After-sales cooperation point recommendation method based on big data mining

Abstract

The invention provides an after-sales cooperation point recommendation method based on big data mining, and the method comprises the following steps: S1, obtaining the external repair data and the address data of a special shop of all vehicles, and carrying out the preprocessing of the external repair data and the address data of the special shop, and obtaining the vehicle information, the position information of an external repair point, the shop name information, and the time information of external repair; s2, clustering the position information of each exterior repair point by adopting DBSCAN (Density Based Spatial Clustering of Applications with Noise) to obtain candidate exterior repair points; s3, using a GeoHash algorithm to calculate the distance between the candidate exterior repair point and the special shop; s4, deducing travel habits based on the travel data of the vehicle owner, and obtaining resident point data of the vehicle owner; selecting an optimal after-sales service cooperation shop address throughout the country by combining the specific distribution of the exterior repair points and the resident points of the vehicle owners; moreover, the method can recommend the after-sales cooperation store address of each region for the special stores under the jurisdiction of the OEM in real time, greatly saves the operation cost of a company, and improves the construction efficiency of the special stores.

Description

Technical Field

[0001] The present invention relates to the technical field of big data processing, and more specifically, to a method for recommending after-sales cooperation points based on big data mining. Background Art

[0002] After-sales service is one of the main sources of revenue for automobile original equipment manufacturers (OEMs). As of 2021, after-sales maintenance revenue has exceeded OEM, accounting for 60% of total revenue. For many car owners, when their vehicles need after-sales services such as repairs and maintenance, since the after-sales service agencies (franchise stores / 4S stores) under the jurisdiction of the OEM are far away and costly, they will choose auto repair shops that are closer and more affordable to maintain their vehicles. Therefore, OEMs will choose to cooperate with appropriate franchise stores or automobile repair and maintenance agencies that are not under their jurisdiction to provide car owners with high-quality after-sales services, improve user experience, and increase revenue from after-sales service business.

[0003] The selection of cooperative after-sales organizations directly affects the revenue of OEMs in after-sales business. Currently, the selection of cooperative organizations is mainly determined by business personnel through on-site inspections, information collection, and value assessment, which consumes a lot of manpower costs and cannot guarantee the comprehensiveness and timeliness of information, resulting in the inability to make timely and effective response plans to some opportunities and changes. Therefore, the selection of cooperative after-sales organizations is an urgent problem for OEMs to solve. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for recommending after-sales cooperation points based on big data mining, which can save the company's operating costs and improve the efficiency of cooperative store construction, in view of the shortcomings of the above-mentioned technical solutions.

[0005] The present invention provides a method for recommending after-sales cooperation points based on big data mining, and the method comprises the following steps:

[0006] S1, obtaining the external repair data and exclusive store address data of all vehicles, and pre-processing the external repair data and exclusive store address data to obtain vehicle information, location information of the external repair point, store name information and external repair time information;

[0007] S2, using DBSCAN to cluster the location information of each external repair point to obtain candidate external repair points;

[0008] S3, using GeoHash algorithm to calculate the distance between the candidate external repair point and the franchise store;

[0009] S4, inferring travel habits based on the owner's travel data and obtaining the owner's permanent location data;

[0010] S5, recommending suitable after-sales business cooperation points based on the data of candidate repair points and the car owner's regular locations and the number of repairmen at the candidate repair points.

[0011] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S1 includes the following steps:

[0012] S11, splitting the location information of the external repair points into longitude columns and latitude columns, removing duplicate longitudes and latitudes and missing longitudes and latitudes, converting the longitudes and latitudes in different coordinate systems into the same coordinate system, and deleting the data that is not in the country according to the longitude and latitude positions;

[0013] S12, selecting the repair point data whose repair time information is between 9 am and 6 pm, and the number of repairs of the single vehicle is less than 10 times per year.

