CN117196318A - Risk analysis method and device for large-scale engineering vehicle and computer equipment - Google Patents
Risk analysis method and device for large-scale engineering vehicle and computer equipment Download PDFInfo
- Publication number
- CN117196318A CN117196318A CN202311445796.7A CN202311445796A CN117196318A CN 117196318 A CN117196318 A CN 117196318A CN 202311445796 A CN202311445796 A CN 202311445796A CN 117196318 A CN117196318 A CN 117196318A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driver
- risk
- information
- scale
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 79
- 238000010276 construction Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000013210 evaluation model Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a risk analysis method, a risk analysis device and computer equipment for a large-scale engineering vehicle. The method comprises the following steps: the method comprises the steps of acquiring operation data and driver information of a large-scale engineering vehicle in a previous evaluation period from a vehicle operator, and acquiring vehicle information, violation information and risk record of the large-scale engineering vehicle to be evaluated; constructing a first risk assessment index of a large-scale industrial vehicle to be assessed; extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data; embedding the large-scale engineering Cheng Cheliang to be evaluated by utilizing a first relationship network and a second relationship network to obtain vehicle embedded information; constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information; and obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index. By adopting the method, the risk of the large-scale engineering vehicle can be accurately predicted.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a risk analysis method, apparatus, and computer device for a large-scale industrial vehicle.
Background
Currently, the premium of a vehicle is estimated, and the potential risk of the vehicle is generally prejudged, so that the premium of the vehicle is estimated, and after a certain running data is accumulated, the running data is introduced to adjust the premium of the vehicle.
In the field of large engineering vehicles, the assessment of the premium is extremely difficult, on one hand, the engineering vehicles are hung under the enterprise name, and the risk of the vehicles cannot be predicted by combining the driving behaviors of drivers, so that the premium is assessed, and on the other hand, the premium of the large engineering vehicles cannot be accurately predicted and assessed due to large differences of the working environments of the large engineering vehicles at different times.
Disclosure of Invention
Based on the above, it is necessary to provide a risk analysis method, apparatus and computer device for a large-scale engineering vehicle, so as to correlate the risk with the premium by analyzing the risk of the large-scale engineering vehicle, thereby accurately predicting the premium.
A risk analysis method for a large industrial vehicle, the method comprising:
the method comprises the steps of acquiring operation data and driver information of a large-scale engineering vehicle in a previous evaluation period from a vehicle operator, and acquiring vehicle information, violation information and risk record of the large-scale engineering vehicle to be evaluated;
constructing a first risk assessment index of the large-scale industrial vehicle to be assessed according to the driver information, the vehicle information, the violation information and the risk record;
extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data;
embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information;
constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index.
In one embodiment, the method further comprises: the method comprises the steps of taking a large-scale engineering vehicle to be evaluated as a center, establishing a first-layer connection relation between the large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same operation task according to the operation data, and then sequentially taking the large-scale engineering vehicle of the first-layer connection relation as the center, establishing at least three layers of connection relation to obtain a first relation network; and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network.
In one embodiment, the method further comprises: embedding a driver according to the neighbor nodes in the second relation network to obtain a driver embedding representation; embedding the driver embedded representation into a large engineering vehicle of a first relation network according to the corresponding relation between the driver and the large engineering vehicle; and embedding the large engineering vehicle to be evaluated according to the neighbor nodes in the first relation network to obtain vehicle embedded information of the large engineering vehicle to be evaluated.
In one embodiment, embedding the driver means embedding a risk factor of the driver, embedding the large-scale vehicle to be evaluated means embedding a fault factor of the large-scale vehicle to be evaluated; further comprises: and obtaining a second risk assessment index of the large-sized industrial vehicle to be assessed according to the risk factors and the fault factors embedded in the vehicle embedded information.
In one embodiment, the method further comprises: and embedding the driver by adopting a Node2Vec model according to the neighbor nodes in the second relation network to obtain driver embedding.
In one embodiment, the method further comprises: constructing basic evaluation characteristics according to the first risk evaluation indexes, and constructing expansion evaluation characteristics according to the second risk evaluation indexes; and after the basic evaluation features and the expansion evaluation features are spliced, inputting a pre-trained evaluation model, and outputting a risk evaluation result of the large-scale industrial vehicle to be evaluated.
