CN112634066A

CN112634066A - Method and device for analyzing sales vehicle type through vehicle identification number

Info

Publication number: CN112634066A
Application number: CN202011566293.1A
Authority: CN
Inventors: 周凯; 常恩浚; 张明磊; 王旭; 康健; 周亚贺
Original assignee: Data Enlighten Beijing Co ltd
Current assignee: Data Enlighten Beijing Co ltd
Priority date: 2020-12-25
Filing date: 2020-12-25
Publication date: 2021-04-09
Anticipated expiration: 2040-12-25
Also published as: CN112634066B

Abstract

The invention discloses a method and a device for analyzing a sales vehicle type through a vehicle identification number. The method comprises the following steps: receiving a vehicle identification number, and extracting relatively independent identification sections according to the coding rule of the vehicle identification number; inquiring the corresponding relation between each identification section in a vehicle type database and each vehicle information part included in the sold vehicle type, and analyzing each identification section into corresponding vehicle information; combining the vehicle information corresponding to each identification section to obtain a sales vehicle type; and outputting the sales vehicle model when the obtained sales vehicle model is unique. The device includes: the vehicle-mounted information processing system comprises an identification section extraction unit, an identification section analysis unit, an information combination unit and a vehicle type output unit. The method and the device realize accurate analysis from the vehicle identification number to the sold vehicle type.

Description

Method and device for analyzing sales vehicle type through vehicle identification number

Technical Field

The invention relates to analysis technology in the field of automobiles, in particular to a method and a device for analyzing a sold vehicle type through a vehicle identification number.

Background

In a supply system of an automobile aftermarket, manufacturers are familiar with technical parameter information of accessory products, concepts of automobiles assembled with the products are fuzzy or nonuniform, automobile distributors cannot clearly know the technical parameters of the accessory products as the manufacturers do, however, the automobile distributors often have deeper understanding of automobile models because of long-term participation in transactions, and automobile model information with the finest granularity, which can be collected by public information, is automobile model selling information, so the automobile distributors can adapt the accessory products to the lower parts of automobile models in the transactions so as to facilitate query and improve the efficiency and the precision of the transactions. However, another problem arises because the automobile dealer needs the vehicle type information to accurately select the matched accessory product when selling, but the automobile repair shop often cannot know the specific and accurate vehicle type information, and the information that the automobile repair shop can see is only the Vehicle Identification Number (VIN) on the physical automobile nameplate, which is unique identification information for each automobile. Therefore, a tool capable of accurately identifying a Vehicle Identification Number (VIN) as a Vehicle model for which a product is adapted by a supplier is an essential part of a supply chain transaction system.

In the second-hand vehicle transaction, when a vehicle dealer receives a vehicle, the dealer needs to know the actual model information corresponding to the vehicle to accurately evaluate the vehicle price, but the information is not available on the vehicle title certificate. Therefore, in most scenes, a driver can only judge the type of the automobile by virtue of own experience and by referring to appearance configurations of some automobiles, but if the automobile is provided with accessories additionally arranged at a later stage, such as a camera, navigation and the like, the judgment of the driver is often greatly influenced. For example, an official guide price of a gasoline audi A6L 2011 version of 2.4L technology is: 44.1 ten thousand; an official guide price of a gasoline audi A6L 2011 version 2.4L luxury is: 54.2 ten thousand, the difference between the two types of vehicles is 10 thousand. From the perspective of configuration differences, the visually apparent difference is the reverse image, but if the owner installs the configuration a second time, only 1-2 thousand dollars may be required. Once misjudged, great economic loss is caused. Therefore, a tool that can accurately identify the VIN as a model of a vehicle for sale would be of great help to the assessment of the price of the vehicle in a used vehicle transaction.

In the insurance field, the insurance premium of the automobile is generally estimated according to the price of the automobile when a new automobile is insured, so that the VIN of an insured automobile is put under the sales edition type information for the convenience of unifying the standard and managing. However, the insurer often does not have the ability to determine the vehicle type, and often places the vehicle under an equal or similar vehicle type based on the vehicle price. Therefore, the difficulty in judging whether the accessories of the vehicle are original accessories or not is greatly brought to claim settlement, for example, SUVs in the market have tides with additional pedals, but the price difference between the original pedals and the additional pedals is even more than ten times, and the great risk of claim error is brought. Therefore, a tool capable of accurately identifying VIN as a vehicle model for sale can bring great help to judgment and loss reduction of insurance claims.

