CN115408580A - Vehicle source model identification method and device - Google Patents
Vehicle source model identification method and device Download PDFInfo
- Publication number
- CN115408580A CN115408580A CN202211068188.4A CN202211068188A CN115408580A CN 115408580 A CN115408580 A CN 115408580A CN 202211068188 A CN202211068188 A CN 202211068188A CN 115408580 A CN115408580 A CN 115408580A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- annual
- model
- classification model
- identified
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of vehicle type identification, and discloses a method and a device for identifying vehicle source models. The method comprises the steps of obtaining vehicle type information and a listing date of a vehicle source to be identified, determining a subordinate annuity group, a corresponding first annuity group classification model and a specific branch of the vehicle source to be identified, automatically generating a plurality of questions and corresponding answers of the questions based on configuration information of the branches recorded in a classification model and a segmentation method, responding to answer information input by a user to each question by combining the answers corresponding to the questions, and positioning to a subordinate branch, so that a next question is generated until the annuity and the model of the vehicle source to be identified are searched in the annuity group classification model. The invention is provided with a picture recognition function, and can be automatically positioned under a certain branch of a yearly money group through pictures, thereby playing a role in reducing questions to be answered. The method can automatically identify the specific annual style and model of the vehicle type, is comprehensive in coverage, does not need to depend on manual experience, and improves the identification accuracy of the vehicle source model.
Description
Technical Field
The invention relates to the technical field of model identification of vehicle types, in particular to a method and a device for identifying vehicle source models.
Background
In order to meet the diversified demands of consumers, different automobile types can be pushed out for automobiles, different annual payments can be realized under one automobile type, and different models can be realized under each annual payment. The technology for recognizing the vehicle type is mature at present, but the recognition of the following year money, particularly the model number, of the vehicle type is a great challenge.
At present, two methods are mainly used for identifying the annual pattern and the model of the vehicle source. One is identified by manual experience, but the method is labor-consuming and dependent on experience, needs to be distinguished by manually remembering typical configurations of hundreds of models, and is difficult to judge more than 5 thousands of models in the whole market. This identification method is very difficult to implement, and therefore the vehicle source models that can be identified are limited and not comprehensive enough. Another method is by carriage number inquiry. However, the information of the annual types and the models is mastered in each vehicle enterprise and is not published to the outside, so that the power assembly can be decoded at most through the inquiry of the frame number, the models cannot be accurately identified, and the error rate of the method for identifying the vehicle type models is high.
Disclosure of Invention
The invention provides a vehicle source model identification method and device, and aims to solve the technical problems that in the prior art, only an identification method which consumes manpower and depends on experience is difficult to identify through manual experience, a small-coverage identification method or a vehicle frame number inquiry method can only identify a power assembly at most, cannot accurately identify the model and has high error rate.
In order to solve the above technical problem, a first embodiment of the present invention provides a vehicle source model identification method, including:
acquiring vehicle type information and a listing date of a vehicle source to be identified, and determining a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group and a specific branch under the first year money group classification model;
acquiring configuration information of each branch under a specific branch under the first annual bank group classification model and a segmentation method under the first annual bank group classification model, and automatically generating a plurality of questions and answers corresponding to the questions;
outputting a first question of the generated plurality of questions to a user, responding to answer information input by the user to the question, and determining a next branch of a specific branch of the first annuity component classification model by combining an answer corresponding to the question;
and outputting a corresponding next question according to a next branch of the specific branch of the first annual fund component classification model, and combining the answer of the user and the answer corresponding to the question until the annual fund and the model of the vehicle source to be identified are searched in the first annual fund component classification model.
According to the invention, the first year money group to which the vehicle source to be identified belongs can be accurately positioned through the registration date and the vehicle type information of the vehicle source, and the corresponding first year money group classification model and the specific branch under the model are found, so that the identification process of the vehicle source type is accelerated, and the identification accuracy of the vehicle source type is improved; according to the configuration information of each branch under the specific branch under the first annual fund component classification model and the segmentation method under the first annual fund component classification model, a plurality of questions and corresponding answers are automatically generated, the answers corresponding to the questions are combined, the answer information input by the user to each question is responded, the next-stage branch of the specific branch is positioned, the next question is generated until the annual fund and the model of the vehicle source to be identified are searched in the annual fund component classification model, and the identification accuracy of the vehicle source model is improved.
