Automobile part recommendation method and system

Abstract

The invention provides an automobile spare part recommendation method and system, and the method constructs general spare part data, and provides a service for constructing a store stock spare part list based on the general spare part data for a store client. The store user does not need to maintain the accessory data by himself / herself, and only needs to download the needed accessory from the universal accessory data. When the automobile parts are searched, the data computing platform executes a two-stage retrieval strategy, and in the first stage, first candidate part data are inquired from general part data and associated data of the automobile types and the parts based on the automobile types and the part types; and in the second stage, matching the first candidate accessory data with a store inventory accessory list, determining an accessory recommendation list, and pushing the accessory recommendation list to a store client. The automobile part recommendation method and system have the advantages of being fast in service response, stable in performance and controllable in cost.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a method and system for recommending automotive parts. Background Technology

[0002] With the changes in car models and the continuous growth of corresponding auto parts, the number of auto parts that repair shops of different sizes need to maintain varies from a few hundred to tens of thousands, and the number of models that each auto part can be used for ranges from tens of thousands to hundreds of thousands.

[0003] Maintaining compatibility between vehicle models and auto parts is very costly. If each store maintains its own set of matching data for each model, the total data volume would be in the tens of trillions, putting enormous pressure on the system's service performance and making it impossible to control the usage costs of existing and new stores. Summary of the Invention

[0004] One or more embodiments of this application describe a method for recommending automotive parts that can at least partially overcome the aforementioned technical problems.

[0005] Firstly, a method for recommending automotive parts is provided, including the following steps: An automotive parts recommendation system is constructed, comprising a store client, a data computing platform, and a database. The database stores general parts data, store operation data, and correlation data between vehicle models and parts. The general parts data includes the general attributes and category attributes of automotive parts. Store users select the required accessories from the general accessories database through the store client, download the selected accessories data to the store client, add the quantity according to the inventory, form a store inventory accessories list, and synchronize the store inventory accessories list to the database; Store users generate work orders through the store client and upload them to the data computing platform; In response to receiving the work order, the data computing platform determines the target vehicle model and target part category based on the work order, queries the database based on the target vehicle model and target part category to obtain first candidate part data, matches the first candidate part data with the store's inventory part list to determine a recommended part list, and feeds back the recommended part list to the store client.

[0006] As an optional implementation of the method described in the first aspect, the general attributes of the automotive parts include OE code, brand, and name; the category attributes of the automotive parts include part category, specifications, and model; and the work order includes vehicle model, repair / maintenance category, required part category, and part quantity.

[0007] As an optional implementation of the method described in the first aspect, the data computing platform determines the target vehicle model and target part category based on the work order, and queries the database to obtain first candidate part data based on the target vehicle model and target part category, specifically including: The data computing platform queries the general accessory data for a list of all accessories under the target accessory category; For each candidate accessory in the accessory list, the vehicle models that the candidate accessory is compatible with are queried based on the association data between the vehicle model and the accessory, and candidate accessories that are compatible with the target vehicle model are selected to construct the first candidate accessory data.

[0008] Specifically, the data computing platform matches the first candidate accessory data with the store's inventory accessory list to determine the recommended accessory list, which includes: The data computing platform calculates the intersection of the first candidate accessory data and the store inventory accessory list to obtain the second candidate accessory data; The inventory quantity of each accessory in the second candidate accessory data is matched with the accessory quantity required in the work order. Accessory data that does not meet the accessory quantity required in the work order is filtered out from the second candidate accessory data to obtain the third candidate accessory data. The accessory recommendation list is then constructed based on the third candidate accessory data.

[0009] Furthermore, the data computing platform constructs the accessory recommendation list based on the third candidate accessory data, specifically including: Based on the inventory quantity, historical sales volume, and target vehicle level of each accessory in the third accessory data, a recommendation factor is determined for each accessory in the third accessory data; the accessories in the third candidate accessory data are sorted based on the recommendation factor to obtain the accessory recommendation list.

