also possible to different.
It should be understood that although Fig. 1 only shows a server 1000, mobile terminal 2000, vehicle 3000, unexpectedly
Taste the respective quantity of limitation, monitor and may include multiple servers 1000, multiple mobile terminals in the system 100 of vehicle-state
2000, multiple vehicles 3000.
Server 1000 supports vehicle to use necessary repertoire for providing；Mobile terminal 2000 can be hand
Machine is equipped with vehicle using application thereon, and vehicle can help user to realize the function using vehicle 3000 using application.
<embodiment of the method>
Fig. 2 is the flow diagram of the method for monitoring vehicle-state according to an embodiment of the present invention, and this method is by server
1000 implement.
According to Fig.2, the method for the present embodiment may include steps of:
Step S2100, server 1000 obtain vehicle pair to be monitored according to the feature vector of the reflection vehicle-state of setting
In the vector value of feature vector.
Vehicle to be monitored is the vehicle it needs to be determined that vehicle-state.
In one example, it can be with being arbitrarily designated it needs to be determined that the vehicle of vehicle-state is vehicle to be monitored.
In one example, it is also possible to as unit of target area, determines that the vehicle being located in target area is wait supervise
Control vehicle.Selected target area is first obtained here, can be, the vehicle for searching again for being located in target area is as vehicle to be monitored
, thus, this kind divides the method that region carries out vehicle monitoring and is conducive to know that the vehicle supply amount of corresponding region whether can
Meet the needs of region, is supported with providing data for vehicle scheduling, realize the equilibrium of supply and demand.
The target area is the regional scope delimited in advance, can be and delimit mesh according to the minimum unit of monitoring vehicle-state
Mark region.For example, carrying out the monitoring of vehicle-state using city as minimum unit, then target area is some city；In another example with
The administrative region in some city is the monitoring that minimum unit carries out vehicle-state, then target area is some administration in some city
Region；For another example carrying out the monitoring of vehicle-state, then mesh using the administrative street of some some administrative region of city as minimum unit
Mark region can be some administrative street etc., it is not limited here.
In the present embodiment, vehicle-state may include the health status of vehicle.
In one example, vehicle-state can be the health value of the directly health status of reflection vehicle, can be health
Value is higher, and corresponding vehicle is more healthy, and, it can be appreciated that being, health value is higher for this, and the failure rate of corresponding vehicle is lower.
In one example, vehicle-state is also possible to the Health Category divided according to specific health value, here, can be with
It is to be compared the health value of vehicle with specific health value, to obtain comparison result, determines and correspond to further according to comparison result
The Health Category of vehicle, the specific health value can be set according to practical application and concrete scene, it is not limited here.
In one example, vehicle-state, which can also be, is directly divided into disabled vehicle according to the actual use situation of vehicle
And non-faulting vehicle, to facilitate operation personnel to manage.
In a further embodiment, vehicle-state also may include remaining capacity state etc., in this embodiment, by right
Remaining capacity state is monitored, and can be marked as when intervening vehicle in vehicle because of not enough power supply, waits intervening to these
Vehicle provides the reward value etc. for encouraging to ride, for these Vehicular chargings to be intervened.
The method of the embodiment of the present invention is suitable for analyze the identification of any vehicle-state obtained, example by data
Such as, health status (failure or non-faulting), remaining capacity state (electricity is sufficient or inadequate), depreciation state etc., herein
Without limitation.
Feature vector, X includes at least one feature x for reflecting vehicle-statej, the natural number that the value of j is 1 to p, p expression
The sum for the feature that feature vector, X has.
In one example, the feature vector for describing vehicle-state can be preselected, for example, according to server
The content that the vehicle data that each vehicle to be monitored has in 1000 database must include selectes this feature vector.
This feature vector can be made of at least one feature related with vehicle-state is determined, and then can be according to the spy
It levies vector and determines corresponding vehicle-state.
In one example, vehicle data can be handled according to existing some processing means, to be described
The feature related with vehicle-state is determined of vehicle data, and then composition characteristic vector.For example, to vehicle data carry out feature from
The characteristic processings such as dispersion, feature cleaning, feature selecting and feature normalization, with extract vehicle parameter feature, vehicle and user it
Between interaction feature and the stand feature of vehicle etc., thus composition characteristic vector.
In one example, the feature vector of the reflection vehicle-state of setting includes vehicle parameter feature, vehicle and user
Between interaction feature and vehicle stand feature in an at least category feature.
The vehicle parameter feature can be including vehicle static parameter attribute and vehicle dynamic parameter feature, vehicle static ginseng
Number feature may include car number, lock electricity voltage and its rate of decay, type of vehicle, vehicle history maintenance frequency, puppet
Healthy car state, vehicle the last time ride time, vehicle for the first time the date of production, the vehicle last date of production, lock hardware with
And vehicle firmware version etc..Vehicle dynamic parameter feature may include always ride within one day number, number of always riding for three days, seven days it is total
Ride number, fortnight is always ridden number, one day short number of riding, three days short number of riding, seven days short number of riding, fortnight
Short number of riding etc..
Interaction feature between the vehicle and user can be including user's riding cycle number, the non-tricycle of user's barcode scanning
Number, user be manually entered in information of vehicles at least one of.
The stand feature of the vehicle can be including locating for the average turn-round rate of rolling stock and region turnover rate ratio, vehicle
Fence type of fence locating for fence and vehicle etc..