At present, although some similar tools for resolving the version through the VIN exist in the market, the precision use has a large problem.

Disclosure of Invention

The invention innovatively provides a method and a device for analyzing a sales vehicle type through a vehicle identification number, and realizes accurate analysis from the vehicle identification number to vehicle sales model information.

In order to achieve the technical purpose, the invention discloses a method for analyzing a sales vehicle type through a vehicle identification number. The method for analyzing the vehicle type for sale through the vehicle identification number comprises the following steps: receiving a vehicle identification number, and extracting relatively independent identification sections according to the coding rule of the vehicle identification number; inquiring the corresponding relation between each identification section in a vehicle type database and each vehicle information part included in the sold vehicle type, and analyzing each identification section into corresponding vehicle information; combining the vehicle information corresponding to each identification section to obtain a sales vehicle type; and outputting the sales vehicle model when the obtained sales vehicle model is unique.

Further, the method for analyzing the vehicle model for sale through the vehicle identification number further comprises the following steps: when the obtained sales vehicle type is not unique, acquiring accessory information through the vehicle identification number; acquiring accessory information respectively included by each sold vehicle type from a vehicle type database; cross matching various accessories in accessory information included in each sales vehicle type acquired from a vehicle type database with similar accessories in accessory information acquired through the vehicle identification number; selecting a selling vehicle model with the highest matching degree of accessories and judging whether the selling vehicle model with the highest matching degree is unique; and outputting the sold vehicle model when the sold vehicle model with the highest matching degree is unique.

Further, for the method for analyzing the sales vehicle types through the vehicle identification numbers, cross-matching various types of accessories in accessory information included in each sales vehicle type acquired from a vehicle type database with similar types of accessories in accessory information acquired through the vehicle identification numbers includes the following positive selection and scoring processes: for similar standard accessories in matching, adding a score corresponding to the weight to a matching degree score corresponding to a sales vehicle type to which the accessory belongs according to the weight configured by the accessory; and the final sold vehicle type with the highest score obtained in the positive loading scoring process is used as the sold vehicle type with the highest matching degree of accessories.

Further, for the method for analyzing the sales vehicle types by the vehicle identification numbers, cross-matching is performed between various types of accessories in accessory information included in each sales vehicle type acquired from a vehicle type database and similar types of accessories in accessory information acquired by the vehicle identification numbers, and the method further comprises the following matching scoring processes: when the sales vehicle model with the highest final score obtained in the positive loading and scoring process is not unique, for similar matching accessories in matching, adding a score corresponding to the weight to a matching degree score corresponding to the sales vehicle model to which the accessory belongs according to the weight configured by the accessories; and the selling vehicle model with the highest final score obtained in the matching scoring process is used as the selling vehicle model with the highest matching degree of accessories.

Further, for the method for analyzing the sales vehicle model by the vehicle identification number, various accessories in accessory information included in each sales vehicle model acquired from a vehicle model database are cross-matched with similar accessories in accessory information acquired by the vehicle identification number, and the method further comprises the steps of

The method comprises the following steps of negative selection grading: when the sale vehicle type with the highest final score obtained in the grading process is selected to be not unique, for the similar standard distribution accessories which are not matched, according to the weight configured by the accessories, deducting the score corresponding to the weight from the matching degree score corresponding to the sale vehicle type to which the accessories belong; and taking the final sold vehicle type with the highest score obtained in the negative loading scoring process as the sold vehicle type with the highest accessory matching degree.

Further, for the method for analyzing the vehicle model sold through the vehicle identification number, the weight of the accessory is related to the identification degree of the accessory, and the weight is larger when the identification degree of the accessory is higher.

Further, in the method for analyzing the model of the vehicle for sale through the vehicle identification number, the weight of the configuration of the matching accessory is greater than the weight of the configuration of the matching accessory.

Further, the method for analyzing the vehicle model for sale through the vehicle identification number further comprises the following steps: when the sold vehicle type with the highest matching degree is not unique, calling a prediction model; inputting at least part of the vehicle identification number into the prediction model to obtain a predicted sales vehicle model; taking an intersection of the predicted sales vehicle type and the sales vehicle type with the highest matching degree; and outputting the sales vehicle type when the sales vehicle type in the intersection is unique.

Further, for the method for analyzing the vehicle model sold through the vehicle identification number, the prediction model comprises a plurality of prediction models with different precision levels, at least part of the vehicle identification number is firstly input into the prediction model with the highest precision level, if no output result exists, the prediction model with one precision level lower than the prediction model with the highest precision level is input, and the like until the output result is obtained.

