A vehicle customer retention clue identification method and system based on multi-source data fusion

Abstract

This application discloses a method and system for identifying vehicle customer leads based on multi-source data fusion, belonging to the field of vehicle customer lead technology. The method collects operational and maintenance status data of the target vehicle's corresponding vehicle identification number, including static data, driving behavior data, fault claims, and navigation electronic map data. After cleaning and preprocessing, the data is correlated and fused to construct a three-dimensional data matrix of vehicle static, operational, and after-sales data. Core driving data for repeat purchases and additional purchases from existing customers are obtained. Repeat purchase intention scenarios are segmented, and feature sets and quantitative judgment rules are configured. An initial customer lead pool is generated based on matrix classification. An effective lead pool is obtained through data collaborative verification, sorted by scenario priority weight, and the judgment rules and weight coefficients are dynamically updated at fixed intervals. Finally, a standardized customer lead list is output. This solution achieves efficient multi-source data fusion and accurate lead identification, dynamically optimizing and improving lead effectiveness and matching efficiency.

Description

Technical Field

[0001] This invention relates to the field of vehicle customer retention clue technology, and in particular to a vehicle customer retention clue identification method based on multi-source data fusion, a vehicle customer retention clue identification system based on multi-source data fusion, electronic equipment, and storage medium. Background Technology

[0003] Currently, customer lead identification for commercial vehicles mainly relies on static tags. Core technologies include: using vehicle purchase year and model manufacturing date as key screening criteria (e.g., defaulting to customers with commercial vehicles over 5 years old as potential replacement buyers); manually reviewing after-sales maintenance records to screen customers with high maintenance frequency; and collecting customer replacement intentions through telephone surveys and offline visits to create a lead list. However, this approach suffers from several drawbacks: low lead accuracy; static tags cannot reflect the actual vehicle usage status (e.g., customers with 5-year-old vehicles but less than 50,000 kilometers on the odometer may not have actual replacement needs, leading to "false leads" and wasted marketing resources); passive demand discovery (manual surveys can only obtain explicit customer needs, failing to capture implicit operational pain points and missing potential leads); and insufficient data synergy (multi-source data such as driving behavior data, fault claim data, and BeiDou positioning data are isolated and lack a unified analytical dimension, making it impossible to build a complete customer usage profile). Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a vehicle customer lead identification method based on multi-source data fusion, a vehicle customer lead identification system based on multi-source data fusion, an electronic device and a storage medium, aiming to identify and cover the repurchase needs of commercial vehicles in multiple scenarios by deeply integrating multi-source data, realize the automated screening of customer leads, and solve the technical problems of low accuracy, poor efficiency and weak scenario adaptability in the prior art.

[0005] This invention provides the following solution:

[0006] According to one aspect of this application, a method for identifying vehicle customer loyalty clues based on multi-source data fusion is provided, comprising the following steps:

[0007] Collect full-state data on the operation and maintenance of the target vehicle;

[0008] The operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data; the operational and maintenance status data is associated with the vehicle identification number (VIN).

[0009] Data cleaning and preprocessing are performed on the collected operation and maintenance status data. Based on the vehicle identification code, the multi-source data corresponding to the same vehicle are associated and fused to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data.

[0010] Obtain the core driving data for repeat purchases and additional purchases by existing vehicle customers. Based on the core driving data for repeat purchases and additional purchases by existing vehicle customers, segment repeat purchase intention scenarios and configure corresponding feature sets and quantitative judgment rules for each intention scenario.

[0011] Based on a three-dimensional data matrix, repeat purchase intention scenarios are classified to generate an initial customer lead pool;

[0012] Based on the initial customer lead pool, data collaborative verification is performed to obtain a valid customer lead pool;

[0013] Set corresponding priority weights for repeat purchase intention scenarios, prioritize leads in the effective customer lead pool based on the weights, perform dynamic model iterations at fixed intervals, and update the judgment rules and scenario weight coefficients corresponding to the policies in sync.

[0014] Based on the priority ranking results, a standardized list of customer leads is generated and output.