The above fence is to be according to the planning delimitation region that Parking permitted or Parking permitted, based on to difference
Region carries out the needs of parking management, many fences can be arranged, which can be city, the administrative region in city, street
Road, grid etc., wherein grid can be obtained by dividing car operation range, for example, car operation range is divided into
100 meters × 100 meters of grid.
It can be with upper railings type and fence or parking fence stopped to prohibit according to fence Attribute transposition, be also possible to basis
Geographical location Attribute transposition is subway fence, bus platform fence and street fence etc., it is not limited here.
In this example embodiment, for example, feature vector, X can have 6 features, i.e., the above p=6, at this point it is possible to by feature to
Amount is expressed as X=(x1,x2,x3,x4,x5,x6), wherein x1,x2,x3,x4,x5,x6x1It can be vehicle release date, vehicle respectively
Liang Ru factory maintenance frequency, user's riding cycle number, the non-riding cycle number of user's barcode scanning, the average turn-round rate of rolling stock and region week
The fence attribute of fence locating for rate of rotation ratio and vehicle, here, vehicle release date, vehicle enter factory's maintenance frequency, user
Locating for the non-riding cycle number of riding cycle number, user's barcode scanning, the average turn-round rate of rolling stock and region turnover rate ratio and vehicle
The corresponding characteristic value of fence attribute of fence can be respectively 2018.1.2, and 5 times, 100 times, 20 times, 20%, parking is enclosed
It column certainly can also be including other features relevant to vehicle-state above, it is not limited here in feature vector, X.
Step S2200, server 1000 according to the mapping relations between vector value and feature vector and vehicle-state, obtain to
Monitor the vehicle-state of vehicle.
Mapping relations between this feature vector and vehicle-state can be mapping function F (x), the mapping function F (x) from
Variable is feature vector, X, and dependent variable F (x) is the vehicle-state to be determined by feature vector, X.It include failure with vehicle-state
For state and non-faulting state, can be functional value is that correspond to vehicle to be monitored be malfunction to true value, i.e., vehicle to be monitored
Belong to fault car, functional value is that correspond to vehicle to be monitored be non-faulting state to falsity, i.e., vehicle to be monitored belongs to normal vehicle；
Being also possible to functional value is that correspond to vehicle to be monitored be non-faulting state to true value, i.e., vehicle to be monitored belongs to normal vehicle, function
Value is that correspond to vehicle to be monitored be malfunction to falsity, i.e., vehicle to be monitored belongs to fault car, as long as according to functional value energy
Enough distinguish vehicle to be monitored for fault car and non-faulting vehicle, it is not limited here.
In the present embodiment, according to step S2100, after the vector value for obtaining the feature vector of vehicle to be monitored, it can incite somebody to action
Vector value substitutes into mapping function F (x), to obtain the vehicle-state of vehicle to be monitored.
Step S2300, server 1000 is when the vehicle-state of vehicle to be monitored meets the condition wait intervene, marked vehicle
For vehicle to be intervened.
In the present embodiment, since vehicle-state includes the health status of vehicle, thus, condition to be intervened includes healthy shape
State is malfunction, that is, it is vehicle to be intervened by the marking of cars in the case where the health status of vehicle is malfunction,
It is performed corresponding processing with facilitating operation personnel to treat intervention vehicle.
According to the method for the embodiment of the present invention, on the one hand, it can be according to the vector of the feature vector of reflection vehicle-state
Value and the mapping function between this feature vector and vehicle-state, obtain the vehicle-state of vehicle to be monitored, to effectively improve
On the other hand the accuracy and validity of vehicle state monitoring can meet in the vehicle-state of vehicle to be monitored wait intervene
Condition when, direct marked vehicle is that vehicle to be intervened to indicate that the vehicle needs to carry out intervention processing realizes the mesh of monitoring
's.
In one embodiment, according to above step S2300 marked vehicle be wait intervene vehicle after, the present invention monitor vehicle
The method of state can further include following steps S2411~S2412:
Step S2411, server 1000 obtain the quantity for the vehicle to be intervened that target area has.
In the present embodiment, if it is malfunction that condition to be intervened, which includes health status, according in above step S2300
Marked vehicle be wait intervene vehicle after, the vehicle of vehicle to be intervened that target area has can be obtained according to step S2411
Quantity, it can be appreciated that being, server 1000 obtains the quantity for the fault car that target area has for this.
In one example, according to step S2300 marked vehicle be wait intervene vehicle after, can be and be marked as to dry
The vehicle of pre- vehicle actively sends the car number of vehicle to be intervened to server 1000, server 1000 according to receive to
The car number for intervening vehicle obtains the quantity for the vehicle to be intervened that target area has.
In one example, according to step S2300 marked vehicle be wait intervene vehicle after, be also possible to by operation personnel
Actively send the car number of vehicle to be intervened to server 1000, server 1000 is according to the vehicle of the vehicle to be intervened received
Number obtains the quantity of vehicle to be intervened that target area has.
Step S2412, server 1000 carry out vehicle scheduling to target area according to the quantity of vehicle to be intervened.
It include for health status is malfunction, being obtained in target area according to step S2411 by condition to be intervened
After the vehicle fleet size of malfunction, server 1000 can dynamically adjust the target according to the vehicle fleet size of malfunction
The vehicle injected volume in region, to realize the reasonable distribution of vehicle, such as can be according to the vehicle number of the malfunction of target area
Amount launches a certain number of vehicles to target area supplement, and the quantity for requiring supplementation with dispensing can be according to current failure state
Vehicle fleet size take into account user's service condition determine.