[0014] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S2 includes the following steps:

[0015] S21, calculating the minimum distance between the external repair points by the distance between the longitude and latitude, wherein the distance calculation formula between the external repair points is: dis(x i , x j ,y i ,y j )=R×arcos[cosy i ×cosy j ×cos(x i -x j )+siny i ×siny j ], where R represents the radius of the earth, (x i , x j ) and (y i ,y j ) correspond to two different longitudes and latitudes, so the distance between the longitudes and latitudes of points i and j is expressed as dis(x i , x j ,y i ,y j ).

[0016] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S3 includes the following steps:

[0017] S31, use GeoHash algorithm to encode the longitude and latitude of the external repair point to obtain 9 rectangular areas, which are represented by wtw37p, wtw37r, wtw37x, wtw37n, wtw37q, wtw37w, wtw37j, wtw37m, and wtw37t respectively. The middle area wtw37q represents the area where the candidate external repair point is located.

[0018] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S3 also includes the following steps:

[0019] S32, calculate the distance between the franchise stores and the candidate external repair points in the 9 rectangular areas, and use the distance calculation formula between external repair points dis(x i , x j ,y i ,y j )=R×arcos[cosy i ×cosy j ×cos(x i -x j )+siny i ×siny j ] is calculated. If the distance between the franchise store and the candidate repair point is less than or equal to 20km, the candidate repair point will be deleted and the remaining repair points will be used as candidate repair point data.

[0020] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S4 includes the following steps:

[0021] S41, extract the driving records of each vehicle within 60 days, and filter out the starting latitude and longitude of the first driving record of each day, generate a set of the starting latitude and longitude of each vehicle, and use (lng, lat) to represent the latitude and longitude of the first trip of the vehicle every day, where lng represents longitude and lat represents latitude. The set of the starting latitude and longitude of the trip of the vehicle within 60 days is represented as L n (lng, lat)={(lng, lat)1, (lng, lat)2...(lng, lat) t}, where n represents the nth vehicle and t represents the tth day.

[0022] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, the step S4 further includes the following steps:

[0023] S42, for each vehicle’s longitude and latitude set L n (lng, lat) performs DBSCAN clustering and finds the clustering point C of the vehicle n (L) = {L n，1 , L n,2 ...Ln, b}, where L n,b represents the bth cluster of vehicle n, that is, the longitude and latitude set of the clustering points, and L n,b ∈L n .

[0024] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, the step S4 further includes the following steps:

[0025] S43, select C n (L) The gathering point data with the highest frequency or a frequency greater than 10 in the set is used as the permanent point data of the car owner.

[0026] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, step S5 includes the following steps:

[0027] S51, calculating the distance between the candidate exterior repair point and the surrounding permanent points of the vehicle owner, using the GeoHash algorithm to perform GeoHash encoding on the candidate exterior repair point, and dividing the area where the candidate exterior repair point is located into 8 rectangular areas around it, and calculating the distance between the permanent points falling in the 8 rectangular areas and the candidate exterior repair point area and the candidate exterior repair point;

[0028] S52, counting the number of external repairmen at the candidate external repair point, and calculating the number of permanent points around the candidate external repair point based on the GeoHash algorithm.

[0029] In the after-sales cooperation point recommendation method based on big data mining described in the present invention, the step S5 further includes the following steps:

[0030] S53, recommending cooperative stores based on the distance between the candidate repair points and the permanent points and the number of repair staff, sorting the distances from near to far and the number of repair staff from many to few, and selecting the top 5 candidate repair points in the area for recommendation.

[0031] The after-sales cooperation point recommendation method based on big data mining of the present invention selects the best after-sales business cooperation store addresses in the whole country by combining the specific distribution of external repair points and car owner's permanent locations, and can recommend the addresses of after-sales cooperation stores in various regions to the OEM's franchise stores in real time, which greatly saves the company's operating costs and improves the efficiency of franchise store construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a flow chart of an embodiment of a method for recommending after-sales cooperation points based on big data mining of the present invention;

[0033] Figure 2 These are 9 rectangular area diagrams in an embodiment of the after-sales cooperation point recommendation method based on big data mining of the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] like Figure 1 , which is a flow chart of an embodiment of a method for recommending after-sales cooperation points based on big data mining according to the present invention. A method for recommending after-sales cooperation points based on big data mining is provided, comprising the following steps:

[0037] In step S1, the repair data and store address data of all vehicles are obtained, and the repair data and store address data are pre-processed to obtain vehicle information, location information of the repair point, store name information and repair time information;

[0038] In step S2, DBSCAN is used to cluster the location information of each repair point to obtain candidate repair points; the distribution of the repair points is analyzed by clustering the GPS data in the repair points. At the same time, in order to ensure the revenue of the after-sales business of the franchise store, the cluster points that are more than 20 km away from the franchise store are selected as candidate repair points.