Further, the obtaining of the vehicle type information and the listing date of the vehicle source to be identified and the determining of the annual fee group to which the vehicle source to be identified belongs, the first annual fee group classification model corresponding to the annual fee group and the specific branch under the first annual fee group classification model specifically include:
determining the sale time of the vehicle source to be identified according to the vehicle type information and the listing date of the vehicle source to be identified, and determining the annual fee group to which the vehicle source to be identified belongs according to the sale time;
according to the determined annual fee group, inquiring a first annual fee group classification model corresponding to the annual fee group in a database;
determining a specific branch under a first annual pattern classification model in the first annual pattern classification model according to the vehicle type information of the vehicle source to be identified;
the vehicle type information comprises vehicle types and part configuration; a plurality of annual bank group classification models are stored in the database; and recording a plurality of models sold in the same time period in each annual bank group classification model, and dividing each model in the same annual bank group classification model according to the configuration information of each model to form a plurality of branches.
As a first aspect of the first embodiment of the present invention, the present invention may determine the sale time of the vehicle source to be identified according to the vehicle type information and the listing date of the vehicle source to be identified, and determine the annual fee group to which the vehicle source belongs according to the sale time, so as to query the corresponding annual fee group classification model in the database, and the various annual fee group classification models stored in the database may make the vehicle source type number identified more comprehensive, thereby improving the accuracy of identifying the vehicle source type number.
Further, the annual fund component classification model is formed in the following specific process:
generating configuration information of each model for a plurality of models in the same year type component classification model according to the configuration of each model;
combining the configuration information of each model to form each branch of the annual fund component classification model till the specific annual fund and model in the annual fund component classification model;
the configuration information of each model comprises the configuration of each model and the partitioning method under the configuration.
As a second aspect of the first embodiment of the present invention, the present invention generates configuration information of each model according to the configuration of each model, so as to form each branch under the annuity component classification model up to a specific annuity and model in the annuity component classification model, thereby forming a plurality of annuity component classification models in the database to cover various vehicle models on the market, and accurately and efficiently identify the vehicle source model.
Further, the forming of each branch under the annual fund grouping classification model to the specific annual fund and model in the annual fund grouping classification model according to the configuration information of each model specifically includes:
in the configuration of each model, selecting the configuration with the largest information gain ratio according to the information gain ratio in the decision tree, and recording the branch segmentation method under the configuration;
and forming each branch in the model until the specific annual fund and model in the annual fund group classification model according to the recorded branch segmentation method.
As a third aspect of the first embodiment of the present invention, in the configuration of each model, the configuration with the largest information gain ratio is selected through the information gain ratio in the decision tree, and the branch segmentation method under the configuration is recorded to form a complete annual fund component classification model, so as to distinguish the models of each vehicle source with the least configuration, so that the user can conveniently and quickly identify the model of the vehicle source, and the efficiency of identifying the model of the vehicle source is improved.
Further, the obtaining of the vehicle type information and the listing date of the vehicle source to be identified specifically includes:
carrying out picture recognition on the vehicle source photo uploaded by the user to acquire the vehicle type information of the vehicle source to be recognized;
or matching the frame number uploaded by the user in a frame number information base to obtain the vehicle type information of the vehicle source to be identified;
or acquiring the vehicle type information of the vehicle source to be identified according to the vehicle type name uploaded by the user.
As a fourth aspect of the first embodiment of the present invention, the vehicle type information of the vehicle source can be obtained by the vehicle source photo, the frame number, or the vehicle type name, and the user can upload the vehicle information of the vehicle source in various ways, so that the user can conveniently identify the vehicle type number, and the efficiency of identifying the vehicle type number is improved.
Further, the specific branch under the first-year style component classification model is specifically:
if the vehicle type information of the vehicle source to be identified is obtained through the vehicle source picture uploaded by the user, the lowest branch corresponding to the configuration identified by the picture is a specific branch under the first year money group classification model;
if the vehicle type information of the vehicle source to be identified is obtained through the frame number uploaded by the user, the lowest branch corresponding to the configuration identified in the frame number information base is a specific branch under the first annual pattern component classification model;
and if the vehicle type information of the vehicle source to be identified is obtained through the vehicle type name uploaded by the user, the first branch under the first year money group classification model is a specific branch of the first year money group.
As a fifth aspect of the first embodiment of the present invention, the vehicle type information can be obtained by different methods, the vehicle source to be identified can be located to one branch of the annual fee component classification model, wherein a certain branch under the model can be located through image identification or frame number matching, and if the vehicle type information is obtained through the vehicle type name, the vehicle type information can only be located to the first branch of the annual fee component classification model, so that the vehicle source type number can be identified by a user more conveniently, and the efficiency of identifying the vehicle type number is improved.
