CN119624604A - Network marketing method based on intelligent matching of geographic data and new enterprise information - Google Patents
Network marketing method based on intelligent matching of geographic data and new enterprise information Download PDFInfo
- Publication number
- CN119624604A CN119624604A CN202411675572.XA CN202411675572A CN119624604A CN 119624604 A CN119624604 A CN 119624604A CN 202411675572 A CN202411675572 A CN 202411675572A CN 119624604 A CN119624604 A CN 119624604A
- Authority
- CN
- China
- Prior art keywords
- website
- matching
- business
- newly
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Remote Sensing (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a website marketing method based on intelligent matching geographic data and newly-opened business information, which comprises the steps of obtaining detailed information of business website and creating a basic snapshot information base, simultaneously obtaining and preprocessing newly-opened business information at fixed time, converting website position and business registration address into longitude and latitude coordinates, screening matching website sets conforming to conditions by using a HAVERSINE formula based on a preset matching distance range, clustering the matching website sets corresponding to stock enterprises by a K-Means clustering algorithm, combining newly-opened business characteristic matching cluster centers to obtain an optimal website list, presetting website scoring indexes, calculating website comprehensive scores according to the website scoring indexes, selecting the website with the highest score as the optimal matching website, pushing the newly-opened business information to a client manager corresponding to the optimal matching website for marketing activities, and re-matching if the information is returned. The method improves the accuracy and efficiency of website marketing and optimizes the service experience of newly opened enterprises.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a website marketing method based on intelligent matching of geographic data and information of a newly opened enterprise.
Background
In modern banking, marketing planning and customer relationship management are key to improving customer satisfaction and promoting business growth. With the development of financial science and technology, the marketing strategy of banks is gradually changed to intelligence and data driving.
An intelligent dispatch control method based on marketing tasks disclosed in China patent with publication number of CN115169859A comprises the steps of S1, obtaining real-time marketing tasks and client manager information, classifying the marketing tasks by an intelligent marketing model according to the client manager, calculating classification confidence of the marketing tasks, S2, judging whether the classification confidence of the marketing tasks exceeds a confidence threshold, if yes, directly dispatching the marketing tasks to a personal operation pool of the corresponding client manager, otherwise, going to step S3, judging whether the marketing tasks have a manager relationship, if yes, dispatching the marketing tasks to the personal operation pool of the corresponding client manager, otherwise, dispatching the marketing tasks to the personal operation pool of the corresponding client manager or receiving the marketing tasks from the personal operation pool of the client manager by the network public operation pool according to the received fine tuning operation information. Compared with the prior art, the invention has the advantages of reducing the dispatching cost, improving the dispatching efficiency, improving the intellectualization of task dispatching and the like, but the invention has the defect of considering geographical position and distance information in the business opportunity distribution process, which leads to the defect of the refinement degree of the business opportunity distribution, increases the risk of waste of the business opportunity and increases the difficulty and the cost of executing the tasks by a client manager and marketing personnel. In banking, geographic location and business information are critical to the successful execution of marketing tasks, and customer managers need to precisely distribute marketing tasks according to the geographic location of customers, the size of businesses, and business requirements to ensure the effectiveness and pertinence of marketing campaigns. Thus, there is a need for a website marketing method that takes into account geographic location and business information.
Disclosure of Invention
In order to solve the problems existing in the prior art, the application provides a website marketing method based on intelligent matching of geographic data and information of a newly opened enterprise.
The technical scheme of the application is as follows:
a website marketing method based on intelligent matching geographic data and newly opened enterprise information comprises the following steps:
acquiring information of a new enterprise of an external system at regular time, and carrying out data preprocessing on the information of the new enterprise to acquire a data set of the information of the new enterprise;
Based on a business website basic snapshot information base and a newly opened enterprise information data set, an intelligent matching algorithm is utilized to obtain an optimal matching website of the newly opened enterprise;
and pushing the newly opened enterprise information data set to a client manager of the corresponding best matching network point, and carrying out a corresponding marketing activity by the client manager.
As a preferred implementation mode of the invention, the business website related information comprises website numbers, website names, website positions, website types, website characteristic business types, website employee numbers, average waiting time of queuing machines for calling public business numbers, average number of public business transactions per day, number of public counters and number of foreign exchange counters, and the newly opened business information comprises legal representatives, establishment time, registration names, registration addresses, registration amounts, industry types and operation ranges.
