A vehicle model data standardization matching method and system

Abstract

The embodiments of this specification provide a method and system for standardizing vehicle model data matching. The method includes: obtaining multiple groups of vehicle model data to be matched, each group of vehicle model data to be matched includes multiple vehicle model features; dividing the multiple vehicle model features of each group of vehicle model data to be matched based on preset conditions, and the divided vehicle model features include at least first-level features and second-level features; using the TF-IDF algorithm, determining the first standardized vehicle model data set corresponding to the vehicle model data to be matched from the standardized vehicle model database based on the vehicle model features in the first-level features of the vehicle model data to be matched, and determining the standardized vehicle model data corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second-level features of the vehicle model data to be matched.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for standardizing and matching vehicle model data. Background Art

[0002] With the booming development of shared travel, car rental, car resale and other industries, the volume of data recorded on cars has also increased dramatically. Due to the inconsistent construction of car data systems among major companies, the volume of recorded vehicle data is large and complex, making it difficult to apply this data.

[0003] Therefore, it is hoped to provide a standardized matching method for vehicle model data. Summary of the invention

[0004] In one aspect, the present specification provides a method for standardizing vehicle model data matching. The method includes: obtaining multiple groups of vehicle model data to be matched, each group of vehicle model data to be matched includes multiple vehicle model features; dividing the multiple vehicle model features of each group of vehicle model data to be matched based on preset conditions, and the divided vehicle model features include at least first-level features and second-level features; using the TF-IDF algorithm, determining a first standardized vehicle model data set corresponding to the vehicle model data to be matched from a standardized vehicle model database based on the vehicle model features in the first-level features of the vehicle model data to be matched, and determining standardized vehicle model data corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second-level features of the vehicle model data to be matched.

[0005] Another aspect of the present specification provides a vehicle model data standardization matching system. The system includes: an acquisition module, which is used to acquire multiple groups of vehicle model data to be matched, each group of vehicle model data to be matched includes multiple vehicle model features; a data processing module, which is used to divide the multiple vehicle model features of each group of vehicle model data to be matched based on preset conditions, and the divided vehicle model features include at least first-level features and second-level features; a matching module, which is used to determine the first standardized vehicle model data set corresponding to the vehicle model data to be matched from the standardized vehicle model database based on the vehicle model features in the first-level features of the vehicle model data to be matched through the TF-IDF algorithm, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second-level features of the vehicle model data to be matched.

[0006] Another aspect of the present specification provides a vehicle model data standardization matching device, comprising at least one processor, wherein the at least one processor is used to execute the method as described above.

[0007] Another aspect of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of the vehicle model data standardization matching method shown in some embodiments of this specification;

[0010] Figure 2 is an exemplary module diagram of a vehicle model data standardization matching system according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of a vehicle model data standardization matching method according to some embodiments of this specification;

[0012] Figure 4 It is an exemplary flow chart of the vehicle model data standardization matching method shown in other embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Although this specification makes various references to certain modules or units in the system according to the embodiments of this specification, any number of different modules or units can be used and run on the client and / or server. The modules are illustrative only, and different aspects of the system and method can use different modules.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Due to the inconsistent construction of automobile data systems of major enterprises, the recorded vehicle data presents a large and complex situation, which will create resistance to the research of automobile data, the overall development trend of the automobile industry, etc., making it difficult to apply these data. The embodiment of this specification provides a standardized matching method for vehicle model data, which realizes standardized matching of vehicle model data by performing one or more of data preprocessing, vehicle model feature division, parallel processing, result evaluation, etc. on vehicle model data, integrates the automobile data specifications scattered in various enterprises, and establishes a unified benchmark naming rule for the automobile industry, which can improve the efficiency and accuracy of standardized matching of vehicle model data, as well as the convenience of research on the automobile industry. In some embodiments, a multi-level vocabulary can be established based on all vehicle model features of vehicle model data, and different weights and / or thresholds are set for each level of vocabulary, and standardized matching of vehicle model data is performed based on the multi-level vocabulary. In some embodiments, multiple groups of vehicle model data can be processed in parallel by a multi-threaded method, and standardized vehicle model data of multiple groups of vehicle model data can be determined at the same time. In some embodiments, the standardized matching results of vehicle model data can be evaluated, and the matching process can be optimized based on the evaluation results.

[0019] Figure 1 It is a schematic diagram of an application scenario of the vehicle model data standardization matching method shown in some embodiments of this specification.

[0020] like Figure 1 As shown, the scenario 100 may include a server 110 , a network 120 , a terminal device 130 , a database 140 , and other data sources 150 .

[0021] In some embodiments, the vehicle model data standardization matching method can be applied to the establishment of a large-scale vehicle database. For example, the server 110 can obtain the vehicle model data to be matched from the terminal device 130, and / or the database 140, and / or other data sources 150 through the network 120, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the standardized vehicle model database through the TF-IDF (term frequency-inverse document frequency) method combined with a multi-level vocabulary and / or multi-threading technology, and establish a vehicle database based on the determined standardized vehicle model data.

[0022] The server 110 can be used to manage resources and process data and / or information from at least one component in the scene 100 or an external data source (e.g., a cloud data center). For example, the server 110 can obtain vehicle model data to be matched from the terminal device 130. For another example, the server 110 can obtain standardized vehicle model data from the database 140. In some embodiments, the server 110 can be part of a vehicle model data standardized matching system. For example, the server 110 can be a background server of a vehicle model data standardized matching system. In some embodiments, the server 110 can be part of the terminal device 130.

[0023] In some embodiments, server 110 can be a single server or a server group. In some embodiments, the server group can be centralized or distributed (for example, server 110 can be a distributed system). In some embodiments, server 110 can be local or remote. For example, server 110 can access information and / or data stored in terminal device 130 and / or database 140 through network 120. For another example, server 110 can be directly connected to terminal device 130 and / or database 140, and / or other data sources 150 to access stored information and / or data. In some embodiments, server 110 can be implemented on a cloud platform. As an example only, a cloud platform can include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, cross cloud, multi-cloud, etc. or any combination of the above examples. In some embodiments, server 110 can be implemented on a computing device, such as a computer, a mobile device, or any device with a computing and processing function.

[0024] In some embodiments, the server 110 may include a processing device 112. The processing device 112 may process various information and / or data related to the standardized matching of vehicle model data to perform one or more functions described in this specification. For example, the processing device 112 may obtain the vehicle model data to be matched from the terminal device 130, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the standardized vehicle model database. In some embodiments, the processing device 112 may include one or more processors (e.g., a single-chip processor or a multi-chip processor). By way of example only, the processing device 112 may include one or more hardware processors, such as a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination of the above examples.