The embodiment is after marking wait intervene vehicle, according to the number for the vehicle to be intervened that the target area of acquisition has
Amount, adjusts the vehicle injected volume of the target area, dynamically so as to realize the reasonable distribution of vehicle.
In one embodiment, according to above step S2300 marked vehicle be wait intervene vehicle after, the present invention monitor vehicle
The method of state can further include following steps S2420:
Step S2420, server 1000 are directed to vehicle to be intervened, and the intervention terminal used to operation personnel, which sends to intervene, to be referred to
Show.
Intervene prompt and carries the car number of vehicle to be intervened and the stand of vehicle to be intervened.
Intervening terminal can be mobile terminal, to facilitate operation personnel's carrying and movement, the intervention terminal for example to can be
It is scanner, PDA (Personal Digital Assistant, handheld terminal), mobile phone, tablet computer, palm PC, wearable
Equipment etc., it is not limited here.
By condition to be intervened include health status be malfunction for, according to 1000 needle of step S2420 server
To the vehicle of malfunction, intervention instruction is sent to terminal is intervened, due to carrying the car number of fault car in intervention instruction
With the stand of fault car, the operation personnel for carrying the intervention terminal can find the vehicle of corresponding malfunction,
And then depot repair either field maintenance is carried out to the vehicle of malfunction.
For the embodiment after marking wait intervene vehicle, server 1000 can be directed to vehicle to be intervened, to intervention terminal
It sends and intervenes instruction, carry the car number of vehicle to be intervened and the stand of vehicle to be intervened due to intervening in instruction,
To improve efficiency and accuracy that operation personnel searches vehicle to be intervened.
In one embodiment, referring to shown in Fig. 3, the method that the present invention monitors vehicle-state be can further include:
Server 1000 executes the feature vector of the reflection vehicle-state according to setting, obtains wait supervise in response to the monitor event of setting
The step of controlling vector value of the vehicle for feature vector.
At least one monitor event can be set in server 1000, which may include the prison of setting
It controls the time then, after any one vehicle to be monitored has executed scheduler task, or appointing in new vehicle to be monitored occurs
Meaning one or more.
In the present embodiment, when any monitor event occurs, server 1000 can be in response to the monitor event, root
According to the feature vector of the reflection vehicle-state of setting, vehicle to be monitored is obtained for the vector value of feature vector.
The embodiment according to the present invention, in response to setting monitor event when, just according to the reflection vehicle-state of setting
Feature vector, obtain vehicle to be monitored for the vector value of feature vector, and further execute any implementation according to the present invention
The method of the monitoring vehicle-state of example, this response monitoring event are gone to execute the mode of monitoring vehicle-state, be can be improved to prison
Control the targeting of vehicle-state.
In one embodiment, it is to reflect that the method that the present invention monitors vehicle-state, which can further include in mapping relations,
In the case where penetrating function, the step of training mapping function, referring to Fig. 4, it can be according to following steps S4100~S4200 training
Mapping function.
Step S4100, server 1000 obtain the accurate vehicle of vehicle-state as training sample.
, can be by training sample training mapping function according to step S4100, the feature vector set and vehicle
Mapping relations between state.
The quantity of training sample is more, after training result is also usually more accurate, but training sample reaches certain amount, training
As a result the increase of precision is by the increasingly slower of change, until orientation is stablized.Here, the precision sum number of training result can be taken into account
The quantity of required training sample is determined according to processing cost.
In one example, the step of accurate vehicle of vehicle-state is as training sample is obtained in above-mentioned steps S4100
It may further include following steps S4110~S4140:
Step S4110, server 1000 obtains the accurate vehicle of vehicle-state of the first setting quantity, as the first training
Sample.
In step S4110, can be and select the artificial mark that a small amount of sample carries out vehicle-state, with provide this first
Training sample, by taking vehicle-state is malfunction and non-faulting state as an example, which includes belonging to vehicle-state for event
The vehicle and vehicle-state of barrier state are the vehicle of non-faulting state.
Vehicle-state is that the vehicle of malfunction can be according to reporting of user fault car data and vehicle storage maintenance
Data determine, that is, it is malfunction that the fault car of reporting of user and storage maintenance vehicle, which are manually labeled as vehicle-state,.
Step S4120, server 1000 obtains the vehicle of the second setting quantity, as the second training sample.
Second setting quantity is much larger than the first setting quantity.
In step S4120, the artificial mark for selecting a certain amount of sample without vehicle-state can be, be somebody's turn to do with providing
Second training sample, that is, the vehicle-state of each vehicle in the second training sample is unknown state, accordingly it is desirable to according to the
One training sample determines the vehicle-state of each vehicle in the second training sample.
Step S4130, server 1000 cluster the second training sample according to the first training sample, obtain the second instruction
Practice the vehicle-state of each vehicle in sample.
In step S4130, the first training sample can gather the second training sample using mixed Gauss model
Class processing, to determine the vehicle-state of each vehicle in the second training sample.