As a preferred implementation mode of the invention, based on a business website basic snapshot information base and a newly opened enterprise information data set, the method for obtaining the best matching website of the newly opened enterprise by using an intelligent matching algorithm comprises the following specific steps:
converting the website position in the business website basic snapshot information base and the registration address in the newly opened business information data set into structured longitude and latitude coordinate data;
presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain matched clustering results, and obtaining an optimal network point list according to the matched clustering results, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
Calculating and obtaining a website scoring index corresponding to a website in an optimal website list according to a business website basic snapshot information base and a newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
And determining a website score index weight according to the user requirement, calculating website comprehensive scores according to the website score index weight and the website score index, and taking the website with the highest website comprehensive score as the best matching website.
In a preferred embodiment of the present invention, the site location in the basic snapshot information base of the business site and the registration address in the information data set of the newly opened business are converted into structured latitude and longitude coordinate data, specifically, the site location of the business site and the registration address of the newly opened business are converted into latitude and longitude coordinate data by using a geocoding service, and the converted latitude and longitude coordinate data is stored in a structured data table, wherein the latitude and longitude coordinate data comprises ID data, longitude and latitude.
The method comprises the steps of presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to a registration address, longitude and latitude coordinate data corresponding to a network point position and the matching distance range;
And calculating the geographical distance between the registration address of the newly opened enterprise and the site position of each business site by using a HAVERSINE formula, matching the site list of the newly opened enterprise in the current matching distance range, and if the matching result is empty, increasing the matching distance step until the maximum matching distance is reached, thereby obtaining a matching network site set.
As a preferred embodiment of the invention, the K-Means clustering algorithm is used for clustering the stock enterprises corresponding to the matching network point set, and the newly opened stock enterprise clustering center is used for carrying out characteristic matching to obtain a matching clustering result, which is specifically as follows:
Extracting business information of corresponding stock enterprises from the network points of the matching network point set, wherein the business information comprises enterprise scale, industry classification and registered capital;
Setting a range of K values, and finding out an optimal K value through multi-round clustering, wherein the multi-round clustering is specifically to cluster standardized business information by using a K-Means algorithm for each K value; comparing the profile coefficients under different K values, and selecting the K value with the maximum profile coefficient as the optimal clustering number K of the K-Means algorithm;
Taking the optimal clustering number K as a K value of a K-Means clustering algorithm, and carrying out clustering analysis on the standardized business information to obtain a plurality of clustering centers;
The method comprises the steps of calculating Euclidean distance between normalized business information of each newly opened enterprise and a clustering center of each stock enterprise, obtaining a matched clustering result, sequencing the matched clustering results in a sequence from small to large, distributing the newly opened enterprises to clusters corresponding to the clustering center with the forefront of the sequenced matched clustering result, extracting dot information corresponding to all the stock enterprises in the clusters, and obtaining an optimal dot list.
As a preferred embodiment of the invention, the node scoring index corresponding to the nodes in the optimal node list is obtained by calculation according to the business node basic snapshot information base and the newly opened business information data set, wherein the node scoring index comprises busyness of public business, distance priority and stock business matching priority, and specifically comprises the following steps:
According to the average waiting time of queuing machines in a basic snapshot information base of business network points for calling public service, the daily handling quantity of public service and the expressions of time length factors, service quantity factors and counter quantity factors obtained for the number of public counters, and according to the time length factors, the service quantity factors and the counter quantity factors, calculating the busyness of the public service, and expressing the busyness of the public service as follows in the formula:
For public service busyness= (average waiting time of queuing machine for public service number/maximum acceptable waiting time) ×ω 1 + (daily number for public service/maximum daily number for public service) ×ω 2 + (1/daily number for public counter) ×ω 3;
wherein omega 1、ω2 and omega 3 are weights corresponding to a time length factor, a service quantity factor and a counter quantity factor respectively, wherein the time length factor is expressed as average waiting time/maximum acceptable waiting time of a queuing machine for public service call numbers in a formula, the service quantity factor is expressed as daily average transacting quantity/maximum daily average transacting quantity of public service in a formula, and the counter quantity factor is expressed as 1/daily counter quantity in a formula;
Calculating the actual geographic distance between the registered address of the newly opened enterprise and longitude and latitude coordinate data corresponding to the business site position in the optimal site list, and carrying out standardization processing on the calculated actual geographic distance, wherein the actual geographic distance is expressed as follows in a formula:
Normalized distance = 1- (actual geographic distance/maximum acceptable distance);
Taking the standardized distance as a distance priority;
converting the matching clustering result into matching priority, and expressing the matching priority as follows:
matching priority = 1/(1+euclidean distance);
the net point composite score is expressed as:
Dot composite score = omega ' 1 + distance priority omega ' 2 + matching priority omega ' 3 for common traffic busyness;
Wherein ω '1、ω'2 and ω' 3 are weights corresponding to the common traffic busyness, the distance priority, and the matching priority, respectively.