A risk analysis device for a large industrial vehicle, the device comprising:
the information acquisition module is used for acquiring the operation data and the driver information of the large-scale engineering vehicle in the previous evaluation period from the vehicle operator and acquiring the vehicle information, the violation information and the risk record of the large-scale engineering vehicle to be evaluated;
the first evaluation index construction module is used for constructing a first risk evaluation index of the large-scale industrial vehicle to be evaluated according to the driver information, the vehicle information, the violation information and the risk record;
the second evaluation index construction module is used for extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data; embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information; constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and the evaluation module is used for obtaining a risk evaluation result of the large-sized vehicle to be evaluated according to the first risk evaluation index and the second risk evaluation index.
In one embodiment, the second evaluation index construction module is further configured to establish a first-layer connection relationship between the large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same task according to the operation data by using the large-scale engineering vehicle to be evaluated as a center, and then sequentially establish at least three-layer connection relationships by using the large-scale engineering vehicle of the first-layer connection relationship as a center, so as to obtain a first relationship network; and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
the method comprises the steps of acquiring operation data and driver information of a large-scale engineering vehicle in a previous evaluation period from a vehicle operator, and acquiring vehicle information, violation information and risk record of the large-scale engineering vehicle to be evaluated;
constructing a first risk assessment index of the large-scale industrial vehicle to be assessed according to the driver information, the vehicle information, the violation information and the risk record;
extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data;
embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information;
constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
the method comprises the steps of acquiring operation data and driver information of a large-scale engineering vehicle in a previous evaluation period from a vehicle operator, and acquiring vehicle information, violation information and risk record of the large-scale engineering vehicle to be evaluated;
constructing a first risk assessment index of the large-scale industrial vehicle to be assessed according to the driver information, the vehicle information, the violation information and the risk record;
extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data;
embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information;
constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index.
According to the risk analysis method, the device, the computer equipment and the storage medium for the large-scale engineering vehicle, firstly, the operation data and the driver information of the large-scale engineering vehicle in the previous evaluation period are acquired from the vehicle operator, the vehicle information, the violation information and the risk record of the large-scale engineering vehicle to be evaluated are acquired, it can be known that the driver information and the vehicle information, the violation information and the risk record of the large-scale engineering vehicle to be evaluated are more conventional information and are basic data for risk evaluation, and the risk information of the large-scale engineering vehicle can be basically evaluated, so that a first risk evaluation index is set, and through the creative operation-based data, a first relation network of the large-scale engineering vehicle and a second relation network of the driver are extracted, and through a graph embedding technology, a second risk evaluation index is constructed, so that the characteristics of centralized operation and non-immobilization of the driver of the large-scale engineering vehicle are reflected, and the risk evaluation result is more accurate by assisting the first risk evaluation index.
Drawings
FIG. 1 is a flow chart of a risk analysis method for a large industrial vehicle in one embodiment;
FIG. 2 is a block diagram of a risk analysis device for a large industrial vehicle in one embodiment;
FIG. 3 is an internal block diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In one embodiment, as shown in fig. 1, there is provided a risk analysis method of a large industrial vehicle, including the steps of:
step 102, the operation data and the driver information of the large engineering vehicle in the previous evaluation period are retrieved from the vehicle operator, and the vehicle information, the violation information and the risk record of the large engineering vehicle to be evaluated are obtained.
It should be noted that, for large engineering vehicles, vehicle tracking and sensors are typically installed to collect data about the vehicle's usage, such as speed, route of travel, etc., and Geographic Information Systems (GIS) are also installed to determine the regional risk of the vehicle operation.
The vehicle data in this step refers to a large number of engineering vehicles, and after the data is cleaned, the work task corresponds to a large engineering vehicle by using a sensor, a Geographic Information System (GIS) and provided text information, and generally, for one work task, a plurality of large engineering vehicles are required to participate, and risks faced by the large engineering vehicle are similar under the influence of the same factors such as geographic environment, work task intensity, weather, etc.
