CN111967882A

CN111967882A - Method and device for legality verification of vehicle type combination

Info

Publication number: CN111967882A
Application number: CN202010770833.1A
Authority: CN
Inventors: 王俊
Original assignee: Gant Software System Shanghai Co ltd
Current assignee: Gant Software System Shanghai Co ltd
Priority date: 2020-08-04
Filing date: 2020-08-04
Publication date: 2020-11-20
Anticipated expiration: 2040-08-04
Also published as: CN111967882B

Abstract

The invention aims to provide a method and a device for verifying the legality of a vehicle type combination. The method according to the invention comprises the following steps: obtaining a plurality of feature families used for vehicle type combination validity verification of a target vehicle, wherein each feature family corresponds to at least one option value; grouping according to the incidence relation among the feature families to obtain a plurality of feature family sets without incidence relation; for each feature family set, generating a corresponding first sample by arranging and combining a predetermined number of feature families with higher priority orders in the feature family set; performing rule checking on the first sample, and taking one or more combinations which fail to pass the verification as a second sample; and removing the vehicle type combination containing the second sample in the sample to be verified, and performing validity verification based on the vehicle type combination remaining in the sample to be verified.

Description

Method and device for legality verification of vehicle type combination

Technical Field

The invention relates to the technical field of computers, in particular to legality verification for vehicle type combination.

Background

In the prior art, in order to predict sales volume and prepare material pulling in advance, the automobile manufacturing industry generally pre-exhausts all vehicle type combinations with different configurations in an enterprise, and because some technical and market constraints exist, such as that a remote control function must be matched with a voice recognition function, and a transmission using ZF8AT must be equipped with an electronic gear shifting, automatic parking, and gear shifting indicator, regular verification needs to be performed on each combination, and unsatisfactory parts are removed. However, such verification is usually very time-consuming and labor-consuming, and is calculated by taking an average time of one second for each type of vehicle combination, and the range of vehicle combination of a traditional vehicle and a single type of vehicle is about millions of orders, which requires 12 days of calculation.

However, based on the scheme in the prior art, the method for checking the vehicle type combination is simple, for example, the options in all the characteristic families are exhausted to obtain N kinds of arrangements, each arrangement is handed to the rule engine to verify the validity, and finally the vehicle type combination passing the checking is left. Since this exhaustive enumeration produces a Cartesian product of all the features, the amount of data can be very large, and the rule-constrained inspection activities themselves are also very complex, leading to computational resource shortages and inefficiencies. With the arrival of the 5G era, the personalized demand of products is more and more strong, and some internet vehicle enterprises develop more and more characteristics for consumers to select, so that vehicle type combinations are rapidly increased to hundreds of millions or even billions of orders. In the face of the increasing amount of computing, it is difficult for many enterprises to have enough computing resources to cope with this scenario.

Disclosure of Invention

The invention aims to provide a method and a device for verifying the legality of a vehicle type combination.

According to an aspect of the present invention, a method for legitimacy verification of a vehicle type combination is provided, wherein the method comprises:

obtaining a plurality of feature families used for vehicle type combination validity verification of a target vehicle, wherein each feature family corresponds to at least one option value;

grouping according to the incidence relation among the feature families to obtain a plurality of feature family sets without incidence relation, wherein each feature family set corresponds to a sample to be verified, and the sample to be verified is all vehicle type combinations obtained on the basis of the feature families contained in the feature family set;

for each feature family set, generating a corresponding first sample by arranging and combining a predetermined number of feature families with higher priority orders in the feature family set;

performing rule checking on the first sample, and taking one or more combinations which fail to pass the verification as a second sample;

and removing the vehicle type combination containing the second sample in the sample to be verified, and performing validity verification based on the vehicle type combination remaining in the sample to be verified.

According to an aspect of the present invention, there is provided a verification apparatus for validity verification of a vehicle type combination, wherein the validity verification includes:

a feature acquisition unit configured to acquire a plurality of feature families used for validity verification of a vehicle type combination for a target vehicle, wherein each feature family corresponds to at least one option value;

the characteristic grouping unit is used for grouping according to the incidence relation among the characteristic families to obtain a plurality of characteristic family sets without incidence relation, wherein each characteristic family set corresponds to a sample to be verified, and the sample to be verified is all vehicle type combinations obtained on the basis of the characteristic families contained in the characteristic family set;

the sample generating unit is used for generating a corresponding first sample by arranging and combining a predetermined number of feature families with higher priority order in each feature family set;

the sample checking unit is used for carrying out rule checking on the first sample and taking one or more combinations which are not verified as second samples;

a sample removing unit for removing the vehicle type combination containing the second sample in the sample to be verified, thereby performing validity verification based on the vehicle type combination remaining in the sample to be verified

According to an aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of an embodiment of the present invention when executing the program.