Further, the information gain ratio specifically includes:
wherein A represents the configuration, D represents a year money group consisting of a plurality of models, g R (D, A) represents the information gain ratio of A, H (D) represents entropy, and H (D | A) represents conditional entropy.
According to the method, the year money component classification model and the specific branch of the vehicle source to be identified are automatically identified by acquiring the basic information such as the registration date and the vehicle type information of the vehicle source to be identified, a plurality of questions and answers are generated according to the configuration information of each branch under the specific branch of the classification model, and the specific year money and model of the vehicle source are automatically identified by combining the answer information of the user; compared with vehicle frame number identification, the method constructs the annual bank group classification model, and improves the accuracy of vehicle source type number identification.
A second embodiment of the present invention provides an apparatus for recognizing a vehicle source model, including: the system comprises a year payment group determining module, a question generating module, an answer and answer matching module and a searching module;
the year money group determining module is used for acquiring vehicle type information and a registration date of a vehicle source to be identified, and determining a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group and a specific branch under the first year money group classification model;
the question generation module is used for acquiring configuration information of each branch under a specific branch under the first annual pattern group classification model and a segmentation method under the first annual pattern group classification model, and automatically generating a plurality of questions and answers corresponding to the questions;
the answer and answer matching module is used for outputting a first question of the generated plurality of questions to a user, responding to answer information input by the user to the question, and determining the next branch of a specific branch of the first annuity component classification model by combining an answer corresponding to the question;
the searching module is used for outputting a corresponding next question according to a next branch of the specific branch of the first annual fund component classification model, and combining the answer of the user and the answer corresponding to the question until the annual fund and the model of the vehicle source to be identified are searched in the first annual fund component classification model.
Further, the annual money group determination module includes: the system comprises a year payment group determining unit, a classification model determining unit and a branch determining unit;
the annual money group determining unit is used for determining the sale time of the vehicle source to be identified according to the vehicle type information and the listing date of the vehicle source to be identified, and determining the annual money group to which the vehicle source to be identified belongs according to the sale time;
the classification model determining unit is used for inquiring a first annual money group classification model corresponding to the annual money group in a database according to the determined annual money group;
the branch determining unit is used for determining a specific branch under a first year type group classification model in the first year type group classification model according to the vehicle type information of the vehicle source to be identified;
the vehicle type information comprises a vehicle type and a part configuration; a plurality of annual bank group classification models are stored in the database; and a plurality of models sold in the same time period are recorded in each annual fund component classification model, and each vehicle source in the same annual fund component classification model is divided according to the configuration information of each model to form a plurality of branches.
Further, the annual bank determining module comprises any one or more combinations of a picture identifying unit, a frame number matching unit and a vehicle type name unit, and specifically comprises:
the picture identification unit is used for carrying out picture identification on the vehicle source picture uploaded by the user and acquiring the vehicle type information of the vehicle source to be identified;
the frame number matching unit is used for matching the frame numbers uploaded by the users in a frame number information base to acquire the vehicle type information of the vehicle source to be identified;
the vehicle type name unit is used for acquiring the vehicle type information of the vehicle source to be identified according to the vehicle type name uploaded by the user.
Drawings
Fig. 1 is a schematic flowchart of an embodiment of a vehicle source model identification method provided by the present invention;
FIG. 2 is a schematic flow chart illustrating a method for identifying a vehicle source model according to another embodiment of the present invention;
fig. 3 is a schematic flowchart of a vehicle source model identification method according to still another embodiment of the present invention;
FIG. 4 is a schematic flow chart diagram illustrating an embodiment of creating a yearly component classification model according to the present invention;
FIG. 5 is a schematic flow chart diagram illustrating another embodiment of establishing a yearly style component classification model according to the present invention;
FIG. 6 is a schematic structural diagram of an embodiment of a vehicle source model identification device provided in the present invention;
fig. 7 is a schematic structural diagram of another embodiment of the vehicle source model identification device provided by the present invention;
FIG. 8 is a schematic diagram of the annual fund component classification provided by the present invention;
FIG. 9 is a diagram of the results of the annual fund component classification model provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In describing the present invention, it should be understood that the terminology used in the present invention is as follows:
1. "vehicle type": a vehicle enterprise gives names to vehicles of the same type, brand, body form, category or series.
"annual money": the vehicle and the enterprise carry out annual small change for upgrading and releasing details in order to keep the competitiveness of products.
"configure": the functions or facilities realized based on certain software and hardware combination are equipped on the automobile.
"model": the vehicle enterprises are names of combinations of different configurations and power assemblies under the same vehicle type and year.