For example, in the last year, a certain engineering vehicle does not violate rules and is not in danger, but in the case that a vehicle working together with the engineering vehicle for a long time breaks down and is in danger, if the risk value of the next year of the engineering vehicle which is not in danger is smaller in a conventional linear calculation index mode, however, in a practical situation, the probability of the occurrence of the fault of the long-term high-strength operation is necessarily increased, and in consideration of this, the possible risk of the engineering vehicle can be estimated more accurately. Likewise, the engineering vehicle has no violations and no danger, and the vehicle working together with the engineering vehicle for a long time has better danger data, which means that the risk value of the whole operation of the engineering vehicle is lower, so that the risk value of no violations and no danger is lower.
And 104, constructing a first risk assessment index of the large-scale industrial vehicle to be assessed according to the driver information, the vehicle information, the violation information and the risk record.
In general, a generalized linear multiplication or addition model may be employed to construct the first risk assessment indicator.
Step 106, extracting a first relation network of the large-scale engineering vehicle and a second relation network of the driver from the operation data.
In the step, after data cleaning, a first relation network of a large-scale engineering vehicle can be extracted through operation data, wherein the first relation network is constructed by taking engineering vehicles as nodes, and whether the engineering vehicles participate in the same operation task or not considers that a connecting edge exists or not, so that the first relation network is constructed.
Similarly, for the driver, whether to participate in the same job task considers whether a binding exists, thereby constructing a second relationship network.
The first relation network and the second relation network can reflect the risk degree of future operation tasks of the engineering vehicle to a certain extent in never operation, so that the possibility that the same driver participates in the same operation task is very high for the driver, and the information can be reflected through the first relation network and the second relation network.
And step 108, embedding the large-scale work Cheng Cheliang to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information.
And according to the connection between the engineering vehicle and the driver, establishing a relation between the first relation network and the second relation network, and then embedding the large engineering vehicle to be evaluated, so that the vehicle embedding information can be obtained.
And 110, constructing a second risk assessment index of the large-sized industrial vehicle to be assessed according to the vehicle embedded information.
And step 112, obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index.
In the risk analysis method of the large engineering vehicle, firstly, the operation data and the driver information of the large engineering vehicle in the previous evaluation period are acquired from the vehicle operator, and the vehicle information, the violation information and the risk record of the large engineering vehicle to be evaluated are acquired, and it is known that the driver information and the vehicle information, the violation information and the risk record of the large engineering vehicle to be evaluated are more conventional information and are basic data for risk evaluation, so that the risk information of the large engineering vehicle can be basically evaluated, and therefore, a first risk evaluation index is set.
In one embodiment, a first-layer connection relation between a large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same operation task is established by taking the large-scale engineering vehicle to be evaluated as a center according to operation data, and then a first relation network is obtained by sequentially taking the large-scale engineering vehicle of the first-layer connection relation as a center and establishing at least three layers of connection relations; and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network. In this embodiment, in order to find potential relationships as much as possible when vehicle evaluation is performed, a first relationship network and a second relationship network of not less than three layers of connections are established.
In one embodiment, embedding the driver according to the neighbor nodes in the second relationship network to obtain a driver embedded representation; embedding the driver embedded representation into the large engineering vehicle of the first relation network according to the corresponding relation between the driver and the large engineering vehicle; embedding the large-scale engineering vehicle to be evaluated according to the neighbor nodes in the first relation network to obtain vehicle embedding information of the large-scale engineering vehicle to be evaluated.
In this embodiment, the information of the driver is fused to the large-scale engineering vehicle, so that the neighboring nodes in the second relationship network are first embedded into the driver to obtain the driver embedded representation, and then the driver embedded representation is embedded into the large-scale engineering vehicle of the first relationship network according to the corresponding relationship between the driver and the large-scale engineering vehicle, and it is worth noting that other neighboring nodes are fused with the information of the driver corresponding to the neighboring nodes.
In one embodiment, embedding the driver means embedding a risk factor of the driver, embedding the large-scale vehicle to be evaluated means embedding a fault factor of the large-scale vehicle to be evaluated; and obtaining a second risk assessment index of the large-sized industrial vehicle to be assessed according to the risk factors and the fault factors embedded in the vehicle embedded information.
