Automobile part intelligent transaction method and system based on big data

Abstract

The invention discloses an automobile part intelligent transaction method and system based on big data, and relates to the field of automobile part transaction management, and the main scheme is as follows: obtaining automobile part information, and obtaining matched automobile part historical transaction data from different shopping platforms according to the automobile part information; analyzing and processing the historical transaction data of the automobile spare parts, and generating a spare part price trend analysis report, a market supply and demand relationship report, a purchase suggestion degree and a platform set; according to the price trend analysis report, the market supply and demand relationship report, the purchase suggestion degree and the platform set, generating an accessory purchase suggestion; the ordering module is associated with the shopping platform, skips to the shopping platform according to the accessory purchase suggestion, and assists in completing ordering; order state tracking and feedback are carried out; according to the scheme, the transaction security is improved, the user is helped to timely know the market dynamic state and grasp the purchase opportunity, the shopping platform is seamlessly connected, the shopping convenience and efficiency are improved, and the market transparency is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of automotive parts trading management, and specifically to an intelligent trading method and system for automotive parts based on big data. Background Art

[0002] In traditional automotive parts trading, there are a large number of counterfeit and shoddy parts on the market, posing safety hazards to vehicle owners. Due to price differences between different shopping platforms, it is difficult for vehicle owners to judge the true price level of parts and predict price change trends. The lack of a solution that can reflect the supply and demand relationship in the automotive parts market in real time makes it difficult for vehicle owners to grasp market trends and purchase opportunities when buying parts. When choosing parts, vehicle owners often lack professional purchase advice, resulting in difficult choices or the purchase of inappropriate parts. Summary of the Invention

[0003] (I) Technical Problems to be Solved

[0004] In view of the deficiencies of the prior art, the present invention provides an intelligent trading method and system for automotive parts based on big data. Through a platform set generated by a credibility index, this technical solution reduces platforms with a large number of counterfeit and shoddy parts, eliminating safety hazards for vehicle owners. Secondly, this solution can collect and analyze transaction data from different shopping platforms to help vehicle owners judge the true price level of parts and predict price change trends. At the same time, through a market supply and demand relationship report generated by a market supply and demand index, vehicle owners can timely understand market dynamics and grasp purchase opportunities. In addition, this solution also provides purchase advice, solving the problem of the lack of guidance for vehicle owners when choosing parts.

[0005] (II) Technical Solutions

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent trading system for automotive parts based on big data, comprising:

[0007] A data collection module: obtains vehicle parts information and acquires matching historical transaction data of automotive parts from different shopping platforms according to the vehicle parts information;

[0008] A data analysis module: analyzes and processes the historical transaction data of the automotive parts to generate an analysis report on parts price trends, a market supply and demand relationship report, a purchase advice degree, and a platform set;

[0009] An intelligent recommendation module: generates a parts purchase advice according to the analysis report on parts price trends, the market supply and demand relationship report, the purchase advice degree, and the platform set;

[0010] An intelligent trading module, associated with a shopping platform, jumps to the shopping platform according to the parts purchase advice, assists in completing the order placement, and prompts order information;

[0011] Information feedback module: It receives the order status information of the shopping platform in real time for order status tracking and feedback; after the order is completed, it conducts evaluations, and in case of problems, it jumps to the customer service page of the shopping platform for contact.

[0012] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the working steps of the data acquisition module are as follows:

[0013] Load the configuration file or parameters matching the shopping platform for connection with different shopping platforms;

[0014] Obtain vehicle part information, and according to the received vehicle part information, extract the historical transaction data of auto parts matching the vehicle information from different shopping platforms.

[0015] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the vehicle information includes: vehicle brand, vehicle model, vehicle type, model year, engine model and displacement, and faulty parts.

[0016] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the working steps of the data analysis module are as follows:

[0017] Receive the historical transaction data of auto parts on different shopping platforms;

[0018] Based on the historical transaction data of different shopping platforms, obtain: the historical average price AP of faulty parts, the part price change rate , the market supply and demand index , the dynamic reference price , the credibility index ;

[0019] Based on the historical average price of faulty parts and the part price change rate generate a price trend report; generate a market supply and demand relationship report based on the market supply and demand index; generate a purchase recommendation degree based on the dynamic reference price ; generate a platform set based on the credibility index.