[0010] Secondly, an auto parts recommendation system is provided, including: a store client, a data computing platform, and a database; The database stores general parts data, store operation data, and data relating vehicle models to parts; the general parts data includes the general attributes and category attributes of automotive parts. Store users select the required accessories from the general accessories database through the store client, download the selected accessories data to the store client, and add the required quantities according to inventory to form a store inventory accessories list; the store client then synchronizes the store inventory accessories list to the database. The store client is also used to generate work orders based on store user operations and upload them to the data computing platform. The data computing platform is used to determine the target vehicle model and target part category based on the work order, query the database based on the target vehicle model and target part category to obtain first candidate part data, match the first candidate part data with the store inventory part list to determine the part recommendation list, and feed the part recommendation list back to the store client.

[0011] As an optional implementation of the system described in the second aspect, the general attributes of the automotive parts include OE code, brand, and name; the category attributes of the automotive parts include part category, specifications, and model; and the work order includes vehicle model, repair / maintenance category, required part category, and part quantity.

[0012] As an optional implementation of the system described in the second aspect, the data computing platform is specifically used for: Query the list of all accessories under the target accessory category in the general accessory data; for each candidate accessory in the accessory list, query the vehicle model that the candidate accessory is compatible with based on the association data between the vehicle model and the accessory, and filter out the candidate accessories that are compatible with the target vehicle model to construct the first candidate accessory data.

[0013] Specifically, the data computing platform is used for: Calculate the intersection of the first candidate accessory data and the store inventory accessory list to obtain the second candidate accessory data; The inventory quantity of each accessory in the second candidate accessory data is matched with the accessory quantity required in the work order. Accessory data that does not meet the accessory quantity required in the work order is filtered out from the second candidate accessory data to obtain the third candidate accessory data. The accessory recommendation list is then constructed based on the third candidate accessory data.

[0014] Furthermore, the data computing platform is also used for: Based on the inventory quantity, historical sales volume, and target vehicle level of each accessory in the third accessory data, a recommendation factor is determined for each accessory in the third accessory data; the accessories in the third candidate accessory data are sorted based on the recommendation factor to obtain the accessory recommendation list.

[0015] Beneficial Effects: One or more embodiments of this application provide a method and system for recommending automotive parts. This method constructs universal parts data and provides a service to store clients that builds a list of store inventory parts based on this universal parts data. Store users do not need to maintain the parts data themselves; they only need to download the required parts from the universal parts data.

[0016] Furthermore, store users do not need to maintain the data on the relationship between parts and vehicle models themselves. When creating a work order, they only need to submit the vehicle model to be maintained, the repair / maintenance category, the required parts category, and the quantity of parts. The data computing platform executes a two-stage retrieval strategy. In the first stage, based on the vehicle model and parts category, it queries general parts data and vehicle-part association data to obtain the first candidate parts data. In the second stage, it matches the first candidate parts data with the store's inventory parts list to determine the recommended parts list, which is then pushed to the store's client. Store users can recommend parts to customers based on the recommended parts list and can place orders based on the recommended parts list.

[0017] The aforementioned method and system for recommending automotive parts have the advantages of rapid service response, stable performance, and controllable costs. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of an automotive parts recommendation system according to one embodiment of this application.

[0020] Figure 2 This is a schematic diagram of the format of a recommended list of accessories involved in one embodiment of this application.

[0021] Figure 3 This is a flowchart illustrating a method for recommending automotive parts according to one embodiment of this application. Detailed Implementation

[0022] First, it should be noted that the terminology used in the embodiments of this invention is for the purpose of describing specific embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0023] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] It should be noted that the steps of the corresponding methods in other embodiments are not necessarily performed in the order shown and described in this application. In some other embodiments, the methods may include more or fewer steps than those described in this application. Furthermore, a single step described in this application may be broken down into multiple steps in other embodiments; and multiple steps described in this application may be combined into a single step in other embodiments.

[0025] The vehicle model and accessory adaptation data maintenance system described in this application will be further described in detail below with reference to the accompanying drawings and specific embodiments. However, this detailed description does not constitute a limitation on the embodiments of this application.

[0026] Please refer to Figure 1 , Figure 1 A schematic diagram of an automotive parts recommendation system is shown, which mainly includes a store client, a data computing platform, and a database.

[0027] First, let me introduce the database. The database stores general parts data, store operation data, and data relating vehicle models and parts.