In this embodiment, by analyzing a driver, the risk factor may be calibrated for the driver, where the risk factor calibration is generally implemented according to driving years, ages, sexes, violation information, etc., so as to evaluate the risk factor of the driver, and the fault factor of the vehicle is generally comprehensively calculated according to factors such as the service life of the vehicle, the intensity of the operation task, the maintenance frequency, etc. For the second relation network, the risk factors can be fused through embedding of a driver, the fused risk factors correspond to the vehicle to be evaluated, and for the first relation network, the fault factors are fused through embedding of the engineering vehicle, so that the vehicle embedding information comprises the fused risk factors and the fused fault factors for the vehicle to be evaluated.
In another embodiment, the risk factor and the fault factor may be combined in a spliced manner, so as to obtain the second risk assessment indicator.
In one embodiment, the Node2Vec model is adopted to embed the driver according to the neighbor nodes in the second relational network, so as to obtain driver embedding. Similarly, large industrial vehicles are embedded in the same manner.
In one embodiment, a basic evaluation feature is constructed according to the first risk evaluation index, and an expansion evaluation feature is constructed according to the second risk evaluation index; and after the basic evaluation features and the expansion evaluation features are spliced, inputting a pre-trained evaluation model, and outputting a risk evaluation result of the large-scale industrial vehicle to be evaluated.
In this embodiment, a traditional generalized linear multiplication or addition model is abandoned, and a model prediction mode is adopted, on one hand, because the second risk assessment index is only an index after data mining and is completely different from the first risk assessment index in dimension, the second risk assessment index is difficult to give corresponding weight to the second risk assessment index through a linear method or an addition model, and therefore the function of the second risk assessment index is exerted. In addition, the sample size constructed by the first risk assessment index and the second risk assessment index is sufficient, and the data change of the settled years can be accurately perceived through the model, so that the effect of the second risk assessment index can be reflected through continuous optimization of the model, and the risk assessment result of the large-scale industrial vehicle can be accurately predicted.
It is worth to say that the risk assessment result reflects the possibility of future faults, violations and other risks of the large-scale vehicle, the size of the risks and the amount of the premium are directly hooked, and the risk assessment result is not repeated.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.
In one embodiment, as shown in fig. 2, there is provided a risk analysis apparatus for a large-sized industrial vehicle, comprising: an information acquisition module 202, a first evaluation index construction module 204, a second evaluation index construction module 206, and an evaluation module 208, wherein:
an information obtaining module 202, configured to retrieve, from a vehicle operator, operation data and driver information of a large-sized industrial vehicle in a previous evaluation period, and obtain vehicle information, violation information and risk record of the large-sized industrial vehicle to be evaluated;
a first evaluation index construction module 204, configured to construct a first risk evaluation index of the large-scale industrial vehicle to be evaluated according to the driver information, the vehicle information, the violation information and the risk record;
a second evaluation index construction module 206 for extracting a first relationship network of the large-scale industrial vehicle and a second relationship network of the driver from the job data; embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information; constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and the evaluation module 208 is configured to obtain a risk evaluation result of the large-sized industrial vehicle to be evaluated according to the first risk evaluation index and the second risk evaluation index.
In one embodiment, the second evaluation index construction module 206 is further configured to, centering on the large-scale engineering vehicle to be evaluated, establish a first-layer connection relationship between the large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same task according to the operation data, and then sequentially establish at least three-layer connection relationships with the large-scale engineering vehicle of the first-layer connection relationship as centering on the large-scale engineering vehicle to be evaluated, so as to obtain a first relationship network; and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network.
In one embodiment, the second evaluation index construction module 206 is further configured to embed a driver according to the neighboring node in the second relationship network, so as to obtain a driver embedded representation; embedding the driver embedded representation into a large engineering vehicle of a first relation network according to the corresponding relation between the driver and the large engineering vehicle; and embedding the large engineering vehicle to be evaluated according to the neighbor nodes in the first relation network to obtain vehicle embedded information of the large engineering vehicle to be evaluated.
In one embodiment, embedding the driver means embedding a risk factor of the driver, embedding the large-scale vehicle to be evaluated means embedding a fault factor of the large-scale vehicle to be evaluated; the second evaluation index construction module 206 is further configured to obtain a second risk evaluation index of the large industrial vehicle to be evaluated according to the risk factor and the fault factor embedded in the vehicle embedded information.
In one embodiment, the second evaluation index construction module 206 is further configured to embed the driver by using a Node2Vec model according to the neighbor nodes in the second relational network, so as to obtain driver embedding.