Example 1
As shown in fig. 1, which is a schematic flow chart of an embodiment of the method for identifying a vehicle source model provided by the present invention, the method includes steps 101 to 104, and each step specifically includes the following steps:
step 101: the method comprises the steps of obtaining vehicle type information and a listing date of a vehicle source to be identified, and determining a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group and a specific branch under the first year money group classification model.
In the first embodiment of the invention, each year has a corresponding sale time, the sale times of two adjacent three years are overlapped sometimes, and all the years with the overlapped sale time form a year group. One annual fee can appear in a plurality of annual fee groups, but due to the fact that the sales time of the vehicle sources to be identified is different, the annual fee groups to which the unique vehicle sources to be identified belong can be located according to the card-showing time. As shown in fig. 8, the sales times of the year money 1 and 2 overlap, and the sales times of the year money 2 and 3 overlap, so the three year money are divided into two year money groups, the first year money group includes the year money 1 and the year money 2, and the second year money group includes the year money 2 and the year money 3.
In the first embodiment of the present invention, as shown in fig. 2, step 101 includes step 201, step 202, and step 203, which are specifically as follows:
step 201: according to the vehicle type information and the listing date of the vehicle source to be identified, the selling time of the vehicle source to be identified is determined, and according to the selling time, the annual money group to which the vehicle source to be identified belongs is determined.
Step 202: and according to the determined annual fee groups, inquiring a first annual fee group classification model corresponding to the annual fee groups in a database.
Step 203: and determining a specific branch under the first annual pattern classification model in the first annual pattern classification model according to the vehicle type information of the vehicle source to be identified.
The vehicle type information comprises a vehicle type and a part configuration; a plurality of annual bank group classification models are stored in the database; and recording a plurality of models sold in the same time period in each annual bank group classification model, and dividing each model in the same annual bank group classification model according to the configuration information of each model to form a plurality of branches.
In the first embodiment of the present invention, the year money component classification model stored in the database is used for identifying the vehicle source type number, and as shown in fig. 4, a specific forming process of the year money component classification model includes steps 401 to 403, specifically:
step 401: and generating configuration information of each model for a plurality of models in the same year type component classification model according to the configuration of each model.
As an example of this example, to facilitate user operation, an easily observable configuration is extracted, such as: configuration information such as a skylight, a gearbox type (manual/automatic), a dual-temperature-zone air conditioner and an electric trunk is used as a basis for forming the branches of the annual bank component classification model, and a complete classification model is established.
Step 402: and forming each branch of the annual fund component classification model till the specific annual fund and model in the annual fund component classification model according to the configuration information of each model.
The configuration information of each model comprises the configuration of the model and the splitting method of each branch under the configuration.
In the first embodiment of the present invention, as shown in fig. 5, step 402 includes step 501 and step 502, which are specifically as follows:
step 501: in the configuration of each type, according to the information gain ratio in the decision tree, selecting the configuration with the largest information gain ratio, and recording the branch division method under the configuration, specifically:
automatically traversing each configuration in the model configuration, and selecting the configuration with the largest information gain ratio; the step of configuration is circularly traversed until all models are completely separated; and recording the branch segmentation method under the configuration according to the configuration selected each time.
In a first embodiment of the present invention, the information gain ratio is selected as
Wherein A represents the configuration, D represents a year money group consisting of a plurality of models, g R (D, A) represents the information gain ratio of A, H (D) represents entropy, and H (D | A) represents conditional entropy.
As an example of this embodiment, in many configurations of models, the information gain ratio is selected to select as few configurations as possible to completely distinguish all models in the annuity group, but many supervised and explanatory classification algorithms, such as decision trees, SVM algorithms, etc., can achieve this goal.
Step 502: and forming each branch of the model according to the recorded branch segmentation method until the specific annual fund and model number in the annual fund group classification model.
As an example of this embodiment, the yearly component classification model is shown in fig. 9. The method comprises the steps of positioning a specific annual fee component classification model and a specific branch according to vehicle type information and a license plate date of a vehicle source to be identified, starting classification according to the type of a gearbox in the model, dividing the branch into an automatic branch and a manual branch, continuously classifying according to the type of a vehicle body or the engine displacement to form a subsequent branch, positioning the branch to a power series branch, and continuously classifying according to configuration information of each model.
In the first embodiment of the present invention, the vehicle type information of the vehicle source may be obtained in multiple ways, as shown in fig. 3, if the user uploads the vehicle source photo, step 301 is performed to perform picture recognition on the vehicle source photo uploaded by the user, and the vehicle type information of the vehicle source to be recognized is obtained; if the user uploads the frame number, the step 302 is carried out, the frame number uploaded by the user is matched in a frame number information base, and the vehicle type information of the vehicle source to be identified is obtained; if the vehicle type name is uploaded by the user, step 303 is performed, and the vehicle type information of the vehicle source to be identified is obtained according to the vehicle type name uploaded by the user.