[0028] General parts data mainly includes the general attributes and category attributes of automotive parts. General attributes refer to the part code (OE code), brand, name, original equipment manufacturer (OEM) part code, etc. Category attributes refer to the category of the automotive part, such as engine oil, tires, oil filters, etc. Category attributes can also include specifications, model, etc. For example, they are all in the category of engine oil, but engine oil has different capacity specifications (such as 1L and 4L) and different viscosities.

[0029] Store operation data refers to the data generated during the operation of a store, such as store inventory data, procurement data, and sales data.

[0030] The data on the relationship between vehicle models and parts describes the compatibility between different car parts and vehicle models.

[0031] Next, we'll introduce the store client. The store client provides an interface for store users. Store users can access the database through the store client, select the required parts from the general parts database, download the selected parts data to the store client, and add the required parts according to inventory quantities to create a store inventory parts list. Furthermore, store customers can also modify the store inventory parts list, including adding and deleting car parts. Whenever a store customer modifies the store inventory parts list, the store client will synchronize the updated store inventory parts list to the database.

[0032] Store customers can also generate work orders through the store client and upload them to the data computing platform. Work orders can include information such as the vehicle model requiring repair / maintenance, the repair / maintenance category, the required parts type, and the quantity of parts. The data computing platform will generate a parts recommendation list based on the work order and send it back to the store client. Store users can also generate a sales order for the work order through the store client for settlement.

[0033] Finally, let's introduce the data computing platform. The data computing platform is primarily used to respond to orders submitted by store clients. Based on the work order, the platform determines the target vehicle model and target part category, queries the database based on the target vehicle model and target part category to obtain the first candidate part data, matches the first candidate part data with the store's inventory of parts, determines the recommended parts list, and then feeds the recommended parts list back to the store client.

[0034] In some specific implementations, the process by which the data computing platform generates the first candidate component data is as follows: The data processing platform queries the general parts data to find all parts under the target parts category. Then, for each candidate parts in the parts list, it queries the vehicle models that the candidate parts are compatible with based on the vehicle model and part association data, and filters out the candidate parts that are compatible with the target vehicle model to construct the first candidate parts data. In other words, the first candidate parts data refers to all parts data under the target parts category specified in the work order that are compatible with the target vehicle model.

[0035] However, the car parts in the first candidate parts data may not be in stock at the store. Or the store may have stock, but not enough to complete the repair / maintenance. For example, a minor service requires 4L of engine oil, but the store only has two 1L cans of engine oil in stock. Obviously, the store's oil stock is not enough to complete the repair / maintenance.

[0036] Therefore, it is also necessary to match the first candidate accessory data with the store's inventory accessory list to determine the recommended accessory list. The specific process by which the data computing platform generates the recommended accessory list is as follows: First, the intersection of the first candidate accessory data and the store's inventory accessory list is calculated to obtain the second candidate accessory data. It should be noted that the specific quantity of inventory is not considered when calculating the intersection.

[0037] Next, the inventory quantity of each component in the second candidate component data is matched with the required component quantity in the work order. Component data that does not meet the required quantity in the work order is filtered out from the second candidate component data, resulting in the third candidate component data. A component recommendation list is then constructed based on the third candidate component data. The inventory quantity of components is considered in this step to ensure that each component in the filtered third candidate component data meets the required quantity in the work order.

[0038] Considering the varying sizes of stores, the quantity of auto parts in store inventory may be substantial, resulting in a large number of auto parts in the third candidate parts data that meet the work order requirements. In such cases, manual screening by store staff remains time-consuming and labor-intensive. Therefore, in some implementations, recommendation factors can be constructed to describe the recommendation priority of each part in the third candidate parts data. For example, the recommendation factor for each part in the third parts data can be determined based on its inventory quantity, historical sales volume, and the target vehicle segment. The construction of recommendation factors can be designed according to requirements, and this embodiment does not impose any restrictions on this. For instance, when making recommendations, the desired goal might be to reduce inventory pressure, select auto parts with higher historical sales volume to increase customer acceptance, and also consider the target vehicle segment. More expensive cars (such as B-segment cars and above) typically recommend more expensive auto parts from major brands, while cheaper cars (such as A-segment cars) typically recommend more cost-effective domestic auto parts. The recommendation factor can then be described using the following formula: ; in, Indicates car parts Recommendation factor, , , These represent the initial scores on the three evaluation criteria: inventory quantity, historical sales volume, and target vehicle segment. Indicates car parts Inventory quantity, This indicates the maximum inventory quantity of the same category of auto parts in the store. Indicates car parts Sales figures within a preset historical time window (e.g., the past month). This indicates the highest sales volume of the same category of auto parts in the store's inventory within a preset historical time window (e.g., the past month). Indicates car parts The compatibility coefficient relative to the target vehicle model is a positive number less than 1. This compatibility coefficient can be set in advance according to the actual situation.