In one embodiment, the evaluation module 208 is further configured to construct a basic evaluation feature according to the first risk evaluation index, and construct an extended evaluation feature according to the second risk evaluation index; and after the basic evaluation features and the expansion evaluation features are spliced, inputting a pre-trained evaluation model, and outputting a risk evaluation result of the large-scale industrial vehicle to be evaluated.
For specific limitations of the risk analysis device for large engineering vehicles, reference may be made to the above limitations of the risk analysis method for large engineering vehicles, and no further description is given here. The respective modules in the risk analysis device of the large-sized industrial vehicle described above may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a risk analysis method for a large industrial vehicle. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment a computer device is provided comprising a memory storing a computer program and a processor implementing the steps of the method of the above embodiments when the computer program is executed.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method of the above embodiments.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (9)
1. A method of risk analysis for a large industrial vehicle, the method comprising:
the method comprises the steps of acquiring operation data and driver information of a large-scale engineering vehicle in a previous evaluation period from a vehicle operator, and acquiring vehicle information, violation information and risk record of the large-scale engineering vehicle to be evaluated;
constructing a first risk assessment index of the large-scale industrial vehicle to be assessed according to the driver information, the vehicle information, the violation information and the risk record;
extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data;
embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information;
constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and obtaining a risk assessment result of the large-scale industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index.
2. The method of claim 1, wherein extracting a first relationship network for a large industrial vehicle and a second relationship network for a driver from the job data comprises:
the method comprises the steps of taking a large-scale engineering vehicle to be evaluated as a center, establishing a first-layer connection relation between the large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same operation task according to the operation data, and then sequentially taking the large-scale engineering vehicle of the first-layer connection relation as the center, establishing at least three layers of connection relation to obtain a first relation network;
and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network.
3. The method of claim 2, wherein embedding the large industrial vehicle to be evaluated using the first relationship network and the second relationship network to obtain vehicle embedded information comprises:
embedding a driver according to the neighbor nodes in the second relation network to obtain a driver embedding representation;
embedding the driver embedded representation into a large engineering vehicle of a first relation network according to the corresponding relation between the driver and the large engineering vehicle;
and embedding the large engineering vehicle to be evaluated according to the neighbor nodes in the first relation network to obtain vehicle embedded information of the large engineering vehicle to be evaluated.
4. A method according to claim 3, characterized in that the embedding of the driver means the embedding of risk factors of the driver, the embedding of the large industrial vehicle to be evaluated means the embedding of fault factors of the large industrial vehicle to be evaluated;
according to the vehicle embedded information, constructing a second risk assessment index of the large-scale industrial vehicle to be assessed, comprising:
and obtaining a second risk assessment index of the large-sized industrial vehicle to be assessed according to the risk factors and the fault factors embedded in the vehicle embedded information.
5. The method of claim 4, wherein embedding the driver according to the neighbor nodes in the second relationship network to obtain the driver embedded representation comprises:
and embedding the driver by adopting a Node2Vec model according to the neighbor nodes in the second relation network to obtain driver embedding.
6. The method according to any one of claims 1 to 5, wherein obtaining a risk assessment result of the large industrial vehicle to be assessed according to the first risk assessment index and the second risk assessment index comprises:
constructing basic evaluation characteristics according to the first risk evaluation indexes, and constructing expansion evaluation characteristics according to the second risk evaluation indexes;
and after the basic evaluation features and the expansion evaluation features are spliced, inputting a pre-trained evaluation model, and outputting a risk evaluation result of the large-scale industrial vehicle to be evaluated.
7. A risk analysis device for a large industrial vehicle, the device comprising:
the information acquisition module is used for acquiring the operation data and the driver information of the large-scale engineering vehicle in the previous evaluation period from the vehicle operator and acquiring the vehicle information, the violation information and the risk record of the large-scale engineering vehicle to be evaluated;
the first evaluation index construction module is used for constructing a first risk evaluation index of the large-scale industrial vehicle to be evaluated according to the driver information, the vehicle information, the violation information and the risk record;
the second evaluation index construction module is used for extracting a first relation network of the large-scale engineering vehicle and a second relation network of a driver from the operation data; embedding a large-scale engineering vehicle to be evaluated by utilizing the first relation network and the second relation network to obtain vehicle embedded information; constructing a second risk assessment index of the large-scale industrial vehicle to be assessed according to the vehicle embedded information;
and the evaluation module is used for obtaining a risk evaluation result of the large-sized vehicle to be evaluated according to the first risk evaluation index and the second risk evaluation index.