[0015] Furthermore, static data includes: basic vehicle static attribute data, vehicle identification data, and vehicle production configuration data;

[0016] Driving behavior data includes: real-time vehicle operating status time-series data and vehicle-to-everything (V2X) dynamic operating time-space data of connected vehicles;

[0017] Fault and Claims Data: Vehicle after-sales fault and claims maintenance data, as well as fault claims data throughout the vehicle's entire lifecycle;

[0018] Navigation electronic map data: Location service data for navigation electronic maps.

[0019] Furthermore, repurchase intention scenarios include: policy-related replacement scenarios, business expansion-related replacement scenarios, performance degradation-related replacement scenarios, and fault claim-related replacement scenarios.

[0020] Furthermore, setting corresponding priority weights for repeat purchase intention scenarios includes:

[0021] Policy-driven replacement purchases take priority over business expansion-related additional purchases.

[0022] Purchases for business expansion have a higher priority than replacements for performance degradation.

[0023] Replacement of products with deteriorating performance has a higher priority than replacement of products with frequent malfunctions.

[0024] Furthermore, a corresponding feature set and quantization judgment rule are configured for each intended scenario, specifically as follows:

[0025] Policy-driven scrapping and replacement scenarios include: meeting the scrapping and replacement policy for old commercial vehicles, passing the subsidy eligibility verification, and meeting the vehicle's failure frequency requirements;

[0026] The quantitative judgment rules are as follows: the vehicle's off-line time is less than or equal to the policy-limited years, or the vehicle's cumulative mileage is greater than or equal to the policy-limited mileage; the subsidy eligibility is passed; and the number of faults in a quarter is greater than the preset threshold.

[0027] Business expansion-related additional purchase scenarios include: meeting targets for mileage increase, meeting targets for attendance rate, and meeting targets for the increase in the number of new loading and unloading points;

[0028] The quantitative judgment rules are as follows: within a continuous time period, the mileage increase is greater than or equal to the first preset threshold, the attendance rate is greater than or equal to the second preset threshold, and the monthly increase of new loading and unloading points is greater than or equal to the third preset threshold.

[0029] The attendance rate is calculated as follows: Attendance rate = Number of days attended / Total number of days × 100%, where the number of days attended is defined as the number of days when the daily mileage meets the preset mileage threshold.

[0030] Performance-degraded replacement scenarios: The characteristic set includes the proportion of fuel consumption increase conditions exceeding the standard, the corresponding model's cumulative mileage reaching the standard, and the vehicle not being scrapped under policy.

[0031] The quantitative judgment rules are as follows: the proportion of operating conditions in which the fuel consumption in the current month is higher than the average of the previous two months is greater than the preset threshold; the cumulative mileage of the corresponding model reaches the preset threshold; and the vehicle is removed from the production line after the policy-limited scrapping age.

[0032] Fault-based replacement scenarios include: major claims, service station stays exceeding the limit, and vehicles not subject to policy-mandated scrapping or performance degradation.

[0033] The quantitative judgment rules are as follows: the number of major claims in a year is greater than or equal to the preset number; the number of times the single stay time at the service station exceeds the preset time is greater than the preset number; and customers whose characteristics overlap with those of the aforementioned performance degradation replacement scenario are excluded.

[0034] Furthermore, data cleaning and preprocessing are performed on the collected operation and maintenance status data, including:

[0035] A sliding window is used to dynamically clean driving behavior data, detecting and deleting duplicate data corresponding to the same vehicle identification number.

[0036] Furthermore, based on the initial customer lead pool, data collaborative verification is performed to obtain a valid customer lead pool, specifically as follows:

[0037] For the business expansion and additional purchase scenarios in the initial customer lead pool, the new loading and unloading point is verified to be the actual vehicle operation station by combining navigation electronic map data;

[0038] Excluding false leads such as inflated mileage, verified leads are included in the pool of valid customer leads.

[0039] Furthermore, corresponding priority weights are set for repeat purchase intention scenarios, specifically as follows:

[0040] The weighting for policy-driven replacement purchases is 0.3; the weighting for business expansion-driven purchases is 0.25; the weighting for performance-degraded replacement purchases is 0.15; and the weighting for high-frequency failure replacement purchases is 0.1.