[0039] A higher recommendation factor indicates a higher priority for the corresponding auto parts, making them more suitable for the current work order. This recommendation factor allows for the sorting of auto parts in the third-party parts data to generate a parts recommendation list. The format of this parts recommendation list can be found in the following reference. Figure 2 .

[0040] Corresponding to the aforementioned automotive parts recommendation system, this embodiment also provides an automotive parts recommendation method, which is implemented based on the automotive parts recommendation system. Please refer to... Figure 3 , Figure 3 A flowchart illustrating a method for recommending automotive parts is shown. Figure 3 As shown, the method includes steps S300 to S306.

[0041] S300: Build an automotive parts recommendation system, including a store client, a data computing platform, and a database.

[0042] The database stores general parts data, store operation data, and data relating vehicle models and parts. General parts data includes the general attributes and category attributes of automotive parts.

[0043] S302: Store users select the required accessories from the general accessories database through the store client, download the selected accessories data to the store client, add the quantity according to the inventory, form a store inventory accessories list, and synchronize the store inventory accessories list to the database.

[0044] S304: Store users generate work orders through the store client and upload them to the data computing platform.

[0045] S306: In response to receiving a work order, the data computing platform determines the target vehicle model and target part category based on the work order, queries the database based on the target vehicle model and target part category to obtain the first candidate part data; matches the first candidate part data with the store's inventory part list to determine the recommended part list, and feeds back the recommended part list to the store's client.

[0046] Specifically, the general attributes of the aforementioned auto parts include OE code, brand, and name; the category attributes of the auto parts include part category, specifications, and model. The aforementioned work order includes vehicle model, repair / maintenance category, required part category, and part quantity.

[0047] Optionally, the data calculation platform determines the target vehicle model and target part category based on the work order, and retrieves the first candidate part data from the database based on the target vehicle model and target part category, specifically including: The data computing platform queries the general parts data for a list of all parts under the target parts category; For each candidate part in the parts list, the model to which the candidate part is compatible is queried based on the correlation data between the model and the part, and candidate parts that are compatible with the target model are filtered out to construct the first candidate part data.

[0048] Optionally, the data processing platform will match the first candidate accessory data with the store's inventory accessory list to determine a recommended accessory list, which specifically includes: The data computing platform calculates the intersection of the first candidate accessory data and the store's inventory accessory list to obtain the second candidate accessory data; Match the inventory quantity of each accessory in the second candidate accessory data with the accessory quantity required in the work order. Filter out accessory data that does not meet the accessory quantity required in the work order from the second candidate accessory data to obtain the third candidate accessory data. Construct an accessory recommendation list based on the third candidate accessory data.

[0049] Optionally, the data computing platform constructs a recommended parts list based on the third candidate parts data, specifically including: Based on the inventory quantity, historical sales volume, and target vehicle level of each part in the third-party parts data, the recommendation factor for each part in the third-party parts data is determined; based on the recommendation factor, the parts in the third-party candidate parts data are sorted to obtain a parts recommendation list.

[0050] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the system of the embodiments of this application. In other embodiments of the specification, the above system may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0051] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0052] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

Claims

1. An automobile parts recommendation method characterized by comprising: The method comprises the steps of: building an automobile accessory recommendation system, including a store client, a data calculation platform and a database, the database storing general accessory data, store operation data and vehicle model and accessory association data; the general accessory data including general attributes and category attributes of automobile accessories; a store user selects required accessories from the general accessory data in the general accessory database through the store client, downloads the selected accessory data to the store client, forms a store inventory accessory list according to the inventory addition quantity, and synchronizes the store inventory accessory list to the database; the store user generates a work order through the store client and uploads it to the data calculation platform; in response to obtaining the work order, the data calculation platform determines a target vehicle model and a target accessory category based on the work order, and queries first candidate accessory data based on the target vehicle model and the target accessory category in the database; matching the first candidate accessory data and the store inventory accessory list to determine an accessory recommendation list, and feeding back the accessory recommendation list to the store client.