[0025] The network 120 can facilitate the exchange of information and / or data. In some embodiments, one or more components in the scene 100 (e.g., the server 110, the terminal device 130, the database 140) can send information and / or data to other components in the scene 100 through the network 120. For example, the server 110 can obtain the vehicle model data to be matched from the terminal device 130 through the network 120. For another example, the server 110 can obtain the standardized vehicle model data from the database 140 through the network 120. In some embodiments, the network 120 can be any one or a combination of a wired network or a wireless network. As an example only, the network 120 may include a cable network, a wired network, an optical fiber network, a remote communication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, a near field communication (NFC) network, etc. or any combination of the above examples. In some embodiments, the network 120 may include one or more network exchange points. For example, network 120 may include wired or wireless network exchange points, such as base stations and / or Internet exchange points 120-1, 120-2, ..., through which one or more components of scene 100 may be connected to network 120 to exchange data and / or information.

[0026] The terminal device 130 can be used to input and / or obtain data and / or information. In some embodiments, the terminal device 130 may include a smart phone 130-1, a tablet computer 130-2, a laptop computer 130-3, etc. In some embodiments, the terminal device 130 may include a mobile terminal device, etc. For example, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, etc., or any combination of the above examples. In some embodiments, the smart home device may include a smart lighting device, a control device for smart appliances, a smart monitoring device, a smart TV, a smart camera, an intercom, etc., or any combination of the above examples. In some embodiments, the wearable device may include a bracelet, shoes and socks, glasses, a helmet, a watch, clothing, a backpack, smart accessories, etc., or any combination of the above examples. In some embodiments, the smart mobile device may include a mobile phone, a personal digital assistant, a gaming device, a navigation device, a POS machine, a laptop computer, a desktop computer, etc., or any combination of the above examples.

[0027] In some embodiments, the user may obtain the to-be-matched vehicle model data and / or the standardized vehicle model data through the terminal device 130. In some embodiments, the user may obtain vehicle data through the terminal device 130. For example, the user may obtain vehicle series, performance parameters, prices, and other data related to rental cars and / or second-hand cars in the standardized vehicle database through the terminal device 130.

[0028] The database 140 may store data and / or instructions. In some embodiments, the database 140 may store data obtained from the terminal device 130 and / or the network 120. In some embodiments, the database 140 may store data and / or instructions for execution or use by the server 110, and the server 110 may implement the exemplary method described in this specification by executing or using these data and / or instructions. In some embodiments, the database 140 may include a large capacity memory, a removable memory, a volatile read-write memory, a read-only memory (ROM), etc., or any combination of the above examples. An exemplary large capacity memory may include a disk, an optical disk, a solid-state disk, etc. An exemplary removable memory may include a flash drive, a floppy disk, an optical disk, a memory card, a compressed disk, a tape, etc. In some embodiments, the database 140 may be implemented on a cloud platform. As an example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, a cross-cloud, a multi-cloud, etc., or any combination of the above examples.

[0029] In some embodiments, the database 140 may be connected to the network 120 to communicate with one or more components in the scene 100 (e.g., the server 110, the terminal device 130). One or more components in the scene 100 may access data or instructions stored in the database 140 through the network 120. In some embodiments, the database 140 may be directly connected or communicated with one or more components in the scene 100 (e.g., the server 110, the terminal device 130). In some embodiments, the database 140 may be part of the server 110 and / or the terminal device 130.

[0030] Other data sources 150 can be used to provide one or more sources of other information for scene 100. In some embodiments, other data sources 150 may include one or more devices, one or more application programming interfaces, one or more database query interfaces, one or more protocol-based information acquisition interfaces, or other ways to obtain information, or a combination of two or more of the above. In some embodiments, the information provided by the data source may include information that already exists when the information is extracted, information that is temporarily generated when the information is extracted, or a combination of the above. In some embodiments, other data sources 150 can be used to provide scene 100 with data such as vehicle model data to be matched, standardized vehicle model data, etc.

[0031] In some alternative embodiments, scenario 100 may also include other components for standardized matching of vehicle model data, for example, may include a second server for establishing a vehicle database based on standardized vehicle model data, etc., which is not limited in this specification.

[0032] Figure 2 It is an exemplary module diagram of a vehicle model data standardization matching system according to some embodiments of this specification.

[0033] like Figure 2 As shown, in some embodiments, system 200 may include acquisition module 210, data processing module 220, matching module 230, data preprocessing module 240, evaluation module 250, optimization module 260, and database generation module 270. These modules may also be implemented as an application or a set of instructions read and executed by a processing engine. In addition, a module may be any combination of hardware circuits and applications / instructions. For example, when a processing engine or processor executes an application / a set of instructions, a module may be part of a processor.

[0034] The acquisition module 210 can be used to acquire the vehicle model data to be matched. In some embodiments, the acquisition module 210 can acquire multiple sets of vehicle model data to be matched from at least two different data sources. In some embodiments, each set of vehicle model data to be matched can include multiple vehicle model features. In some embodiments, each set of vehicle model data to be matched can correspond to a set of operation data of a vehicle.

[0035] The data processing module 220 can be used to divide the multiple vehicle model features of the vehicle model data to be matched based on preset conditions. In some embodiments, the divided vehicle model features may include first-level features and second-level features, and the importance of the first-level features is higher than the importance of the second-level features. In some embodiments, the divided vehicle model features may also include third-level features, and the importance of the third-level features is lower than the importance of the second-level features.

[0036] The matching module 230 can be used to determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the standardized vehicle model database based on the divided vehicle model features through the TF-IDF algorithm. In some embodiments, the matching module 230 can determine the first standardized vehicle model data set corresponding to the vehicle model data to be matched from the standardized vehicle model database based on the vehicle model features in the first level features of the vehicle model data to be matched, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second level features of the vehicle model data to be matched. In some embodiments, the matching module 230 can filter the stop words in the vehicle model data to be matched based on a preset stop word library before determining the first standardized vehicle model data set corresponding to the vehicle model data to be matched. In some embodiments, the matching module 230 can determine the second standardized vehicle model data set corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second level features of the vehicle model data to be matched through the TF-IDF algorithm, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the second standardized vehicle model data set based on the vehicle model features in the third level features of the vehicle model data to be matched. In some embodiments, the matching module 230 can determine the standardized vehicle model data set of the corresponding vehicle model from the standardized vehicle model database according to the vehicle model of the vehicle model data to be matched, and perform standardized vehicle model data matching based on the standardized vehicle model data set of the corresponding vehicle model. In some embodiments, the matching module 230 can determine the standardized vehicle model data of the second vehicle model data to be matched from the second vehicle model database when the second vehicle model data to be matched is similar to the first vehicle model data to be matched which has been standardized and matched.

