Vehicle store optimization control method and device

Abstract

The invention provides a vehicle store optimization control method and device, and relates to the technical field of strategy optimization control, and the method comprises the steps: capturing and storing the business incremental data of each store for a first current user vehicle in real time, and carrying out the preprocessing of the business incremental data; when a preset time point is reached, re-clustering the preprocessed service incremental data and historical service data, and performing distributed storage according to a clustering result; optimizing control strategies corresponding to each user category, each theme category, each service category and each vehicle category in each store based on a clustering result; and on the basis of the optimized control strategy, each store is controlled in real time to execute corresponding operation for the second current user vehicle, so that the technical problems that in the prior art, data is dispersed and difficult to treat, and an effective store resource optimization decision cannot be generated are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of strategic optimization control, and in particular to a vehicle store optimization control method and device. Background Art

[0002] The multi-store operations of large-scale repair chain companies generate a large amount of distributed data, including repair work orders, vehicle information, inventory records, and online order data from third-party platforms. Due to the lack of a unified data management platform, this critical business data is scattered across independent systems, creating severe data silos and making it difficult to ensure data consistency.

[0003] On this basis, when the company's management conducts strategic planning and resource optimization, it is difficult to provide effective decision-making analysis support based on the scattered and inconsistent data of each store. It is also impossible to optimize the operating turnover of each store to provide better services to customers, which is not conducive to the market share of such Leno repair companies. Summary of the Invention

[0004] The purpose of the present invention is to provide a vehicle store optimization control method and device to alleviate the technical problems existing in the prior art, such as the difficulty in managing data dispersion and the inability to generate effective store resource optimization decisions.

[0005] In a first aspect, the present invention provides a vehicle store optimization control method, comprising: Capturing and storing incremental business data of each store for the first current user's vehicle in real time, and preprocessing the incremental business data; When the preset time point is reached, the pre-processed incremental business data and historical business data are re-clustered and distributedly stored according to the clustering results; Based on the clustering results, optimize the control strategy corresponding to each user category, subject category, business category and vehicle category in each store; Based on the optimized control strategy, each store is controlled in real time to perform corresponding operations on the second current user's vehicle.

[0006] In an optional embodiment, the method further comprises: Using association rules to mine the business data in the clustering results, determine the correlation between vehicle maintenance failures and parts usage, and optimize the parts inventory management of each store; By using the real-time order data in the clustering results described by the time series model, the maintenance needs of different models in different seasons are predicted, and the maintenance resource management of each store is optimized.

[0007] In an optional embodiment, based on the clustering results, the step of optimizing the control strategy corresponding to each user category, subject category, business category, and vehicle category in each store includes: Based on the clustering results, the user and vehicle levels of each store service are divided according to each user category, subject category, business category and vehicle category; According to the number of each user's vehicle level in each store in each subject category and each business category, the control strategy corresponding to each store in each subject category and each business is optimized; wherein the control strategy includes an early warning strategy and a marketing strategy.

[0008] In an optional embodiment, based on the optimized control strategy, the steps of controlling each store in real time to perform corresponding operations on the second current user's vehicle include: Based on the incremental business data of the second current user's vehicle captured in real time by each store, the corresponding target strategy is selected from the optimized control strategies according to each user category, subject category, business category and vehicle category; Based on the target strategy, push targeted marketing plans to the second current user vehicle of each store; and / or, Based on the target strategy, issuing an inventory warning of spare parts required for repairing the second current user's vehicle to each store; and / or, Based on the target strategy, a marketing activity change plan for the current time period is issued to each store.

[0009] In an optional embodiment, when a preset time point is reached, the steps of re-clustering the pre-processed incremental business data and historical business data and performing distributed storage according to the clustering results include: When the preset time point is reached, the offline processing mode is triggered, and the pre-processed incremental business data and historical business data stored in real time are re-clustered according to user category, topic category, business category and vehicle category as clustering targets; The clustering results of the pre-processed business incremental data and historical business data corresponding to each clustering target are stored in a distributed manner.

[0010] In an optional embodiment, the step of capturing and storing incremental business data of each store for the first current user's vehicle in real time and preprocessing the incremental business data includes: Obtain unstructured data of each store for the current user's vehicle in real time through the Kafka message queue, and obtain structured data of each store for the current user's vehicle in real time through the binlog link; wherein the structured data and the unstructured data constitute incremental business data; Storing the incremental business data in real time and filtering invalid data in the incremental business data; Based on the user categories, subject categories, business categories and vehicle categories corresponding to the filtered business incremental data, similar business data is determined from the historical business data, and the filtered business incremental data of each store is corrected and completed.