According to an aspect of the present invention, there is provided a computer-readable storage medium on which a computer program is stored, characterized in that the program, when executed by a processor, implements the method of an embodiment of the present invention.

Compared with the prior art, the invention has the following advantages: according to the embodiment of the invention, the legality verification feature families used for vehicle type combination of the target vehicle are grouped to obtain a plurality of feature family sets, and verification is continuously performed on the basis of the feature family sets respectively, so that the calculation of the number of vehicle type combinations to be verified by using Cartesian products is avoided, for example, the vehicle type combinations to be verified are converted from an M x N form to an M + N form, the number of vehicle type combinations to be verified is greatly reduced, calculation resources are saved, and the efficiency is improved; moreover, according to the embodiment of the invention, the feature families in each set are sorted according to the priorities, and the combination of the feature families with higher priorities is used as the verified sample space, so that the number of samples to be verified in the whole sample space is sharply reduced; moreover, according to the embodiment of the invention, the sample space is sampled for a plurality of times in an iterative manner, the number of samples to be verified can be further reduced, and thus good performance can be maintained when an ultra-large data set is encountered.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:

FIG. 1 illustrates a flow chart of a method for legitimacy verification of a vehicle type combination according to the present invention;

fig. 2 is a schematic structural diagram illustrating a verification apparatus for validity verification of a vehicle type combination according to the present invention;

fig. 3 illustrates a schematic diagram of an exemplary set of feature families in accordance with the present invention.

The same or similar reference numbers in the drawings identify the same or similar elements.

Detailed Description

The present invention is described in further detail below with reference to the attached drawing figures.

Fig. 1 illustrates a flow chart of a method for legitimacy verification of a vehicle type combination according to the present invention.

Wherein the method according to the invention is implemented by means of an authentication means comprised in a computer device. The computer device includes an electronic device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and hardware thereof includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a programmable gate array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like. The computer device comprises a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network server, a server group consisting of a plurality of network servers, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network servers, wherein Cloud Computing is one of distributed Computing, a super virtual computer consisting of a collection of loosely coupled computers. The user equipment includes, but is not limited to, any electronic product that can interact with a user through a keyboard, a mouse, a remote controller, a touch panel, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a PDA, a game console, or an IPTV. The network where the user equipment and the network equipment are located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

It should be noted that the ue, the network device and the network are only examples, and other existing or future ues, network devices and networks may also be included in the scope of the present invention and are included by reference.

Referring to fig. 1, in step S1, the verification device acquires a plurality of feature families used for validity verification of a vehicle type combination for a target vehicle.

Wherein each family of features corresponds to at least one option value. The feature family is used to represent a certain type of features of the vehicle, for example, a steering system, a transmission, a trim style, etc. of the vehicle, which can be respectively used as a feature family, so as to be classified and managed based on data of the feature family. Wherein the option value of each feature family is used to indicate the categories that the feature family can select. For example, if the user-selectable feature family includes 2 electronic shifts, 3 transmissions, and 2 steering systems, the corresponding feature family is established and corresponding option values are generated based on "electronic shift", "transmission", and "steering system", respectively, where "electronic shift" includes two option values, transmission "includes three option values, and steering system" includes two option values.

Wherein the option value comprises various kinds of information that can be used to uniquely identify a certain family of features, e.g. a number consisting of letters or numbers, etc.

According to one embodiment, the verification means obtains predetermined constraint information. Then, the verification device uses a plurality of feature families related to the constraint information as feature families for performing validity verification of the vehicle type combination based on the constraint information.

Wherein the constraint information includes various preset rules or conditions. The plurality of feature families related to the constraint information refer to feature families appearing in the constraint information.

According to a first example of the present invention, the verification apparatus is incorporated in a device for performing validity verification of a vehicle type combination on a target vehicle of a certain vehicle establishment. The characteristics of the vehicle enterprise, which are selected by a user, comprise 6 interior decoration styles, 2 exterior decoration styles, 2 powers, 2 steering systems, 2 electronic gear shifting and the like. The verification device generates a corresponding feature family based on each characteristic, and uses a predetermined number to indicate option values included in each feature family.

