CN113129064A - Automobile part price prediction method, system, equipment and readable storage medium - Google Patents
Automobile part price prediction method, system, equipment and readable storage medium Download PDFInfo
- Publication number
- CN113129064A CN113129064A CN202110448808.6A CN202110448808A CN113129064A CN 113129064 A CN113129064 A CN 113129064A CN 202110448808 A CN202110448808 A CN 202110448808A CN 113129064 A CN113129064 A CN 113129064A
- Authority
- CN
- China
- Prior art keywords
- price
- data set
- transaction
- transaction data
- model
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims description 16
- 238000012549 training Methods 0.000 claims abstract description 115
- 238000013461 design Methods 0.000 claims abstract description 42
- 238000004140 cleaning Methods 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 34
- 238000012795 verification Methods 0.000 claims description 23
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 14
- 238000012417 linear regression Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008439 repair process Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting the price of an automobile part, which comprises the following steps: collecting an original transaction data set of a target automobile accessory; cleaning the original transaction data set to obtain an effective transaction data set; analyzing key design features influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design features comprise at least one non-price transaction element of transaction attributes, accessory attributes and environment attributes; extracting a transaction data set comprising the key design characteristics from the effective transaction data set as a training data set, and training a preset initial prediction model by using the training data set to obtain a price prediction model; predicting a current price of the target auto-parts using the price prediction model. The invention can quickly and accurately predict the price of the automobile parts.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to a method, a system, a device, and a readable storage medium for predicting a price of an automobile part.
Background
With the development of the automobile part market, the price of more and more automobile parts has the problems of non-transparent information, multiple levels, difficulty in monitoring and supervision of circulation links and the like. In the prior art, price determination obtains less data, and the price is determined by performing simple mathematical operation according to the obtained data. However, in practical application scenarios, there are many factors that affect the price determination of the automobile parts, and the price of the automobile parts fluctuates periodically with the various factors, so that the price cannot be determined accurately and quickly.
Disclosure of Invention
The application provides a method, a system, equipment and a readable storage medium for predicting the price of an automobile part, which can solve the problem that the price of the automobile is difficult to predict in the prior art.
To achieve the above object, the present application provides an automobile parts price predicting method, including:
collecting an original transaction data set of a target automobile accessory;
cleaning the original transaction data set to obtain an effective transaction data set;
analyzing key design features influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design features comprise at least one non-price transaction element of transaction attributes, accessory attributes and environment attributes;
extracting a transaction data set comprising the key design characteristics from the effective transaction data set as a training data set, and training a preset initial prediction model by using the training data set to obtain a price prediction model;
predicting a current price of the target auto-parts using the price prediction model.
Further, the collecting the raw transaction data set of the target auto-parts comprises:
automobile part information is crawled from a preset third-party data platform in a network crawler mode, transaction data of automobile parts are extracted from the automobile part information and stored in the original transaction data set, wherein the third-party data platform comprises an automobile part transaction platform and an automobile part information platform.
Further, the cleaning the original transaction data set to obtain an effective transaction data set includes:
and filtering the original transaction data set according to a preset filtering rule to obtain the effective transaction data set, wherein the filtering rule comprises removing abnormal transaction data in the original transaction data set, and the abnormal transaction data comprises transaction data with transaction elements missing or messy codes and transaction data with transaction prices higher than or lower than a preset multiple of the transaction price average of the original transaction data.
Further, the analyzing key design features affecting the transaction price of the target automobile part from the effective transaction data set according to preset analysis rules comprises:
identifying the transaction price and non-price transaction elements of each transaction data in the effective transaction data set by a character identification technology;
and finding out non-price trading elements influencing the trading price by adopting a grey system theoretical model and a time series model as the key design characteristics.
Further, the extracting a transaction data set including the key design features from the effective transaction data set as a training data set, and training a preset initial prediction model with the training data set to obtain a price prediction model includes:
acquiring transaction data including the key design features in the effective transaction data set as a training data set, wherein the transaction data includes the non-price transaction element and accessory price data conforming to the non-price transaction element, and the transaction data is any transaction data in the training data set;
randomly dividing the transaction data in the training data set into a training sample data set and a verification sample data set;
training the initial prediction model according to the transaction data in the training sample data set to obtain a non-price transaction element model;
and verifying the non-price transaction element model according to the transaction data in the verification sample data set, and correcting the non-price transaction element model according to a verification result to obtain the price prediction model.
Further, the verifying the non-price transaction element model according to the transaction data in the verification sample data set, and correcting the non-price transaction element model according to a verification result to obtain the price prediction model includes:
inputting non-price transaction elements of the target automobile parts in the training sample data set into the initial prediction model to obtain a predicted price;
and performing model correction on the initial prediction model according to the transaction price in the accessory price data and the predicted price to obtain the non-price transaction element model, wherein the model correction comprises adjusting the weight of the non-price transaction element in the initial prediction model.