In step S4130, it can assume that each sample standard deviation meets a single Gauss model in the first training sample, and
First training sample is generated by M single Gauss model altogether, and M single Gauss model weighted sum is just obtained gauss hybrid models
The calculation formula of probability distributing density function, the probability distributing density function of gauss hybrid models can indicate are as follows:
Wherein, j is each natural number from 1 to M, and M is the sum of single Gauss model, i be from 1 to n each from
So number, n are the sum of the first training sample, Nj(xi；μj, ∑j) be j-th of single Gauss model probability distributing density function, xi
For i-th of first training samples, αjFor the weight of j-th of single Gauss model,μjFor the phase of j-th of single Gauss model
Prestige value, ∑jFor the variance of j-th of single Gauss model.
It is j-th single high in the calculation formula of the probability distributing density function of gauss hybrid models shown in above formula (1)
The weight α of this modelj, the desired value μ of j-th of single Gauss modeljAnd the variance ∑ of j-th of single Gauss modeljIt is unknown, here,
It can be and the above α is calculated using maximum likelihood function either desired value maximal functionj、μjAnd ∑j, to obtain Gaussian Mixture mould
Each sample in second training sample can be substituted into the probability distribution of gauss hybrid models by the probability distributing density function of type
In density function, the probability distributing density function of corresponding gauss hybrid models is obtained.
By taking vehicle-state includes malfunction and non-faulting state as an example, it is calculated using the first training sample above
αj、μjAnd ∑jIt, can will be in the second training sample and after obtaining the probability distributing density function of determining gauss hybrid models
Each sample substitute into the probability distributing density function of gauss hybrid models, obtain the probability point of corresponding gauss hybrid models
Cloth density function, here, can be setting probability threshold value, for example, it may be in the probability of the corresponding gauss hybrid models of sample
When distribution density function is more than or equal to probability threshold value, determine that vehicle-state is malfunction, conversely, determining that vehicle-state is
Non-faulting state, in another example, be also possible to be greater than in the probability distributing density function of the corresponding gauss hybrid models of sample or
When equal to probability threshold value, determines that vehicle-state is non-faulting state, conversely, determining that vehicle-state is malfunction, do not do herein
It limits.
Step S4140, server 1000 is using the second training sample after the first training sample and cluster as training sample.
In step S4140, it can be by according to the first training sample obtained in step S4110, and according to step
The second training sample after the cluster that S4130 is obtained is as training sample, due to the vehicle shape of each vehicle in the training sample
State is known state, it is thus possible to according to the accurate training sample training mapping function of the vehicle-state.
The example can be unknown to a large amount of vehicle-state according to a small amount of accurate first training sample of vehicle-state
Second training sample is clustered, to determine the vehicle-state of each vehicle in the second training sample, and by the first training sample
It is used as training sample to train mapping function with the second training sample after cluster.Here, since the example is using a small amount of
The training sample of vehicle-state go to determine the vehicle-state of the unknown training sample of a large amount of vehicle-state, thus, it is possible to subtract
Small cost of labor improves the efficiency and accuracy for obtaining training sample, further increases the efficiency of trained mapping function and accurate
Property.
Step S4200, server 1000 are corresponding according to vector value and training sample of the training sample for feature vector
Vehicle-state obtains mapping function.
In step S4200, can vector value based on this feature vector of training sample and corresponding vehicle-state,
Mapping function F (x) is obtained by various fitting means.
In one example, it can use arbitrary multiple linear regression model and obtain mapping function F (x).
For example, the multiple linear regression model can be the polynomial function for simply reflecting the mapping function F (x),
In, each level number of polynomial function is unknown, by by the vector value of the category feature vector of case sample and corresponding
Case type substitutes into the polynomial function, can determine each level number of polynomial function, and then obtain mapping function F (x).
The multiple linear regression model for example can be LR model, Bayesian model etc., it is not limited here.
In one example, various addition models be can use, vector value and institute to this feature vector of training sample
Corresponding vehicle-state carries out more wheel training, and each round all learns the residual error after last round of fitting, and iteration T wheel can be by residual error
Control is in very low value, so that finally obtained mapping function F (x) has very high accuracy.The addition model is for example
It is GBDT, LightGBM, XGBoost etc., it is not limited here.
In one example, the feature x for including in feature vector, XjA fairly large number of situation under, can be first benefit
With e.g. GBDT model carry out feature discretization, feature clean, the characteristic processings such as feature selecting and feature combination, and will progress
For feature vector, X after characteristic processing as the input for being, for example, LR model, the output of LR model is vehicle-state.It is utilized above
When GBDT model carries out the characteristic processings such as feature discretization, feature cleaning, feature selecting and feature combination, it can be and first select certainly
The number of plan tree and the depth of decision tree, to carry out feature discretization, feature cleaning, feature selecting and feature according to decision tree
The characteristic processings such as combination, wherein the number of decision tree is more and the depth of decision tree is higher, and it is clear to carry out feature discretization, feature
Wash, feature selecting and feature combination etc. characteristic processings when it is more complicated.
The method that mapping function is obtained according to the accurate vehicle training of vehicle-state that the embodiment provides, it is with higher
Accuracy can accurately obtain the vehicle-state of vehicle to be monitored.
In one embodiment, referring to Fig. 5, the method that the present invention monitors vehicle-state can further include following step
Rapid S5100~S5500:
Step S5100, server 1000 obtain the accurate vehicle of vehicle-state, as verifying sample.
In step S5100, it can be and select the artificial mark that a small amount of sample carries out vehicle-state, the reality as sample
Border vehicle-state, to provide the verifying sample, by taking vehicle-state is malfunction and non-faulting state as an example, the verifying sample packet
Include the vehicle that vehicle-state is malfunction and the vehicle that vehicle-state is non-faulting state.