Wherein, the predetermined constraint rule and the corresponding characteristic expression are shown in the following table 1:

TABLE 1

The verification device uses the feature family related to the constraint rule as a feature family for verifying the validity of the vehicle type combination based on the constraint rule shown in the table. In particular, taking the first rule in table 1, a101& B101& a201< ═ C101 as an example, there are 4 feature families, A1, B1, A2, C1, and C1 are affected by the previous three feature families. By using graph algorithm, taking A1, B1, A2 and C1 as vertexes on the graph, the abstract dependency relationship can be expressed as A1- > C1, B1- > C1, A2- > C1 as three edges. Similarly, three vertices B1, B2, and ZA, and two sides B1- > ZA, B2- > ZA, are identified by the second rule in table 1. Where vertex B1 has occurred in the first rule, thus multiplexing the B1 vertices.

All the rest rules are abstracted into vertexes and edges according to the same logic, and then are loaded into a memory map by using a map algorithm. By traversing the vertices of the graph, any family of features that do not appear in the graph can be considered to be irrelevant to the constraint rules shown in table 1, and thus, a plurality of families of features relevant to the constraint rules are used as families of features for performing legitimacy verification of vehicle type combination.

Finally, the verification apparatus determines in step S1 that assuming that the constraint rule relates to 21 feature families and that there are 25 overall feature families, 4 feature families that can participate in the validity verification of the vehicle type combination are rejected, and assuming that the number of selectable items in the 4 feature families that have been rejected is 6, 3, and 2, respectively, the number of permutations of the vehicle type combination that it produces is 6 × 3 — 108. That is, the verification device reduces the total number of permutations required to perform the validity verification of the vehicle type combination by 108 times through the above steps.

Continuing with the description of fig. 1, in step S2, the verification apparatus groups feature families according to their association relationship to obtain a plurality of feature family sets having no association relationship with each other.

Each feature family set corresponds to a sample to be verified, and the samples to be verified are all vehicle type combinations obtained based on feature families contained in the feature family set.

Wherein the association relationship is used to indicate whether the feature families are technically closely associated.

For example, for the construction of a whole vehicle, it is composed of a plurality of subsystems, such as power, body, chassis, interior and exterior, electronic and electric appliances, etc., each subsystem is taken charge of by different departments of business in terms of organization, and not all of them are closely related in terms of technology, for example, the interior and exterior are obviously related to the body, but may not be related to the chassis.

After a plurality of feature family sets which are not related to each other are obtained, the verification device selects one feature family set to verify the legality of the vehicle type combination generated in the feature family set. And after the verification is finished, verifying the next feature family set until the verification of all the feature family sets is finished. Assuming that 4 feature family sets are obtained, each including M, N, X and Y option values, the vehicle type combination to be verified can be converted from M × N × X Y types to M + N + X + Y types through step S2.

Continuing with the foregoing first example, the associations between the selected 21 feature families (denoted as a1, a2, A3, B1, B2, B3, C1, C3, D1, D2, D3, E1, E2, E3, E4, F2, G1, H1, H2, Z1, and ZA, respectively) are shown in fig. 3. Referring to fig. 3, according to the association relationship shown in fig. 3, two feature family sets having no association relationship with each other are obtained, the left feature set _1 includes 18 feature families (a1, a2, A3, B1, B2, C1, D1, D2, E1, E2, E3, E4, F2, G1, H1, H2, Z1, and ZA), and the right feature set _2 includes 3 feature families (B3, C3, D3). The number of permutation combinations generated by the feature sets set _1 and set _2 is 2¹⁸262144 and 2³＝8。

Continuing with the description of fig. 1, in step S3, the verification apparatus generates, for each feature family set, a corresponding first sample by arranging and combining a predetermined number of feature families with higher priority orders in the feature family set.

According to one embodiment, step S3 further includes step S301 and step S302.

In step S301, the verification device prioritizes each feature family in each feature family set based on the option values included in each feature family in the feature family set.

In step S302, the verification apparatus selects a predetermined number of feature families with higher priority order to perform permutation and combination according to the sorting result, and generates a corresponding first sample.

Preferably, corresponding restrictions may be set on the number of first samples, for example, setting the first sample space to 1% of the total samples, and so on.

Preferably, the method prioritizes the various feature families through a web page ranking algorithm.