Further, for the method for analyzing the sales vehicle types through the vehicle identification numbers, when the sales vehicle types in the intersection are not unique, a significant difference item algorithm is called to obtain significant difference items of all the sales vehicle types in the intersection and return the significant difference items to the user; and receiving the click of the configuration condition in the significant difference item by the user according to the vehicle configuration condition, obtaining the unique sold vehicle type and outputting the unique sold vehicle type.

In order to achieve the above technical object, in another aspect, the present invention discloses an apparatus for analyzing a model of a vehicle for sale by a vehicle identification number. The device for analyzing the vehicle type for sale through the vehicle identification number comprises: the identification section extraction unit is used for receiving the vehicle identification number and extracting each relatively independent identification section according to the coding rule of the vehicle identification number; the identification section analysis unit is used for inquiring the corresponding relation between each identification section in the vehicle type database and each vehicle information part included in the sales vehicle type so as to analyze each identification section into corresponding vehicle information; the information combination unit is used for combining the vehicle information corresponding to each identification section to obtain a sales vehicle type; and a vehicle type output unit for outputting the sales vehicle type when the obtained sales vehicle type is unique.

To achieve the above technical object, in yet another aspect, the present invention discloses a computing device. The computing device includes: one or more processors, and a memory coupled with the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the above-described method.

To achieve the above technical objects, in yet another aspect, the present invention discloses a machine-readable storage medium. The machine-readable storage medium stores executable instructions that, when executed, cause the machine to perform the above-described method.

The invention has the beneficial effects that:

the method and the device for analyzing the vehicle type for sale through the vehicle identification number realize accurate analysis from the vehicle identification number to the type through the matching algorithm. The mapping between the vehicle identification number configuration information and the SID configuration information is established, the accuracy of the relationship from VIN to SID can be detected, and batch adjustment and repair can be carried out when problems occur. And establishing a complete grading mechanism comprising positive and negative option and configuration item weight ranking so as to ensure the uniqueness and accuracy of the analyzed SID. Through big data analysis, a set of prediction mechanism is established, and VIN to SID with strong rules are solidified so as to assist in resolving the condition that the VIN and SID are not unique. And a set of complete VIN rules under the SID is established to ensure that all algorithm analysis results are within a correct optional range, so that the analysis accuracy is further guaranteed. And establishing a significant difference item algorithm under each main model information, so as to be used for distinguishing the SID to be unique through significant difference item point selection in the case that the SID is not unique.

Drawings

In the figure, the position of the upper end of the main shaft,

fig. 1 is a flowchart of a method for analyzing a vehicle type for sale through a vehicle identification number according to embodiment 1 of the present invention;

FIG. 2 is a flow chart of a method for resolving a model of a vehicle for sale via a vehicle identification number according to an exemplary embodiment of the present invention;

FIG. 3 is a flow chart of a method for resolving a model of a vehicle for sale via a vehicle identification number according to another embodiment of the present invention;

FIG. 4 is a flow chart of a method for resolving a model of a vehicle for sale via a vehicle identification number according to yet another example of the present invention;

fig. 5 is a flowchart of a method for analyzing a vehicle type for sale through a vehicle identification number according to embodiment 2 of the present invention;

fig. 6 is a flowchart of step S509 in embodiment 2 according to an example of the present invention;

fig. 7 is a schematic structural diagram of an apparatus for analyzing a model of a vehicle for sale through a vehicle identification number according to embodiment 3 of the present invention;

fig. 8 is a block diagram of a computing device for processing a sales vehicle model resolved by vehicle identification number according to an embodiment of the present invention.

Detailed Description

The method and the device for analyzing the vehicle model (SID) through the Vehicle Identification Number (VIN) according to the present invention will be explained and explained in detail with reference to the drawings.

Fig. 1 is a flowchart of a method for analyzing a vehicle model for sale through a vehicle identification number according to embodiment 1 of the present invention.

As shown in fig. 1, in step S110, a Vehicle Identification Number (VIN) is received, and relatively independent identification sections are extracted according to an encoding rule of the vehicle identification number. Where VIN may be an encoding of 17-bit characters.

In step S120, the correspondence relationship between each identification section and each vehicle information portion included in the sales vehicle type in the vehicle type database is queried, so that each identification section is resolved into corresponding each vehicle information. The vehicle information may include, among other things, manufacturer, year of manufacture, and/or model such as luxury, general, etc.