As a preferred embodiment of the invention, the newly opened enterprise information data set is pushed to the client manager of the corresponding best matching network point, the client manager of the best matching network point selects whether to manually return the newly opened enterprise information data set according to the actual condition of the network point, if the newly opened enterprise information data set is returned, the newly opened enterprise is redistributed to the to-be-distributed list, and the best matching network points except the current best matching network point are re-matched.
The invention also provides a website marketing system based on intelligent matching geographic data and newly-opened enterprise information, which comprises a data acquisition module, a geographic position coding module, a distance calculation and website matching module and a result output module, wherein:
The data acquisition module is used for acquiring related information of business points from an API (application program interface) of an external system and creating a basic snapshot information base of the business points;
the geographic position coding module is used for converting the website position in the basic snapshot information base of the business website and the registered address in the information data set of the newly opened business into structured longitude and latitude coordinate data by using an API (application program interface) of the public map service, and transmitting the structured longitude and latitude coordinate data to the distance calculation and website matching module;
the distance calculation and dot matching module is internally provided with an intelligent matching algorithm for obtaining the best matching dot of a newly opened enterprise, and the intelligent matching algorithm is specifically:
presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain matched clustering results, and obtaining an optimal network point list according to the matched clustering results, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
Calculating and obtaining a website scoring index corresponding to a website in an optimal website list according to a business website basic snapshot information base and a newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
Determining a website scoring index weight according to the user requirement, calculating website comprehensive scores according to the website scoring index weight and the website scoring index, and taking the website with the highest website comprehensive score as the best matching website;
the result output module is used for pushing the newly opened enterprise information data set to a client manager of the corresponding best matching network point, and the client manager performs a corresponding marketing activity.
As a preferred implementation mode of the invention, the system is obtained by modularized design based on a JAVA micro-service architecture, a Quartz timing tool is arranged in the system, automatic work of a data acquisition module, a geographic position coding module, a distance calculation and lattice matching module and a result output module is realized by combining the Quartz timing tool with a big data cloud platform intelligent scheduling component, a data circulation link corresponding to the automatic work is constructed, and a tracking mechanism and operation blood-edge monitoring are realized based on the data circulation link.
Compared with the prior art, the invention has the beneficial effects that:
1) The invention provides a website marketing method based on intelligent matching geographic data and newly opened business information, which is characterized in that the business website and the newly opened business position information are converted into longitude and latitude coordinates, a HAVERSINE formula is used for calculating the distance, and a K-Means clustering algorithm is combined for characteristic matching, so that the matching accuracy of the newly opened business and the business website is greatly improved, the possible matching error in the traditional method is avoided, and the effectiveness of marketing activities is improved;
2) The invention provides a website marketing method based on intelligent matching geographic data and information of a newly opened enterprise, which calculates comprehensive scores according to busyness of public service, distance priority and stock business matching priority, selects the website with the highest comprehensive score as the best matching website, and dynamically adjusts according to feedback of a client manager, so that the allocation of website resources is optimized, the newly opened enterprise can quickly and accurately obtain the most suitable financial service, and meanwhile, ineffective resource waste is reduced;
3) The invention provides a website marketing method based on intelligent matching geographic data and newly-opened enterprise information, which directly pushes the newly-opened enterprise information data set to a client manager of the best matching website, and the client manager carries out marketing activities according to actual conditions, and redistributes and matches the information if the information is returned, so that the efficiency of the marketing activities is greatly improved, the time delay of information transmission and processing is reduced, and the newly-opened enterprise can obtain required services and support more quickly.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
The invention provides a website marketing method based on intelligent matching of geographic data and information of a newly opened enterprise.