And if the user uploads the vehicle source photo or the vehicle frame number, the vehicle type information of the vehicle source can be automatically identified through the image identification model or the vehicle frame number information base. If the vehicle source photo or the frame number is not uploaded, the user is required to manually input the vehicle type name to acquire the vehicle type information of the vehicle source.
In the first embodiment of the invention, if the vehicle type information of the vehicle source to be identified is obtained through the vehicle source photo uploaded by the user, the lowest branch corresponding to the configuration identified by the picture is a specific branch under the first annual bank classification model; if the vehicle type information of the vehicle source to be identified is obtained through the frame number uploaded by the user, the lowest branch corresponding to the configuration identified in the frame number information base is a specific branch under the first annual pattern component classification model; and if the vehicle type information of the vehicle source to be identified is determined through the vehicle type name uploaded by the user, the first branch under the first annual bank group classification model is a specific branch of the first annual bank group.
Step 102: and acquiring configuration information of each branch under a specific branch under the first annual bank group classification model and a segmentation method under the first annual bank group classification model, and automatically generating a plurality of questions and answers corresponding to the questions.
In the first embodiment of the present invention, the classification model of each annuity group is fixed in the database, and therefore, the arrangement information and the division method of each branch under the classification model of the annuity group are also fixed. Because only the powertrain branch can be located at most according to the vehicle information uploaded by the user, in order to identify a specific year and model, a problem output to the user needs to be formed according to the configuration information of each lower branch in the located branches, and an answer is formed according to a corresponding segmentation method, so that the subsequent identification process is completed.
Step 103: and outputting a first question of the generated plurality of questions to a user, responding to answer information input by the user to the question, and determining a next branch of a specific branch of the first annuity component classification model by combining an answer corresponding to the question.
Step 104: and outputting a corresponding next question according to a next branch of the specific branch of the first annual fund group classification model, and combining the answer of the user and the answer corresponding to the question until the annual fund and the model of the vehicle source to be identified are searched in the first annual fund group classification model.
In the first embodiment of the invention, after the user inputs the vehicle information, the system can only identify the power assembly branch at most, so the system needs to output the questions generated according to the configuration, after the user answers the first question, the system can combine the answer of the user and the answer of the question to position to the next-stage branch so as to form the next question, until the determined specific year and model branch, and output the model of the vehicle source to the user.
In conclusion, the invention can accurately position the annual fund group and the classification model thereof belonging to the vehicle source to be identified and position the specific branch through the vehicle type information and the registration date of the vehicle source to be identified, thus accelerating the identification process of the vehicle source type and improving the identification accuracy of the vehicle source type; the method comprises the steps of automatically generating a plurality of questions and corresponding answers based on configuration information of each branch recorded in a classification model and a segmentation method, responding answer information input by a user to each question by combining the answers corresponding to the questions, and positioning to a next branch, so that the next question is generated until the annual payment and the model of a vehicle source to be identified are searched in an annual payment component classification model, the specific annual payment and the model of the vehicle source are identified by the least questions, the specific annual payment and the model of the vehicle source can be comprehensively and accurately positioned, and the identification accuracy of the vehicle source model is improved.
Example 2
As shown in fig. 6, which is a schematic structural diagram of an embodiment of the apparatus for identifying a vehicle source model provided by the present invention, the apparatus includes a annuity group determining module 601, a question generating module 602, an answer and answer matching module 603, and a searching module 604, and specifically includes:
the annual payment group determining module 601 is used for acquiring vehicle type information and a listing date of a vehicle source to be identified, and determining a annual payment group to which the vehicle source to be identified belongs, a first annual payment group classification model corresponding to the annual payment group, and a specific branch under the first annual payment group classification model;
the question generation module 602 is configured to obtain configuration information of each branch under a specific branch under the first yearly style group classification model and a segmentation method under the first yearly style group classification model, and automatically generate a plurality of questions and answers corresponding to the questions;
the answer and answer matching module 603 is configured to output a first question of the generated plurality of questions to a user, respond to answer information input by the user for the question, and determine, in combination with an answer corresponding to the question, a next branch of a specific branch of the first annuity component classification model;
the searching module 604 is configured to output a corresponding next question according to a next branch of the specific branch of the first annual fee component classification model, and combine the answer of the user and the answer corresponding to the question until the annual fee and the model of the vehicle source to be identified are searched in the first annual fee component classification model.