Further, the initial prediction model includes a first initial model, a second initial model and a third initial model, and the training of the training data set on the preset initial prediction model to obtain the price prediction model includes:
when the data volume of the training data set is smaller than a first preset value, inputting the training data set into the first initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the first initial model is a mode or a mean value of the transaction data;
when the data volume of the training data set is larger than a first preset value and smaller than a second preset value, inputting the training data set into the second initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the second initial model is linear regression;
when the data volume of the training data set is larger than a second preset value, inputting the training data set into the third initial model to perform training to obtain the price prediction model, wherein the preset algorithm of the third initial model is to predict a first basic price through a linear regression algorithm, predict a second basic price through an extreme gradient lifting algorithm, and then average the first basic price and the second basic price.
To achieve the above object, the present application provides an automobile parts price prediction system, the system comprising:
the acquisition module is used for acquiring an original transaction data set of the target automobile part;
the data cleaning module is used for cleaning the original transaction data set to obtain an effective transaction data set;
the analysis module is used for analyzing key design characteristics influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design characteristics comprise at least one non-price transaction element in transaction attributes, accessory attributes and environment attributes;
the extraction module is used for extracting a transaction data set comprising the key design characteristics from the effective transaction data set to serve as a training data set, and training a preset initial prediction model by using the training data set to obtain a price prediction model;
and the price prediction module is used for predicting the current price of the target automobile accessory by using the price prediction model.
To achieve the above object, the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the computer program, when executed by the processor, implements the steps of the automobile parts price prediction method as described above.
To achieve the above object, the present application provides a computer-readable storage medium having a computer program stored therein, the computer program being executable by at least one processor to cause the at least one processor to perform the steps of the automobile parts price prediction method as described above.
Compared with the prior art, the automobile part price prediction method, the system, the equipment and the readable storage medium provided by the invention have the advantages that the initial prediction model is generated based on the key design characteristics, the prediction initial model is trained according to the key design characteristics to form the price prediction model, the price prediction model can be properly adjusted according to the input non-price trading elements, the flexibility is realized, and the generated price prediction is more accurate.
Drawings
FIG. 1 is a flowchart illustrating a method for predicting prices of auto parts according to a first embodiment of the present invention.
Fig. 2 is a flowchart of step S140 in the first embodiment of the method for predicting the price of an automobile accessory according to the present invention.
Fig. 3 is a flowchart of a first embodiment of step S160 in the first embodiment of the method for predicting the price of an automobile accessory according to the present invention.
Fig. 4 is a flowchart of step S163 in the first embodiment of the method for predicting prices of automobile parts according to the present invention.
Fig. 5 is a flowchart of a second embodiment of step S160 in the first embodiment of the method for predicting the price of an automobile accessory according to the present invention.
FIG. 6 is a block diagram of a second embodiment of the system for forecasting prices of auto-parts according to the present invention.
Fig. 7 is a schematic diagram of a hardware structure of a third embodiment of the computer apparatus according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. 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 application.
It should be noted that the descriptions in this application referring to "first", "second", etc. are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present application.
Example one
Referring to fig. 1, a flowchart illustrating steps of a method for predicting prices of automobile parts according to a first embodiment of the present invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The following description is made by taking the computer device 2 as an execution subject, and the computer device 2 may be a mobile phone, a tablet, a portable device, a PC, a server, or other electronic devices. The details are as follows.
Step S100, collecting an original transaction data set of the target automobile accessory.
In an embodiment of the present invention, the original transaction data includes transaction elements such as transaction price, transaction address, transaction time, etc. of the target automobile parts. The method comprises the steps of collecting original transaction data of different transaction platforms aiming at target automobile accessories and ensuring the diversity of original transaction data sources. To expand the data collection scope, a plurality of website platforms may be predetermined, for example, according to the amount of data of the automobile accessory transaction, the selection includes: the method comprises the steps of acquiring trading data of automobile target accessories through background data extraction and third-party data platforms, wherein the trading data of automobile target accessories are acquired through millions of stages of production insurance platforms, tens of millions of data volume creation and distribution trading platforms, tens of thousands of data volume enterprise resource planning platforms, third-party data companies and other website platforms with different orders of magnitude. The above platform transaction data are all available data.
Exemplarily, the step S100 further includes:
automobile part information is crawled from a preset third-party data platform in a network crawler mode, transaction data of automobile parts are extracted from the automobile part information and stored in the original transaction data set, wherein the third-party data platform comprises an automobile part transaction platform and an automobile part information platform.
In the embodiment of the invention, the transaction data comprises non-price transaction elements such as transaction time, automobile part production area, automobile and automobile part brand, automobile part quality, automobile part inventory condition, maintenance factory preference, automobile type and delivery date of each data platform to the target automobile part. The automobile parts information platform comprises an automobile latest information platform, an automobile parts information platform and the like, and the automobile parts transaction platform comprises an automobile manufacturer official website, an automobile repair manufacturer official website and the like. To ensure the legitimacy of the information, the manner in which data is crawled by the web crawler does not involve personal or confidential information, compliance with the terms and services of the website, permission by the owner, etc.
And step S120, cleaning the original transaction data set to obtain an effective transaction data set.
In the embodiment of the invention, the collected original transaction data is cleaned and come, for example, the data with unqualified formats is removed, and abnormal data with 10 times or more difference with the median of the price is removed, so that an effective transaction data set with the price data of invalid accessories removed is obtained.