[0039] In step S3, the distance between the candidate repair point and the franchise store is calculated using the GeoHash algorithm; in step S4, the travel habits are inferred based on the owner's travel data to obtain the owner's permanent location data;

[0040] In step S5, a suitable after-sales service cooperation point is recommended based on the candidate repair point and the vehicle owner's permanent location data and the number of repairers at the candidate repair point.

[0041] In one embodiment, the step S1 comprises the following steps:

[0042] In step S11, the location information of the external repair point is split into longitude columns and latitude columns, and then the duplicate longitudes and latitudes are removed, and the missing longitudes and latitudes are converted to the same coordinate system after removal, and then the data outside the country is deleted according to the longitude and latitude positions;

[0043] In step S12, the repair point data whose repair time information is between 9 am and 6 pm is selected, and the number of repairs of a single vehicle is less than 10 times per year.

[0044] In one embodiment, the step S2 comprises the following steps:

[0045] In step S21, the minimum distance between the external repair points is calculated by the distance between the longitude and latitude, wherein the distance calculation formula between the external repair points is: dis(x i , x j ,y i ,y j )=R×arcos[cosy i ×cosy j ×cos(x i -x j )+siny i ×siny j ], where R represents the radius of the earth, (x i , x j ) and (y i ,y j ) correspond to two different longitudes and latitudes, so the distance between the longitudes and latitudes of points i and j is expressed as dis(x i , x j ,y i ,y j ).

[0046] The specific step S2 also includes setting the minimum sample size, that is, the number of external repair points in the class. In the same category, the minimum value of the total number of sample points is set. In this application, the setting in DBSCAN is 10, that is, there are at least 10 points in a class. The result of clustering the location information of each external repair point by DBSCAN is the new external repair point data, with one major category as a maintenance point. Delete noise points, that is, outlier external repair points. In the result of DBSCAN clustering the location information of each external repair point, the point with label -1 is a noise point and needs to be removed. The purpose of clustering external repair points using DBSCAN is to reduce data redundancy; the purpose of deleting noise points, that is, outlier external repair points, is to reduce outliers.

[0047] In one embodiment, the step S3 comprises the following steps:

[0048] In step S31, the GeoHash algorithm is used to encode the longitude and latitude of the external repair point to obtain 9 rectangular areas, which are represented by wtw37p, wtw37r, wtw37x, wtw37n, wtw37q, wtw37w, wtw37j, wtw37m, and wtw37t respectively, among which the middle area wtw37q represents the area where the candidate external repair point is located.

[0049] In one embodiment, the step S3 further includes the following steps:

[0050] In step S32, the distance between the franchised stores and the candidate repair points in the 9 rectangular areas is calculated, and the distance calculation formula between the repair points dis(x i , x j ,y i ,y j )=R×arcos[cosy i ×cosy j ×cos(x i -x j )+siny i ×siny j ] is calculated. If the distance between the franchise store and the candidate repair point is less than or equal to 20km, the candidate repair point will be deleted and the remaining repair points will be used as candidate repair point data.

[0051] Specifically, cluster points that are more than 20 km away from franchise stores are selected as candidate repair points. The purpose of this is to ensure the after-sales business revenue of the franchise stores themselves. Due to the large number of franchise stores and candidate points, calculating the distance one by one consumes more resources and time. In order to improve the calculation efficiency, the GeoHash algorithm is used to calculate the distance between the franchise stores and the candidate points.