In a second embodiment of the invention, the device for identifying the vehicle source model comprises a annuity group determination module, a question generation module, an answer and answer matching module and a search module, and the annuity and the model of the vehicle source can be efficiently and accurately identified on the basis of organic combination of the modules.
As shown in fig. 7, which is a schematic structural diagram of another embodiment of the apparatus for identifying a vehicle source model provided in the present invention, the annuity group determining module includes a annuity group determining unit 701, a classification model determining unit 702, and a branch determining unit 703, and specifically includes:
the annuity group determination unit 701 is used for determining the sale time of the vehicle source to be identified according to the vehicle type information and the registration date of the vehicle source to be identified, and determining the annuity group to which the vehicle source to be identified belongs according to the sale time;
the classification model determining unit 702 is configured to query, according to the determined annual fee group, a first annual fee group classification model corresponding to the annual fee group in a database;
the branch determining unit 703 is configured to determine, according to the vehicle type information of the vehicle source to be identified, a specific branch under the first annual pattern classification model in the first annual pattern classification model;
the vehicle type information comprises a vehicle type and a part configuration; a plurality of annual fund component classification models are stored in the database; and a plurality of vehicle sources sold in the same time period are recorded in each annual fund component classification model, and each model in the same annual fund component classification model is divided according to the configuration information of each model to form a plurality of branches.
In a second embodiment of the present invention, the annuity group determination module includes any one or more combinations of a picture identification unit, a frame number matching unit, and a vehicle type name unit, and specifically includes:
the picture identification unit is used for carrying out picture identification on the vehicle source picture uploaded by the user and acquiring the vehicle type information of the vehicle source to be identified;
the frame number matching unit is used for matching the frame numbers uploaded by the users in a frame number information base to acquire the vehicle type information of the vehicle source to be identified;
the vehicle type name unit is used for acquiring the vehicle type information of the vehicle source to be identified according to the vehicle type name uploaded by the user.
In conclusion, the device for identifying the vehicle source model is constructed, the specific annual pattern and model of the vehicle source are comprehensively and accurately positioned on the basis of the organic combination of the modules, and the annual pattern and model of the vehicle source are efficiently and accurately identified.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these modifications and substitutions should also be regarded as the protection scope of the present invention.
Claims (10)
1. A vehicle source model identification method is characterized by comprising the following steps:
obtaining vehicle type information and a registration date of a vehicle source to be identified, and determining a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group, and a specific branch under the first year money group classification model;
acquiring configuration information of each branch under a specific branch under the first annual pattern classification model and a segmentation method under the first annual pattern classification model, and automatically generating a plurality of questions and answers corresponding to the questions;
outputting a first question of the plurality of questions to a user, responding to answer information input by the user to the question, and determining a next branch of a specific branch of the first annuity component classification model by combining an answer corresponding to the question;
and outputting a corresponding next question according to a next branch of the specific branch of the first annual fund group classification model, and combining the answer of the user and the answer corresponding to the question until the annual fund and the model of the vehicle source to be identified are searched in the first annual fund group classification model.
2. The vehicle source model identification method according to claim 1, wherein the obtaining of the vehicle type information and the date of registration of the vehicle source to be identified determines a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group, and a specific branch under the first year money group classification model, specifically:
determining the sale time of the vehicle source to be identified according to the vehicle type information and the listing date of the vehicle source to be identified, and determining the annual fee group to which the vehicle source to be identified belongs according to the sale time;
according to the determined annual fee group, inquiring a first annual fee group classification model corresponding to the annual fee group in a database;
determining a specific branch under a first annual pattern classification model in the first annual pattern classification model according to the vehicle type information of the vehicle source to be identified;
the vehicle type information comprises vehicle types and part configuration; a plurality of annual bank group classification models are stored in the database; and a plurality of models sold in the same time period are recorded in each year type group classification model, and each model in the same year type group classification model is divided according to the configuration information of each model to form a plurality of branches.
3. The vehicle source model identification method according to claim 2, wherein the annual fund component classification model is formed by the following specific processes:
generating configuration information of each model according to the configuration of each model for a plurality of models in the same year type group classification model;
forming branches under the annual fund component classification model until specific annual fund and model in the annual fund component classification model according to the configuration information of each model;
the configuration information of each model comprises the configuration of each model and the partitioning method under the configuration.