[0020] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the calculation steps of the historical average price of faulty parts and the part price change rate are as follows:

[0021] The historical transaction data of auto parts includes at least the historical price data of different shopping platforms , and calculate the historical average price of faulty parts according to the historical prices of different shopping platforms , based on the following formula:

[0022] ;

[0023] Among them, takes values of 1, 2, 3... n, where n is the total number of transactions and takes positive integer values, is the price of the i-th transaction;

[0024] The historical transaction data of auto parts also includes the current part price and the benchmark price . According to the current part price and the benchmark price , calculate the part price change rate , based on the following formula:

[0025] ;

[0026] The principle of the part change rate formula is to calculate the difference between the current price and the benchmark price, then divide this difference by the benchmark price to get a relative change amount; finally, multiply this relative change amount by 100% to convert it into a percentage form. The price change rate can intuitively reflect the direction and degree of price changes.

[0027] Preferably, in the above-mentioned big data-based intelligent trading system for auto parts, the calculation steps of the market supply and demand index and the creditworthiness index are as follows:

[0028] The historical transaction data of auto parts also includes the vehicle ownership and the part production cost . According to the vehicle ownership and the part production cost , calculate the market supply and demand index , based on the following formula:

[0029] ;

[0030] Preset the supply and demand balance threshold , and compare the market supply and demand index with the supply and demand balance threshold ;

[0031] When the market supply and demand index the supply and demand balance threshold , it is in short supply; when the market supply and demand index the supply and demand balance threshold , it is in oversupply; when the market supply and demand index Supply - demand balance threshold indicates supply - demand balance; the value of the supply - demand balance threshold is 1;

[0032] The formula directly reflects the proportional relationship between the vehicle ownership and the production cost of auto parts; an increase in vehicle ownership usually means an increase in the demand for auto parts, while an increase in the production cost of parts may limit the supply; therefore, When the MSDI value is greater than the supply - demand balance threshold , it indicates a shortage of supply, and the price drops; when the MSDI value is less than the supply - demand balance threshold , it indicates an oversupply, and the price rises.

[0033] Historical transaction data of auto parts also includes the number of positive reviews , the number of evaluations , the number of transactions and the number of returns . Based on the number of positive reviews , the number of evaluations , the number of transactions and the number of returns , the credibility index is calculated. The formula is as follows:

[0034] ;

[0035] Preset high - credibility threshold , compare the credibility index with the high - credibility threshold . Generate a platform set for the platforms with a credibility index higher than the high - credibility threshold ; Remove the platforms with a credibility index lower than the high - credibility threshold ; The value of the high - credibility threshold is 80.

[0036] The principle of the formula is that the positive - review rate is calculated by the ratio of the number of positive reviews to the number of evaluations plus 1; adding 1 here is to prevent the denominator from being zero, which is a common mathematical treatment, especially when dealing with a possible zero divisor. The higher the positive - review rate, the higher the user's satisfaction with the product or service, and thus it has a positive contribution to the credibility of the product or service; the return rate is calculated by the ratio of the number of returns to the number of transactions Calculated by the ratio of adding 1; similarly, adding 1 is to prevent the denominator from being zero; the return rate reflects the degree of dissatisfaction of users with the product or service, or possible quality problems; the higher the return rate, the lower the credibility of the product or service, so the return rate has a negative contribution in the formula; the transaction volume usually reflects the popularity of the product or service and the market scale; in the formula, the transaction volume is processed through the square root, which is to smooth its impact; when the transaction volume is very large, directly incorporating it into the formula may cause index distortion, because even a small return rate will have a significant impact on the overall credibility. By taking the square root, we can reduce this impact while still maintaining the positive contribution of the transaction volume to the credibility;

[0037] Preferably, in the above-mentioned intelligent trading system for automotive parts based on big data, the dynamic reference price is calculated as follows:

[0038] Based on the historical average price of the faulty parts and the parts price change rate calculate the dynamic reference price , and the formula is as follows:

[0039] ;

[0040] Compare the dynamic reference price with the current parts price to obtain the purchase recommendation degree; if the current parts price is greater than the dynamic reference price , it is not recommended to purchase; if the current parts price is less than the dynamic reference price , it is recommended to purchase; the specific value of the current parts price is adjusted according to the actual situation;

[0041] The principle of this formula is to predict a reference price in the current market environment based on the average price of historical transaction data and the current price change rate ; if the price change rate is positive, then will be higher than , indicating that the price is rising; if the price change rate is negative, then will be lower than , indicating that the price is falling.