[0037] The data preprocessing module 240 can be used to perform data preprocessing on the vehicle model features in the vehicle model data to be matched. In some embodiments, the preprocessing can include but is not limited to one or more combinations of data cleaning, normalization, value analysis, encoding, grading, combination, filtering, etc.

[0038] The evaluation module 250 can be used to evaluate the matching accuracy of the vehicle model data to be matched and at least one of its corresponding standardized vehicle model data, and determine the first vehicle model database and the second vehicle model database based on the evaluation results. The first vehicle model database includes vehicle model data that is not accurately matched and its corresponding standardized vehicle model data, and the second vehicle model database includes vehicle model data that is accurately matched and its corresponding standardized vehicle model data; the first vehicle model database is used to optimize the TF-IDF algorithm, and the second vehicle model database is used to index the standardized vehicle model data of the vehicle model data to be matched. In some embodiments, the evaluation module 250 can calculate the similarity of the vehicle model features between the vehicle model data to be matched and its corresponding standardized vehicle model data, and automatically score the matching accuracy based on the similarity; and determine the first vehicle model database and the second vehicle model database based on the scoring results.

[0039] The optimization module 260 can be used to update the multi-level bag-of-words model in the TF-IDF algorithm based on the vehicle model features of the vehicle model data to be matched in the first vehicle model database and the vehicle model features of the corresponding standardized vehicle model data. In some embodiments, the updating of the multi-level bag-of-words model may include adding synonym expressions of vehicle model features to the multi-level bag-of-words.

[0040] The database generation module 270 can be used to merge at least part of the operating data of the vehicles corresponding to the matching vehicle model data with the same corresponding standardized vehicle model data in the multiple groups of matching vehicle model data to generate a vehicle operation database, and automatically determine the price and vehicle model data source of the vehicle to be evaluated based on the vehicle operation database.

[0041] In some embodiments, the system 200 may process at least two groups of to-be-matched vehicle model data in parallel among the multiple groups of to-be-matched vehicle model data, and simultaneously determine the standardized vehicle model data of the at least two groups of to-be-matched vehicle model data. For example, the system 200 may simultaneously perform data preprocessing on the vehicle model features of at least two groups of to-be-matched vehicle model data. For another example, the system 200 may simultaneously divide the vehicle model features of at least two groups of to-be-matched vehicle model data. For another example, the system 200 may simultaneously determine the standardized vehicle model data of at least two groups of to-be-matched vehicle model data from the standardized vehicle model database.

[0042] It should be understood that the system and its modules shown can be implemented in various ways. For example, in some embodiments, the system 200 and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (e.g., firmware).

[0043] It should be noted that the above description of the system 200 and its modules is only for convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem connected with other modules without deviating from this principle. In some embodiments, the acquisition module 210, the data processing module 220, the matching module 230, the data preprocessing module 240, the evaluation module 250, the optimization module 260, and the database generation module 270 can be different modules in a system, or a module can realize the functions of two or more modules mentioned above. In some embodiments, the acquisition module 210, the data processing module 220, the matching module 230, the data preprocessing module 240, the evaluation module 250, the optimization module 260, and the database generation module 270 can share a storage module, and each module can also have its own storage module. Such variations are all within the protection scope of this specification.

[0044] Figure 3 It is an exemplary flow chart of the vehicle model data standardization matching method shown in some embodiments of this specification.

[0045] like Figure 3 As shown, process 300 can be executed by a processing device (such as server 110) or a vehicle model data standardization matching system (such as system 200). It includes:

[0046] Step 310 , obtaining multiple sets of vehicle model data to be matched. In some embodiments, step 310 may be performed by the obtaining module 210 .

[0047] The vehicle model data to be matched may be original vehicle model data defined by various enterprises that have not yet been standardized. In some embodiments, a set of vehicle model data to be matched may include multiple vehicle model features. In some embodiments, vehicle model features may include but are not limited to the brand, car series, year, displacement, gearbox type, best horsepower, guide price, transaction price, mileage, etc. of the vehicle. For example, a set of vehicle model data to be matched may be: 2015 model (year) Peugeot 308S (car series) 1.6L (displacement) manual (gearbox type). In some embodiments, the processing device may obtain vehicle model data to be matched from channels such as automobile manufacturers and automobile trading websites. For example, the processing device may obtain vehicle model data of all vehicles produced by corresponding manufacturers from automobile manufacturers such as Dongfeng, Volkswagen, Changan, Citroen, Xiali, Mercedes-Benz, and Audi as vehicle model data to be matched. For another example, the processing device may obtain vehicle model data of all vehicles on the corresponding website from second-hand car trading websites such as Guazi, Tiantianpai, Che300, Renrenche, and / or car rental websites such as Yihi, Shenzhou, and Wukong as vehicle model data to be matched.

[0048] In some embodiments, the processing device can obtain multiple sets of vehicle model data to be matched from at least two different data sources. The different data sources can be two or more channels of different types, or two or more different companies of the same type. For example, the processing device can simultaneously obtain multiple sets of vehicle model data to be matched from automobile manufacturers and used car trading websites. For another example, the processing device can simultaneously obtain multiple sets of vehicle model data to be matched from the trading websites corresponding to Guazi and Che300. In some embodiments, the method of obtaining the vehicle model data to be matched may include but is not limited to direct acquisition, cooperative relationship acquisition, etc., and this specification does not limit this.

[0049] In some embodiments, each set of to-be-matched vehicle model data may correspond to a set of operating data of a vehicle. For example, a set of to-be-matched vehicle model data may be data such as the brand, model series, year, displacement, gearbox type, guide price, transaction price, mileage, and vehicle age of a second-hand vehicle.

[0050] Step 315 , preprocessing the acquired vehicle model data to be matched. In some embodiments, step 315 may be performed by the data preprocessing module 240 .

[0051] In some embodiments, the processing device may perform data preprocessing on the vehicle model features in the acquired vehicle model data to be matched. In some embodiments, the preprocessing method may include but is not limited to a combination of one or more of data cleaning, normalization, value analysis, encoding, grading, combination, filtering, etc. In some embodiments, for each group of vehicle model data to be matched, the continuous vehicle model features such as transaction price, guide price, body length, width, height, mileage, etc. may be subjected to data cleaning, normalization, value analysis, etc. preprocessing operations, and the discrete vehicle model features such as gearbox type, year, brand, car series, high and low configuration in the vehicle model data to be matched may be subjected to coding, grading, combination, etc. preprocessing operations. For example, the processing device may remove redundant data such as extra zeros and units in the price by performing value analysis on the guide price / transaction price in the vehicle model features. For another example, the processing device may combine and encode the car series and year in the vehicle model features, and perform standardized matching based on the combined and encoded vehicle model features. For another example, the processing device may filter out the group of vehicle model data to be matched whose guide price is obviously abnormal.