4. The vehicle source model identification method according to claim 3, wherein the forming of each branch under the annual fund component classification model to a specific annual fund and model in the annual fund component classification model according to the configuration information of each model specifically comprises:
in the configuration of each type number, selecting the configuration with the maximum information gain ratio according to the information gain ratio in the decision tree, and recording the branch segmentation method under the configuration;
and forming each branch of the model according to the recorded branch segmentation method until the specific annual fund and model number in the annual fund group classification model.
5. The vehicle source model identification method according to claim 1, wherein the acquiring of the vehicle type information and the listing date of the vehicle source to be identified specifically comprises:
carrying out picture recognition on the vehicle source photo uploaded by the user to acquire the vehicle type information of the vehicle source to be recognized;
or matching the frame number uploaded by the user in a frame number information base to obtain the vehicle type information of the vehicle source to be identified;
or acquiring the vehicle type information of the vehicle source to be identified according to the vehicle type name uploaded by the user.
6. The vehicle source model identification method according to claim 1, wherein a specific branch under the first year money group classification model is specifically:
if the vehicle type information of the vehicle source to be identified is obtained through the vehicle source picture uploaded by the user, the lowest branch corresponding to the configuration identified by the picture is a specific branch under the first year money group classification model;
if the vehicle type information of the vehicle source to be identified is obtained through the frame number uploaded by the user, the lowest branch corresponding to the configuration identified in the frame number information base is a specific branch under the first annual pattern component classification model;
and if the vehicle type information of the vehicle source to be identified is obtained through the vehicle type name uploaded by the user, the first branch under the first annual bank group classification model is a specific branch of the first annual bank group.
7. The vehicle source model identification method according to claim 4, wherein the information gain ratio specifically comprises:
wherein A represents the configuration, D represents a yearly group consisting of a plurality of models, g R (D, A) represents the information gain ratio of A, H (D) represents entropy, and H (D | A) represents conditional entropy.
8. An apparatus for recognizing a vehicle source type, comprising: the system comprises a yearly payment group determining module, a question generating module, an answer and answer matching module and a searching module;
the year money group determining module is used for acquiring vehicle type information and a registration date of a vehicle source to be identified, and determining a year money group to which the vehicle source to be identified belongs, a first year money group classification model corresponding to the year money group and a specific branch under the first year money group classification model;
the question generation module is used for acquiring configuration information of each branch under a specific branch under the first annual pattern group classification model and a segmentation method under the first annual pattern group classification model, and automatically generating a plurality of questions and answers corresponding to the questions;
the answer and answer matching module is used for outputting a first question of the generated plurality of questions to a user, responding to answer information input by the user for the question, and determining the next branch of a specific branch of the first annual fund component classification model by combining an answer corresponding to the question;
the searching module is used for outputting a corresponding next question according to a next branch of the specific branch of the first annual fund component classification model, and combining the answer of the user and the answer corresponding to the question until the annual fund and the model of the vehicle source to be identified are searched in the first annual fund component classification model.
9. The vehicle source model identification device according to claim 7, wherein the annual fund group determination module comprises: the system comprises a year payment group determining unit, a classification model determining unit and a branch determining unit;
the annual money group determining unit is used for determining the sale time of the vehicle source to be identified according to the vehicle type information and the listing date of the vehicle source to be identified, and determining the annual money group to which the vehicle source to be identified belongs according to the sale time;
the classification model determining unit is used for inquiring a first annual money group classification model corresponding to the annual money group in a database according to the determined annual money group;
the branch determining unit is used for determining a specific branch under a first annual pattern classification model in the first annual pattern classification model according to the vehicle type information of the vehicle source to be identified;
the vehicle type information comprises a vehicle type and a part configuration; a plurality of annual bank group classification models are stored in the database; and recording a plurality of models sold in the same time period in each annual bank group classification model, and dividing each model in the same annual bank group classification model according to the configuration information of each model to form a plurality of branches.