[0042] Preferably, in the above-mentioned intelligent trading system for automotive parts based on big data, the working steps of the intelligent recommendation module are as follows:

[0043] The receiving data analysis module generates an analysis report on the price trend of auto parts, a report on the market supply and demand relationship, a recommended purchase degree, and a platform set, and generates a purchase recommendation.

[0044] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the purchase recommendation includes: auto part brand, price range, purchase platform, and purchase recommendation degree.

[0045] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the working steps of the intelligent trading module are as follows:

[0046] According to the purchase recommendation, form multiple purchase plans, form links with shopping platforms, and after selecting a link, jump to the shopping platform and purchase link interface corresponding to the purchase plan.

[0047] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the working steps of the information feedback module are as follows:

[0048] Receive the order status information of the shopping platform in real time, and give feedback on the change of the order status; conduct an evaluation after the order is completed, and jump to the customer service page of the shopping platform to contact in case of problems.

[0049] Preferably, in the above-mentioned intelligent trading system for auto parts based on big data, the shopping platforms may include:

[0050] B2B platforms, including Alibaba International Station, DHgate, TradeKey;

[0051] O2O platforms, including auto parts chain stores, Meituan, Dianping;

[0052] Artificial intelligence e-commerce trading platforms.

[0053] The present invention also discloses an intelligent trading method for auto parts based on big data, which is used to implement the above-mentioned intelligent trading system:

[0054] Obtain vehicle part information, and obtain matching historical transaction data of auto parts from different shopping platforms according to the vehicle part information;

[0055] Analyze and process the historical transaction data of the auto parts to generate an analysis report on the price trend of auto parts, a report on the market supply and demand relationship, a purchase recommendation degree, and a platform set;

[0056] Generate a purchase recommendation for auto parts according to the price trend analysis report, the market supply and demand relationship report, the purchase recommendation degree, and the platform set;

[0057] According to the purchase recommendation for auto parts, jump to the shopping platform, assist in completing the order placement, and prompt the order information;

[0058] Receive the order status information of the shopping platform in real time, track and feedback the order status. After the order is completed, conduct an evaluation. In case of problems, jump to the customer service page of the shopping platform for contact.

[0059] (III) Beneficial effects

[0060] The present invention provides an intelligent trading method and system for automotive parts based on big data, having the following beneficial effects:

[0061] (1) By preloading configuration information adapted to multiple shopping platforms, flexibly receiving the parts information directly input by users or automatically obtained from the vehicle identification system, and widely querying the historical transaction data of each platform, the flexibility, security, accuracy and efficiency of data collection are effectively improved;

[0062] (2) By analyzing the transaction data of different shopping platforms, it helps vehicle owners judge the real price level of parts, predict the price change trend, enabling vehicle owners to make purchase decisions based on real market data, avoiding price fraud caused by information asymmetry, and realizing the transparency of automotive parts prices; through the market supply and demand relationship report generated by the market supply and demand index, vehicle owners can timely understand the market dynamics and grasp the purchase opportunity; it helps vehicle owners make more reasonable purchase decisions when the price fluctuates greatly, reducing the economic risks brought by market fluctuations; provides purchase suggestions to help vehicle owners quickly lock in the parts that best meet their needs, realizing efficient and accurate shopping decisions; by constructing a platform set generated by the credibility index, the present invention effectively reduces the platforms with a large number of fake and shoddy parts, significantly improves the security of automotive parts transactions, provides a reliable trading environment for vehicle owners, and improves transaction security;

[0063] (3) By comprehensively analyzing the price trend and market supply and demand relationship, screening reasonable parts and preferentially selecting high-credibility platforms, generating detailed purchase suggestions, providing a scientific basis for users, optimizing purchase decisions, enhancing the experience, promoting the healthy development of the market, and efficiently utilizing resources;

[0064] (4) Through the seamless connection of the intelligent trading module with the shopping platform, generating a personalized purchase plan and automatically jumping to the recommended page, simplifying the purchase process, improving the purchase efficiency and security, and greatly enhancing the user experience and satisfaction;

[0065] (5) Through real-time order status tracking and feedback, evaluation guidance after the order is completed, and a quick problem-solving mechanism, the integrity and satisfaction of the user shopping experience are significantly improved; it ensures that users can grasp the order dynamics in real time and obtain problem solutions in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a step schematic diagram of an intelligent trading method and system for automotive parts based on big data of the present invention. Detailed implementation manners