Exemplarily, the step S120 further includes:
and filtering the original transaction data set according to a preset filtering rule to obtain the effective transaction data set, wherein the filtering rule comprises removing abnormal transaction data in the original transaction data set, and the abnormal transaction data comprises transaction data with transaction elements missing or messy codes and transaction data with transaction prices higher than or lower than a preset multiple of the transaction price average of the original transaction data.
In an embodiment of the present invention, the preset filtering rules include: OE code (steam Equipment number) cleaning rules and accessory price cleaning rules. OE code cleaning rules include: remove special characters, such as: (| \' - [ ] { } [ >) > () -% $ # @.), lower case becomes upper case; and reversely deducing an OE code according to the VIN code (Vehicle Identification Number) and the accessory name, and further cleaning the OE code. The part price cleaning rules include: setting upper and lower price limits according to historical transaction data, and considering the transaction prices exceeding the upper and lower price limits as abnormal transaction data to be cleaned; eliminating abnormal prices from the boxed line graph; price correction, some transaction prices are tax price, goods adjusting price or freight price, so it is necessary to eliminate tax, goods adjusting price, freight and the like, correct them, and other rules. The box diagram drawing process is as follows: firstly, finding out an upper edge, a lower edge, a median and two quartiles of a group of transaction data; then, connecting the two quartiles to draw a box body; and connecting the upper edge and the lower edge with the box body, wherein the median is arranged in the middle of the box body to form the box body, and eliminating abnormal transaction data outside the box body.
Step S140, analyzing key design characteristics influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design characteristics comprise at least one non-price transaction element of transaction attributes, accessory attributes and environment attributes.
In an embodiment of the invention, the factors that influence the price of the accessory are: trade area, trade time, accessory brand, accessory quality, accessory inventory, vendor preference, repair shop preference, busy season, whether the accessory is cold or hot, automobile brand, automobile model, automobile year, etc. The transaction attributes include: trade area, trade time, etc.; the accessory attributes include: the brand of the accessories, the quality of the accessories, the cold door or the hot door of the accessories, the brand of the automobile, the type of the automobile, the annual style of the automobile and the like; the environmental attributes include: parts inventory conditions, supplier preferences, repair shop preferences, etc.; these non-price trading factor factors are extracted as key design features.
Exemplarily, referring to fig. 2, the step S140 further includes:
step S141, identifying the transaction price and non-price transaction elements of each transaction data in the effective transaction data set by a character identification technology; and S142, finding out non-price trading elements influencing the trading price by adopting a grey system theoretical model and a time series model as the key design characteristics.
In an embodiment of the invention, the transaction price and non-price transaction elements of each transaction data in the valid transaction data set are identified and stored in a predetermined format, for example, sorted according to a predetermined OE code. The effective transaction data set is predicted by adopting a grey system theoretical model GM (1, 1) and a time sequence model, unknown elements in the effective data set containing known information and unknown information are weakened by adopting accumulation and subtraction modes, and the influence degree of the known elements is strengthened, so that the prediction purpose is realized, and the elements which can obviously influence the price of accessories are found, wherein the elements are key design features. The training model can be adjusted repeatedly by adjusting the weight proportion of different key design characteristics in the data cleaning process, and the technical purpose of accurately and quickly determining the price of the accessory is achieved. It can be understood that the effective data set is changed to be more regular through a grey system theoretical model, and the relation of the effective data set and the time is judged through a time series model. The updating situation of the automobile parts can be predicted through the prediction, such as a slack season or a busy season, so that the current price can be predicted more accurately.
Step S160, a transaction data set including the key design characteristics is extracted from the effective transaction data set to serve as a training data set, and the training data set is trained on a preset initial prediction model to obtain a price prediction model.
In the embodiment of the invention, the preset price initial model is trained through the transaction data set to obtain the price prediction model capable of predicting the current price of the automobile parts according to the current non-price transaction elements of the automobile parts. The initial model may be adjusted based on the data volume of the transaction data in the transaction data set to make the price prediction more accurate.
Exemplarily, referring to fig. 3, the step S160 further includes:
step S161, obtaining transaction data including the key design feature in the effective transaction data set as a training data set, where the transaction data includes the non-price transaction element and the accessory price data conforming to the non-price transaction element, and the transaction data is any transaction data in the training data set; step S162, randomly dividing the transaction data in the training data set into a training sample data set and a verification sample data set; step S163, training the initial prediction model according to the transaction data in the training sample data set to obtain a non-price transaction element model; and S164, verifying the non-price transaction element model according to the transaction data in the verification sample data set, and correcting the non-price transaction element model according to a verification result to obtain the price prediction model.
In the embodiment of the invention, the non-price trading element is used as the input of the initial prediction model, and the accessory price data is used as the input of the initial prediction model to train the initial prediction model so as to obtain the price prediction model which can output the current price of the automobile accessory according to the non-price trading element of the automobile accessory. When the model training is performed, the trained initial prediction model needs to be verified, so that the current price output by the price prediction model is more accurate. Before training, a training data set is randomly divided into a training sample data set and a verification sample data set, and the training sample data set is used for training an initial prediction model to obtain a non-price trading element model. And the verification sample data set is used for verifying the non-price transaction element model, the weight ratio of each non-price transaction element in the non-price transaction element model is adjusted according to the verification result, and the price prediction model is obtained after the adjustment. After the non-price trading element model is trained, when the prediction result is verified, the model result can be comprehensively evaluated from a plurality of evaluation indexes such as mse (mean square error) and R2 (decision coefficient).