Step S5200, server 1000 obtain the vehicle-state conduct of each vehicle in verifying sample according to mapping relations
Predict vehicle-state.
In step S5200, server 1000 can be according to mapping relations, which is, for example, to be implemented according to above
The mapping function that example obtains obtains the vehicle-state of each vehicle in verifying sample as prediction vehicle-state, so as to will be each
The prediction vehicle-state of vehicle and the actual vehicle state of each sample are compared, and then obtain the judge value of mapping relations.
Step S5300, server 1000 will verify the reality of the prediction vehicle-state and corresponding vehicle of each vehicle in sample
Border vehicle-state compares, and obtains the judge value of mapping relations.
Quality of the judge value of mapping relations to judge mapping relations, the judge value for example can be recall rate, can also
To be accuracy rate, it is not limited here.
Step S5400, server 1000 are worth according to judge, judge whether mapping relations are effective.
In step S5400, server 1000 can be one judge threshold value of setting, to be reflected according to the judge threshold decision
Whether effective penetrate relationship.Such as can be in the case where judge value is more than to judge threshold value, judge that mapping relations are effective, it can also be with
It is to judge that mapping relations are invalid in the case where judge value is less than and judges threshold value.
Step S5500, server 1000 is in the effective situation of mapping relations, then executes according to vector value and feature vector
Mapping relations between vehicle-state, the step of obtaining the vehicle-state of vehicle to be monitored.
The example after obtaining mapping relations, by choose verify sample, and by verify sample in each vehicle it is pre-
Vehicle-state is surveyed to obtain judge value compared with the actual vehicle state of corresponding vehicle, and then is judging to map according to judge value
In the effective situation of relationship, just executes according to the mapping relations between vector value and feature vector and vehicle-state, obtain to be monitored
The step of vehicle-state of vehicle, thus, it is possible to ensure obtain mapping relations accuracy, further increase acquisition wait supervise
Control the accuracy of the vehicle-state of vehicle.
Step S5600, server 1000 in the case where mapping relations are invalid, can by adjusting selected feature to
At least one of in amount and the sample size of training sample, re -training obtains mapping relations.
The example in the case where judging that mapping relations are invalid according to judge value, can by adjusting feature vector, and/or
Training sample, re -training obtain mapping relations, so that the vehicle-state of prediction is more and more accurate.
It, can be according to the present embodiment to this in the case where mapping relations are the mapping function obtained according to above-described embodiment
The validity of mapping function is detected, and finally obtains effective mapping function, predicts vehicle by mapping function to improve
The accuracy of state.
<example>
Fig. 6 shows the side of corresponding monitoring vehicle-state so that vehicle-state includes malfunction and non-faulting state as an example
Method, in the example, the method for monitoring vehicle-state be may include steps of:
Step S6110, server 1000 obtain selected target area.
Step S6120, the search of server 1000 are located at the vehicle in target area as vehicle to be monitored.
Step S6130, server 1000 in response to setting monitor event, according to setting reflection vehicle-state feature
Vector obtains vehicle to be monitored for the vector value of feature vector.
Feature vector includes that the stand of the interaction feature and vehicle between vehicle parameter feature, vehicle and user is special
An at least category feature in sign.
Step S6140, the mapping function between 1000 training feature vector of server and vehicle-state.
In the example, referring to Fig. 7, mapping function in step S6140 between training feature vector and vehicle-state can be with
Further comprise:
Step S6141, server 1000 obtains the accurate vehicle of vehicle-state of the first setting quantity, as the first training
Sample.
Step S6142, server 1000 obtains the vehicle of the second setting quantity, as the second training sample.
Step S6143, server 1000 cluster the second training sample according to the first training sample, obtain the second instruction
Practice the vehicle-state of each vehicle in sample.
Step S6144, server 1000 is using the second training sample after the first training sample and cluster as training sample.
Step S6145, server 1000 are corresponding according to vector value and training sample of the training sample for feature vector
Vehicle-state obtains mapping function.
Step S6151, server 1000 obtain the accurate vehicle of vehicle-state, as verifying sample, and according to mapping letter
Number obtains the vehicle-state of each vehicle in verifying sample as prediction vehicle-state.
Step S6152, server 1000 will verify the reality of the prediction vehicle-state and corresponding vehicle of each vehicle in sample
Border vehicle-state compares, and obtains the judge value of mapping function.
Step S6153, server 1000 are worth according to judge, judge whether mapping function is effective, and in effective situation,
Step S6154 is executed, conversely, executing step S6180.
Step S6154, server 1000 is in the effective situation of mapping function, according to vector value and feature vector and vehicle
Mapping relations between state obtain the vehicle-state of vehicle to be monitored.
Step S6160, for server 1000 when the vehicle-state of vehicle to be monitored is malfunction, marked vehicle is failure
Vehicle.
Step S6171, server 1000 obtains the quantity for the fault car that target area has, according to quantity, to target
Region carries out vehicle scheduling.
Step S6172, server 1000 are directed to fault car, send intervention instruction to terminal is intervened.
In the example, the execution of above step 6171 and step S6172 sequentially, can be in no particular order and first carry out step
S6171, then step S6172 is executed, it is also possible to first carry out step S6172, is executing step S6171, can also be while holding
Row step S6171 and step S6172.
Step S6180, server 1000 is in the case where mapping function is invalid, by adjusting feature vector and training sample
Sample size at least one of, re -training obtains mapping function.