[0011] In an optional embodiment, the method further comprises: If it is monitored that the pre-processed incremental business data has quality anomalies, the real-time stored incremental business data is called to perform the pre-processing operation again based on the time period corresponding to the incremental business data with quality anomalies.

[0012] In a second aspect, the present invention provides a vehicle store optimization control device, comprising: The multi-source data collection layer captures and stores each store's incremental business data for the first current user's vehicle in real time; The data cleaning and conversion layer pre-processes the incremental business data; Thematic data storage layer, when reaching a preset time point, re-clustering the pre-processed incremental business data and historical business data, and distributing and storing them according to the clustering results; The data service and application layer optimizes the control strategies corresponding to each user category, subject category, business category, and vehicle category in each store based on the clustering results; and based on the optimized control strategies, controls each store in real time to perform corresponding operations for the second current user's vehicle.

[0013] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a program stored in the memory and capable of running on the processor, wherein the processor implements a method as described in any one of the aforementioned embodiments when executing the program.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the method described in any one of the aforementioned embodiments is implemented.

[0015] The embodiment of the present invention provides a vehicle store optimization control method and device, which obtains and stores the business incremental data of the current user vehicles of each store in real time, changes from real-time incremental mode to offline full mode when a preset time point is reached, and re-clusters the pre-processed business incremental data and historical business data to generate clustering results for distributed storage. The clustering results are then used to optimize the control strategies corresponding to each user category, subject category, business category and vehicle category of each store. The optimized control strategies guide each store's service to subsequent user vehicles. Under the condition of effective data management, it can provide each store with service decision support that meets user requirements.

[0016] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flow chart of a vehicle store optimization control method provided by an embodiment of the present invention; Figure 2 A data warehouse architecture diagram provided by an embodiment of the present invention; Figure 3 A schematic diagram of the functional modules of a vehicle store optimization control device provided by an embodiment of the present invention; Figure 4 A schematic diagram of the hardware architecture of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] Currently, corporate management urgently needs comprehensive business data support for strategic planning and resource optimization. However, the current fragmented data architecture cannot provide real-time analysis of core operational indicators such as store repair volume, vehicle maintenance demand structure, and parts inventory turnover efficiency, severely restricting the timeliness and scientific nature of management decisions.

[0022] In an increasingly competitive market, improving customer service quality has become a core competitive advantage for businesses. While building a data warehouse to integrate customer repair records and service preference data can significantly improve service accuracy and personalization, insufficient existing data processing capabilities have severely hindered achieving this goal.

[0023] Based on this, the embodiments of the present invention provide a vehicle store optimization control method and device, which can effectively manage data dispersion and optimize the operation control of each vehicle store.

[0024] To facilitate understanding of this embodiment, a data warehouse architecture disclosed in an embodiment of the present invention is first introduced in detail.

[0025] Figure 2 A data warehouse architecture diagram provided for an embodiment of the present invention.

[0026] Reference Figure 2 The architecture includes multi-source data collection layer, data cleaning and conversion layer, thematic data storage layer, data service and application layer, Figure 2 The structural relationship and data flow between each layer in real-time processing and offline processing are shown in Figure 2.

[0027] Multi-source data collection layer: Multi-source data obtained from databases, message queues Kafka, and incremental logs Binlog can be seamlessly connected to maintenance management systems, parts inventory systems, customer relationship management systems, etc. through a universal data collection interface. Various business data can be collected in real time or on a scheduled basis, including maintenance work order details, parts in and out records, basic customer information, and maintenance feedback.

[0028] Data cleaning and conversion layer: Each type of business data corresponds to different topics, and each topic includes subdivided business categories, such as Figure 2 As shown, topics include marketing, finance, merchandise, stores, and supply chain. By comparing historical work order data from offline business data with repair work order data from similar vehicle models with the same topic in current real-time business data, we identify and correct abnormal work order amounts, work order quantities, and work order completion times. We also remove duplicate values ​​and assign default values ​​to null values ​​to achieve data cleansing. Furthermore, we convert the format and unify the encoding of the collected data according to pre-set data standards to ensure data consistency and availability.