Exemplarily, referring to fig. 4, the step S163 includes:
step S163A, inputting the non-price trading elements of the target automobile parts in the training sample data set into the initial prediction model to obtain a predicted price; step S163B, performing model correction on the initial prediction model according to the transaction price in the accessory price data and the predicted price to obtain the non-price transaction element model, where the model correction includes adjusting the weight of the non-price transaction element in the initial prediction model.
In the embodiment of the invention, the non-price trading element model is trained through the training sample data set and the initial prediction model. The market conditions of the automobile change along with the change of time, the transaction price of the automobile parts also changes along with the change of time, the original transaction data in the recent time period, such as 2021 to 2008, is collected and is used as a training data set after being cleaned, and the non-price transaction element model is reconstructed.
Illustratively, the initial prediction model includes a first initial model, a second initial model and a third initial model, and referring to fig. 5, the step S160 further includes:
step S160A, when the data size of the training data set is smaller than a first preset value, inputting the training data set to the first initial model to perform training to obtain the price prediction model, where a preset algorithm of the first initial model is a mode or an average of the transaction data; step S160B, when the data volume of the training data set is larger than a first preset value and smaller than a second preset value, inputting the training data set into the second initial model to perform training to obtain the price prediction model, wherein a preset algorithm of the second initial model is linear regression; step S160C, when the data size of the training data set is greater than a second preset value, inputting the training data set into the third initial model to perform training to obtain the price prediction model, where the preset algorithm of the third initial model is to predict a first basic price through a linear regression algorithm, predict a second basic price through an extreme gradient lifting algorithm, and then average the first basic price and the second basic price.
In the embodiment of the invention, when the price prediction model is constructed, different algorithms are selected as the initial prediction model to construct the model according to the data volume of the transaction data in the training data set. In this embodiment, the first preset value is set to be one thousand, and the second preset value is set to be ten thousand. When the data volume is less than 1000, using a mode or an average value as a preset algorithm; when the data volume is more than 1000 and less than 1 ten thousand, linear regression is used as a preset algorithm; when the data volume is larger than 1 ten thousand, the preset algorithm is to predict a first basic price by using linear regression, predict a second basic price by using an extreme gradient lifting algorithm XGBOOST, and then average the first basic price and the second basic price to obtain the current price of the automobile part. The extreme gradient lifting algorithm XGBOST is combined with a plurality of weak learners to give a final learning result, the weak learners are linear regression algorithms or classification algorithms (mean values or mode), and the optimal price prediction model is constructed by using the idea of a regression task. The output result of each weak learner is treated as a continuous value, so that the result of each weak learner can be accumulated, and the loss function can be better utilized to optimize the model.
Because in the actual data, the data volume difference of the automobile parts is large according to the selling age, the annual output and other factors of the automobile type, if the same preset algorithm is adopted for training, the error of the prediction result is large, the data volume of the training data set is segmented in a stepped mode, and the price prediction output by the price prediction model is accurate.
And step S180, predicting the current price of the target automobile part by using the price prediction model.
In the embodiment of the invention, the current non-price trading element of the target automobile part is obtained and input into the price prediction model so as to output the current price of the target automobile part through the price prediction model. The method comprises the steps of generating an initial model based on key design characteristics, and then compounding and forming a price prediction model according to verification performance indexes of the key design characteristics, wherein the model can be properly adjusted according to input commodity attribute parameters of accessories to be predicted and commodity environment parameters, so that the flexibility is realized, and the generated price prediction is more accurate.
Example two
Referring to fig. 6, a schematic diagram of program modules of a second embodiment of the system for forecasting prices of automobile accessories is shown. In the embodiment, the automobile parts price prediction system 20 may include or be divided into one or more program modules, and the one or more program modules are stored in a storage medium and executed by one or more processors to implement the present invention and implement the automobile parts price prediction method. The program modules referred to in the embodiments of the present invention refer to a series of computer program instruction segments capable of performing specific functions, and are more suitable than the program itself for describing the execution process of the automobile parts price prediction system 20 in the storage medium. The following description will specifically describe the functions of the program modules of the present embodiment:
the collection module 200 is configured to collect an original transaction data set of a target automobile part.
In an embodiment of the present invention, the original transaction data includes transaction elements such as transaction price, transaction address, transaction time, etc. of the target automobile parts. The method comprises the steps of collecting original transaction data of different transaction platforms aiming at target automobile accessories and ensuring the diversity of original transaction data sources. To expand the data collection scope, a plurality of website platforms may be predetermined, for example, according to the amount of data of the automobile accessory transaction, the selection includes: the method comprises the steps of acquiring trading data of automobile target accessories through background data extraction and third-party data platforms, wherein the trading data of automobile target accessories are acquired through millions of stages of production insurance platforms, tens of millions of data volume creation and distribution trading platforms, tens of thousands of data volume enterprise resource planning platforms, third-party data companies and other website platforms with different orders of magnitude. The above platform transaction data are all available data.