8. The apparatus of claim 7, wherein the second evaluation index construction module is further configured to, based on the operation data, establish a first-layer connection relationship between the large-scale engineering vehicle to be evaluated and the large-scale engineering vehicle of the same operation task, and then sequentially establish a connection relationship of not less than three layers with the large-scale engineering vehicle of the first-layer connection relationship as a center, so as to obtain a first relationship network; and setting up a first-layer connection relation between the driver and the driver of the same operation task according to the operation data by taking the driver as a center, and setting up at least three layers of connection relations by taking the driver of the first-layer connection relation as a center in sequence to obtain a second relation network.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311445796.7A CN117196318B (en) | 2023-11-02 | 2023-11-02 | Risk analysis method and device for large-scale engineering vehicle and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311445796.7A CN117196318B (en) | 2023-11-02 | 2023-11-02 | Risk analysis method and device for large-scale engineering vehicle and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117196318A true CN117196318A (en) | 2023-12-08 |
| CN117196318B CN117196318B (en) | 2024-01-30 |
Family
ID=88985351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311445796.7A Active CN117196318B (en) | 2023-11-02 | 2023-11-02 | Risk analysis method and device for large-scale engineering vehicle and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196318B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306367A (en) * | 2011-08-05 | 2012-01-04 | 江苏吉美思物联网产业股份有限公司 | Internet-of-things-based online risk evaluation and control system for engineering machine |
| CN103150675A (en) * | 2013-01-30 | 2013-06-12 | 郁佳敏 | Risk monitoring system of automobile insurance |
| US9396494B1 (en) * | 2013-03-14 | 2016-07-19 | Liberty Mutual Insurance Company | Carsharing peril analysis |
| CN106447139A (en) * | 2016-12-06 | 2017-02-22 | 北京中交兴路信息科技有限公司 | Actuarial method and device based on vehicle driving behaviors |
| KR20170115831A (en) * | 2016-04-08 | 2017-10-18 | 삼성에스디에스 주식회사 | Method and apparatus for guiding automobile insurance using driver recognizing |
| US20170365007A1 (en) * | 2016-06-16 | 2017-12-21 | Allstate Insurance Company | Traveling-Based Insurance Ratings |
| CN109544351A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | Vehicle risk appraisal procedure, device, computer equipment and storage medium |
| US20190100216A1 (en) * | 2017-09-29 | 2019-04-04 | Denso International America, Inc. | Risk Assessment System For Assessing Current Driver Behavior Relative to Past Behavior and Behaviors of Other Drivers |
| CN109636250A (en) * | 2019-01-17 | 2019-04-16 | 长安大学 | A kind of prediction technique of dangerous cargo truck survival probability and dangerous probability |
| US10529046B1 (en) * | 2016-02-08 | 2020-01-07 | Allstate Insurance Company | Vehicle rating system |
| CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
| CN112039956A (en) * | 2020-08-13 | 2020-12-04 | 宜宾凯翼汽车有限公司 | Driving data-based vehicle insurance data monitoring and processing system and method |
| US20210110480A1 (en) * | 2019-10-13 | 2021-04-15 | TrueLite Trace, Inc. | Intelligent machine sensing and machine learning-based commercial vehicle insurance risk scoring system |
| CN113065902A (en) * | 2021-04-22 | 2021-07-02 | 中国平安财产保险股份有限公司 | Data processing-based cost setting method and device and computer equipment |
-
2023
- 2023-11-02 CN CN202311445796.7A patent/CN117196318B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306367A (en) * | 2011-08-05 | 2012-01-04 | 江苏吉美思物联网产业股份有限公司 | Internet-of-things-based online risk evaluation and control system for engineering machine |
| CN103150675A (en) * | 2013-01-30 | 2013-06-12 | 郁佳敏 | Risk monitoring system of automobile insurance |
| US9396494B1 (en) * | 2013-03-14 | 2016-07-19 | Liberty Mutual Insurance Company | Carsharing peril analysis |
| US10529046B1 (en) * | 2016-02-08 | 2020-01-07 | Allstate Insurance Company | Vehicle rating system |