[0029] Thematic data storage layer: Utilizing distributed storage technologies, such as Hadoop-based HDFS, a thematic data storage structure is constructed. Based on business process and entity clustering, higher-level business concept domains (topics) are formed for storage. Store topics are established to store data related to repair work orders, store technical information, and so on; supply chain topics cover data on parts inventory, procurement, and suppliers; member topics contain customer information, repair history, and customer reviews; transaction topics store data such as orders, returns, and reviews from various online trading platforms; marketing topics cover data on events, coupons, membership cards, and packages; product topics cover data such as SKUs, products, and categories; vehicle topics contain data on member vehicles, models, and repair history; and financial topics contain data related to finance.

[0030] Data Service and Application Layer: This layer provides a rich set of data interfaces, supporting access to various data analysis tools and business application systems. It also develops a visual data analysis platform, providing management with intuitive reports and charts to aid decision-making. It also provides maintenance personnel with a maintenance knowledge base and intelligent diagnostic tools to improve maintenance efficiency and quality. It also offers customers online query and service reservation capabilities to enhance the customer experience.

[0031] An embodiment of the present invention also provides a vehicle store optimization control method executed through the above-mentioned architecture, which can be applied to intelligent control devices such as host computers, servers, controllers, etc. deployed with a data warehouse architecture.

[0032] Figure 1 A flow chart of a vehicle store optimization control method provided by an embodiment of the present invention.

[0033] Reference Figure 1 , the method comprising: Step S102 : Capture and store the incremental business data of each store for the first current user's vehicle in real time, and pre-process the incremental business data.

[0034] Using message queue technologies such as Kafka and data collection tools like Sqoop and Dafax, we achieve real-time synchronization of data across stores, ensuring data timeliness. For example, when a new repair order is generated, parts are shipped in and out of the warehouse, or customer information is updated, incremental data can be immediately transferred to the data warehouse for processing.

[0035] For example, the embodiment of the present invention can perform real-time incremental update and effective cleaning of multi-source business data. Step S102 can be implemented by the following steps, including: Step 1.1: Obtain the unstructured data of each store for the current user's vehicle in real time through the Kafka message queue, and obtain the structured data of each store for the current user's vehicle in real time through the binlog link.

[0036] Among them, structured data and unstructured data constitute incremental business data; through Kafka message queues and Binlog, various business systems (orders, work orders, membership systems, etc.) are linked to capture events (such as work order creation, member behavior data, etc.) in real time, thereby realizing real-time updates of incremental business data from different data sources.

[0037] Step 1.2: Store the incremental business data in real time and filter out invalid data in the incremental business data.

[0038] First, the incremental business data captured in real time is stored in real time to facilitate subsequent data anomaly backtracking. Then, the stream processing engine Flink is used to clean the incremental business data in real time, filtering out invalid data (such as negative work order amounts) and incomplete missing fields in the associated dimension table (vehicle model data).

[0039] As an optional embodiment, the incremental business data can be cleaned in real time through the stream processing engine Flink to filter out invalid data (such as negative work order amounts) and incomplete missing fields in the associated dimension table (vehicle model data). The output standardized data stream is then written into the Hbase real-time partition.

[0040] Step 1.3: Based on the user category, subject category, business category, and vehicle category corresponding to the filtered incremental business data, similar business data is determined from the historical business data, and the filtered incremental business data of each store is corrected and completed.

[0041] The validation rule engine compares filtered incremental business data with similar business data in historical business data to verify completeness, accuracy, and consistency. Completeness checks for missing required fields (such as work order amounts); accuracy checks for work order amount ranges (e.g., triggering an alert if the price of an accessory exceeds 10,000 yuan). Consistency compares the fluctuation threshold of historical work order amounts (±30%) to the store's historical work order amounts. Monitoring results are stored in Elasticsearch and visualized in the Grafana alert dashboard.

[0042] During the actual preprocessing process, if there are anomalies in the incremental business data, in order to ensure reliable decision support in subsequent steps, the method also includes: In step 2.1, if it is detected that the pre-processed incremental business data has quality anomalies, the real-time stored incremental business data is called to perform pre-processing again based on the time period corresponding to the incremental business data with quality anomalies.

[0043] When an anomaly is detected, a correction task is automatically invoked, extracting the problematic data time period from the storage layer (e.g., work orders from 2025-07-31 10:00-11:00), rerunning the cleansing task for that time period, overwriting the erroneous data partition, and generating a correction report for subsequent audits. This embodiment of the present invention establishes a data quality monitoring system to monitor data integrity, accuracy, and consistency in real time. Once a data quality issue is discovered, a backtracking mechanism is automatically triggered to recollect, clean, and convert the problematic data, enabling data quality monitoring and backtracking to ensure data reliability.