[0067] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0068] Please refer to Figure 1 , the present invention provides an intelligent trading system for automotive parts based on big data, including the following steps:

[0069] Step 1: Obtain vehicle parts information, and obtain matching historical transaction data of automotive parts from different shopping platforms according to the vehicle parts information;

[0070] Step 1 includes the following steps:

[0071] Step 101: Before the data acquisition module is started, first load the configuration files or parameters matching each shopping platform; these configuration files or parameters contain the necessary information required to establish a connection with the shopping platform, such as API interface address, access key, request parameter format;

[0072] Step 102: The data acquisition module receives the vehicle parts information input by the user through the system interface or other means, such as vehicle model, year, part name, model, etc.; this information will be used as the basis for subsequent queries on the shopping platform; in addition, the data acquisition module can also support automatically obtaining vehicle parts information from the vehicle identification system, such as the VIN code identification system, to improve the efficiency and accuracy of data acquisition;

[0073] Step 103: According to the received vehicle parts information, the data acquisition module will query each shopping platform to obtain historical transaction data matching the vehicle parts, such as price, sales volume, evaluation, etc.;

[0074] By combining the content of Step 101 to Step 103:

[0075] By preloading the configuration information adapted to multiple shopping platforms, flexibly receiving the parts information directly input by the user or automatically obtained from the vehicle identification system, and widely querying the historical transaction data of each platform, the flexibility, security, accuracy and efficiency of data acquisition are effectively improved.

[0076] Step 2: Analyze and process the historical transaction data of the automotive parts to generate an analysis report on the price trend of parts, a report on the market supply and demand relationship, a purchase recommendation degree, and a platform set;

[0077] Step 2 includes the following content:

[0078] Step 201: Receive the historical transaction data of auto parts on different shopping platforms;

[0079] The historical transaction data of auto parts includes at least the historical price data on different shopping platforms , and calculate the historical average price of faulty parts based on the historical prices on different shopping platforms , and the formula is as follows:

[0080] ;

[0081] Among them, the value of i is 1, 2, 3... n, where n is the total number of transactions and is a positive integer, is the price of the i-th transaction;

[0082] The historical transaction data of auto parts also includes the current part price and the benchmark price , and calculate the part price change rate based on the current part price and the benchmark price , and the formula is as follows:

[0083] ;

[0084] The principle of the part change rate formula is to calculate the difference between the current price and the benchmark price, then divide this difference by the benchmark price to get a relative change amount; finally, multiply this relative change amount by 100% to convert it into a percentage form. The price change rate can intuitively reflect the direction and degree of price changes;

[0085] The historical transaction data of auto parts also includes the vehicle ownership and the part production cost , and calculate the market supply and demand index and the part production cost , and the formula is as follows:

[0086] ;

[0087] Preset the supply and demand balance threshold , and compare the market supply and demand index with the supply and demand balance threshold ;

[0088] When the market supply and demand index the supply and demand balance threshold , it indicates a supply falling short of demand; when the market supply and demand index Supply and demand balance threshold , it indicates a supply exceeding demand; when the market supply and demand index Supply and demand balance threshold , it indicates a supply-demand balance; the value of the supply and demand balance threshold is 1;

[0089] The formula directly reflects the proportional relationship between the vehicle ownership and the production cost of auto parts; an increase in vehicle ownership usually means an increase in the demand for auto parts, while an increase in the production cost of parts may limit the supply; therefore, when the MSDI value is greater than the supply and demand balance threshold , it indicates a supply falling short of demand and the price drops; when the MSDI value is less than the supply and demand balance threshold , it indicates a supply exceeding demand and the price rises.

[0090] Step 205: The historical transaction data of auto parts also includes the number of positive reviews , the number of evaluations , the number of transactions and the number of returns . Calculate the credibility index , the number of evaluations , the number of transactions and the number of returns according to the number of positive reviews , and the formula is as follows:

[0091] ;

[0092] Preset high credibility threshold . Compare the credibility index with the high credibility threshold , and generate a platform set for the platforms with the credibility index higher than the high credibility threshold ; remove the platforms with the credibility index lower than the high credibility threshold ; the value of the high credibility threshold is 80.