[0052] In some embodiments, preprocessing operations can be performed simultaneously or separately on the continuous and discrete vehicle model features of the vehicle model data to be matched. Preferably, preprocessing operations can be performed simultaneously on the continuous and discrete vehicle model features of the vehicle model data to be matched. In some embodiments, the processing device can simultaneously perform data preprocessing operations on at least two groups of vehicle model data to be matched among the multiple groups of vehicle model data to be matched. For example, the processing device can preprocess all the acquired vehicle model data to be matched at the same time, or preprocess two groups of vehicle model data to be matched at the same time, or preprocess half of the vehicle model data to be matched among the multiple groups of vehicle model data to be matched at the same time. In some embodiments, the processing device can preprocess the vehicle model features of the vehicle model data to be matched by means of a trained algorithm model.

[0053] By preprocessing the feature data in the vehicle model data to be matched, redundant, unreasonable information data in the feature data can be filtered out, and standardized matching of vehicle model data can be performed based on the preprocessed vehicle model feature data to improve matching efficiency and accuracy.

[0054] Step 320 , based on the preset conditions, divide the multiple vehicle model features of the vehicle model data to be matched. In some embodiments, step 320 may be performed by the data processing module 220 .

[0055] In some embodiments, the preset conditions may include, but are not limited to, a combination of one or more of the conditions, quantity, type, level, number of groups, etc., for dividing vehicle model features. For example, the preset conditions may be: dividing all vehicle model features into two groups according to the category to which each vehicle model feature belongs, or dividing all vehicle model features into multiple groups according to the importance of each vehicle model feature to vehicle brand recognition, etc. In some embodiments, the preset conditions may be direct division rules for vehicle model features. For example, the preset conditions may be: dividing the brand and car series in the vehicle model data into the first group of vehicle model features, and dividing the displacement, gearbox type, and optimal horsepower in the vehicle model data into the second group of vehicle model features.

[0056] In some embodiments, the divided vehicle model features may include multiple feature groups of different importance. For example, the divided vehicle model features may include first-level features and second-level features, wherein the importance of the first-level features is higher than that of the second-level features. For another example, the divided vehicle model features may include first-level features, second-level features, and third-level features, wherein the importance of the first-level features is higher than that of the second-level features, and the importance of the second-level features is higher than that of the third-level features. As an example only, the first-level features may be brand (e.g., Jiangling, Suzuki, Dongfeng Xiaokang, Southeast, Foton, Hongqi, etc.), car series (e.g., Teshun New Energy, Beidouxing, Dongfeng Xiaokang K05S, Fulika, Savannah, Century Star, etc.), etc., which are set by the vehicle manufacturer and must be kept consistent; the second-level features may be displacement (e.g., 4.8L, 1.3L, 3.6L, etc.), transmission type (e.g., manual, automatic, manual-automatic), etc., which may be defined by the manufacturer, for example, the displacement of the vehicle may be defined as 1.6T or 1.6L; the third-level features may be other vehicle features other than the first-level features and the second-level features, such as vehicle class (e.g., mid-size car, small car, etc.), horsepower (e.g., 103 horsepower, 108 horsepower, etc.). In some alternative embodiments, the third-level features may be part of other vehicle features, for example, the third-level features may not include the vehicle features such as the guide price, transaction price, emission standards, etc., which are included in other vehicle features, and this specification does not limit this.

[0057] By dividing vehicle model features into multiple feature groups with different importance, standardized vehicle model data matching can be performed step by step according to the importance of each feature group. After matching multiple layers of standardized vehicle model data, the final matching result is more accurate.

[0058] Step 330 , using the TF-IDF algorithm, based on the divided vehicle model features, determines the standardized vehicle model data corresponding to the vehicle model data to be matched from the standardized vehicle model database. In some embodiments, step 330 may be performed by the matching module 230 .

[0059] The standardized vehicle model database refers to a standardized definition data system established by giving standardized definitions to the various elements that make up the car (i.e., vehicle model features). For example, the displacement of the vehicle can be standardized as "digital + T", and "manual and automatic" can be standardized as "automatic", etc. In some embodiments, the standardized vehicle model database may include multiple vehicle models and multiple vehicle model features. For example, the standardized vehicle model database may include more than 90,000 vehicle models and more than 300 vehicle model features. In some embodiments, the processing device may determine the standardized definition of vehicle model features based on the vehicle model data of the automobile manufacturer, manufacturer, and / or second-hand car trading website. For example, the definition of vehicle model features of various types of vehicles in the second-hand car trading platform-Che300 can be directly determined as the standardized definition of vehicle model data, and a standardized vehicle model database can be established based on the platform vehicle database. For another example, the standardized definition of vehicle model data can be determined based on the definition of each element of the vehicle by the automobile manufacturer, and a standardized vehicle model database can be established based on the vehicle data of the manufacturer. In some embodiments, the processing device can determine the standardized definition of vehicle model data based on the user's expression habits. For example, the habitual expression of each element of the vehicle by the general public can be determined as a standardized definition, and a standardized vehicle model database can be established based on the category of the vehicle. In some embodiments, the processing device can determine the standardized definition of vehicle model data based on international standards. For example, the standard definition of vehicle model data may be determined based on international units and international conventional / standard expressions of various elements of a vehicle. In some alternative embodiments, the standardized definition of vehicle model data may be determined in any reasonable manner, and this specification does not limit this.

[0060] In some embodiments, the vehicle model features corresponding to the standardized vehicle model data in the standardized vehicle model database may be divided. For example, the vehicle model features corresponding to the vehicle model data to be matched may be divided into first-level features, second-level features, and third-level features. The processing device may match the standardized vehicle model data based on the feature groups corresponding to the divided vehicle model features.

[0061] In some embodiments, the standardized vehicle model database may be updated regularly based on the update of vehicle model data. For example, the standardized vehicle model feature definition in the standardized vehicle model database may be updated weekly, daily, or monthly. In some embodiments, the standardized vehicle model database may be updated based on the production time of the vehicle. For example, the corresponding standardized vehicle model data may be added to the standardized vehicle model database based on the newly produced vehicle.