[0044] Step S104: When a preset time point is reached, the pre-processed incremental business data and historical business data are re-clustered and distributedly stored according to the clustering results.

[0045] The preset time point can be set according to actual conditions, such as night time. For example, when the preset time point is reached, the offline mode is triggered, and the business data of each store is fully updated offline, and distributed storage is implemented, specifically including: Step 3.1: When the preset time point is reached, the offline processing mode is triggered, and the pre-processed business incremental data and historical business data stored in real time are re-clustered according to user category, topic category, business category and vehicle category as clustering targets.

[0046] At this time, after re-clustering, business data corresponding to each user category, subject category, business category and vehicle category are generated.

[0047] In step 3.2, the clustering results of the pre-processed incremental business data and historical business data corresponding to each clustering target are distributedly stored.

[0048] The clustering results can be interpreted as cluster labels for user, topic, business, and vehicle categories, along with the corresponding business data for each category. The Spark MLlib analysis engine can be used for offline analysis (T+1 cycle). For example, cluster analysis can be performed by categorizing customers into high, medium, and low value categories based on member topic data (repair frequency, vehicle type, and spending amount).

[0049] As an optional implementation, building on the aforementioned implementation's combination of incremental and full updates, the update strategy can be dynamically adjusted based on the frequency and importance of business data changes. For frequently changing repair work order data, incremental updates improve data processing efficiency; for relatively stable data, such as customer information, regular full updates ensure data integrity.

[0050] Step S106 , based on the clustering results, optimizing the control strategy corresponding to each user category, subject category, business category and vehicle category in each store.

[0051] For example, further analysis can be performed based on the clustering results to optimize targeted strategies for users, businesses, etc. in each store. Step S106 can be implemented by the following steps, including: Step 4.1: Based on the clustering results, the user vehicle level of each store service is divided according to each user category, topic category, business category and vehicle category.

[0052] Based on the above categories, we analyze historical T+1 business data offline, label each car owner (such as high-value customers, sophisticated customers, etc.), and collect historical work order data for each car.

[0053] In step 4.2, according to the number of each user's vehicle level in each store in each theme category and business category, optimize the control strategy corresponding to each store in each theme and each business.

[0054] Control strategies include early warning strategies and marketing strategies. For example, when a customer visits a store, the real-time architecture can recommend services based on customer tags generated by the offline architecture and historical work order data. For example, if a customer washes their car weekly, they can be recommended for a deep beauty treatment like crystal coating. If the car is in its maintenance period, a maintenance recommendation is pushed to the corresponding store in real time based on the marketing strategy developed through offline optimization.

[0055] Step S108: Based on the optimized control strategy, each store is controlled in real time to perform corresponding operations on the second current user's vehicle.

[0056] Based on the above embodiment, the store operation control in step S108 can also be implemented according to the following steps: In step 5.1, based on the incremental business data of the second current user's vehicle captured in real time by each store, the corresponding target strategy is selected from the optimized control strategies according to each user category, subject category, business category and vehicle category.

[0057] Here, the second current user vehicle is the vehicle belonging to the user who needs to handle the corresponding business / service at each store at this moment. The second current user vehicle exists in the same situation as the first current user vehicle; according to the current business growth of each store, the target strategy of the corresponding category is selected from the offline optimization strategy to control each store in a targeted manner.

[0058] Step 5.2: Based on the target strategy, push a targeted marketing plan to the second current user vehicle of each store.

[0059] As an optional embodiment, if the incremental business data of a store does not meet expectations, the target strategy can be a marketing strategy, and a marketing plan corresponding to this marketing strategy is pushed to the store, such as price reduction and discount, to facilitate business development.

[0060] and / or, In step 5.3, based on the target strategy, an inventory warning of the spare parts required for repairing the second current user's vehicle is issued to each store.

[0061] As an optional embodiment, if the incremental business data of a store shows that the store has a large number of repairs of a certain type, approaching or reaching a preset threshold, the target strategy may be an inventory warning strategy, which pushes inventory warning notifications of the corresponding accessories for this type of repair to the store so that the store can meet customers' needs for this type of repair.