[0093] The principle of the formula is that the positive review rate is calculated by the ratio of the number of positive reviews to the number of evaluations plus 1; adding 1 here is to prevent the denominator from being zero, which is a common mathematical treatment, especially when dealing with a possible zero divisor. The higher the positive review rate, the higher the user's satisfaction with the product or service, thus making a positive contribution to the credibility of the product or service; the return rate is calculated by the ratio of the number of returns to the number of transactions calculated by the ratio of adding 1; similarly, adding 1 is to prevent the denominator from being zero; the return rate reflects the dissatisfaction of users with the product or service, or possible quality problems; the higher the return rate, the lower the credibility of the product or service, so the return rate has a negative contribution in the formula; the transaction volume usually reflects the popularity of the product or service and the market size; in the formula, the transaction volume is processed by taking the square root, which is to smooth its impact; when the transaction volume is very large, directly including it in the formula may lead to index distortion, because even a small return rate will have a significant impact on the overall credibility; by taking the square root, we can reduce this impact while still maintaining the positive contribution of the transaction volume to the credibility;

[0094] Step 206: According to the historical average price of the faulty parts and the price change rate of the parts calculate the dynamic reference price , and the formula is as follows:

[0095] ;

[0096] Use the dynamic reference price to compare with the current parts price to obtain the purchase recommendation degree; if the current parts price is greater than the dynamic reference price , it is not recommended to purchase; if the current parts price is less than the dynamic reference price , it is recommended to purchase; the specific data of the current parts price is adjusted according to the actual scenario;

[0097] The principle of this formula is to predict a reference price in the current market environment based on the average price of historical transaction data and the current price change rate ; if the price change rate is positive, then will be higher than AP, indicating that the price is rising; if the price change rate is negative, then will be lower than AP, indicating that the price is falling;

[0098] Step 207: Generate a price trend report based on the historical average price of the faulty parts and the price change rate of the parts ; the structure of the price trend report is: historical price trend, price change rate, future price prediction;

[0099] Generate a market supply and demand relationship report based on the market supply and demand index; the structure of the market supply and demand relationship report is: market supply and demand index, current situation of market supply and demand relationship, future trend of supply and demand relationship;

[0100] According to the dynamic reference price Generate a purchase recommendation degree;

[0101] Generate a platform set according to the credibility index;

[0102] By combining the content of steps 201 to 207:

[0103] By analyzing the transaction data of different shopping platforms, it helps car owners judge the true price level of auto parts, predict the price change trend, enables car owners to make purchase decisions based on real market data, avoids price fraud caused by information asymmetry, and realizes the transparency of auto parts prices; through the market supply and demand relationship report generated by the market supply and demand index, car owners can timely understand the market dynamics and grasp the purchase opportunity; helps car owners make more reasonable purchase decisions when the price fluctuates greatly, reduces the economic risks brought by market fluctuations; provides purchase suggestions to help car owners quickly lock in the auto parts that best meet their needs, and realizes efficient and accurate shopping decisions; through the platform set constructed by generating the credibility index, the present invention effectively reduces the platforms with a large number of fake and shoddy auto parts, significantly improves the security of auto parts transactions, provides a reliable trading environment for car owners, and improves the trading security.

[0104] Step three: Generate an auto parts purchase recommendation according to the price trend analysis report, market supply and demand relationship report, purchase recommendation degree and platform set;

[0105] Step three includes the following steps:

[0106] Step 301: Receive the auto parts price trend analysis report, market supply and demand relationship report, recommended purchase degree and platform set generated by the data analysis module;

[0107] Step 302: According to the price trend analysis report and market supply and demand relationship report, screen out the auto parts with reasonable prices and balanced supply and demand in the current market environment;

[0108] Step 303: Select the platform with the highest credibility index in the platform set;

[0109] Step 305: Integrate the above information into specific purchase suggestions, including auto parts brand, price range, purchase platform, purchase recommendation degree, and display it to the user through the system interface;

[0110] By combining the content of steps 301 to 305:

[0111] By comprehensively analyzing the price trend and market supply and demand relationship, screening reasonable auto parts and preferentially selecting high-credibility platforms, generating detailed purchase suggestions, providing a scientific basis for users, optimizing purchase decisions, enhancing the experience, promoting the healthy development of the market, and efficiently utilizing resources.

[0112] Step 4: Associate with the shopping platform. According to the accessory purchase suggestions, jump to the shopping platform to assist in completing the order placement and prompt the order information.