[0062] TF-IDF (term frequency–inverse document frequency) is a weighted technology used for information retrieval and data mining. Among them, TF refers to term frequency, and IDF refers to inverse document frequency. TF-IDF can be used to evaluate the importance of a word to a text set or one of the texts in a corpus. The importance of a word increases in direct proportion to the number of times it appears in the text, but at the same time it decreases in inverse proportion to the frequency of its appearance in the corpus. In some embodiments, the processing device can determine the first standardized vehicle model data set corresponding to the vehicle model data to be matched from the standardized vehicle model database based on the vehicle model features in the first level features of the vehicle model data to be matched by the TF-IDF algorithm, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second level features of the vehicle model data to be matched. In some embodiments, the processing device can determine the second standardized vehicle model data set corresponding to the vehicle model data to be matched from the first standardized vehicle model data set based on the vehicle model features in the second level features of the vehicle model data to be matched by the TF-IDF algorithm, and determine the standardized vehicle model data corresponding to the vehicle model data to be matched from the second standardized vehicle model data set based on the vehicle model features in the third level features of the vehicle model data to be matched. For example, based on the first-level features of the vehicle model data to be matched, the vehicle model features, brand and series, 10 groups of standardized vehicle model data related to the vehicle model data to be matched are matched from the standardized vehicle model database, based on the second-level features, model year, displacement, and transmission type, 5 groups of standardized vehicle model data related to the vehicle model data to be matched can be further matched from the 10 groups of standardized vehicle model data, and based on the third-level features, vehicle model level and horsepower, a group of standardized vehicle model data corresponding to the vehicle model data to be matched can be matched from the 5 groups of standardized vehicle model data. In some embodiments, the standardized vehicle model data matching result can be determined based on the importance of the group corresponding to the vehicle model features of the vehicle model data to be matched. For example, if the first-level features of the vehicle model data to be matched do not match the corresponding standardized vehicle model data from the standardized vehicle model database, the subsequent matching is not performed; or if the second-level features of the vehicle model data to be matched do not match the corresponding standardized vehicle model data from the first standardized vehicle model data set, the subsequent matching is not performed; or if the third-level features of the vehicle model data to be matched do not match the corresponding standardized vehicle model data from the second standardized vehicle model data set, the matching is considered to have failed (i.e., the corresponding standardized vehicle model data is not matched).

[0063] In some embodiments, the processing device may determine the standardized vehicle model data corresponding to the vehicle model data to be matched based on the similarity distance between the vehicle model features of the vehicle model data to be matched and the corresponding vehicle model features of the standardized vehicle model data. For example, when the similarity distance value between the vehicle model features of the vehicle model data to be matched and the corresponding vehicle model features of the standardized vehicle model data is greater than a preset matching threshold, the standardized vehicle model data may be determined to be the standardized vehicle model data corresponding to the vehicle model data to be matched. In some embodiments, the similarity distance value being greater than the preset matching threshold may include that the similarity distance between each vehicle model feature of the vehicle model data to be matched and the corresponding vehicle model feature of the standardized vehicle model data is greater than the preset matching threshold, or the similarity distance between some vehicle model features of the vehicle model data to be matched and the corresponding vehicle model features of the standardized vehicle model data is greater than the preset matching threshold, or the average of the similarity distances between all or some vehicle model features of the vehicle model data to be matched and the corresponding vehicle model features of the standardized vehicle model data is greater than the preset matching threshold.

[0064] In some embodiments, different standardized matching thresholds for vehicle model data may be set for each group of vehicle model features based on the importance of the vehicle model features. For example, the matching threshold corresponding to the first-level features of the vehicle model data may be 0.6, the matching threshold corresponding to the second-level features may be 0.8, and the matching threshold corresponding to the third-level features may be 0.95. For another example, the matching threshold corresponding to the first-level features of the vehicle model data may be 0.5, the matching threshold corresponding to the second-level features may be 0.7, and the matching threshold corresponding to the third-level features may be 0.9. For another example, the matching threshold corresponding to the first-level features of the vehicle model data may be 0.8, the matching threshold corresponding to the second-level features may be 0.9, and the matching threshold corresponding to the third-level features may be 0.98. In some embodiments, the preset matching threshold corresponding to each group of vehicle model features may be any reasonable value, and this specification does not limit this.

[0065] In some embodiments, the conditions for each group of vehicle model features to meet the preset matching threshold may be all the same, all different, or partially the same. For example, the standardized matching based on the first-level features of the vehicle model data to be matched may be that the similarity distance values ​​between all vehicle model features of the first-level features and the corresponding vehicle model features of the standardized vehicle model data are all greater than the corresponding preset matching threshold, the standardized matching based on the second-level features may be that the similarity distance values ​​between all vehicle model features of the second-level features and the corresponding vehicle model features of the standardized vehicle model data are all greater than the corresponding preset matching threshold, and the standardized matching based on the third-level features may be that the average of the similarity distances between all vehicle model features of the third-level features and the corresponding vehicle model features of the standardized vehicle model data is greater than the corresponding preset matching threshold.

[0066] In some embodiments, before determining the first standardized vehicle model dataset corresponding to the vehicle model data to be matched, the processing device may filter out the stop words in the vehicle model data to be matched based on a preset stop word library. Stop words refer to the words or characters that are filtered out in information retrieval to save storage space and improve search efficiency. In some embodiments, the stop words may include, but are not limited to, English characters, numbers, mathematical characters, punctuation marks, as well as frequently used modal particles, adverbs, prepositions, conjunctions (e.g., "in", "le", "de", "ba", etc.). In some embodiments, the processing device may filter out stop words through the TF-IDF algorithm or other methods.

[0067] In some embodiments, before performing the standardized vehicle model data matching, the processing device may determine the standardized vehicle model dataset corresponding to the vehicle series of the vehicle model data to be matched from the standardized vehicle model database. The processing device may perform the standardized matching of the vehicle model data based on the standardized vehicle model dataset corresponding to the vehicle series. For example, if the vehicle series of the vehicle model data to be matched is "Dongfeng Xiaokang K05S", the standardized vehicle model data to be matched can be directly searched in the standardized vehicle model data corresponding to "Dongfeng Xiaokang K05S" in the standardized vehicle model database.

[0068] In some embodiments, the standardized matching result of the vehicle model data to be matched may include a successful match and a failed match. A successful match means that the vehicle model data to be matched matches at least one standardized vehicle model data, and a failed match means that the vehicle model data to be matched does not match the corresponding standardized vehicle model data in the standardized vehicle model database.

[0069] In some alternative embodiments, the standardized vehicle model data matching of the vehicle model data to be matched may be performed through other algorithms capable of realizing data matching, and this specification does not limit this.

[0070] Step 340: Evaluate the matching accuracy between the vehicle model data to be matched and its corresponding standardized vehicle model data, and determine the first vehicle model database and the second vehicle model database based on the evaluation result. In some embodiments, step 340 may be executed by the evaluation module 250.