| KR20170115831A (en) * | 2016-04-08 | 2017-10-18 | 삼성에스디에스 주식회사 | Method and apparatus for guiding automobile insurance using driver recognizing |
| US20170365007A1 (en) * | 2016-06-16 | 2017-12-21 | Allstate Insurance Company | Traveling-Based Insurance Ratings |
| CN106447139A (en) * | 2016-12-06 | 2017-02-22 | 北京中交兴路信息科技有限公司 | Actuarial method and device based on vehicle driving behaviors |
| US20190100216A1 (en) * | 2017-09-29 | 2019-04-04 | Denso International America, Inc. | Risk Assessment System For Assessing Current Driver Behavior Relative to Past Behavior and Behaviors of Other Drivers |
| CN109544351A (en) * | 2018-10-12 | 2019-03-29 | 平安科技（深圳）有限公司 | Vehicle risk appraisal procedure, device, computer equipment and storage medium |
| CN109636250A (en) * | 2019-01-17 | 2019-04-16 | 长安大学 | A kind of prediction technique of dangerous cargo truck survival probability and dangerous probability |
| CN110717821A (en) * | 2019-09-09 | 2020-01-21 | 上海凯京信达科技集团有限公司 | Vehicle loan assessment method and device, computer storage medium and electronic equipment |
| US20210110480A1 (en) * | 2019-10-13 | 2021-04-15 | TrueLite Trace, Inc. | Intelligent machine sensing and machine learning-based commercial vehicle insurance risk scoring system |
| CN112039956A (en) * | 2020-08-13 | 2020-12-04 | 宜宾凯翼汽车有限公司 | Driving data-based vehicle insurance data monitoring and processing system and method |
| CN113065902A (en) * | 2021-04-22 | 2021-07-02 | 中国平安财产保险股份有限公司 | Data processing-based cost setting method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117196318B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10248490B2 (en) | Systems and methods for predictive reliability mining | |
| US8880962B2 (en) | Maintenance planning and failure prediction from data observed within a time window | |
| Antonio et al. | Micro-level stochastic loss reserving for general insurance | |
| Fauriat et al. | Optimization of an aperiodic sequential inspection and condition-based maintenance policy driven by value of information | |
| Godoy et al. | Critical spare parts ordering decisions using conditional reliability and stochastic lead time | |
| Braaksma et al. | A quantitative method for failure mode and effects analysis | |
| Said et al. | Utilizing telematics data to support effective equipment fleet-management decisions: Utilization rate and hazard functions | |
| Khaleghei et al. | Reliability estimation of a system subject to condition monitoring with two dependent failure modes | |
| Li et al. | What makes long‐term monitoring convenient? A parametric analysis of value of information in infrastructure maintenance | |
| CN110471945B (en) | Active data processing method, system, computer equipment and storage medium | |
| Chen et al. | Optimal variability sensitive condition-based maintenance with a Cox PH model | |
| CN102693262A (en) | Method of determining the influence of a variable in a phenomenon | |
| Apeland et al. | A fully subjective approach to modelling inspection maintenance | |
| CN111666171A (en) | Fault identification method and device, electronic equipment and readable storage medium | |
| US11488083B2 (en) | Risk failure prediction for line assets | |
| Nichols et al. | Structural integrity management system (SIMS) implementation within PETRONAS’operations | |
| CN117196318B (en) | Risk analysis method and device for large-scale engineering vehicle and computer equipment | |
| Clarke-Sather et al. | Application of lean engineering to bridge inspection | |
| Geara et al. | Hybrid inspection-monitoring approach for optimal maintenance planning | |
| CN113824590B (en) | Method for predicting problem in micro service network, computer device, and storage medium | |
| Larsson Ivanov et al. | The practical value of structural health information for time dependence in bridge maintenance | |
| Joshi | Recent Enhancement of Indian Bridge Management System | |
| Ha et al. | Simplified nonlinear model for the weight estimation of FPSO plant topside using the statistical method | |
| Straub | Reliability assessment of deteriorating structures: Challenges and (some) solutions | |
| US20200143004A1 (en) | Visualization of machine structure damage from machine sensor data using machine learning |
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 |