10. The vehicle source model identification device according to claim 7, wherein the annuity determination module comprises any one or more of a combination of a picture identification unit, a frame number matching unit and a vehicle type name unit, and specifically comprises:
the picture identification unit is used for carrying out picture identification on the vehicle source picture uploaded by the user and acquiring the vehicle type information of the vehicle source to be identified;
the frame number matching unit is used for matching the frame number uploaded by the user in a frame number information base to acquire the vehicle type information of the vehicle source to be identified;
the vehicle type name unit is used for acquiring the vehicle type information of the vehicle source to be identified according to the vehicle type name uploaded by the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211068188.4A CN115408580B (en) | 2022-08-31 | 2022-08-31 | Vehicle source model identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211068188.4A CN115408580B (en) | 2022-08-31 | 2022-08-31 | Vehicle source model identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115408580A true CN115408580A (en) | 2022-11-29 |
| CN115408580B CN115408580B (en) | 2023-04-25 |
Family
ID=84164027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211068188.4A Active CN115408580B (en) | 2022-08-31 | 2022-08-31 | Vehicle source model identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115408580B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090070152A1 (en) * | 2007-09-12 | 2009-03-12 | Rolling Solutions Llc | Systems and methods for dynamic quote generation |
| CN108573198A (en) * | 2017-03-14 | 2018-09-25 | 优信互联（北京）信息技术有限公司 | A kind of method and device identifying vehicle information according to Vehicle Identify Number |
| CN110555024A (en) * | 2019-08-13 | 2019-12-10 | 广东数鼎科技有限公司 | Accurate automobile model matching system based on artificial intelligence algorithm |
| CN111310804A (en) * | 2020-01-22 | 2020-06-19 | 浙江大搜车软件技术有限公司 | Method, apparatus, device and medium for handling vehicle fault problem based on decision tree |
| CN111582178A (en) * | 2020-05-09 | 2020-08-25 | 山东建筑大学 | Vehicle weight recognition method and system based on multi-azimuth information and multi-branch neural network |
| CN112883086A (en) * | 2021-04-29 | 2021-06-01 | 江苏荣泽信息科技股份有限公司 | Product supply chain query management device and method based on block chain |
-
2022
- 2022-08-31 CN CN202211068188.4A patent/CN115408580B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090070152A1 (en) * | 2007-09-12 | 2009-03-12 | Rolling Solutions Llc | Systems and methods for dynamic quote generation |
| CN108573198A (en) * | 2017-03-14 | 2018-09-25 | 优信互联（北京）信息技术有限公司 | A kind of method and device identifying vehicle information according to Vehicle Identify Number |
| CN110555024A (en) * | 2019-08-13 | 2019-12-10 | 广东数鼎科技有限公司 | Accurate automobile model matching system based on artificial intelligence algorithm |
| CN111310804A (en) * | 2020-01-22 | 2020-06-19 | 浙江大搜车软件技术有限公司 | Method, apparatus, device and medium for handling vehicle fault problem based on decision tree |
| CN111582178A (en) * | 2020-05-09 | 2020-08-25 | 山东建筑大学 | Vehicle weight recognition method and system based on multi-azimuth information and multi-branch neural network |
| CN112883086A (en) * | 2021-04-29 | 2021-06-01 | 江苏荣泽信息科技股份有限公司 | Product supply chain query management device and method based on block chain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115408580B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Klepper | Nano-economics, spinoffs, and the wealth of regions | |
| CN110110038B (en) | Telephone traffic prediction method, device, server and storage medium | |
| CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
| CN108520270B (en) | Part matching method, system and terminal | |
| CN102651013A (en) | Method and system for extracting area information from enterprise name data | |
| CN112866759B (en) | E-commerce live broadcast platform based on deep learning and cloud computing and cloud communication server | |
| Ahtesham et al. | House price prediction using machine learning algorithm-the case of Karachi city, Pakistan | |
| CN111723178A (en) | Method, system, server and equipment for providing sales suggestions in real time | |
| CN110619545B (en) | Vehicle insurance data pushing method, system, equipment and storage medium based on big data | |
| CN112613627A (en) | Vehicle maintenance information pushing method, device, system, equipment and storage medium | |
| CN110765776A (en) | Method and device for generating return visit labeling sample data | |
| CN116363440A (en) | Deep learning-based identification and detection method and system for colored microplastic in soil | |
| CN110610169A (en) | Picture labeling method and device, storage medium and electronic device | |
| CN115510261A (en) | Online circuit diagram quick retrieval system | |
| CN117422232B (en) | AIGC-based vehicle owner and customer operation method and system | |
| CN116524725B (en) | Intelligent driving traffic sign image data identification system | |
| CN115408580A (en) | Vehicle source model identification method and device | |
| CN111915368B (en) | System, method and medium for identifying customer ID in automobile industry | |
| Berger et al. | ZEBRA: Z-order Curve-based Event Retrieval Approach to Efficiently Explore Automotive Data | |
| CN112990868A (en) | Method, system, equipment and storage medium for automatic vehicle insurance claims | |
| CN107563148A (en) | A kind of overall protein identification method and system based on ion index | |
| US20040111434A1 (en) | Method for the identification of stored information | |
| CN113627477A (en) | Vehicle multi-attribute identification method and system | |
| Thonglek et al. | Ivaa: Intelligent vehicle accident analysis system | |
| CN112417113A (en) | Intelligent question-answering method and system based on voice recognition technology |
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 |