[0071] The first vehicle model database may include vehicle model data that is not accurately matched and its corresponding standardized vehicle model data. In some alternative embodiments, the first vehicle model database may include a combination of one or more of vehicle model data that is not accurately matched, standardized vehicle model data that is matched corresponding to the group of vehicle model data, or correct standardized vehicle model data that is matched corresponding to the group of vehicle model data. In some embodiments, the first vehicle model database may be used to optimize the TF-IDF algorithm, for example, step 343. The second vehicle model database may include vehicle model data that is accurately matched and its corresponding standardized vehicle model data. In some embodiments, the second vehicle model database may include vehicle model data that is accurately matched or its corresponding standardized vehicle model data. In some embodiments, the second vehicle model database may be used to index standardized vehicle model data of vehicle model data to be matched, for example, step 415 in process 400.

[0072] In some embodiments, the processing device may evaluate the matching accuracy of each group of vehicle model data to be matched and at least one of the corresponding standardized vehicle model data, and determine the first vehicle model database and the second vehicle model database based on the evaluation results. For example, the TOP N standardized vehicle model data corresponding to the vehicle model data to be matched may be selected to evaluate the matching accuracy, where N is an arbitrary positive integer. In some embodiments, for each group of vehicle model data to be matched, the processing device may respectively calculate the similarity of the corresponding vehicle model features between the vehicle model data to be matched and at least one of the corresponding standardized vehicle model data, and automatically score the matching accuracy based on the similarity value; and determine the first vehicle model database and the second vehicle model database based on the scoring results. In some embodiments, the processing device may automatically score based on the similarity distance between all vehicle model features of the vehicle model data to be matched and the corresponding vehicle model features in the corresponding standardized vehicle model data. In some embodiments, automatic scoring may be performed using regression technology. In some embodiments, the matching accuracy of the vehicle model data to be matched and its corresponding standardized vehicle model data may be evaluated using a machine learning model.

[0073] In some embodiments, the first vehicle model database and the second vehicle model database may be determined by setting a second threshold value. For example, the vehicle model data to be matched with a score greater than the second threshold value and its corresponding standardized vehicle model data may be determined as the second vehicle model database, and the vehicle model data to be matched with a score less than or equal to the second threshold value and its corresponding standardized vehicle model data may be determined as the first vehicle model database.

[0074] Step 343 , optimizing the TF-IDF algorithm based on the first vehicle model database. In some embodiments, step 343 may be performed by the optimization module 260 .

[0075] In some embodiments, the processing device can update the multi-level bag-of-words model in the TF-IDF algorithm based on the vehicle model features of the vehicle model data to be matched in the first vehicle model database and the vehicle model features of the corresponding standardized vehicle model data. The bag-of-words model refers to a set of words that puts all words into a bag without considering the lexical and word order issues of the words, and each word in the bag of words is independent of each other and does not depend on whether other words appear. In some embodiments, the bag-of-words model can be part of the TF-IDF algorithm, and the TF-IDF algorithm can automatically construct a bag-of-words model based on input data and thesaurus during data matching. In the embodiments of this specification, the multi-level bag-of-words model refers to a set of words that can construct multiple bags of words at different levels according to the different levels of each group of vehicle model features after division. In some embodiments, the multi-level bag-of-words model can be updated based on the vehicle model features in the vehicle model data to be matched in the first vehicle model data and its corresponding standardized vehicle model data. As an example only, the inaccurately matched vehicle model data in the first vehicle model database due to language inconsistency, naming update, etc. and the corresponding correct standardized vehicle model data can be input into the TF-IDF algorithm, and the TF-IDF algorithm can add the English translation of the corresponding vehicle model features (such as the English translation of "Toyota" corresponding to "TOYOTA", etc.), the original name (such as other names corresponding to "Bentley", etc.) and other synonym expressions in the multi-level word bag based on this group of data. For example, if the inaccurately matched original vehicle model data is "Bentley 2010 Continental 6.0T Automatic Edition", and the corresponding correct standardized vehicle model data is "Bentley 2010 Continental 6.0T Automatic Edition", the multi-level word bag constructed by the optimized TF-IDF algorithm can include words such as "Bentley 2010 Continental 6.0T Automatic Edition Bentley".

[0076] In some embodiments, the processing device can optimize the TF-IDF algorithm based on the recall rate (the ratio of the to-be-matched vehicle model data that matches the standardized vehicle model data to all the to-be-matched vehicle model data that undergo standardized matching), precision, AUC indicator (the relationship curve between accuracy and recall), etc. of the TF-IDF algorithm.

[0077] In some alternative embodiments, other parts of the TF-IDF algorithm may be updated based on the first vehicle model database and / or other data, or other parts of the vehicle model data standardized matching method may be updated, for example, a multi-level feature vocabulary of vehicle model features may be updated (e.g., based on the vehicle model features in the first vehicle model database, the division method of vehicle model features is updated, etc.), and this specification does not impose any restrictions on this.

[0078] In some embodiments, the processing device (or vehicle model data standardization matching system) can process at least two groups of vehicle model data to be matched in parallel among the multiple groups of vehicle model data to be matched, and simultaneously determine the standardized vehicle model data of the at least two groups of vehicle model data to be matched. For example, the processing device can simultaneously perform data preprocessing, data processing, stop word filtering, and standardized vehicle model data matching operations on 10 groups, or 20 groups, or 50 groups, or 100 groups of vehicle model data to be matched, so as to simultaneously determine the standardized vehicle model data corresponding to the 10 groups, or 20 groups, or 50 groups, or 100 groups of vehicle model data to be matched.

[0079] In some embodiments, a vehicle database can be established based on the matching results of the standardized vehicle model data of the vehicle model data to be matched. For example, the vehicle model features in the vehicle model data to be matched that do not match the corresponding standardized vehicle model data can be changed to the vehicle model feature description in the standardized vehicle model data, and the source of the group of vehicle model data to be matched can be marked to build a vehicle database corresponding to all vehicle model data to be matched. In some embodiments, at least part of the operating data of the vehicle corresponding to the vehicle model data to be matched that has the same standardized vehicle model data in the plurality of groups of vehicle model data to be matched can be merged to generate a vehicle operation database, and the price and vehicle model data source of the vehicle to be evaluated can be automatically determined based on the vehicle operation database. In some embodiments, the price of the vehicle to be evaluated can be determined by one or more of the replacement cost method, the current valuation method, the current value of income method, the current market price method, etc. For example, based on the vehicle model features in the vehicle operation database, the average price of vehicles of the same style, year, and service life in the market can be used as the basis, and the current technical status assessment coefficient of the vehicle to be evaluated can be considered, and the price of the vehicle can be determined by multiplying the average price by the coefficient. In some embodiments, the price of the vehicle to be evaluated can be determined directly based on the recommended price in the standardized vehicle model data of the vehicle. For example, a certain amount can be added / subtracted on the basis of the recommended price.