[0041] The model is dynamically iterated on a fixed cycle, specifically on a calendar month basis. The content updated synchronously includes the threshold of the quantitative judgment rules corresponding to the policy and the priority weight coefficient of each repurchase intention scenario adjusted according to the actual conversion rate of the leads.

[0042] According to two aspects of this application, a vehicle customer retention clue identification system based on multi-source data fusion is provided, comprising:

[0043] The module includes a data acquisition module, a data preprocessing module, a scenario segmentation module, an initial customer lead pool generation module, a data verification module, a priority sorting module, and a result output module.

[0044] The data acquisition module is used to collect operational and maintenance status data of the target vehicle. The operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data. The operational and maintenance status data is associated with the vehicle identification number.

[0045] The data preprocessing module is used to perform data cleaning and data preprocessing on the collected operation and maintenance status data. Based on the vehicle identification code, it associates and merges multi-source data corresponding to the same vehicle to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data.

[0046] The scenario segmentation module is used to obtain the core driving data of repeat purchases and additional purchases by existing vehicle customers. Based on the core driving data of repeat purchases and additional purchases by existing vehicle customers, the module segments repeat purchase intention scenarios and configures corresponding feature sets and quantitative judgment rules for each intention scenario.

[0047] The initial customer lead pool generation module is used to classify repeat purchase intention scenarios based on a three-dimensional data matrix and generate an initial customer lead pool.

[0048] The data verification module is used to perform collaborative data verification based on the initial customer lead pool to obtain a valid customer lead pool.

[0049] The priority ranking module is used to set corresponding priority weights for repeat purchase intention scenarios, and to prioritize the leads in the effective customer lead pool based on the weights; the model is dynamically iterated at a fixed period to synchronously update the judgment rules and scenario weight coefficients corresponding to the policy.

[0050] The results output module is used to sort the results according to priority, generate a standardized list of customer leads, and output it.

[0051] According to three aspects of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0052] The memory stores a computer program, which, when executed by a processor, causes the processor to perform steps of a vehicle customer loyalty clue identification method based on multi-source data fusion.

[0053] According to four aspects of the present invention, a computer-readable storage medium is provided that stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a vehicle customer tracing identification method based on multi-source data fusion.

[0054] Compared with the prior art, the present invention has the following advantages:

[0055] This application eliminates the reliance on manual surveys, the limitations of filtering isolated static data, and the investment in additional data collection hardware and interfaces in traditional commercial vehicle customer lead identification. It relies solely on the vehicle network dynamic data and fault claim data transmitted by the standard TBOX in commercial vehicles, and innovatively integrates multi-dimensional information such as vehicle network dynamic data, fault claim data, and Beidou map data. While significantly reducing the cost of manual operation and additional hardware investment, it can generalize the customer lead identification model under different repurchase scenarios and different commercial vehicle models, greatly improving the accuracy and scenario adaptability of commercial vehicle customer lead identification to adapt to policy guidance and the needs of existing market competition. Attached Figure Description

[0056] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0057] Figure 1 This is a flowchart of a vehicle customer retention clue identification method based on multi-source data fusion provided by one or more embodiments of the present invention.

[0058] Figure 2 This is a structural diagram of a vehicle customer loyalty clue identification system based on multi-source data fusion provided by one or more embodiments of the present invention.

[0059] Figure 3 This is a flowchart of a vehicle customer loyalty clue identification method based on multi-source data fusion, provided by a specific embodiment of the present invention.

[0060] Figure 4 This is a block diagram of an electronic device for identifying vehicle customer loyalty clues based on multi-source data fusion, provided by one or more embodiments of the present invention. Detailed Implementation

[0061] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0063] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0064] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0065] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0066] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0067] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0068] Figure 1 This is a flowchart of a vehicle customer retention clue identification method based on multi-source data fusion provided by one or more embodiments of the present invention.