In step S130, the vehicle information corresponding to each identification section is combined to obtain a sales vehicle type (SID).

In step S140, when the obtained sales vehicle model is unique, the sales vehicle model is output.

Specifically, the model data refers to the sum of defined fields required to accurately describe the model in the model database. The greater the number of defined fields, the longer the length of the different defined fields in a certain logical arrangement, and the more information the defined fields contain, the more accurate the vehicle type data. The vehicle model data may be specifically classified into vehicle model data and attached vehicle model parameter data. The vehicle model data is used for defining a vehicle model. The vehicle model parameter data is used for describing vehicle model configuration. Vehicle model data can be generally subdivided in a variety of forms, such as host plant vehicle model name, department post number, distribution channel sales layout, vehicle body form, country, and/or taxonomically defined parameter configuration. The data in the vehicle model database of this embodiment is the representation of different vehicle models that have been used in the market of the after-market after the vehicle is sorted, a set of more standardized vehicle model description information is sorted after the standardization of field definitions, and the vehicle model information of the host factory, such as a chassis number, an engine model, and/or a transmission model, is combined at the same time. A set of vehicle group definition specifications is formed from the host factory chassis dimension, and vehicle type definition is more accurate and understandable. As a specific example, the entire vehicle model database has more than 15 pieces of information in the transverse direction, covers 99.9% of vehicle models of passenger vehicles, has more than 150 detailed fields with reasonable value in each vehicle model in the longitudinal direction for representing, and can include chassis number data, vehicle chassis classification data, engine and replacement number data, department of industry bulletin number data, suspension and damper data, tire hub data, and information of marketing condition and replacement change.

Next, a method of establishing correspondence between each identification section in the vehicle type database and each vehicle information portion included in the sales vehicle type will be described by way of example.

For the independent brand and the joint-venture brand, a vehicle bulletin number is reported to a letter department during vehicle production, and the bulletin number comprises the front 8 characters of a Vehicle Identification Number (VIN) and engine information. When the sold vehicle type (SID) data is established, the notice number information can also be used as vehicle type description information, so that the corresponding relation between the notice number and the SID can be obtained, and the 8-bit character rule in front of the VIN of the notice number can be mapped under the SID through the corresponding relation. Meanwhile, according to the international VIN coding rule, the corresponding relation between the production year and the first 10 characters of the VIN can be obtained. Finally, a mapping relationship between the first 8 bits of VIN + the first 10 bits of VIN and SID is obtained.

For imported brands, VIN inquiry accumulation depending on long-term service is realized, a large number of VIN codes are used for calling services based on VIN inquiry OE by users, and automobile accessory OE numbers refer to numbers adopted by automobile manufacturers for conveniently managing accessories. Each OE number corresponds to a unique product, but the same product is assembled on different vehicle types, so that several different OE numbers are possible, the type (generator, starter or motor parts), specific performance and detailed parameters of the product can be inquired through the OE numbers, and the specific automobile brand, vehicle type series, factory year and corresponding specific model of an engine, which are applied to the product, can also be known. The service of querying the OE based on the VIN code further comprises basic vehicle type information resolving capability, the basic vehicle type information can comprise brands, labels, vehicle series, years, displacement, gears and/or the like, a large number of relationships between VINs and basic vehicle type information are accumulated, the VINs are cut into the first 8-bit characters of VINs + the first 10-bit characters of VINs, and the basic vehicle type information is mapped to the SIDs through an artificial mapping table, so that the mapping relationship between the first 8-bit characters of VINs + the first 10-bit characters of VINs and the SIDs is obtained.

As shown in fig. 2, further, the method for resolving a vehicle model for sale through a vehicle identification number according to this embodiment may further include the following steps:

in step S210, when the obtained sales vehicle type is not unique, accessory information is acquired by the vehicle identification number. Obtaining accessory information via a vehicle identification number may obtain a full-scale applicable OE list under the VIN by invoking a service that queries for OE based on the VIN code.

In step S220, accessory information included in each of the sales vehicle types is acquired from the vehicle type database.

In step S230, each type of parts in the parts information included in each sales vehicle type acquired from the vehicle type database is cross-matched with the same type of parts in the parts information acquired by the vehicle identification number.

In step S240, the model of the vehicle sold with the highest matching degree of the parts is selected and whether the model of the vehicle sold with the highest matching degree is unique is determined.