<Installation practice>
Fig. 8 shows the functional block diagram of the device of monitoring fault car according to an embodiment of the present invention.According to Fig.8,
The device 8000 includes that the first acquisition module 8100, second obtains module 8200 and mark module 8300.
First obtains the feature vector for the reflection vehicle-state that module 8100 is used for according to setting, obtains vehicle pair to be monitored
In the vector value of feature vector.
Second, which obtains module 8200, is used to be obtained according to the mapping relations between the vector value and feature vector and vehicle-state
Obtain the vehicle-state of vehicle to be monitored.
Mark module 8300 be used for when the vehicle-state of vehicle to be monitored meets the condition wait intervene, marked vehicle be to
Intervene vehicle.
In one embodiment, which can be used for: in response to the monitor event of setting, execute root
According to the feature vector of the reflection vehicle-state of setting, the step of obtaining vector value of the vehicle to be monitored for feature vector.
In one embodiment, which can also include target search module, which is used for: obtaining
Take selected target area；And search is located at the vehicle in the target area as vehicle to be monitored.
In one embodiment, which can also include scheduler module, which is used for: obtaining target area
The quantity for the vehicle to be intervened that domain has；Vehicle scheduling is carried out to target area according to the quantity.
In one embodiment, which can also include intervention module, which be used for: for it is described to
Intervene vehicle, sends intervention instruction to terminal is intervened；Wherein, intervene prompt and carry the car number of vehicle to be intervened and to dry
The stand of pre- vehicle.
In one embodiment, the above mapping relations are mapping function, which can also include training module, the training
Module is used for: obtaining the accurate vehicle of vehicle-state as training sample；According to the corresponding described eigenvector of training sample
Vector value and the corresponding vehicle-state of training sample obtain mapping function.
In one embodiment, the above training module can be also used for: the vehicle-state for obtaining the first setting quantity is accurate
Vehicle, as the first training sample；The vehicle for obtaining the second setting quantity, as the second training sample；According to the first training
Sample clusters the second training sample, obtains the vehicle-state of each vehicle in the second training sample；By the first training sample
This is with the second training sample after cluster as training sample.
In one embodiment, which can also include authentication module, which is used for: it is quasi- to obtain vehicle-state
True vehicle, as verifying sample；According to mapping relations, the vehicle-state of each vehicle in verifying sample is obtained as pre- measuring car
State；The prediction vehicle-state of each vehicle in sample will be verified to compare with the actual vehicle state of corresponding vehicle, obtained
The judge value of mapping relations；According to the judge value, judge whether mapping relations are effective；In the effective situation of mapping relations, then
It notifies the second acquisition module 8200 to execute according to the mapping relations between vector value and feature vector and vehicle-state, obtains to be monitored
The operation of the vehicle-state of vehicle.
In one embodiment, which is also used to: in the case where mapping relations are invalid, notice training module is logical
It crosses adjustment feature vector and at least one in the sample size of the trained training sample for obtaining mapping relations, re -training is obtained
To new mapping relations, wherein the training sample is the accurate vehicle of the vehicle-state.
<server example>
In the present embodiment, a kind of server 1000 is also provided, as shown in figure 9, it may include any according to the present invention
The device 8000 of the monitoring vehicle-state of embodiment, the method for the monitoring vehicle-state for implementing any embodiment of that present invention.
Referring to Fig.1, which can also include processor 1100 and memory 1200, and the memory is for storing
Executable instruction；The processor 1200 is used to be executed according to the control runtime server 1000 of instruction any real according to the present invention
The method for applying the monitoring vehicle-state of example.
The present invention can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing operation of the present invention can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the invention
Face.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or block diagram describes various aspects of the invention.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show the system of multiple embodiments according to the present invention, method and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.It is right
For those skilled in the art it is well known that, by hardware mode realize, by software mode realize and pass through software and
It is all of equal value that the mode of combination of hardware, which is realized,.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In principle, the practical application or to the technological improvement in market for best explaining each embodiment, or make the art its
Its those of ordinary skill can understand each embodiment disclosed herein.The scope of the present invention is defined by the appended claims.
Claims (11)
1. a kind of method for monitoring vehicle-state, comprising:
According to the feature vector of the reflection vehicle-state of setting, vehicle to be monitored is obtained for the vector of described eigenvector
Value；
According to the mapping relations between the vector value and described eigenvector and the vehicle-state, the vehicle to be monitored is obtained
Vehicle-state；
When the vehicle-state of the vehicle to be monitored meets the condition wait intervene, marking the vehicle is vehicle to be intervened.
2. according to the method described in claim 1, wherein, the method also includes:
In response to the monitor event of setting, execute the feature vector of the reflection vehicle-state according to setting, obtain to
Monitor operation of the vehicle for the vector value of described eigenvector.
3. according to the method described in claim 1, wherein, the method also includes:
Obtain selected target area；
Search is located at the vehicle in the target area as the vehicle to be monitored.
4. according to the method described in claim 3, wherein, the method also includes:
Obtain the quantity for the vehicle to be intervened that the target area has；
According to the quantity, vehicle scheduling is carried out to the target area.
5. according to the method described in claim 1, wherein, the method also includes:
For the vehicle to be intervened, intervention instruction is sent to terminal is intervened；Wherein, the intervention prompt carries described to dry
The stand of the car number of pre- vehicle and the vehicle to be intervened.