In step S4, the verification device performs rule verification on the first sample, and takes one or more combinations in which the verification is not passed as a second sample.

In step S5, the verification device removes the vehicle type combination including the second sample in the sample to be verified, thereby performing validity verification based on the vehicle type combinations remaining in the sample to be verified.

Continuing with the description of the foregoing first example, the number of samples currently to be verified in the feature family set _1 is 262144. In step S301, the authentication apparatus performs priority ranking on each feature family based on a web page ranking (PageRank) algorithm based on the option value included in each feature family in the feature family set _1, and the ranking result is shown in table 2 below:

TABLE 2

Priority level	Family of features	Option value	Number of options
				1	B1	B101、B102、B103、B104	4
2	A1	A101、A102、A103	3
				3	B2	B201、B202、B203	3
4	F2	F201、F202、F203	3
				5	ZA	ZA01、ZA02、ZA03	3
6	C1	C101、C102、C103	3
				7	H1	H101、H102	2
8	A2	A201、A202	2
				…	…

As shown in table 2, the feature family B1 has four options of B101, B102, B103, and B104, the feature family A1 has three options of a101, a102, and a103, and the feature family B2 has three options of B201, B202, and B203. If the verification of these high priority ranked advanced vehicle type combinations proves that some of them are not legal, they are certainly not legal to a greater extent, and the number of verifications is reduced.

The total number of combinations of feature groups B1, a1, B2 is 4 × 3 — 36, and the total number of combinations of B1, a1, B2, F2 is 4 × 3 — 108. Assume that the sample space is defined as 1% of the total samples, but each sampling does not exceed 1000, so as to avoid that 1% is still a small number when the total sample size is too large. The comparing device selects the feature families B1, a1, B2 and F2 with the top 4 priority ranks for permutation and combination according to the ranking result shown in table 2 in step S302 to generate the corresponding first sample.

Next, the verification means performs rule checking on the first sample in step S4, and takes one or more combinations in which the verification is not passed as a second sample.

Assuming that the combination of B101& a101& B201& F201 is found not to satisfy the predetermined constraint rule, the combinations of B101& a101& B201& F201& ZA01&. The verification apparatus removes combinations that do not satisfy the constraint rules, such as B101& a101& B201& F201& ZA01&.. and B101& a101& B201& F201& ZA02&.. from the sample to be verified, thereby performing legitimacy verification based on the vehicle type combinations remaining in the sample to be verified.

Through the above processing, the number of samples to be verified corresponding to the feature family set _1 is reduced from 262144 to less than fifty thousand. Then, the verification device performs validity verification of the vehicle type combination through a predetermined rule engine based on the reduced sample to be verified.

Finally, the rules engine can calculate 32384 and 6 of the feature family sets set 1 and set 2, respectively, that really satisfy the constraint within ten minutes. Combining those isolated feature groups, i.e., the feature groups excluded in step S1 and not related to the constraint rule, to obtain the combination common of the target vehicle model and the actual producible combination

32384*6*(226492416/2097152)＝20984832。

According to one embodiment, the method further comprises step S6 and step S7 after step S1 to step S5.

Here, the processes of steps S1 to S5 are not described herein.

In step S6, the verification apparatus replaces the selected feature family having the higher priority order for permutation and combination, and generates new first and second samples, thereby further reducing the number of samples to be verified.

Wherein the verification means may replace the selected family of features based on various rules. For example, assuming that the selected feature family is the top 5 prioritized feature family, the authentication apparatus may replace the 5 th feature family with the 6 th prioritized feature family, or the authentication apparatus may randomly select to replace one or more of the 5 feature families.

In step S7, the verification apparatus repeatedly performs step S6 in an iterative manner until the number of samples to be verified is less than a predetermined threshold.

Continuing with the description of the first example, the rules for the replacement feature family predetermined by the verification device are: and (4) according to the priority ranking result, sequentially replacing the last feature family in the ranking according to the priority from high to low. For the feature families B1, a1, B2, F2 whose top 4 prior prioritized names have been selected, the verification apparatus in step S6 replaces the last feature family F2 with the feature family ZA based on the rule and the ranking result shown in table 2 above, thereby performing permutation and combination based on the feature families B1, a1, B2, and ZA, generating new first and second samples, and further reducing the number of samples to be verified. Next, the verification device changes the feature family ZA among the feature families B1, a1, B2, and ZA to the feature family C1, and performs permutation and combination based on the feature families B1, a1, B2, and C1, thereby generating new first and second samples again. The verification device repeatedly performs the above arrangement in an iterative manner until the total number of combinations of samples to be verified is less than 10 ten thousand.