[0080] It should be noted that the above description of process 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, in some embodiments, steps 315-330 can be implemented by a model that has the functions of data preprocessing, data processing, data matching, etc., or can be implemented by three models that have the functions of data preprocessing, data processing, and data matching, respectively.

[0081] Figure 4 It is an exemplary flow chart of the vehicle model data standardization matching method shown in other embodiments of this specification.

[0082] like Figure 4As shown, in some embodiments, the processing device (or vehicle model data standardization matching system) can determine the standardized vehicle model data of the second vehicle model data to be matched based on the determined second vehicle model database when the second vehicle model data to be matched is similar to the first vehicle model data to be matched that has been standardized and matched. Among them, in process 400, steps 410, 415, and 420-440 correspond to steps 310, 315, and 320-340 in process 300, respectively. For more information, please refer to Figure 3 And the related description will not be repeated here.

[0083] In step 413, the processing device may first determine whether the vehicle model data to be matched is similar to the vehicle model data that has been standardized and matched. When the vehicle model data to be matched is not similar to the vehicle model data that has been standardized and matched, the standardized vehicle model data of the vehicle model data to be matched is determined through steps 415 to 440; when the vehicle model data to be matched is similar to the vehicle model data that has been standardized and matched, the standardized vehicle model data of the vehicle model data to be matched is determined directly from the second vehicle model database through an index through step 445.

[0084] In some embodiments, it is possible to determine whether the vehicle model data to be matched is similar to the vehicle model data that has been standardized and matched based on the vehicle model features. For example, whether the corresponding vehicle model features are consistent or similar. By constructing a second vehicle model database, when the same or similar vehicle model data to be matched is input again, the corresponding standardized vehicle model data can be directly indexed from the second vehicle model database to improve the efficiency of standardized matching of vehicle model data. For example, if the first vehicle model data to be matched is the vehicle model data "Volkswagen Lavida 2015 1.6T Automatic Comfort Edition" from Guazi, the standardized vehicle model data of this group of vehicle model data is determined to be "Volkswagen Lavida 2015 1.6L Automatic Comfort Edition" through standardized matching, and the group of data is accurately matched after evaluation, and added to the second vehicle model database; then if the second vehicle model data to be matched is the vehicle model data "Volkswagen Lavida 2015 1.6T Automatic Comfort Edition" from Renrenche, the corresponding standardized vehicle model data "Volkswagen Lavida 2015 1.6L Automatic Comfort Edition" can be directly indexed from the second vehicle model database.

[0085] In some embodiments, the processing device (or the vehicle model data standardization matching system) can standardize the vehicle model data based on the second vehicle model database determined by the vehicle model data standardization matching. For example, the standardized vehicle model data of the vehicle model data can be obtained from the second vehicle model database.

[0086] It should be noted that the above description of process 400 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 400 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, process 400 can also include step 443 similar to step 343 in process 300, optimizing the TF-IDF algorithm based on the first vehicle model database.

[0087] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) by dividing the vehicle model features into multiple feature groups, the vehicle model data is standardized step by step based on the vehicle model features of each feature group, which can improve the matching accuracy and efficiency; (2) by processing multiple groups of vehicle model data to be matched in parallel, the efficiency of standardized matching of vehicle model data can be improved; (3) by evaluating the matching results, a first vehicle model database for optimizing the matching algorithm and a second vehicle model database for indexing are constructed based on the evaluation results, which can improve the matching accuracy and matching efficiency. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other possible beneficial effects.

[0088] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0089] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0090] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0091] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0092] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0093] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0094] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A vehicle model data standardization matching method, characterized in that: The method comprises: Acquire multiple sets of vehicle model data to be matched, each set of vehicle model data to be matched includes multiple vehicle model features; Based on preset conditions, the plurality of vehicle model features of each group of vehicle model data to be matched are divided, wherein the divided vehicle model features include at least first-level features and second-level features, and the importance of the first-level features is higher than that of the second-level features; the first-level features include vehicle brands and series, and the second-level features include displacement and transmission type; Determine, by a TF-IDF algorithm, a first standardized vehicle model data set corresponding to the vehicle model data to be matched from a standardized vehicle model database based on the vehicle model features in the first-level features of the vehicle model data to be matched, and determine, from the first standardized vehicle model data set, standardized vehicle model data corresponding to the vehicle model data to be matched, based on the vehicle model features in the second-level features of the vehicle model data to be matched; and Performing a matching accuracy evaluation on the to-be-matched vehicle model data and at least one corresponding standardized vehicle model data, and determining a first vehicle model database and a second vehicle model database based on the evaluation result; Among them, the first vehicle model database includes inaccurately matched vehicle model data and its corresponding standardized vehicle model data, which are used to optimize the TF-IDF algorithm; the second vehicle model database includes accurately matched vehicle model data and its corresponding standardized vehicle model data, which are used to index the standardized vehicle model data of the vehicle model data to be matched, specifically including: when the second vehicle model data to be matched is similar to the first vehicle model data to be matched that has been standardized and matched, determining the standardized vehicle model data of the second vehicle model data to be matched from the second vehicle model database.

2. The method according to claim 1, characterized in that At least two groups of vehicle model data to be matched among the multiple groups of vehicle model data to be matched are processed in parallel, and standardized vehicle model data of the at least two groups of vehicle model data to be matched are determined simultaneously.

3. The method according to claim 1, characterized in that Before determining the standardized vehicle model data corresponding to the to-be-matched vehicle model data by the TF-IDF algorithm, the method further includes: According to the vehicle series of the vehicle model data to be matched, a standardized vehicle model data set of the corresponding vehicle series is determined from the standardized vehicle model database, and standardized vehicle model data matching is performed based on the standardized vehicle model data set of the corresponding vehicle series.

4. The method according to claim 1, characterized in that: Before determining the first standardized vehicle model data set corresponding to the to-be-matched vehicle model data, the method further includes: The stop words in the vehicle model data to be matched are filtered based on a preset stop word library.

5. The method according to claim 1, characterized in that Also includes: Data preprocessing is performed on the multiple vehicle model features in each group of the to-be-matched vehicle model data, and the preprocessing at least includes data cleaning, normalization, value analysis, encoding, grading, combination, or filtering.

6. The method according to claim 1, characterized in that The divided vehicle model features further include third-level features, the third-level features include vehicle model levels, and the importance of the second-level features is higher than the importance of the third-level features; The determining, from the first standardized vehicle model data set, the standardized vehicle model data corresponding to the vehicle model data to be matched based on the vehicle model features in the second level features of the vehicle model data to be matched, comprises: Through the TF-IDF algorithm, the second standardized vehicle model data set corresponding to the vehicle model data to be matched is determined from the first standardized vehicle model data set based on the vehicle model features in the second-level features of the vehicle model data to be matched, and the standardized vehicle model data corresponding to the vehicle model data to be matched is determined from the second standardized vehicle model data set based on the vehicle model features in the third-level features of the vehicle model data to be matched.