Illustratively, the acquisition module 200 is further configured to:
automobile part information is crawled from a preset third-party data platform in a network crawler mode, transaction data of automobile parts are extracted from the automobile part information and stored in the original transaction data set, wherein the third-party data platform comprises an automobile part transaction platform and an automobile part information platform.
In the embodiment of the invention, the transaction data comprises non-price transaction elements such as transaction time, automobile part production area, automobile and automobile part brand, automobile part quality, automobile part inventory condition, maintenance factory preference, automobile type and delivery date of each data platform to the target automobile part. The automobile parts information platform comprises an automobile latest information platform, an automobile parts information platform and the like, and the automobile parts transaction platform comprises an automobile manufacturer official website, an automobile repair manufacturer official website and the like.
And the data cleaning module 202 is configured to clean the original transaction data set to obtain an effective transaction data set.
In the embodiment of the invention, the collected original transaction data is cleaned and come, for example, the data with unqualified formats is removed, and abnormal data with 10 times or more difference with the median of the price is removed, so that an effective transaction data set with the price data of invalid accessories removed is obtained.
Illustratively, the data cleansing module 202 is further configured to:
and filtering the original transaction data set according to a preset filtering rule to obtain the effective transaction data set, wherein the filtering rule comprises removing abnormal transaction data in the original transaction data set, and the abnormal transaction data comprises transaction data with transaction elements missing or messy codes and transaction data with transaction prices higher than or lower than a preset multiple of the transaction price average of the original transaction data.
In an embodiment of the present invention, the preset filtering rules include: OE code (steam Equipment number) cleaning rules and accessory price cleaning rules. OE code cleaning rules include: remove special characters, such as: (| \' - [ ] { } [ >) > () -% $ # @.), lower case becomes upper case; and reversely pushing out the OE code according to the VIN code and the accessory name, further cleaning the OE code, and the like. The part price cleaning rules include: setting upper and lower price limits according to historical transaction data, and considering the transaction prices exceeding the upper and lower price limits as abnormal transaction data to be cleaned; eliminating abnormal prices from the boxed line graph; price correction, some transaction prices are tax price or adjusting price or carrying freight price, so tax, adjusting price, freight cost and the like need to be removed, corrected and the like. The box diagram drawing process is as follows: firstly, finding out an upper edge, a lower edge, a median and two quartiles of a group of transaction data; then, connecting the two quartiles to draw a box body; and connecting the upper edge and the lower edge with the box body, wherein the median is arranged in the middle of the box body to form the box body, and eliminating abnormal transaction data outside the box body.
The parsing module 204 is configured to parse key design features affecting the transaction price of the target automobile part from the valid transaction data set according to a preset parsing rule, where the key design features include at least one non-price transaction element of a transaction attribute, an accessory attribute, and an environment attribute.
In an embodiment of the invention, the factors that influence the price of the accessory are: trade area, trade time, accessory brand, accessory quality, accessory inventory, vendor preference, repair shop preference, busy season, whether the accessory is cold or hot, automobile brand, automobile model, automobile year, etc. The transaction attributes include: trade area, trade time, etc.; the accessory attributes include: the brand of the accessories, the quality of the accessories, the cold door or the hot door of the accessories, the brand of the automobile, the type of the automobile, the annual style of the automobile and the like; the environmental attributes include: parts inventory conditions, supplier preferences, repair shop preferences, etc.; these non-price trading factor factors are extracted as key design features.
Illustratively, the parsing module 204 is further configured to:
identifying the transaction price and non-price transaction elements of each transaction data in the effective transaction data set by a character identification technology; and finding out non-price trading elements influencing the trading price by adopting a grey system theoretical model and a time series model as the key design characteristics.
In an embodiment of the invention, the transaction price and non-price transaction elements of each transaction data in the valid transaction data set are identified and stored in a predetermined format, for example, sorted according to a predetermined OE code. The effective transaction data set is predicted by adopting a grey system theoretical model GM (1, 1) and a time sequence model, unknown elements in the effective data set containing known information and unknown information are weakened by adopting accumulation and subtraction modes, and the influence degree of the known elements is strengthened, so that the prediction purpose is realized, and the elements which can obviously influence the price of accessories are found, wherein the elements are key design features. It can be understood that the effective data set is changed to be more regular through a grey system theoretical model, and the relation of the effective data set and the time is judged through a time series model. The updating situation of the automobile parts can be predicted through the prediction, such as a slack season or a busy season, so that the current price can be predicted more accurately.
An extracting module 206, configured to extract a transaction data set including the key design features from the valid transaction data set as a training data set, and train a preset initial prediction model with the training data set to obtain a price prediction model.
In the embodiment of the invention, the preset price initial model is trained through the transaction data set to obtain the price prediction model capable of predicting the current price of the automobile parts according to the current non-price transaction elements of the automobile parts. The initial model may be adjusted based on the data volume of the transaction data in the transaction data set to make the price prediction more accurate.
Illustratively, the extraction module 206 is further configured to:
acquiring transaction data including the key design features in the effective transaction data set as a training data set, wherein the transaction data includes the non-price transaction element and accessory price data conforming to the non-price transaction element, and the transaction data is any transaction data in the training data set; randomly dividing the transaction data in the training data set into a training sample data set and a verification sample data set; training the initial prediction model according to the transaction data in the training sample data set to obtain a non-price transaction element model; and verifying the non-price transaction element model according to the transaction data in the verification sample data set, and correcting the non-price transaction element model according to a verification result to obtain the price prediction model.