In step S250, when the sales vehicle model with the highest matching degree is unique, the sales vehicle model is output.

As an alternative embodiment, step S230 may include the following positive package scoring process: for the similar standard accessories in matching, adding a score corresponding to the weight to a matching degree score corresponding to a sales vehicle type to which the accessory belongs according to the weight configured by the accessory; and the final sold vehicle type with the highest score obtained in the positive loading scoring process is used as the sold vehicle type with the highest matching degree of accessories.

Further, step S230 may further include the following matching scoring process: when the sales vehicle model with the highest final score obtained in the positive loading and grading process is not unique, for the matched similar matching accessories, adding a score corresponding to the weight to the matching degree score corresponding to the sales vehicle model to which the accessories belong according to the weight configured by the accessories; and the selling vehicle model with the highest final score obtained in the matching scoring process is used as the selling vehicle model with the highest matching degree of accessories.

Further, step S230 may further include the following negative option scoring process: when the sale vehicle type with the highest final score obtained in the grading process is selected to be not unique, for the similar standard distribution accessories which are not matched, according to the weight configured by the accessories, the score corresponding to the weight is deducted from the matching degree score corresponding to the sale vehicle type to which the accessories belong; and taking the final sold vehicle type with the highest score obtained in the negative loading scoring process as the sold vehicle type with the highest accessory matching degree.

The weight configured by the accessory may be related to the identification of the accessory, and the higher the identification of the accessory is, the higher the weight is. The degree of identification of accessory means that people judge the vehicle through the outward appearance and have the degree of difficulty of this accessory, also can be called the apparent degree of accessory, for example the degree of identification in skylight is higher than the degree of identification of seat heating function, because people judge the vehicle through the outward appearance relatively easily and have the skylight, and difficult judge the vehicle through the outward appearance and have not been equipped with the seat heating function. As an alternative embodiment, the weight assigned to the matching component is greater than the weight assigned to the matching component.

As shown in fig. 3, further, the method for resolving a vehicle model for sale through a vehicle identification number according to this embodiment may further include the following steps:

and step S310, calling a prediction model when the sold vehicle type with the highest matching degree is not unique.

And step S320, inputting at least part of the vehicle identification number into a prediction model to obtain the predicted sales vehicle type. The prediction model can comprise a plurality of prediction models with different precision levels, at least part of the vehicle identification number is firstly input into the prediction model with the highest precision level, if no output result exists, the prediction model with one precision level lower than the prediction model with the highest precision level is input, and the like until the output result is obtained.

And step S330, taking intersection of the predicted sales vehicle type and the sales vehicle type with the highest matching degree.

And step S340, outputting the sales vehicle types when the sales vehicle types in the intersection are unique.

Specifically, a set of high-precision historical database of VIN-to-SID relationship can be accumulated through a scoring algorithm in a continuous service process, and the relationship can be analyzed to see that the first 14 bits of VIN have a certain correlation with SID. Each VIN represents a vehicle, each SID represents a sales vehicle type, and SIDs predicted by VIN belong to classification problems in machine learning and belong to multi-classification problems. The decision tree algorithm is a more classical multi-classification problem algorithm in machine learning, has the advantages of low calculation complexity, easy understanding of output results, insensitivity to loss of intermediate values, capability of processing irrelevant characteristic data and the like, and has good applicability to numerical data, so that the decision tree algorithm can be used for predicting VIN to SID. As a specific example, 70% of data in the local database may be used as a training set, 30% of data may be used as a verification set, a suitable model is trained through a decision tree algorithm, a pre-pruning manner is adopted in the training process to prevent overfitting, a splitting manner with a minimum kini (gini) coefficient is used to calculate a leaf node, and data with an accuracy of 90% on the verification set is used to predict the SID corresponding to the VIN. In the business level, different users have different requirements on the precision of the SID, so that the vehicle model data can be divided into 4 precision levels, and the prediction models of the precision levels are trained respectively for the different precision levels.

Here, a large amount of VIN-to-SID mapping historical data needs to be collected for supporting optimization of a vehicle model database and data training of a VIN-to-SID prediction model. And a feedback analysis mechanism can be established continuously through feedback in a large number of transactions, the analysis result from VIN to SID can be optimized in real time when problems occur, and batch repair of similar problems is realized.