6. according to the method described in claim 1, wherein, the mapping relations are mapping function, and the method also includes training
The step of mapping function, comprising:
The accurate vehicle of the vehicle-state is obtained as training sample；
According to the vector value of the corresponding described eigenvector of the training sample and the corresponding vehicle-state of the training sample, obtain
Obtain the mapping function.
7. according to the method described in claim 6, wherein, the acquisition accurate vehicle of vehicle-state is as training sample
The step of, comprising:
The accurate vehicle of vehicle-state for obtaining the first setting quantity, as the first training sample；
The vehicle for obtaining the second setting quantity, as the second training sample；
Second training sample is clustered according to first training sample, is obtained each in second training sample
The vehicle-state of vehicle；
Using second training sample after first training sample and cluster as the training sample.
8. method according to any one of claim 1 to 7, wherein the method also includes:
The accurate vehicle of vehicle-state is obtained, as verifying sample；
According to the mapping relations, the vehicle-state of each vehicle in the verifying sample is obtained as prediction vehicle-state；
The prediction vehicle-state of each vehicle in the verifying sample is compared with the actual vehicle state of corresponding vehicle, is obtained
The judge value of the mapping relations；
According to the judge value, judge whether the mapping relations are effective；
In the effective situation of the mapping relations, then execute described according to the vector value and described eigenvector and the vehicle
Mapping relations between state, the step of obtaining the vehicle-state of the vehicle to be monitored.
9. according to the method described in claim 8, wherein, the method also includes:
In the case where the mapping relations are invalid, the mapping relations are obtained by adjusting described eigenvector and for training
Training sample sample size at least one of, re -training obtains the mapping relations, wherein the training sample is institute
State the accurate vehicle of vehicle-state.
10. a kind of device for monitoring fault car, comprising:
First obtains module, for the feature vector according to the reflection vehicle-state of setting, obtain vehicle to be monitored for
The vector value of described eigenvector；
Second obtains module, for according to the mapping relations between the vector value and described eigenvector and the vehicle-state,
Obtain the vehicle-state of the vehicle to be monitored；
Mark module, for when the vehicle-state of the vehicle to be monitored meets the condition wait intervene, marking the vehicle to be
Vehicle to be intervened.
11. a kind of server, including device described in any one of claim 10；Or, comprising:
Memory, for storing executable instruction；
Processor executes according to claim 1 any one of -9 for running the server according to the control of described instruction
The method of the monitoring vehicle-state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910251192.6A CN110084481A (en) | 2019-03-29 | 2019-03-29 | Monitor the method, apparatus and server of vehicle-state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910251192.6A CN110084481A (en) | 2019-03-29 | 2019-03-29 | Monitor the method, apparatus and server of vehicle-state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084481A true CN110084481A (en) | 2019-08-02 |
Family
ID=67413922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910251192.6A Pending CN110084481A (en) | 2019-03-29 | 2019-03-29 | Monitor the method, apparatus and server of vehicle-state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084481A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570647A (en) * | 2019-09-06 | 2019-12-13 | 北京嘀嘀无限科技发展有限公司 | prompting method and system based on electronic fence |
| CN110782088A (en) * | 2019-10-25 | 2020-02-11 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
| CN110826787A (en) * | 2019-10-30 | 2020-02-21 | 上海钧正网络科技有限公司 | Electric quantity early warning method and device, computer equipment and storage medium |
| CN111126774A (en) * | 2019-11-26 | 2020-05-08 | 北京摩拜科技有限公司 | Abnormal vehicle identification method and device and electronic equipment |
| CN111114671A (en) * | 2019-11-08 | 2020-05-08 | 上海钧正网络科技有限公司 | Early warning method, system, device, equipment and storage medium |
| CN111123778A (en) * | 2019-12-23 | 2020-05-08 | 北京摩拜科技有限公司 | Method and device for monitoring vehicle use condition and electronic equipment |
| CN111126773A (en) * | 2019-11-26 | 2020-05-08 | 北京摩拜科技有限公司 | Abnormal vehicle identification method and device and electronic equipment |
| CN112466389A (en) * | 2020-12-04 | 2021-03-09 | 深圳市新合生物医疗科技有限公司 | Method and system for obtaining tumor marker based on machine learning algorithm |
| CN112731837A (en) * | 2020-12-23 | 2021-04-30 | 北京百度网讯科技有限公司 | Method, device, equipment, medium, product and vehicle for determining vehicle state |
| CN114964367A (en) * | 2022-05-20 | 2022-08-30 | 中国船级社武汉规范研究所 | LNG tank fault forecasting method and system based on time-varying parameters |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN107679576A (en) * | 2017-10-11 | 2018-02-09 | 北京摩拜科技有限公司 | The fault monitoring method and device of vehicle |
| CN107833311A (en) * | 2017-11-15 | 2018-03-23 | 中国联合网络通信集团有限公司 | A kind of fault detection method and platform of shared bicycle |
| CN109492894A (en) * | 2018-10-31 | 2019-03-19 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server that vehicle is launched |
-
2019