[0062] and / or, In step 5.4, based on the target strategy, a marketing activity change plan for the current time period is issued to each store.

[0063] As an optional embodiment, if the current time period falls on a specific marketing holiday, the target strategy may be a holiday marketing strategy, and the marketing plan corresponding to this holiday marketing strategy may be pushed to each store so that each store can change to the optimal marketing that is more in line with the current time period.

[0064] In a preferred embodiment of actual application, the incremental business data of the current user vehicles of each store is acquired and stored in real time. When the preset time point is reached, the real-time incremental mode is changed to the offline full mode. The clustering results generated by re-clustering the pre-processed incremental business data and historical business data are distributed and stored. The clustering results are then used to optimize the control strategies corresponding to each user category, subject category, business category and vehicle category of each store. The optimized control strategies guide each store's services to subsequent user vehicles. Under the condition of effective data governance, it can provide each store with service decision support that meets user requirements.

[0065] In some embodiments, the method of the present invention can also implement intelligent data analysis and prediction, specifically including: Step 6.1: Use association rules to mine the business data in the clustering results, determine the correlation between vehicle maintenance failures and parts usage, and optimize the parts inventory management of each store.

[0066] This embodiment of the present invention uses machine learning algorithms, such as cluster analysis, association rule mining, and time series forecasting, to conduct in-depth analysis of maintenance data. Cluster analysis helps categorize customers for precision marketing, while association rule mining helps identify the correlation between maintenance failures and parts usage, optimizing parts inventory management.

[0067] In step 6.2, the real-time order data in the time series model clustering results are used to predict the maintenance needs of different car models in different seasons and optimize the maintenance resource management of each store.

[0068] Here, real-time online order data can be read through prediction engines such as time series models to predict future order volumes for a certain activity or certain specific categories of demand, and then manage the spare parts resources of each store.

[0069] The embodiment of the present invention can deploy a data warehouse server cluster in the headquarters data center of a large chain repair shop, and reasonably configure the server hardware resources according to the data volume and business needs. Deploy a business system in each store to be responsible for the storage and uploading of local data; at the same time, formulate a data collection plan, and set an appropriate collection time interval based on the characteristics of different data sources and the frequency of data updates. Regularly optimize data cleaning tasks, adjust cleaning rules and algorithms, implement data collection and cleaning task scheduling, and improve cleaning effectiveness and efficiency. In addition, develop corresponding data analysis applications based on the needs of management, maintenance personnel, and customers. Deploy these applications to the enterprise's internal network or cloud for easy user access and use. At the same time, establish a user feedback mechanism to continuously optimize the functions and performance of the application based on user feedback.

[0070] In some embodiments, as Figure 3 As shown, an embodiment of the present invention provides a vehicle store optimization control device, comprising: The multi-source data collection layer captures and stores each store's incremental business data for the first current user's vehicle in real time; The data cleaning and conversion layer pre-processes the incremental business data; Thematic data storage layer, when reaching a preset time point, re-clustering the pre-processed incremental business data and historical business data, and distributing and storing them according to the clustering results; The data service and application layer optimizes the control strategies corresponding to each user category, subject category, business category, and vehicle category in each store based on the clustering results; and based on the optimized control strategies, controls each store in real time to perform corresponding operations for the second current user's vehicle.

[0071] An embodiment of the present invention provides an electronic device for implementing an electronic device. In this embodiment, the electronic device may be, but is not limited to, a personal computer (PC), a laptop computer, a monitoring device, a server, or other computer device with analysis and processing capabilities.

[0072] As an exemplary embodiment, see Figure 4The electronic device 110 includes a communication interface 111, a processor 112, a memory 113 and a bus 114. The processor 112, the communication interface 111 and the memory 113 are connected via the bus 114. The above-mentioned memory 113 is used to store a computer program that supports the processor 112 to execute the above-mentioned method. The above-mentioned processor 112 is configured to execute the program stored in the memory 113.

[0073] The machine-readable storage medium referred to herein can be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, and the like. For example, the machine-readable storage medium can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, a storage drive (such as a hard drive), any type of storage disk (such as a CD, DVD, etc.), or similar storage media, or a combination thereof.

[0074] The non-volatile medium may be a non-volatile memory, a flash memory, a storage drive (such as a hard drive), any type of storage disk (such as an optical disk, a DVD, etc.), or similar non-volatile storage media, or a combination thereof.