[0113] Step 4 includes the following steps:

[0114] Step 401: According to the purchase suggestions, the intelligent transaction module generates multiple specific purchase plans. Each plan includes recommended accessories, estimated prices, recommended shopping platforms, and purchase links on the platforms.

[0115] Step 402: For each purchase plan, the intelligent transaction module generates a unique and valid shopping platform link that directly points to the purchase page of the recommended accessories.

[0116] Step 403: After the user selects a purchase plan, the intelligent transaction module automatically triggers a jump instruction to guide the user to the selected shopping platform and purchase link interface.

[0117] By combining the content of Step 401 to Step 403:

[0118] Through the seamless connection between the intelligent transaction module and the shopping platform, personalized purchase plans are generated and automatically jumped to the recommended page, simplifying the purchase process, improving the purchase efficiency and security, and greatly enhancing the user experience and satisfaction.

[0119] Step 5: Receive the order status information of the shopping platform in real time for order status tracking and feedback; conduct an evaluation after the order is completed, and jump to the shopping platform customer service page for contact in case of problems.

[0120] Step 5 includes the following steps:

[0121] Step 501: The information feedback module establishes a stable data transmission interface with the shopping platform to ensure that it can receive order status information in real time. The received order information includes order creation, payment success, shipment, in transit, receipt, return and exchange application, and after-sales processing.

[0122] Step 502: When receiving the order status change information sent by the shopping platform, the information feedback module immediately feeds back the order status change to the user in real time through system notifications, text messages, emails, or in-app message pushes, ensuring that the user can timely understand the latest progress of the order.

[0123] Step 503: When the order status shows "completed" or a similar status, the information feedback module automatically triggers an evaluation guidance process, displays an evaluation page or link to the user, and invites the user to evaluate aspects such as the purchased accessories, the service of the shopping platform, and the delivery speed.

[0124] Step 504: If the user encounters any problems during the order process, the information feedback module will jump to the customer service page of the shopping platform to help the user quickly find a way to solve the problem;

[0125] By combining the content of Steps 501 to 504:

[0126] Through real-time order status tracking and feedback, evaluation guidance after order completion, and quick problem-solving, the integrity and satisfaction of the user shopping experience have been significantly improved; it ensures that users can keep track of order dynamics in real time and obtain problem-solving solutions in a timely manner.

[0127] On the other hand, the present invention also discloses a big data-based intelligent trading method for automotive parts to implement the above intelligent trading system. The steps are as follows:

[0128] Obtain vehicle parts information and obtain matching historical trading data of automotive parts from different shopping platforms according to the vehicle parts information;

[0129] Analyze and process the historical trading data of the automotive parts to generate an analysis report on parts price trends, a report on market supply and demand relationships, a purchase recommendation degree, and a platform set;

[0130] Generate a parts purchase recommendation based on the price trend analysis report, market supply and demand relationship report, purchase recommendation degree, and platform set;

[0131] According to the parts purchase recommendation, jump to the shopping platform to assist in placing an order and prompt order information;

[0132] Receive the order status information of the shopping platform in real time for order status tracking and feedback; conduct an evaluation after the order is completed, and jump to the customer service page of the shopping platform to contact if there are any problems.

[0133] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application.

Claims

1. An intelligent trading system for auto parts based on big data, characterized in that: The following steps are involved: Data collection module: obtain vehicle parts information, and obtain matching auto parts historical transaction data from different shopping platforms based on the vehicle parts information; Data analysis module: Analyze and process the historical transaction data of auto parts to generate an analysis report on the price trend of auto parts, a market supply and demand relationship report, a purchase recommendation and a platform collection; Intelligent recommendation module: generating accessory purchase recommendations based on the price trend analysis report, market supply and demand relationship report, purchase recommendation degree and platform set; The intelligent transaction module is associated with the shopping platform. It jumps to the shopping platform based on the accessories purchase suggestions, assists in completing the order, and prompts the order information; Information feedback module: receive order status information from the shopping platform in real time, and conduct order status tracking and feedback; After the order is completed, please give an evaluation. If you encounter any problems, please jump to the customer service page of the shopping platform to contact them.

2. According to the big data-based intelligent trading system for auto parts according to claim 1, it is characterized in that: The working steps of the data acquisition module are as follows: Loading configuration files or parameters matching the shopping platform to establish connections with different shopping platforms; Obtain vehicle parts information, and based on the received vehicle parts information, extract historical transaction data of auto parts that matches the vehicle information from different shopping platforms.