[0069] like Figure 1 As shown, it includes the following steps:

[0070] Step S1: Collect the full operational and maintenance status data of the target vehicle; the full operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data; the full operational and maintenance status data is associated with the vehicle identification number;

[0071] Specifically, static data includes: basic vehicle static attribute data, vehicle identification data, and vehicle production configuration data;

[0072] Driving behavior data includes: real-time vehicle operating status time-series data and vehicle-to-everything (V2X) dynamic operating time-space data of connected vehicles;

[0073] Fault and Claims Data: Vehicle after-sales fault and claims maintenance data, as well as fault claims data throughout the vehicle's entire lifecycle;

[0074] Navigation electronic map data: Location service data for navigation electronic maps.

[0075] In one embodiment, the vehicle static data includes: VIN, product line, platform, powertrain type, emission type, and production date;

[0076] Driving behavior data includes: longitude, latitude, mileage, attendance rate, fuel consumption, and timestamps;

[0077] Fault and claim data includes: fault type, fault occurrence time, fault location, and major claim identifier;

[0078] Navigation electronic map data: parking point points (POIs), altitude, and ambient temperature data.

[0079] Step S2: Perform data cleaning and data preprocessing on the collected operation and maintenance status data. Based on the vehicle identification code, link and fuse the multi-source data corresponding to the same vehicle to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data.

[0080] Specifically, data cleaning and preprocessing are performed on the collected operation and maintenance status data, including:

[0081] A sliding window is used to dynamically clean driving behavior data, detecting and deleting duplicate data corresponding to the same vehicle identification number.

[0082] Step S3: Obtain the core driving data of repeat purchases and additional purchases by existing vehicle customers. Based on the core driving data of repeat purchases and additional purchases by existing vehicle customers, divide the repeat purchase intention scenarios and configure corresponding feature sets and quantitative judgment rules for each intention scenario.

[0083] Specifically, repurchase intention scenarios include: policy-related replacement scenarios, business expansion-related replacement scenarios, performance degradation-related replacement scenarios, and fault claim-related replacement scenarios.

[0084] Configure a corresponding feature set and quantization judgment rule for each intended scenario, specifically as follows:

[0085] Policy-driven scrapping and replacement scenarios: The characteristic set includes compliance with the old operating vehicle scrapping and replacement policy, passing the subsidy eligibility verification, and meeting the vehicle failure frequency standard;

[0086] Specifically, the following conditions must be met: The vehicle must meet the following requirements: service life ≥ 8 years / cumulative mileage ≥ 1 million kilometers; subsidy eligibility verification passed; vehicle malfunction frequency ≥ 2 times per quarter.

[0087] The quantitative judgment rules are as follows: the vehicle's off-line time is less than or equal to the policy-limited years, or the vehicle's cumulative mileage is greater than or equal to 1 million kilometers; the subsidy eligibility is passed; and the number of faults in the quarter is greater than 2.

[0088] Business expansion-driven additional purchase scenario: Its characteristic set includes mileage increase target, attendance rate target, and increase in the number of new loading and unloading points target;

[0089] In one embodiment, the specific measures include: monthly mileage increase ≥ 25%; attendance rate ≥ 85%; and monthly increase in the number of new loading and unloading points ≥ 60%.

[0090] The quantitative judgment rules are as follows: mileage increase ≥ 25% for two consecutive months; attendance rate = attendance days (daily mileage ≥ 20km) / total days × 100% ≥ 85%; increase in new loading and unloading points ≥ 60%;

[0091] The attendance rate is calculated as follows: Attendance rate = Number of days attended / Total number of days × 100%, where the number of days attended is defined as the number of days when the daily mileage meets the preset mileage threshold.

[0092] Performance-degraded replacement scenarios: The characteristic set includes the proportion of fuel consumption increase conditions exceeding the standard, the corresponding model's cumulative mileage reaching the standard, and the vehicle not being scrapped under policy.

[0093] In one embodiment, the specific conditions are: fuel consumption increase conditions account for >85%; J6 model cumulative mileage >600,000 km / J7 model >700,000 km; and the vehicle is not a policy-mandated scrapped vehicle.