[0075] It can be understood that the specific operation methods of each functional module in this embodiment can refer to the detailed description of the corresponding steps in the above method embodiment, and will not be repeated here.

[0076] The computer-readable storage medium provided in the embodiments of the present invention stores a computer program. When the computer program code is executed, the method described in any of the above embodiments can be implemented. For specific implementation, please refer to the method embodiment, which will not be repeated here.

[0077] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0078] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0079] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0080] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-mentioned embodiments, ordinary technicians in this field should understand that any technician familiar with this technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed by the present invention, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention.

Claims

1. A vehicle store optimization control method, characterized in that: include: Capturing and storing incremental business data of each store for the first current user's vehicle in real time, and pre-processing the incremental business data; When the preset time point is reached, the pre-processed incremental business data and historical business data are re-clustered and distributedly stored according to the clustering results; Based on the clustering results, optimize the control strategy corresponding to each user category, subject category, business category and vehicle category in each store; Based on the optimized control strategy, each store is controlled in real time to perform corresponding operations on the second current user's vehicle.

2. The method according to claim 1, characterized in that The method further comprises: Using association rules to mine the business data in the clustering results, determine the correlation between vehicle maintenance failures and parts usage, and optimize the parts inventory management of each store; By using the real-time order data in the clustering results described by the time series model, the maintenance needs of different models in different seasons are predicted, and the maintenance resource management of each store is optimized.

3. The method according to claim 1, characterized in that Based on the clustering results, the steps of optimizing the control strategy corresponding to each user category, subject category, business category, and vehicle category in each store include: Based on the clustering results, the user and vehicle levels of each store service are divided according to each user category, subject category, business category and vehicle category; According to the number of each user's vehicle level in each store in each subject category and each business category, the control strategy corresponding to each store in each subject category and each business is optimized; wherein the control strategy includes an early warning strategy and a marketing strategy.

4. The method according to claim 3, characterized in that Based on the optimized control strategy, each store is controlled in real time to perform corresponding operations on the second current user's vehicle, including: Based on the incremental business data of the second current user's vehicle captured in real time by each store, the corresponding target strategy is selected from the optimized control strategies according to each user category, subject category, business category and vehicle category; Based on the target strategy, push targeted marketing plans to the second current user vehicle of each store; and / or, Based on the target strategy, issuing an inventory warning to each store for parts required for repairing the second current user's vehicle; and / or, Based on the target strategy, a marketing activity change plan for the current time period is issued to each store.

5. The method according to claim 1, wherein When the preset time point is reached, the pre-processed incremental business data and historical business data are re-clustered and distributedly stored according to the clustering results, including the following steps: When the preset time point is reached, the offline processing mode is triggered, and the pre-processed incremental business data and historical business data stored in real time are re-clustered according to user category, topic category, business category and vehicle category as clustering targets; The clustering results of the pre-processed business incremental data and historical business data corresponding to each clustering target are stored in a distributed manner.

6. The method according to claim 1, characterized in that The steps of capturing and storing incremental business data of each store for the first current user's vehicle in real time and preprocessing the incremental business data include: Obtain unstructured data of each store for the current user's vehicle in real time through the Kafka message queue, and obtain structured data of each store for the current user's vehicle in real time through the binlog link; wherein the structured data and the unstructured data constitute incremental business data; Storing the incremental business data in real time and filtering invalid data in the incremental business data; Based on the user categories, subject categories, business categories and vehicle categories corresponding to the filtered business incremental data, similar business data is determined from the historical business data, and the filtered business incremental data of each store is corrected and completed.

7. The method according to claim 6, characterized in that The method further comprises: If it is monitored that the pre-processed incremental business data has quality anomalies, the real-time stored incremental business data is called to perform the pre-processing operation again based on the time period corresponding to the incremental business data with quality anomalies.

8. A vehicle store optimization control device, characterized in that: include: The multi-source data collection layer captures and stores each store's incremental business data for the first current user's vehicle in real time; The data cleaning and conversion layer pre-processes the incremental business data; Thematic data storage layer, when reaching a preset time point, re-clustering the pre-processed incremental business data and historical business data, and distributing and storing them according to the clustering results; The data service and application layer optimizes the control strategy corresponding to each user category, subject category, business category, and vehicle category in each store based on the clustering results; Based on the optimized control strategy, each store is controlled in real time to perform corresponding operations on the second current user's vehicle.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a program stored in the memory and capable of being run on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.

Images