According to the method provided by the embodiment of the invention, the legality verification feature families used for vehicle type combination of the target vehicle are grouped to obtain a plurality of feature family sets, and verification is continuously carried out on the basis of the feature family sets respectively, so that the calculation of the number of vehicle type combinations to be verified by using Cartesian products is avoided, for example, the vehicle type combinations to be verified are converted from an M + N form into an M + N form, the number of vehicle type combinations to be verified is greatly reduced, the calculation resources are saved, and the efficiency is improved; moreover, according to the embodiment of the invention, the feature families in each set are sorted according to the priorities, and the combination of the feature families with higher priorities is used as the verified sample space, so that the number of samples to be verified in the whole sample space is sharply reduced; moreover, according to the embodiment of the invention, the sample space is sampled for a plurality of times in an iterative manner, the number of samples to be verified can be further reduced, and thus good performance can be maintained when an ultra-large data set is encountered.

Fig. 2 is a schematic structural diagram illustrating a verification apparatus for validity verification of a vehicle type combination according to the present invention. The verification apparatus includes a feature acquisition unit 1, a feature grouping unit 2, a sample generation unit 3, a sample verification unit 4, and a sample removal unit 5.

Referring to fig. 2, in step S1, the feature acquisition unit 1 acquires a plurality of feature families used for the validity verification of the vehicle type combination for the target vehicle.

Wherein each family of features corresponds to at least one option value.

The feature family is used to represent a certain type of features of the vehicle, for example, a steering system, a transmission, a trim style, etc. of the vehicle, which can be respectively used as a feature family, so as to be classified and managed based on data of the feature family. Wherein the option value of each feature family is used to indicate the categories that the feature family can select. For example, if the user-selectable feature family includes 2 electronic shifts, 3 transmissions, and 2 steering systems, the corresponding feature family is established and corresponding option values are generated based on "electronic shift", "transmission", and "steering system", respectively, where "electronic shift" includes two option values, transmission "includes three option values, and steering system" includes two option values.

According to one embodiment, the feature acquisition unit includes a constraint acquisition unit and a feature selection unit.

A constraint acquisition unit acquires predetermined constraint information. Then, the feature selection unit takes a plurality of feature families related to the constraint information as a feature family for performing validity verification of the vehicle type combination based on the constraint information.

The feature grouping unit 2 groups the feature families according to the association relationship between the feature families to obtain a plurality of feature family sets without the association relationship.

After a plurality of feature family sets which are not related to each other are obtained, the verification device selects one feature family set to verify the legality of the vehicle type combination generated in the feature family set. And after the verification is finished, verifying the next feature family set until the verification of all the feature family sets is finished. Assuming that 4 feature family sets are obtained, each including M, N, X and Y option values, the vehicle type combination to be verified can be converted from M × N × X Y types to M + N + X + Y types by the operation of the feature grouping unit 2.

The sample generation unit 3 generates a corresponding first sample by arranging and combining a predetermined number of feature families having a higher priority order in each feature family set.

According to one embodiment, the sample generation unit 3 further comprises.

The ranking unit ranks, for each feature family set, the respective feature families in the feature family set in a priority order based on the option values included in the respective feature families.

And the sub-generation unit selects a predetermined number of feature families with higher priority order to perform permutation and combination according to the sorting result to generate a corresponding first sample.

Preferably, corresponding restrictions may be set on the number of the first samples, for example, setting the first sample space to 1% of the total samples, and so on.

Preferably, the sorting unit prioritizes the respective feature families by a web page ranking algorithm.

The sample checking unit is used for carrying out rule checking on the first sample and taking one or more combinations which are not verified as second samples.

The sample removing unit 5 removes the vehicle type combination including the second sample in the sample to be verified, thereby performing validity verification based on the vehicle type combination remaining in the sample to be verified.

According to one embodiment, the validation apparatus further comprises a sample exchange unit.

The sample replacing unit replaces the selected feature family with higher priority order to perform permutation and combination, and generates a new first sample and a new second sample, thereby further reducing the number of samples to be verified.

Wherein the sample replacement unit may replace the selected feature family based on various rules. For example, assuming that the selected feature family is the top 5 prioritized feature family, the authentication apparatus may replace the 5 th feature family with the 6 th prioritized feature family, or the authentication apparatus may randomly select to replace one or more of the 5 feature families.