- 2019-03-29 CN CN201910251192.6A patent/CN110084481A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN107679576A (en) * | 2017-10-11 | 2018-02-09 | 北京摩拜科技有限公司 | The fault monitoring method and device of vehicle |
| CN107833311A (en) * | 2017-11-15 | 2018-03-23 | 中国联合网络通信集团有限公司 | A kind of fault detection method and platform of shared bicycle |
| CN109492894A (en) * | 2018-10-31 | 2019-03-19 | 北京摩拜科技有限公司 | Monitor the method, apparatus and server that vehicle is launched |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570647A (en) * | 2019-09-06 | 2019-12-13 | 北京嘀嘀无限科技发展有限公司 | prompting method and system based on electronic fence |
| CN110782088A (en) * | 2019-10-25 | 2020-02-11 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
| CN110782088B (en) * | 2019-10-25 | 2022-07-05 | 嘉应学院 | UWB-based vehicle scheduling optimization system and method thereof |
| CN110826787A (en) * | 2019-10-30 | 2020-02-21 | 上海钧正网络科技有限公司 | Electric quantity early warning method and device, computer equipment and storage medium |
| CN111114671A (en) * | 2019-11-08 | 2020-05-08 | 上海钧正网络科技有限公司 | Early warning method, system, device, equipment and storage medium |
| CN111126773A (en) * | 2019-11-26 | 2020-05-08 | 北京摩拜科技有限公司 | Abnormal vehicle identification method and device and electronic equipment |
| CN111126774A (en) * | 2019-11-26 | 2020-05-08 | 北京摩拜科技有限公司 | Abnormal vehicle identification method and device and electronic equipment |
| CN111126773B (en) * | 2019-11-26 | 2023-09-05 | 汉海信息技术(上海)有限公司 | Abnormal vehicle identification method and device and electronic equipment |
| CN111123778A (en) * | 2019-12-23 | 2020-05-08 | 北京摩拜科技有限公司 | Method and device for monitoring vehicle use condition and electronic equipment |
| CN111123778B (en) * | 2019-12-23 | 2021-07-27 | 汉海信息技术(上海)有限公司 | Method and device for monitoring vehicle use condition and electronic equipment |
| CN112466389A (en) * | 2020-12-04 | 2021-03-09 | 深圳市新合生物医疗科技有限公司 | Method and system for obtaining tumor marker based on machine learning algorithm |
| CN112466389B (en) * | 2020-12-04 | 2024-05-17 | 深圳市新合生物医疗科技有限公司 | Method and system for acquiring tumor marker based on machine learning algorithm |
| CN112731837A (en) * | 2020-12-23 | 2021-04-30 | 北京百度网讯科技有限公司 | Method, device, equipment, medium, product and vehicle for determining vehicle state |
| CN114964367A (en) * | 2022-05-20 | 2022-08-30 | 中国船级社武汉规范研究所 | LNG tank fault forecasting method and system based on time-varying parameters |
| CN114964367B (en) * | 2022-05-20 | 2024-02-23 | 中国船级社武汉规范研究所 | LNG tank fault prediction method and system based on time-varying parameters |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084481A (en) | Monitor the method, apparatus and server of vehicle-state | |
| Quddus et al. | Modeling electric vehicle charging station expansion with an integration of renewable energy and Vehicle-to-Grid sources | |
| Pevec et al. | A data‐driven statistical approach for extending electric vehicle charging infrastructure | |
| CN109214719B (en) | Marketing inspection analysis system and method based on artificial intelligence | |
| CN109492894A (en) | Monitor the method, apparatus and server that vehicle is launched | |
| Ye et al. | A method for driving route predictions based on hidden Markov model | |
| CN109561387A (en) | Adjust the method, apparatus and server of fence | |
| CN108537691A (en) | A kind of region visit intelligent management system and method | |
| CN112132327A (en) | Multi-source data fusion-oriented intelligent planning system for power distribution network | |
| CN110471965A (en) | A kind of grid equipment NQI one-stop service cloud platform system | |
| Simolin et al. | Charging powers of the electric vehicle fleet: Evolution and implications at commercial charging sites | |
| Feng et al. | [Retracted] Design and Simulation of Human Resource Allocation Model Based on Double‐Cycle Neural Network | |
| CN109819403A (en) | Generate the method, apparatus and electronic equipment of fence | |
| CN107305653A (en) | Low-voltage power distribution station area integrated evaluating method and device based on attribute mathematicses | |
| CN111914940B (en) | Shared vehicle station clustering method, system, device and storage medium | |
| Lin et al. | Intelligent bus operation optimization by integrating cases and data driven based on business chain and enhanced quantum genetic algorithm | |
| CN109670637A (en) | Building energy consumption prediction technique, storage medium, device and system | |
| Lu et al. | Charging and relocating optimization for electric vehicle car-sharing: an event-based strategy improvement approach | |
| Wang et al. | Big data in telecommunication operators: data, platform and practices | |
| Kamel et al. | A modelling platform for optimizing time-dependent transit fares in large-scale multimodal networks | |
| Fu et al. | Exploration of the spatiotemporal heterogeneity of metro ridership prompted by built environment: A multi‐source fusion perspective | |
| CN111277515A (en) | Source network load storage ubiquitous adjustable resource pool system and construction method | |
| CN111123778B (en) | Method and device for monitoring vehicle use condition and electronic equipment | |
| CN111208384A (en) | Smart power grid management system | |
| CN115049158B (en) | Method, system, storage medium and terminal for predicting running state of urban system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201216 Address after: Room 168, building 6, 741 Hangzhou Road, Yangpu District, Shanghai 200090 Applicant after: HANHAI INFORMATION TECHNOLOGY SHANGHAI Co.,Ltd. Address before: Room Bnan 1231, 2 bungalows, No. 5 Road, College, Haidian District, Beijing, 100191 Applicant before: BEIJING MOBIKE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right |