3. The big data-based intelligent trading system for automobile parts according to claim 2 is characterized in that: The working steps of the data analysis module are as follows: Receive historical transaction data of auto parts on different shopping platforms; Based on historical transaction data from different shopping platforms: the historical average price of faulty parts , Accessories price change rate , Market Supply and Demand Index , Dynamic reference price , credibility index ; Based on the historical average price of faulty parts and accessories price change rate Generate price trend reports; generate market supply and demand relationship reports based on market supply and demand index; generate market supply and demand relationship reports based on dynamic reference prices Generate purchase recommendations; generate platform collections based on credibility indexes.

4. The intelligent trading system for automobile parts based on big data according to claim 3 is characterized in that: The historical average price and accessories price change rate The calculation steps are: The historical transaction data of auto parts includes at least the historical price data of different shopping platforms. , according to the historical prices of different shopping platforms Calculate the historical average price of faulty parts , the formula is as follows: ; in, The value of is 1, 2, 3...n, where n is the total number of transactions and is a positive integer. It is The price of the transaction; Auto parts historical transaction data also includes current parts prices and base price , based on current accessory prices and base price Calculate the price change rate of accessories , the formula is as follows: 。 5. The intelligent trading system for automobile parts based on big data according to claim 4 is characterized in that: The market supply and demand index and credibility index The calculation steps are: Auto parts historical transaction data also includes car ownership and accessories production costs , according to the number of cars and accessories production costs Calculate market supply and demand index , the formula is as follows: ; Preset supply and demand balance threshold , the market supply and demand index Balance threshold with supply and demand Make comparisons; When the market supply and demand index Supply and demand balance threshold , which means that the supply is insufficient to meet the demand; when the market supply and demand index Supply and demand balance threshold , which means oversupply; when the market supply and demand index Supply and demand balance threshold , for the balance of supply and demand; Auto parts historical transaction data also includes the number of positive reviews , Number of reviews , Transaction Quantity and return quantity , according to the number of positive reviews , Number of reviews , Transaction Quantity and return quantity Calculating the credibility index , the formula is as follows: ； Preset high reputation threshold , the credibility index With high reputation threshold Compare the credibility index High reputation threshold The platform generates a platform set; remove the credibility index High reputation threshold platform.

6. The intelligent trading system for automobile parts based on big data according to claim 5 is characterized in that: The dynamic reference price The calculation steps are: Based on the historical average price of faulty parts and accessories price change rate Calculate dynamic reference price , the formula is as follows: ; Using dynamic reference prices With current accessory prices Compare and get purchase recommendations; if the current price of accessories Dynamic reference price , it is not recommended to buy; if the current price of accessories Dynamic reference price , it is recommended to buy.

7. The big data-based intelligent trading system for auto parts according to claim 6 is characterized in that: The working steps of the intelligent recommendation module are as follows: Receive the accessory price trend analysis report, market supply and demand relationship report, recommended purchase degree and platform collection generated by the data analysis module, and generate purchase recommendations.

8. The big data-based intelligent trading system for auto parts according to claim 7 is characterized by: The working steps of the intelligent trading module are as follows: Based on the purchase suggestions, multiple purchase plans are formed and linked to the shopping platform. After selecting the link, you will be redirected to the shopping platform and purchase link interface corresponding to the purchase plan.

9. The big data-based intelligent trading system for auto parts according to claim 8, characterized in that: The working steps of the information feedback module are: Receive order status information from the shopping platform in real time and provide feedback on changes in order status; provide evaluation after the order is completed, and jump to the shopping platform customer service page to contact them if any problems arise.

10. An intelligent trading method for automobile parts based on big data, used to implement the intelligent trading system of any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Obtain vehicle parts information, and obtain matching auto parts historical transaction data from different shopping platforms based on the vehicle parts information; Step 2: Analyze and process the historical transaction data of auto parts to generate an auto parts price trend analysis report, a market supply and demand relationship report, a purchase recommendation and a platform collection; Step 3: Generate accessory purchase recommendations based on the price trend analysis report, market supply and demand relationship report, purchase recommendation level and platform set; Step 4: According to the accessories purchase suggestions, jump to the shopping platform to assist in completing the order and prompt the order information; Step 5: Receive order status information from the shopping platform in real time, and conduct order status tracking and feedback; After the order is completed, please give an evaluation. If you encounter any problems, please jump to the customer service page of the shopping platform to contact them.

Images