[0094] The quantitative judgment rules are as follows: the proportion of operating conditions in which the fuel consumption in the current month is higher than the average of the previous two months is greater than 85%; the cumulative mileage of the corresponding model reaches the preset threshold; and the vehicle is removed from the production line after the policy's scrapping limit.

[0095] Fault claim-based trade-in scenario: Its characteristic set includes major claims, service station stay time exceeding the standard, non-policy scrapping and performance degradation vehicles;

[0096] In one embodiment, the specific circumstances are: a major claim occurs; a single stay at a service station is ≥4 hours; or the vehicle is not scrapped due to policy reasons or performance degradation.

[0097] The quantitative judgment rules are as follows: the number of major claims per year is greater than or equal to 1; the number of times the single stay at the service station exceeds 4 hours is greater than or equal to 2; and customers whose characteristics overlap with those of the aforementioned performance degradation replacement scenario are excluded.

[0098] Step S4: Classify repeat purchase intention scenarios based on the three-dimensional data matrix to generate an initial customer lead pool;

[0099] Step S5: Based on the initial customer lead pool, perform data collaborative verification to obtain a valid customer lead pool;

[0100] Specifically, based on the initial customer lead pool, data collaborative verification is performed to obtain a valid customer lead pool, which includes:

[0101] For the business expansion and additional purchase scenarios in the initial customer lead pool, the new loading and unloading point is verified to be the actual vehicle operation station by combining navigation electronic map data;

[0102] Excluding false leads such as inflated mileage, verified leads are included in the pool of valid customer leads.

[0103] Step S6: Set corresponding priority weights for repeat purchase intention scenarios, and prioritize the leads in the effective customer lead pool based on the weights; perform dynamic model iteration at fixed intervals, and update the judgment rules and scenario weight coefficients corresponding to the policies in sync.

[0104] In one embodiment, setting a corresponding priority weight for repeat purchase intention scenarios includes:

[0105] Policy-driven replacement purchases take priority over business expansion-related additional purchases.

[0106] Purchases for business expansion have a higher priority than replacements for performance degradation.

[0107] Replacement of products with deteriorating performance has a higher priority than replacement of products with frequent malfunctions.

[0108] Step S7: Generate and output a standardized customer lead list based on the priority sorting results.

[0109] For scenarios involving repeat purchase intentions, set corresponding priority weights, specifically as follows:

[0110] The weighting for policy-driven replacement purchases is 0.3; the weighting for business expansion-driven purchases is 0.25; the weighting for performance-degraded replacement purchases is 0.15; and the weighting for high-frequency failure replacement purchases is 0.1.

[0111] The model is dynamically iterated on a fixed cycle, specifically on a calendar month basis. The content updated synchronously includes the threshold of the quantitative judgment rules corresponding to the policy and the priority weight coefficient of each repurchase intention scenario adjusted according to the actual conversion rate of the leads.

[0112] Among them, the threshold of the judgment rule and the scene weight coefficient are iteratively optimized at a fixed period. This can adapt to the dynamic adjustment of policy changes, market environment, vehicle structure and customer behavior, so that the customer lead recognition model has the ability to learn, adapt and be effective in the long term, and ensure the continuous stability of recognition accuracy.

[0113] Specifically, by collecting vehicle static data, driving behavior data, fault and claim data, and navigation electronic map data, and using the vehicle identification number as the unique identifier for correlation and fusion, a three-dimensional data matrix of static-operation-after-sales is constructed. This achieves structured and standardized integration of vehicle lifecycle data, solves the problems of scattered data, single dimensions, and difficulty in creating a global profile in traditional customer lead mining, and provides a high-quality data foundation for subsequent accurate identification.

[0114] By categorizing existing customer repeat purchase and upgrade needs into four scenarios—policy obsolescence, business expansion, performance degradation, and fault claim—and configuring a unique feature set and quantitative judgment rules for each scenario, the system achieves a shift from experience-based judgment to data-driven, rule-quantifiable analysis. This significantly improves the objectivity, consistency, and reproducibility of customer lead identification and reduces subjective bias.