As shown in fig. 4, further, the method for resolving a vehicle model for sale through a vehicle identification number according to this embodiment may further include the following steps:

and S410, when the sales vehicle types in the intersection are not unique, calling a significant difference item algorithm to obtain significant difference items of all the sales vehicle types in the intersection and returning the significant difference items to the user.

And step S420, receiving the click of the configuration condition in the significant difference item by the user according to the vehicle configuration condition, obtaining and outputting the unique selling vehicle type.

In particular, the significant difference term is intended to distinguish between multiple SIDs with a minimum, optimal configuration term. Rank each configuration with the motorcycle type database according to the degree of distinguishing, for example people can judge very easily through the outward appearance that the vehicle has or not have the skylight, and whether difficult judgement vehicle has the tire pressure monitoring function, therefore the degree of distinguishing in skylight ranks and is higher than the tire pressure monitoring. For a plurality of SIDs, in the configuration item list with difference, the configuration item list with least number of configuration items and highest configuration item identification ranking capable of distinguishing the plurality of SIDs is calculated by an algorithm, and the configuration item list is the significant difference item.

	Tire pressure monitoring	Skylight window	Seat heating	Rear camera
					SID1	Is provided with	Is provided with	Is free of	Is provided with
SID2	Is free of	Is free of	Is free of	Is provided with
					SID3	Is provided with	Is provided with	Is free of	Is free of

As an example of 3 SIDs and 4 configurations thereof in the above table, 3 different SIDs can be distinguished by at least two configurations. The 3 SIDs are configured into a tire pressure monitoring, a skylight and a rear camera differently, wherein configuration items of the tire pressure monitoring and the skylight are the same in each SID, and the identification rank of the skylight is higher than that of the tire pressure monitoring, so that the skylight is selected from the tire pressure monitoring and the skylight, and the rear camera is added to obtain a significant difference item of the SID. And returning the significant difference item to the user, and selecting the corresponding configuration condition in the significant difference item by the user according to the actual vehicle configuration condition to obtain the corresponding unique SID result.

Fig. 5 is a flowchart of a method for analyzing a vehicle model for sale through a vehicle identification number according to embodiment 2 of the present invention.

As shown in fig. 5, in step S501, after receiving the VIN code input by the user, the VIN rule is invoked to parse the VIN code.

In step S503, it is determined whether or not there is a return result. If there is a return result, the flow proceeds to step S505, otherwise the flow proceeds to the analysis failure step.

In step S505, a SID result set obtained by VIN code parsing is obtained.

In step S507, it is determined whether the result in the SID result set is unique, if the result is unique, the process proceeds to the parsing success step and returns the unique SID result to the user, otherwise, the process proceeds to step S509.

In step S509, each accessory information included in each SID in the SID result set is subjected to similar accessory matching with the accessory information acquired through the VIN code, and an accessory matching scoring algorithm is used.

In step S511, it is determined whether the SID with the highest matching score is unique. If the obtained SID is unique, the flow proceeds to the parsing success step, otherwise the flow proceeds to step S513.

In step S513, a VIN to SID prediction model is called, and the SID obtained by the prediction model intersects with the SID result set.

In step S515, it is determined whether the SID in the intersection is unique. If the obtained SID is unique, the flow goes to the step of successful analysis and returns the result of the unique SID to the user, otherwise, the flow goes to the step S517.

In step S517, a significant difference term algorithm is invoked.

In step S519, the user is returned with the significant difference items, for example, the configuration items in the significant difference items may be set within 5 configuration items.

In step S521, the user clicks on the configuration in the significant difference item according to the vehicle configuration, and a unique sales vehicle type is obtained and output. The flow proceeds to the resolve success step and returns the user unique SID result.

As shown in fig. 6, further, the step of using the accessory matching scoring algorithm in step S509 may include the following steps:

in step S50910, when it is determined in step S507 that the result in the SID result set is not unique, performing positive option scoring;

in step S50920, it is determined whether the SID result with the highest score is unique, and if so, the SID result is returned to the user, otherwise, the process proceeds to step S50930;

in step S50930, a matching score is performed;

in step S50940, it is determined whether the SID result with the highest score is unique, and if so, the SID result is returned to the user, otherwise, the process proceeds to step S50950;

in step S50950, negative option scoring is performed;

in step S50960, it is determined whether the SID result with the highest score is unique, and if so, the SID result is returned to the user, otherwise, the process proceeds to step S513 to invoke the VIN-to-SID prediction model.