7. The method according to claim 1, characterized in that The performing matching accuracy evaluation on the to-be-matched vehicle model data and its corresponding at least one standardized vehicle model data, and determining the first vehicle model database and the second vehicle model database based on the evaluation result comprises: Calculating the similarity of vehicle model features between the vehicle model data to be matched and its corresponding standardized vehicle model data, and automatically scoring the matching accuracy based on the similarity; The first vehicle model database and the second vehicle model database are determined based on the scoring results.

8. The method according to claim 1, characterized in that The first vehicle model database is used to optimize the TF-IDF algorithm, specifically including: Based on the vehicle model features of the to-be-matched vehicle model data in the first vehicle model database and the vehicle model features of the corresponding standardized vehicle model data, updating the multi-level bag-of-words model in the TF-IDF algorithm; The updating of the multi-level bag-of-words model at least includes adding synonymous expressions of vehicle model features into the multi-level bag-of-words.

9. The method according to claim 1, characterized in that: Also includes: A plurality of groups of to-be-matched vehicle model data are obtained from at least two different data sources, each group of to-be-matched vehicle model data corresponding to a group of operating data of a vehicle.

10. The method according to claim 9, characterized in that Also includes: At least part of the operating data of the vehicles corresponding to the to-be-matched vehicle model data having the same corresponding standardized vehicle model data in the multiple groups of to-be-matched vehicle model data are merged to generate a vehicle operating database, and the price and vehicle model data source of the to-be-evaluated vehicle are automatically determined based on the vehicle operating database.

11. A vehicle model data standardization matching system, characterized in that: The system comprises: An acquisition module is used to acquire multiple sets of vehicle model data to be matched, each set of vehicle model data to be matched includes multiple vehicle model features; a data processing module, configured to divide the plurality of vehicle model features of each group of vehicle model data to be matched based on preset conditions, wherein the divided vehicle model features include at least first-level features and second-level features, wherein the importance of the first-level features is higher than that of the second-level features; the first-level features include vehicle brands and series, and the second-level features include displacement and transmission type; a matching module, configured to determine, by a TF-IDF algorithm, a first standardized vehicle model data set corresponding to the vehicle model data to be matched from a standardized vehicle model database based on the vehicle model features in the first-level features of the vehicle model data to be matched, and to determine, from the first standardized vehicle model data set, standardized vehicle model data corresponding to the vehicle model data to be matched, based on the vehicle model features in the second-level features of the vehicle model data to be matched; and An evaluation module, configured to evaluate the matching accuracy of the to-be-matched vehicle model data and at least one corresponding standardized vehicle model data, and determine a first vehicle model database and a second vehicle model database based on the evaluation result; Among them, the first vehicle model database includes inaccurately matched vehicle model data and its corresponding standardized vehicle model data, which are used to optimize the TF-IDF algorithm; the second vehicle model database includes accurately matched vehicle model data and its corresponding standardized vehicle model data, which are used to index the standardized vehicle model data of the vehicle model data to be matched, specifically including: when the second vehicle model data to be matched is similar to the first vehicle model data to be matched that has been standardized and matched, determining the standardized vehicle model data of the second vehicle model data to be matched from the second vehicle model database.

12. The system according to claim 11, characterized in that At least two groups of vehicle model data to be matched among the multiple groups of vehicle model data to be matched are processed in parallel, and standardized vehicle model data of the at least two groups of vehicle model data to be matched are determined simultaneously.

13. The system according to claim 11, characterized in that The matching module is also used for: According to the vehicle series of the vehicle model data to be matched, a standardized vehicle model data set of the corresponding vehicle series is determined from the standardized vehicle model database, and standardized vehicle model data matching is performed based on the standardized vehicle model data set of the corresponding vehicle series.

14. The system according to claim 11, characterized in that The matching module is further used before determining the first standardized vehicle model data set corresponding to the vehicle model data to be matched: The stop words in the vehicle model data to be matched are filtered based on a preset stop word library.

15. The system according to claim 11, characterized in that It also includes a data preprocessing module for performing data preprocessing on the multiple vehicle model features in each group of the to-be-matched vehicle model data, wherein the preprocessing at least includes data cleaning, normalization, value analysis, encoding, grading, combination, or filtering.

16. The system according to claim 11, characterized in that The divided vehicle model features further include third-level features, the third-level features include vehicle model levels, and the importance of the second-level features is higher than the importance of the third-level features; The matching module is also used for: Through the TF-IDF algorithm, the second standardized vehicle model data set corresponding to the vehicle model data to be matched is determined from the first standardized vehicle model data set based on the vehicle model features in the second-level features of the vehicle model data to be matched, and the standardized vehicle model data corresponding to the vehicle model data to be matched is determined from the second standardized vehicle model data set based on the vehicle model features in the third-level features of the vehicle model data to be matched.

17. The system according to claim 11, characterized in that The evaluation module is also used to: Calculating the similarity of vehicle model features between the vehicle model data to be matched and its corresponding standardized vehicle model data, and automatically scoring the matching accuracy based on the similarity; The first vehicle model database and the second vehicle model database are determined based on the scoring results.

18. The system according to claim 11, characterized in that The system further comprises an optimization module, wherein the optimization module is configured to: Based on the vehicle model features of the to-be-matched vehicle model data in the first vehicle model database and the vehicle model features of the corresponding standardized vehicle model data, updating the multi-level bag-of-words model in the TF-IDF algorithm; The updating of the multi-level bag-of-words model at least includes adding synonymous expressions of vehicle model features into the multi-level bag-of-words.

19. The system according to claim 11, characterized in that The acquisition module acquires multiple groups of to-be-matched vehicle model data from at least two different data sources, and each group of to-be-matched vehicle model data corresponds to a group of operation data of a vehicle.

20. The system according to claim 19, characterized in that The system further comprises a database generation module, wherein the database generation module is used for: At least part of the operating data of the vehicles corresponding to the to-be-matched vehicle model data having the same corresponding standardized vehicle model data in the multiple groups of to-be-matched vehicle model data are merged to generate a vehicle operating database, and the price and vehicle model data source of the to-be-evaluated vehicle are automatically determined based on the vehicle operating database.

21. A vehicle model data standardization matching device, comprising at least one processor, wherein the at least one processor is used to execute the method according to any one of claims 1 to 10.

22. A computer-readable storage medium, wherein the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 10.

Images