[0115] By conducting multi-dimensional data cross-validation on the initial lead pool, especially by combining navigation electronic map data to verify the authenticity of operations, false leads such as inflated mileage and fake operations are effectively eliminated, significantly improving the accuracy and conversion rate of the final customer retention leads and reducing the waste of marketing resources.

[0116] Figure 2 This is a structural diagram of a vehicle customer loyalty clue identification system based on multi-source data fusion provided by one or more embodiments of the present invention.

[0117] like Figure 2 As shown, it includes:

[0118] The module includes a data acquisition module, a data preprocessing module, a scenario segmentation module, an initial customer lead pool generation module, a data verification module, a priority sorting module, and a result output module.

[0119] The data acquisition module is used to collect the full operational and maintenance status data of the target vehicle; the full operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data; the full operational and maintenance status data corresponds to the vehicle identification number;

[0120] The data preprocessing module is used to perform data cleaning and data preprocessing on the collected operation and maintenance status data. Based on the vehicle identification code, it associates and merges multi-source data corresponding to the same vehicle to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data.

[0121] The scenario segmentation module is used to obtain the core driving data of repeat purchases and additional purchases by existing vehicle customers. Based on the core driving data of repeat purchases and additional purchases by existing vehicle customers, the module segments repeat purchase intention scenarios and configures corresponding feature sets and quantitative judgment rules for each intention scenario.

[0122] The initial customer lead pool generation module is used to classify repeat purchase intention scenarios based on a three-dimensional data matrix and generate an initial customer lead pool.

[0123] The data verification module is used to perform collaborative data verification based on the initial customer lead pool to obtain a valid customer lead pool.

[0124] The priority ranking module is used to set corresponding priority weights for repeat purchase intention scenarios, and to prioritize the leads in the effective customer lead pool based on the weights; the model is dynamically iterated at a fixed period to synchronously update the judgment rules and scenario weight coefficients corresponding to the policy.

[0125] The results output module is used to sort the results according to priority, generate a standardized list of customer leads, and output it.

[0126] It is worth noting that although only some basic functional modules are disclosed in this embodiment, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, what this embodiment intends to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules does not mean that the scope of protection of the claims of this invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above device is described separately according to its functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0127] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0128] Figure 3 This is a flowchart of a vehicle customer loyalty clue identification method based on multi-source data fusion, provided by a specific embodiment of the present invention.

[0129] like Figure 3 As shown, in one specific embodiment, the following steps are included:

[0130] Step A1: Multi-source data acquisition.

[0131] a) Vehicle static data: VIN, product series, platform, power type, emission type, and production date;

[0132] b) Vehicle-to-everything (V2X) dynamic data: longitude, latitude, mileage, attendance rate, fuel consumption, timestamp;

[0133] c) Fault and Claims Data: Fault type, fault occurrence time, fault location, major claim identifier;

[0134] d) BeiDou map data: parking point POI, altitude and ambient temperature data.

[0135] Step A2: Data cleaning and data preprocessing.

[0136] a) Dynamic data cleaning: A sliding window is used for data cleaning to detect and delete duplicate data for the same vehicle, ensuring data uniqueness;

[0137] b) Data association: Using VIN as the unique key, link vehicle static data, vehicle network dynamic data, fault data, claim data, and Beidou map data to form a three-dimensional data matrix of static-operation-after-sales.

[0138] Step A3: Construct a repeat purchase classification model driven by existing scenarios.

[0139] Based on the "Implementation Rules for the Scrapping and Renewal of Old Operating Freight Vehicles in 2025" and customer needs under the competition for existing stock, we divide the repurchase scenarios into 4 categories and design a combined judgment logic of core operational characteristics and mathematical judgment rules.

[0140] Repeat purchase scenarios include: policy-related replacement scenarios, business expansion-related additional purchase scenarios, performance degradation-related replacement scenarios, and fault claim-related replacement scenarios.

[0141] Step A4: Data Collaboration Verification.