Fig. 7 is a schematic structural diagram of an apparatus for analyzing a model of a vehicle for sale through a vehicle identification number according to embodiment 3 of the present invention. As shown in fig. 7, the apparatus 700 for resolving a vehicle model for sale by a vehicle identification number according to this embodiment includes an identification section extracting unit 710, an identification section resolving unit 720, an information combining unit 730, and a vehicle model output unit 740.

The identification section extraction unit 710 is configured to receive a vehicle identification number and extract relatively independent identification sections according to an encoding rule of the vehicle identification number. The operation of the recognition section extracting unit 710 may refer to the operation of step S110 described above with reference to fig. 1.

The identification section analyzing unit 720 is configured to query the correspondence between each identification section in the vehicle type database and each vehicle information portion included in the sales vehicle type, so as to analyze each identification section into corresponding each vehicle information. The operation of the identification section parsing unit 720 may refer to the operation of step S120 described above with reference to fig. 1.

The information combining unit 730 is configured to combine the vehicle information corresponding to each identification section to obtain a sales vehicle type. The operation of the information combining unit 730 may refer to the operation of step S130 described above with reference to fig. 1.

The vehicle type output unit 740 is configured to output a sales vehicle type when the obtained sales vehicle type is unique. The operation of the vehicle type output unit 740 may refer to the operation of step S140 described above with reference to fig. 1.

As shown in fig. 8, computing device 800 may include at least one processor 810, storage 820, memory 830, communication interface 840, and internal bus 850, with the at least one processor 810, storage 820, memory 830, and communication interface 840 being connected together via bus 850. The at least one processor 810 executes at least one computer-readable instruction (i.e., an element described above as being implemented in software) stored or encoded in a computer-readable storage medium (i.e., the memory 820).

In one embodiment, stored in the memory 820 are computer-executable instructions that, when executed, cause the at least one processor 810 to: receiving a Vehicle Identification Number (VIN), and extracting relatively independent identification sections according to the encoding rule of the vehicle identification number; inquiring the corresponding relation between each identification section in the vehicle type database and each vehicle information part included in the sold vehicle type, and analyzing each identification section into corresponding vehicle information; combining the vehicle information corresponding to each identification section to obtain a sales vehicle type (SID); and outputting the sales vehicle model when the obtained sales vehicle model is unique.

It should be understood that the computer-executable instructions stored in the memory 820, when executed, cause the at least one processor 810 to perform the various operations and functions described above in connection with fig. 1-7 in the various embodiments of the present invention.

In the present disclosure, computing device 800 may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, Personal Digital Assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronics, and so forth.

According to one embodiment, a program product, such as a non-transitory machine-readable medium, is provided. A non-transitory machine-readable medium may have instructions (i.e., elements described above as being implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 1-7 in various embodiments of the present disclosure.

Specifically, a system or apparatus may be provided which is provided with a readable storage medium on which software program code implementing the functions of any of the above embodiments is stored, and causes a computer or processor of the system or apparatus to read out and execute instructions stored in the readable storage medium.

In this case, the program code itself read from the readable medium can realize the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of the present invention.

Examples of the readable storage medium include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or from the cloud via a communications network.

The above description is only an embodiment of the present invention, and not intended to limit the scope of the claims, and all equivalent structures or equivalent processes that are transformed by the content of the specification and the drawings, or directly or indirectly applied to other related technical fields are included in the scope of the claims.

Claims

1. A method for analyzing a sales vehicle type through a vehicle identification number is characterized by comprising the following steps:

receiving a vehicle identification number, and extracting relatively independent identification sections according to the coding rule of the vehicle identification number;

inquiring the corresponding relation between each identification section in a vehicle type database and each vehicle information part included in the sold vehicle type, and analyzing each identification section into corresponding vehicle information;

combining the vehicle information corresponding to each identification section to obtain a sales vehicle type;

and outputting the sales vehicle model when the obtained sales vehicle model is unique.

2. The method for resolving a vehicle model for sale through a vehicle identification number according to claim 1, further comprising:

when the obtained sales vehicle type is not unique, acquiring accessory information through the vehicle identification number;

acquiring accessory information respectively included by each sold vehicle type from a vehicle type database;

cross matching various accessories in accessory information included in each sales vehicle type acquired from a vehicle type database with similar accessories in accessory information acquired through the vehicle identification number;

selecting a selling vehicle model with the highest matching degree of accessories and judging whether the selling vehicle model with the highest matching degree is unique;

and outputting the sold vehicle model when the sold vehicle model with the highest matching degree is unique.