In the embodiment of the invention, the non-price trading element is used as the input of the initial prediction model, and the accessory price data is used as the input of the initial prediction model to train the initial prediction model so as to obtain the price prediction model which can output the current price of the automobile accessory according to the non-price trading element of the automobile accessory. When the model training is performed, the trained initial prediction model needs to be verified, so that the current price output by the price prediction model is more accurate. Before training, a training data set is randomly divided into a training sample data set and a verification sample data set, and the training sample data set is used for training an initial prediction model to obtain a non-price trading element model. And the verification sample data set is used for verifying the non-price transaction element model, the weight ratio of each non-price transaction element in the non-price transaction element model is adjusted according to the verification result, and the price prediction model is obtained after the adjustment. After the non-price trading element model is trained, when the prediction result is verified, the model result can be comprehensively evaluated from a plurality of evaluation indexes such as mse (mean square error) and R2 (decision coefficient).
Illustratively, the extraction module 206 is further configured to:
inputting non-price transaction elements of the target automobile parts in the training sample data set into the initial prediction model to obtain a predicted price; and performing model correction on the initial prediction model according to the transaction price in the accessory price data and the predicted price to obtain the non-price transaction element model, wherein the model correction comprises adjusting the weight of the non-price transaction element in the initial prediction model.
In the embodiment of the invention, the non-price trading element model is trained through the training sample data set and the initial prediction model. The market conditions of the automobile change along with the change of time, the transaction price of the automobile parts also changes along with the change of time, the original transaction data in the recent time period, such as 2021 to 2008, is collected and is used as a training data set after being cleaned, and the non-price transaction element model is reconstructed.
Illustratively, the initial prediction models include a first initial model, a second initial model, and a third initial model, and the extraction module 206 is further configured to:
when the data volume of the training data set is smaller than a first preset value, inputting the training data set into the first initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the first initial model is a mode or a mean value of the transaction data; when the data volume of the training data set is larger than a first preset value and smaller than a second preset value, inputting the training data set into the second initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the second initial model is linear regression; when the data volume of the training data set is larger than a second preset value, inputting the training data set into the third initial model to perform training to obtain the price prediction model, wherein the preset algorithm of the third initial model is to predict a first basic price through a linear regression algorithm, predict a second basic price through an extreme gradient lifting algorithm, and then average the first basic price and the second basic price.
In the embodiment of the invention, when the price prediction model is constructed, different algorithms are selected as the initial prediction model to construct the model according to the data volume of the transaction data in the training data set. In this embodiment, the first preset value is set to be one thousand, and the second preset value is set to be ten thousand. When the data volume is less than 1000, using a mode or an average value as a preset algorithm; when the data volume is more than 1000 and less than 1 ten thousand, linear regression is used as a preset algorithm; when the data volume is larger than 1 ten thousand, the preset algorithm is to predict a first basic price by using linear regression, predict a second basic price by using an extreme gradient lifting algorithm XGBOOST, and then average the first basic price and the second basic price to obtain the current price of the automobile part.
Because in the actual data, the data volume difference of the automobile parts is large according to the selling age, the annual output and other factors of the automobile type, if the same preset algorithm is adopted for training, the error of the prediction result is large, the data volume of the training data set is segmented in a stepped mode, and the price prediction output by the price prediction model is accurate.
A price prediction module 208 for predicting a current price of the target auto-parts using the price prediction model.
In the embodiment of the invention, the current non-price trading element of the target automobile part is obtained and input into the price prediction model so as to output the current price of the target automobile part through the price prediction model.
EXAMPLE III
Fig. 7 is a schematic diagram of a hardware architecture of a computer device according to a third embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown in FIG. 7, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and an auto parts price prediction system 20, which are communicatively connected to each other via a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system and various application software installed in the computer device 2, such as the program codes of the automobile parts price prediction system 20 in the second embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the server 2 and other electronic devices. For example, the network interface 23 is used to connect the server 2 to an external terminal via a network, establish a data transmission channel and a communication connection between the server 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 7 only shows the computer device 2 with components 20-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the automobile parts price prediction system 20 stored in the memory 21 can be further divided into one or more program modules, and the one or more program modules are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 6 is a schematic diagram of program modules of an embodiment implementing the automobile parts price prediction system 20, in which the automobile parts price prediction system 20 can be divided into the acquisition module 200, the data washing module 202, the parsing module 204, the extraction module 206, and the price prediction module 208. The program modules referred to herein are a series of computer program instruction segments that can perform specific functions, and are more suitable than programs for describing the execution process of the auto parts price prediction system 20 in the computer device 2. The specific functions of the program modules 200 and 208 have been described in detail in the second embodiment, and are not described herein again.
Example four
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the embodiment is used for a computer program, and when executed by a processor, the computer program implements the method for predicting the price of an automobile part of the first embodiment.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different from that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the present application are not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications that can be made by the use of the equivalent structures or equivalent processes in the specification and drawings of the present application or that can be directly or indirectly applied to other related technologies are also included in the scope of the present application.