[0142] Operational authenticity verification: For additional purchase leads due to business expansion, combine Beidou parking point POIs to confirm that the new loading and unloading points are actual operating stations, not temporary stops, to avoid mileage inflation caused by short-term orders.

[0143] Step A5: Prioritizing and dynamically iterating clues.

[0144] a) Priority weight design: Policy-driven scrapping and replacement type (weight 0.3) > Business expansion type additional purchase (weight 0.25) > Performance degradation type replacement (weight 0.15) > High frequency failure replacement type (weight 0.1);

[0145] b) Dynamic iteration: Two items are updated monthly: ① Policy rules, such as subsequent policy adjustments to the scrapping period, and the offline time threshold for scrapping and replacement products is updated synchronously; ② Weight coefficient, such as if the conversion rate of "performance degradation replacement" leads increases to 30% in a certain month, the weight is adjusted to 0.25.

[0146] Step A6: Output clues.

[0147] Output: Generate a "Customer Lead List" for four types of repeat purchase scenarios, including VIN, platform, product line, emissions, vehicle production date, repeat purchase type, and recommended action. Provided to marketing personnel for follow-up.

[0148] Figure 4 This is a block diagram of an electronic device for identifying vehicle customer loyalty clues based on multi-source data fusion, provided by one or more embodiments of the present invention.

[0149] like Figure 4As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0150] The memory stores a computer program that, when executed by the processor, causes the processor to perform steps of a vehicle customer loyalty clue identification method based on multi-source data fusion.

[0151] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform steps of a vehicle customer loyalty clue identification method based on multi-source data fusion.

[0152] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0153] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying vehicle customer retention clues based on multi-source data fusion, characterized in that, Includes the following steps: Collect full-state data on the operation and maintenance of the target vehicle; The operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data; the operational and maintenance status data is associated with the vehicle identification number (VIN). Data cleaning and preprocessing are performed on the collected operation and maintenance status data. Based on the vehicle identification code, the multi-source data corresponding to the same vehicle are associated and fused to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data. The core driving data for repeat purchases and additional purchases by existing vehicle customers is obtained. Based on the core driving data for repeat purchases and additional purchases by existing vehicle customers, repeat purchase intention scenarios are divided, and corresponding feature sets and quantitative judgment rules are configured for each intention scenario. Based on the aforementioned three-dimensional data matrix, repeat purchase intention scenarios are classified to generate an initial customer lead pool; Based on the initial customer lead pool, data collaborative verification is performed to obtain a valid customer lead pool; Set corresponding priority weights for repeat purchase intention scenarios, and prioritize leads in the effective customer lead pool based on the weights; perform dynamic model iteration at fixed intervals, and synchronously update the judgment rules and scenario weight coefficients corresponding to the policies. Based on the priority ranking results, a standardized list of customer leads is generated and output.

2. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 1, characterized in that, include: The static data includes: basic vehicle static attribute data, vehicle identification data, and vehicle production configuration data; The driving behavior data includes: real-time vehicle operating status time-series data and vehicle-to-everything (V2X) dynamic operating space-time data of connected vehicles. The fault and claim data includes: vehicle after-sales fault and claim maintenance data, as well as vehicle lifecycle fault claim data; The navigation electronic map data refers to the location service data of the navigation electronic map.

3. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 1, characterized in that, The repurchase intention scenarios include: policy-related replacement scenarios, business expansion-related replacement scenarios, performance degradation-related replacement scenarios, and fault claim-related replacement scenarios.

4. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 3, characterized in that, The priority weights set for repeat purchase intention scenarios include: The policy prioritizes replacement purchases for scrapped items over additional purchases for business expansion. Purchases for business expansion have a higher priority than replacements for performance degradation. Replacement of products with deteriorating performance has a higher priority than replacement of products with frequent malfunctions.

5. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 4, characterized in that, The specific steps for configuring a corresponding feature set and quantization judgment rule for each intended scenario are as follows: Policy-driven scrapping and replacement scenarios include: meeting the scrapping and replacement policy for old commercial vehicles, passing the subsidy eligibility verification, and meeting the vehicle's failure frequency requirements; The quantitative judgment rule is: the vehicle's off-line time is less than or equal to the policy-limited years, or the vehicle's cumulative mileage is greater than or equal to the policy-limited mileage; The subsidy eligibility has been approved; The number of quarterly failures exceeds the preset threshold; Business expansion-related additional purchase scenarios include: meeting targets for mileage increase, meeting targets for attendance rate, and meeting targets for the increase in the number of new loading and unloading points; The quantitative judgment rules are as follows: within a continuous time period, the mileage increase is greater than or equal to the first preset threshold, the attendance rate is greater than or equal to the second preset threshold, and the monthly increase of new loading and unloading points is greater than or equal to the third preset threshold. Performance-degradation-related replacement scenarios include: fuel consumption exceeding the standard in the proportion of operating conditions, the corresponding model's cumulative mileage reaching the standard, and vehicles not subject to policy-mandated scrapping. The quantitative judgment rule is: the percentage of operating conditions in which the fuel consumption in the current month is higher than the average of the previous two months is greater than the preset threshold; The cumulative mileage of the corresponding vehicle model has reached a preset threshold; The vehicle's production date is later than the policy's scrapping age limit; Fault-based replacement scenarios include: major claims, service station stays exceeding the limit, and vehicles not subject to policy-mandated scrapping or performance degradation. The quantitative determination rule is: the number of major claims in a year is greater than or equal to the preset number; The number of times the single stay at the service station exceeded the preset duration was greater than the preset number; Exclude customers whose characteristics overlap with those of the aforementioned performance degradation-related trade-in scenario.

6. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 1, characterized in that, The data cleaning and preprocessing performed on the collected operation and maintenance status data includes: A sliding window is used to dynamically clean driving behavior data, detecting and deleting duplicate data corresponding to the same vehicle identification number.

7. The vehicle customer retention clue identification method based on multi-source data fusion according to claim 1, characterized in that, The step of performing data collaborative verification based on the initial customer lead pool to obtain a valid customer lead pool specifically involves: For business expansion and additional purchase scenarios in the initial customer lead pool, the navigation electronic map data is used to verify that the new loading and unloading point is the actual operating station of the vehicle, eliminating false leads with inflated mileage, and the verified genuine leads are included in the valid customer lead pool.

8. A vehicle customer retention clue identification system based on multi-source data fusion, characterized in that, include: The module includes a data acquisition module, a data preprocessing module, a scenario segmentation module, an initial customer lead pool generation module, a data verification module, a priority sorting module, and a result output module. The data acquisition module is used to collect operational and maintenance status data of the target vehicle. The operational and maintenance status data includes: static data, driving behavior data, fault and claim data, and navigation electronic map data; the operational and maintenance status data is associated with the vehicle identification number (VIN). The data preprocessing module is used to perform data cleaning and data preprocessing on the collected operation and maintenance status data. Based on the vehicle identification code, it associates and merges multi-source data corresponding to the same vehicle to construct a three-dimensional data matrix of the target vehicle's static, operation and after-sales data. The scenario segmentation module is used to obtain the core driving data of repeat purchases and additional purchases by existing vehicle customers. Based on the core driving data of repeat purchases and additional purchases by existing vehicle customers, the module segments repeat purchase intention scenarios and configures corresponding feature sets and quantitative judgment rules for each intention scenario. The initial customer lead pool generation module is used to classify repeat purchase intention scenarios based on the three-dimensional data matrix and generate an initial customer lead pool. The data verification module is used to perform collaborative data verification based on the initial customer lead pool to obtain a valid customer lead pool. The priority ranking module is used to set corresponding priority weights for repeat purchase intention scenarios, and to prioritize the leads in the effective customer lead pool based on the weights; the model is dynamically iterated at a fixed period to synchronously update the judgment rules and scenario weight coefficients corresponding to the policy. The results output module is used to sort the results according to priority, generate a standardized list of customer leads, and output it.

9. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the vehicle customer retention clue identification method based on multi-source data fusion as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a vehicle customer tracing identification method based on multi-source data fusion as described in any one of claims 1-7.

Images