And the sample replacing unit repeatedly performs the operation of replacing the selected feature family with higher priority order to perform permutation and combination in an iterative manner, and generates new first samples and second samples until the number of the samples to be verified is less than a preset threshold value.

According to the scheme of the embodiment of the invention, the legality verification feature families used for vehicle type combination of the target vehicle are grouped to obtain a plurality of feature family sets, and verification is continuously carried out on the basis of the feature family sets respectively, so that the calculation of the number of vehicle type combinations to be verified by using Cartesian products is avoided, for example, the vehicle type combinations to be verified are converted from an M + N form into an M + N form, the number of vehicle type combinations to be verified is greatly reduced, the calculation resources are saved, and the efficiency is improved; moreover, according to the embodiment of the invention, the feature families in each set are sorted according to the priorities, and the combination of the feature families with higher priorities is used as the verified sample space, so that the number of samples to be verified in the whole sample space is sharply reduced; moreover, according to the embodiment of the invention, the sample space is sampled for a plurality of times in an iterative manner, the number of samples to be verified can be further reduced, and thus good performance can be maintained when an ultra-large data set is encountered.

The software program of the present invention can be executed by a processor to implement the steps or functions described above. Also, the software programs (including associated data structures) of the present invention can be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functionality of the present invention may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various functions or steps.

In addition, some of the present invention can be applied as a computer program product, such as computer program instructions, which when executed by a computer, can invoke or provide the method and/or technical solution according to the present invention through the operation of the computer. Program instructions which invoke the methods of the present invention may be stored on a fixed or removable recording medium and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored within a working memory of a computer device operating in accordance with the program instructions. An embodiment according to the invention herein comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or solution according to embodiments of the invention as described above.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims

1. A method for legitimacy verification of a vehicle type combination, wherein the method comprises:

2. The method of claim 1, wherein the method further comprises:

replacing the selected feature families with higher priority order to perform permutation and combination to generate new first samples and second samples, thereby further reducing the number of samples to be verified;

and repeating the steps in an iterative mode until the number of the samples to be verified is less than a preset threshold value.

3. The method according to claim 1 or 2, wherein the step of obtaining a plurality of feature families for legality verification of a vehicle type combination comprises:

acquiring preset constraint information;

and based on the constraint information, taking a plurality of feature families related to the constraint relation as feature families for performing legality verification of the vehicle type combination.

4. The method according to claim 1 or 2, wherein the step of generating, for each feature family set, a corresponding first sample by permutation and combination of a predetermined number of feature families with higher priority orders in the feature family set comprises the steps of:

for each feature family set, carrying out priority ranking on each feature family based on the option value contained in each feature family in the feature family set;

and selecting a predetermined number of feature families with higher priority order to perform permutation and combination according to the sorting result to generate a corresponding first sample.

5. The method of claim 4, wherein the method prioritizes the respective families of features through a web page ranking algorithm.

6. A verification apparatus for validity verification of a vehicle type combination, wherein the validity verification includes:

and the sample removing unit is used for removing the vehicle type combination containing the second sample in the sample to be verified, so that the legality verification is carried out based on the vehicle type combination remaining in the sample to be verified.

7. The authentication apparatus of claim 6, wherein the authentication apparatus further comprises:

the sample replacing unit is used for replacing the selected feature family with higher priority order to carry out permutation and combination, and generating a new first sample and a new second sample, thereby further reducing the number of samples to be verified;

the sample replacing unit repeats the steps in an iterative mode until the number of the samples to be verified is smaller than a preset threshold value.

8. The authentication apparatus according to claim 6 or 7, wherein the feature acquisition unit comprises:

a constraint acquisition unit for acquiring predetermined constraint information;

and the characteristic selection unit is used for taking a plurality of characteristic families related to the constraint relation as characteristic families used for carrying out legality verification on the vehicle type combination based on the constraint information.

9. The authentication apparatus according to claim 6 or 7, wherein the sample generation unit comprises:

the sorting unit is used for carrying out priority sorting on each feature family based on the option value contained in each feature family in the feature family set for each feature family set;

and the sub-generation unit is used for selecting a preset number of feature families with higher priority order to carry out permutation and combination according to the sorting result to generate a corresponding first sample.

10. A verification device according to claim 9 wherein the verification device prioritizes the respective families of features by a web page ranking algorithm.

11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 5 when executing the program.

12. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 5.