[0052] Among them, GeoHash is a spatial address encoding method that can encode two-dimensional spatial latitude and longitude data into a string. Figure 2 All points in the 9 rectangular areas wtw37p, wtw37r, wtw37x, wtw37n, wtw37q, wtw37w, wtw37j, wtw37m, wtw37t share the same GeoHash string. In this way, all the addresses of the franchise stores located in a certain area can be cached with the GeoHash of the area as the key, and the middle area wtw37q represents the area where the candidate point is located.

[0053] In one embodiment, the step S4 comprises the following steps:

[0054] In step S41, the driving records of each vehicle within 60 days are extracted, and the latitude and longitude of the starting point of the first driving record of each day are screened out to generate a set of latitude and longitude of the driving starting point of each vehicle. The latitude and longitude of the first trip of the vehicle every day are represented by (lng, lat), where lng represents longitude and lat represents latitude. The set of latitude and longitude of the starting point of the trip of the vehicle within 60 days is represented as L n(lng, lat)={(lng, lat)1, (lng, lat)2...(lng, lat) t}, where n represents the nth vehicle and t represents the tth day.

[0055] In one embodiment, the step S4 further includes the following steps:

[0056] In step S42, the longitude and latitude set L of each vehicle is n (lng, lat) performs DBSCAN clustering and finds the clustering point C of the vehicle n (L) = {L n，1 , L n,2 …L n，b}, where L n,b represents the bth cluster of vehicle n, that is, the longitude and latitude set of the clustering points, and L n，b ∈L n .

[0057] In one embodiment, the step S4 further includes the following steps:

[0058] In step S43, select C n (L) The gathering point data with the highest frequency or a frequency greater than 10 in the set is used as the permanent point data of the car owner.

[0059] In one embodiment, step S5 comprises the following steps:

[0060] In step S51, the distance between the candidate exterior repair point and the surrounding permanent points of the vehicle owner is calculated, the candidate exterior repair point is GeoHash encoded using the GeoHash algorithm, and 8 rectangular areas are divided around the area where the candidate exterior repair point is located as the center, and the distance between the permanent points falling in the 8 rectangular areas and the candidate exterior repair point area and the candidate exterior repair point is calculated;

[0061] In step S52, the number of people who have repaired the candidate repair point is counted, and the number of permanent points around the candidate repair point is calculated based on the GeoHash algorithm.

[0062] In one embodiment, the step S5 further includes the following steps:

[0063] In step S53, cooperative stores are recommended based on the distance between the candidate repair points and the permanent points and the number of repair people. The distances are sorted from near to far, and the number of people is sorted from many to few. The top five candidate repair points in the area are selected for recommendation.

[0064] This application identifies the best cooperative store locations across the country by combining the specific distribution of external repair shops and users, and can recommend cooperative store locations in various regions to OEMs in real time, greatly saving the company's operating costs and improving the efficiency of cooperative store construction.

[0065] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0067] Therefore, the above is only a preferred specific implementation mode of the present invention, and the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for recommending after-sales cooperation points based on big data mining, characterized in that: The method comprises the following steps: S1, obtaining the external repair data and exclusive store address data of all vehicles, and pre-processing the external repair data and exclusive store address data to obtain vehicle information, location information of the external repair point, store name information and external repair time information; S2, using DBSCAN to cluster the location information of each external repair point to obtain candidate external repair points; S3, using GeoHash algorithm to calculate the distance between the candidate external repair point and the franchise store; S4, inferring travel habits based on the owner's travel data and obtaining the owner's permanent location data; S5, recommending suitable after-sales business cooperation points based on the data of candidate repair points and the car owner's regular locations and the number of repairmen at the candidate repair points.

2. The after-sales cooperation point recommendation method based on big data mining according to claim 1 is characterized in that: The step S1 comprises the following steps: S11, splitting the location information of the external repair points into longitude columns and latitude columns, removing duplicate longitudes and latitudes and missing longitudes and latitudes, converting the longitudes and latitudes in different coordinate systems into the same coordinate system, and deleting the data that is not in the country according to the longitude and latitude positions; S12, selecting the repair point data whose repair time information is between 9 am and 6 pm, and the number of repairs for a single vehicle is less than 10 times per year.