Claims (10)
1. An automobile parts price prediction method, characterized in that the method comprises:
collecting an original transaction data set of a target automobile accessory;
cleaning the original transaction data set to obtain an effective transaction data set;
analyzing key design features influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design features comprise at least one non-price transaction element of transaction attributes, accessory attributes and environment attributes;
extracting a transaction data set comprising the key design characteristics from the effective transaction data set as a training data set, and training a preset initial prediction model by using the training data set to obtain a price prediction model;
predicting a current price of the target auto-parts using the price prediction model.
2. The auto-parts price prediction method of claim 1, wherein the collecting a raw transaction data set of a target auto-parts comprises:
automobile part information is crawled from a preset third-party data platform in a network crawler mode, transaction data of automobile parts are extracted from the automobile part information and stored in the original transaction data set, wherein the third-party data platform comprises an automobile part transaction platform and an automobile part information platform.
3. The method of predicting the price of an automobile part as set forth in claim 1, wherein said cleansing the raw transaction data set to obtain a valid transaction data set comprises:
and filtering the original transaction data set according to a preset filtering rule to obtain the effective transaction data set, wherein the filtering rule comprises removing abnormal transaction data in the original transaction data set, and the abnormal transaction data comprises transaction data with transaction elements missing or messy codes and transaction data with transaction prices higher than or lower than a preset multiple of the transaction price average of the original transaction data.
4. The auto-parts price prediction method of claim 1, wherein the parsing key design features affecting the transaction price of the target auto-parts from the valid transaction data set according to preset parsing rules comprises:
identifying the transaction price and non-price transaction elements of each transaction data in the effective transaction data set by a character identification technology;
and finding out non-price trading elements influencing the trading price by adopting a grey system theoretical model and a time series model as the key design characteristics.
5. The method for forecasting prices of automobile parts according to any one of claims 1 to 4, wherein the extracting a transaction data set including the key design features from the valid transaction data set as a training data set, and training the training data set on a preset initial forecasting model to obtain a price forecasting model comprises:
acquiring transaction data including the key design features in the effective transaction data set as a training data set, wherein the transaction data includes the non-price transaction element and accessory price data conforming to the non-price transaction element, and the transaction data is any transaction data in the training data set;
randomly dividing the transaction data in the training data set into a training sample data set and a verification sample data set;
training the initial prediction model according to the transaction data in the training sample data set to obtain a non-price transaction element model;
and verifying the non-price transaction element model according to the transaction data in the verification sample data set, and correcting the non-price transaction element model according to a verification result to obtain the price prediction model.
6. The method for forecasting the prices of auto-parts according to claim 5, wherein the verifying the non-price trading element model according to the trading data in the verification sample data set and modifying the non-price trading element model according to the verification result to obtain the price forecasting model comprises:
inputting non-price transaction elements of the target automobile parts in the training sample data set into the initial prediction model to obtain a predicted price;
and performing model correction on the initial prediction model according to the transaction price in the accessory price data and the predicted price to obtain the non-price transaction element model, wherein the model correction comprises adjusting the weight of the non-price transaction element in the initial prediction model.
7. The method of claim 6, wherein the initial prediction model comprises a first initial model, a second initial model and a third initial model, and the training data set to the preset initial prediction model to obtain the price prediction model comprises:
when the data volume of the training data set is smaller than a first preset value, inputting the training data set into the first initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the first initial model is a mode or a mean value of the transaction data;
when the data volume of the training data set is larger than a first preset value and smaller than a second preset value, inputting the training data set into the second initial model to perform training so as to obtain the price prediction model, wherein a preset algorithm of the second initial model is linear regression;
when the data volume of the training data set is larger than a second preset value, inputting the training data set into the third initial model to perform training to obtain the price prediction model, wherein the preset algorithm of the third initial model is to predict a first basic price through a linear regression algorithm, predict a second basic price through an extreme gradient lifting algorithm, and then average the first basic price and the second basic price.
8. An automobile parts price prediction system, the system comprising:
the acquisition module is used for acquiring an original transaction data set of the target automobile part;
the data cleaning module is used for cleaning the original transaction data set to obtain an effective transaction data set;
the analysis module is used for analyzing key design characteristics influencing the transaction price of the target automobile accessory from the effective transaction data set according to preset analysis rules, wherein the key design characteristics comprise at least one non-price transaction element in transaction attributes, accessory attributes and environment attributes;
the extraction module is used for extracting a transaction data set comprising the key design characteristics from the effective transaction data set to serve as a training data set, and training a preset initial prediction model by using the training data set to obtain a price prediction model;
and the price prediction module is used for predicting the current price of the target automobile accessory by using the price prediction model.
9. A computer arrangement, characterized in that the computer arrangement comprises a memory, a processor, the memory having stored thereon a computer program being executable on the processor, the computer program, when being executed by the processor, realizing the steps of the method for price prediction of auto parts according to any of the claims 1-7.