2. The method of claim 1, wherein, The general attributes of the automobile accessories include OE code, brand and name; the category attributes of the automobile accessories include accessory category, specification parameter and model; and the work order contains vehicle model, maintenance category, required accessory category and accessory quantity.

3. The method of claim 1, wherein, The data calculation platform determines a target vehicle model and a target accessory category based on the work order, and queries first candidate accessory data based on the target vehicle model and the target accessory category in the database, specifically including: the data calculation platform queries all accessory lists under the target accessory category in the general accessory data; for each candidate accessory in the accessory list, the data calculation platform queries vehicle models to which the candidate accessory is adapted based on the vehicle model and accessory association data, and filters out candidate accessories adapted to the target vehicle model to construct the first candidate accessory data.

4. The method of claim 3, wherein, The data calculation platform matches the first candidate accessory data and the store inventory accessory list to determine the accessory recommendation list, specifically including: The data calculation platform calculates the intersection of the first candidate accessory data and the store inventory accessory list to obtain second candidate accessory data; matching the inventory quantity of each accessory in the second candidate accessory data with the required accessory quantity in the work order, filtering out accessory data that does not meet the required accessory quantity in the work order from the second candidate accessory data to obtain third candidate accessory data, and constructing the accessory recommendation list based on the third candidate accessory data.

5. The method of claim 4, wherein, The data calculation platform constructs the accessory recommendation list based on the third candidate accessory data, specifically including: determining a recommendation factor of each accessory in the third accessory data based on the inventory quantity, historical sales volume and level of the target vehicle model of each accessory in the third accessory data; sorting the accessories in the third candidate accessory data based on the recommendation factor to obtain the accessory recommendation list.

6. An automobile parts recommendation system characterized by comprising: The method comprises the steps of: a store client, a data calculation platform and a database; The database stores general accessory data, store operation data, and vehicle and accessory association data; the general accessory data includes general attributes and category attributes of the automobile accessories; The store user selects a required accessory from the general accessory data of the general accessory database through the store client, downloads the selected accessory data to the store client, and forms a store inventory accessory list according to an inventory addition quantity; The store client synchronizes the store inventory accessory list to the database; The store client is further configured to generate a work order based on a store user operation and upload the work order to the data computing platform; The data computing platform is configured to determine a target vehicle model and a target accessory category based on the work order, query first candidate accessory data in the database based on the target vehicle model and the target accessory category; The first candidate accessory data and the store inventory accessory list are matched to determine an accessory recommendation list, and the accessory recommendation list is fed back to the store client.

7. The system of claim 6, wherein, The general attributes of the automobile accessories include OE codes, brands, and names; the category attributes of the automobile accessories include accessory categories, specification parameters, and models; and the work order includes a vehicle model, a maintenance category, a required accessory category, and an accessory quantity.

8. The system of claim 6, wherein, The data computing platform is specifically configured to: query all accessory lists under the target accessory category in the general accessory data; for each candidate accessory in the accessory list, query vehicle models to which the candidate accessory is adapted based on the vehicle and accessory association data, and filter out candidate accessories adapted to the target vehicle model to construct the first candidate accessory data.

9. The system of claim 8, wherein, The data computing platform is specifically configured to: calculate an intersection of the first candidate accessory data and the store inventory accessory list to obtain second candidate accessory data; match an inventory quantity of each accessory in the second candidate accessory data with a required accessory quantity in the work order, filter out accessory data that does not satisfy the required accessory quantity in the work order from the second candidate accessory data to obtain third candidate accessory data, and construct the accessory recommendation list based on the third candidate accessory data.

10. The system of claim 9, wherein, The data computing platform is further configured to: determine a recommendation factor of each accessory in the third accessory data based on an inventory quantity, a historical sales quantity of each accessory in the third accessory data, and a level of the target vehicle model; sort the accessories in the third candidate accessory data based on the recommendation factor to obtain the accessory recommendation list.

Images