3. The after-sales cooperation point recommendation method based on big data mining according to claim 2 is characterized in that: The step S2 comprises the following steps: S21, calculating the minimum distance between the external repair points by the distance between the longitude and latitude, wherein the distance calculation formula between the external repair points is: dis(x i ,x j ,y i ,y j )=R×arcos[cos y i ×cos y j ×cos(x i -x j )+sin y i ×sin y j ], where R represents the radius of the earth, (x i ,x j ) and (y i ,y j ) correspond to two different longitudes and latitudes, so the distance between the longitudes and latitudes of points i and j is expressed as dis(x i ,x j ,y i ,y j ).

4. The after-sales cooperation point recommendation method based on big data mining according to claim 3 is characterized in that: The step S3 comprises the following steps: S31, use GeoHash algorithm to encode the longitude and latitude of the external repair point to obtain 9 rectangular areas, which are represented by wtw37p, wtw37r, wtw37x, wtw37n, wtw37q, wtw37w, wtw37j, wtw37m, and wtw37t respectively. The middle area wtw37q represents the area where the candidate external repair point is located.

5. The after-sales cooperation point recommendation method based on big data mining according to claim 4 is characterized in that: The step S3 further comprises the following steps: S32, calculate the distance between the franchise stores and the candidate external repair points in the 9 rectangular areas, and use the distance calculation formula between external repair points dis(x i ,x j ,y i ,y j )=R×arcos[cos y i ×cos y j ×cos(x i -x j )+sin y i ×sin y j ] is calculated. If the distance between the franchise store and the candidate repair point is less than or equal to 20km, the candidate repair point will be deleted and the remaining repair points will be used as candidate repair point data.

6. The after-sales cooperation point recommendation method based on big data mining according to claim 5 is characterized in that: The step S4 comprises the following steps: S41, extract the driving records of each vehicle within 60 days, and filter out the starting latitude and longitude of the first driving record of each day, generate a set of the starting latitude and longitude of each vehicle, and use (lng, lat) to represent the latitude and longitude of the first trip of the vehicle every day, where lng represents longitude and lat represents latitude. The set of the starting latitude and longitude of the trip of the vehicle within 60 days is represented as L n (lng,lat)={(lng,lat)1,(lng,lat)2…(lng,lat) t }, where n represents the nth vehicle and t represents the tth day.

7. The after-sales cooperation point recommendation method based on big data mining according to claim 6 is characterized in that: The step S4 further comprises the following steps: S42, for each vehicle’s longitude and latitude set L n (lng, lat) performs DBSCAN clustering and finds the clustering point C of the vehicle n (L) = {L n,1 ,L n,2 …L n,b }, where L n,b represents the bth cluster of vehicle n, that is, the longitude and latitude set of the clustering points, and L n,b ∈L n .

8. The after-sales cooperation point recommendation method based on big data mining according to claim 7 is characterized in that: The step S4 further comprises the following steps: S43, select C n (L) The gathering point data with the highest frequency or a frequency greater than 10 in the set is used as the permanent point data of the car owner.

9. The after-sales cooperation point recommendation method based on big data mining according to claim 8 is characterized in that: The step S5 comprises the following steps: S51, calculating the distance between the candidate exterior repair point and the surrounding permanent points of the vehicle owner, using the GeoHash algorithm to perform GeoHash encoding on the candidate exterior repair point, and dividing the area where the candidate exterior repair point is located into 8 rectangular areas around it, and calculating the distance between the permanent points falling in the 8 rectangular areas and the candidate exterior repair point area and the candidate exterior repair point; S52, counting the number of external repairmen at the candidate external repair point, and calculating the number of permanent points around the candidate external repair point based on the GeoHash algorithm.

10. The after-sales cooperation point recommendation method based on big data mining according to claim 8, characterized in that: The step S5 further comprises the following steps: S53, recommending cooperative stores based on the distance between the candidate repair points and the permanent points and the number of repair staff, sorting the distances from near to far and the number of repair staff from many to few, and selecting the top 5 candidate repair points in the area for recommendation.

Images