3. The method for analyzing sales vehicle types according to the vehicle identification number as claimed in claim 2, wherein the cross-matching of each type of parts in the parts information included in each sales vehicle type acquired from the vehicle type database with the same type of parts in the parts information acquired by the vehicle identification number comprises the following positive option scoring process:

for similar standard accessories in matching, adding a score corresponding to the weight to a matching degree score corresponding to a sales vehicle type to which the accessory belongs according to the weight configured by the accessory;

and the final sold vehicle type with the highest score obtained in the positive loading scoring process is used as the sold vehicle type with the highest matching degree of accessories.

4. The method for analyzing sales vehicle types according to the vehicle identification number as claimed in claim 3, wherein each type of parts in the parts information included in each sales vehicle type acquired from the vehicle type database is cross-matched with the same type of parts in the parts information acquired by the vehicle identification number, and further comprising a matching scoring process of:

when the sales vehicle model with the highest final score obtained in the positive loading and scoring process is not unique, for similar matching accessories in matching, adding a score corresponding to the weight to a matching degree score corresponding to the sales vehicle model to which the accessory belongs according to the weight configured by the accessories;

and the selling vehicle model with the highest final score obtained in the matching scoring process is used as the selling vehicle model with the highest matching degree of accessories.

5. The method for analyzing sales vehicle types according to the vehicle identification number of claim 4, wherein each type of parts in the parts information included in each sales vehicle type acquired from a vehicle type database is cross-matched with the same type of parts in the parts information acquired by the vehicle identification number, and the method further comprises the following negative optional grading process:

when the sale vehicle type with the highest final score obtained in the grading process is selected to be not unique, for the similar standard distribution accessories which are not matched, according to the weight configured by the accessories, deducting the score corresponding to the weight from the matching degree score corresponding to the sale vehicle type to which the accessories belong;

and taking the final sold vehicle type with the highest score obtained in the negative loading scoring process as the sold vehicle type with the highest accessory matching degree.

6. The method for resolving a model of a vehicle for sale via a vehicle identification number according to any of claims 3-5, wherein the weight with which the accessory is configured is related to the identity of the accessory, the higher the identity of the accessory the greater the weight.

7. The method for resolving a model of a vehicle for sale through a vehicle identification number according to claim 4 or 5, wherein the weight assigned to the fitting for standard matching is greater than the weight assigned to the fitting for matching.

8. The method for resolving vehicle models for sale through vehicle identification numbers as claimed in claim 2, further comprising:

when the sold vehicle type with the highest matching degree is not unique, calling a prediction model;

inputting at least part of the vehicle identification number into the prediction model to obtain a predicted sales vehicle model;

taking an intersection of the predicted sales vehicle type and the sales vehicle type with the highest matching degree;

and outputting the sales vehicle type when the sales vehicle type in the intersection is unique.

9. The method of claim 8, wherein the predictive models include multiple predictive models with different accuracy levels, at least part of the vehicle identification number is input into the predictive model with the highest accuracy level, if no output result is obtained, the predictive model with one accuracy level lower than the predictive model with the highest accuracy level is input, and so on until an output result is obtained.

10. The method for resolving a model of a vehicle for sale by vehicle identification number according to claim 8 or 9,

when the sales vehicle types in the intersection are not unique, calling a significant difference item algorithm to obtain significant difference items of all the sales vehicle types in the intersection and returning the significant difference items to the user;

and receiving the click of the configuration condition in the significant difference item by the user according to the vehicle configuration condition, obtaining the unique sold vehicle type and outputting the unique sold vehicle type.

11. An apparatus for analyzing a model of a vehicle for sale by a vehicle identification number, comprising:

the identification section extraction unit is used for receiving the vehicle identification number and extracting each relatively independent identification section according to the coding rule of the vehicle identification number;

the identification section analysis unit is used for inquiring the corresponding relation between each identification section in the vehicle type database and each vehicle information part included in the sales vehicle type so as to analyze each identification section into corresponding vehicle information;

the information combination unit is used for combining the vehicle information corresponding to each identification section to obtain a sales vehicle type;

and a vehicle type output unit for outputting the sales vehicle type when the obtained sales vehicle type is unique.

12. A computing device, comprising:

one or more processors, and

a memory coupled with the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A machine-readable storage medium having stored thereon executable instructions that, when executed, cause the machine to perform the method of any one of claims 1 to 10.