10. A computer-readable storage medium, in which a computer program is stored which is executable by at least one processor to cause the at least one processor to perform the steps of the method for predicting the price of an automobile accessory according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448808.6A CN113129064A (en) | 2021-04-25 | 2021-04-25 | Automobile part price prediction method, system, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448808.6A CN113129064A (en) | 2021-04-25 | 2021-04-25 | Automobile part price prediction method, system, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113129064A true CN113129064A (en) | 2021-07-16 |
Family
ID=76779898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110448808.6A Pending CN113129064A (en) | 2021-04-25 | 2021-04-25 | Automobile part price prediction method, system, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129064A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115600942A (en) * | 2022-12-15 | 2023-01-13 | 中汽传媒（天津）有限公司（Cn） | Automobile part transaction management method and system |
| CN117235677A (en) * | 2023-11-10 | 2023-12-15 | 邦邦汽车销售服务(北京)有限公司 | Automobile accessory price anomaly identification detection method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW542982B (en) * | 2000-05-19 | 2003-07-21 | Manugistics Atlanta Inc | Dynamic pricing system |
| CN109658150A (en) * | 2018-12-19 | 2019-04-19 | 中化资本有限公司 | Prediction technique, device, computer equipment and the storage medium of product price |
| CN111008861A (en) * | 2019-11-25 | 2020-04-14 | 上海欧冶采购信息科技有限责任公司 | Intelligent prediction-based commodity online transaction system and method |
| CN111652653A (en) * | 2020-06-10 | 2020-09-11 | 创新奇智(南京)科技有限公司 | Price determination and prediction model construction method, device, equipment and storage medium |
| CN112150205A (en) * | 2020-09-27 | 2020-12-29 | 浪潮通用软件有限公司 | Price prediction method and device and electronic equipment |
| CN112598446A (en) * | 2020-12-28 | 2021-04-02 | 深圳壹账通创配科技有限公司 | Accessory pricing method, system, device and storage medium |
-
2021
- 2021-04-25 CN CN202110448808.6A patent/CN113129064A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW542982B (en) * | 2000-05-19 | 2003-07-21 | Manugistics Atlanta Inc | Dynamic pricing system |
| CN109658150A (en) * | 2018-12-19 | 2019-04-19 | 中化资本有限公司 | Prediction technique, device, computer equipment and the storage medium of product price |
| CN111008861A (en) * | 2019-11-25 | 2020-04-14 | 上海欧冶采购信息科技有限责任公司 | Intelligent prediction-based commodity online transaction system and method |
| CN111652653A (en) * | 2020-06-10 | 2020-09-11 | 创新奇智(南京)科技有限公司 | Price determination and prediction model construction method, device, equipment and storage medium |
| CN112150205A (en) * | 2020-09-27 | 2020-12-29 | 浪潮通用软件有限公司 | Price prediction method and device and electronic equipment |
| CN112598446A (en) * | 2020-12-28 | 2021-04-02 | 深圳壹账通创配科技有限公司 | Accessory pricing method, system, device and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115600942A (en) * | 2022-12-15 | 2023-01-13 | 中汽传媒（天津）有限公司（Cn） | Automobile part transaction management method and system |
| CN115600942B (en) * | 2022-12-15 | 2023-03-31 | 中汽传媒(天津)有限公司 | Automobile part transaction management method and system |
| CN117235677A (en) * | 2023-11-10 | 2023-12-15 | 邦邦汽车销售服务(北京)有限公司 | Automobile accessory price anomaly identification detection method |
| CN117235677B (en) * | 2023-11-10 | 2024-02-20 | 邦邦汽车销售服务(北京)有限公司 | Automobile accessory price anomaly identification detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111401609B (en) | Prediction method and prediction device for traffic flow time series | |
| CN110516910B (en) | Insurance policy and insurance model training method and insurance risk assessment method based on big data | |
| Murthy et al. | New product warranty: A literature review | |
| CN109740760B (en) | Text quality inspection automatic training method, electronic device and computer equipment | |
| CN108876213B (en) | Block chain-based product management method, device, medium and electronic equipment | |
| CN113129064A (en) | Automobile part price prediction method, system, equipment and readable storage medium | |
| CN110634021A (en) | Big data based vehicle estimation method, system, device and readable storage medium | |
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| CN112633461B (en) | Application assistance system and method, and computer-readable recording medium | |
| Toledo et al. | Optimal periodic maintenance policy under imperfect repair: A case study on the engines of off-road vehicles | |
| CN111768287A (en) | Period identification method, period identification device, server and readable storage medium | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN112508308A (en) | Data processing method, device and equipment and readable storage medium | |
| CN112734072A (en) | Power load prediction method, system, terminal device and medium | |
| US10733533B2 (en) | Apparatus and method for screening data for kernel regression model building | |
| CN113343577B (en) | Parameter optimization method, device, equipment and medium based on machine learning | |
| CN114298829A (en) | Data processing method and device for credit assessment | |
| CN113902576A (en) | Deep learning-based information pushing method and device, electronic equipment and medium | |
| CN112348584A (en) | Vehicle estimation method, device and equipment | |
| CN111754103A (en) | Enterprise risk image method, device, computer equipment and readable storage medium | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium | |
| CN110674129A (en) | Abnormal event processing method, system, computer equipment and storage medium | |
| CN113011624A (en) | User default prediction method, device, equipment and medium | |
| CN116862561B (en) | Product heat analysis method and system based on convolutional neural network | |
| CN110533449A (en) | Data recommendation method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210716 |
|
| RJ01 | Rejection of invention patent application after publication |