Example 1
The embodiment provides a website marketing method based on intelligent matching of geographic data and newly-opened enterprise information, which comprises the following steps:
S1, acquiring business website related information and creating a basic snapshot information base of the business website;
s11, the related information of the business website comprises website numbers, website names, website positions, website types, website characteristic business types, website employee numbers, average waiting time of queuing machine for calling public business, daily transaction numbers for public business, public counter numbers and foreign exchange counter numbers;
S2, acquiring new enterprise information of an external system at fixed time, and preprocessing data of the new enterprise information to obtain a new enterprise information data set;
Acquiring new enterprise information from an external system at fixed time, wherein the new enterprise information is generally uploaded in batches in a file form (such as CSV, JSON and the like) and is analyzed into an internal system library table, and the new enterprise information comprises legal representatives, establishment time, registration names, registration addresses, registration amounts, industry types and operation ranges;
In order to ensure the quality and usability of the information of the new enterprise, the acquired information of the new enterprise is subjected to data preprocessing, wherein the data preprocessing comprises data standardization and data cleaning, and the data preprocessing comprises the following specific steps of:
S21, data standardization is used for ensuring the unification of the format of data and facilitating subsequent processing and analysis, and comprises field unification, data format conversion and data word segmentation, wherein:
The field unification comprises field naming unification and data type unification, wherein the field naming unification is to modify the naming of each field to be consistent, such as company name, registration address, establishment date and the like, the data type unification is to standardize the data types of all the fields, such as converting the establishment date field into unified date format (YYYY-MM-DD);
The data format conversion comprises address standardization, telephone number standardization and Code conversion, wherein the address standardization is used for standardizing address information and removing unnecessary symbols and redundant information, such as 'No. 123, ABC Street, city, province and ZIP Code', the telephone number standardization is used for unifying telephone number formats and removing blank spaces and specific characters, the Code conversion is used for converting codes (such as UTF-8 codes) in different formats into unified Code formats,
The data word segmentation comprises company name word segmentation and address word segmentation, wherein the company name word segmentation specifically comprises the steps of word segmentation processing of company names, keyword extraction and convenience in subsequent matching and analysis, and the address word segmentation specifically comprises the steps of word segmentation of address information, extraction of province, city, district, street and other information, and convenience in processing of geographic information;
s22, data cleaning is to remove invalid data and incomplete data, and ensures the quality of the data, and comprises missing value processing, outlier processing, duplicate removal processing and invalid data rejection, wherein:
the missing value processing includes missing value detection and missing value filling, specifically, detecting whether missing values exist in data, such as that some fields are null or invalid data, and filling the missing values by using a proper strategy, such as using a mean value, a median value or using a specific default value.
The abnormal value processing comprises abnormal value detection and abnormal value processing, specifically, whether abnormal values exist in data or not is detected, such as a date, an address and the like which are obviously unreasonable, and the abnormal values are processed, such as marked as invalid data or corrected;
the duplicate removal processing comprises duplicate data detection and duplicate data processing, specifically, detecting whether duplicate records exist in data, deleting the duplicate records, and ensuring the uniqueness of the data;
The invalid data rejection comprises invalid data detection and invalid data processing, specifically, whether obvious invalid data exists in the data or not is detected, such as enterprises with empty addresses and annotated and revoked addresses, and the invalid data is rejected, so that the cleanness and the usability of the data are ensured;
S23, storing the preprocessed newly opened enterprise information in a proper database or a data warehouse to obtain a newly opened enterprise information data set, and facilitating subsequent analysis and use, wherein the proper database selects a relational database, such as ORACLE, mySQL or PostgreSQL, and an index is created for common fields, wherein the common fields comprise company names, registered addresses and the like, so that the query efficiency is improved;
s3, based on the business website basic snapshot information base and the newly opened enterprise information data set, obtaining the best matching website of the newly opened enterprise by utilizing an intelligent matching algorithm;
s31, converting the site positions in the business site basic snapshot information base and the registered addresses in the newly opened business information data set into structured longitude and latitude coordinate data;
Converting the site location of the business site and the registration address of the newly opened business into longitude and latitude coordinate data by using a geocoding service, wherein the geocoding service comprises but is not limited to a Google map service API, a Google Maps API and Baidu Map API;
Preferably, the converted coordinates are verified, so that the analysis result of the geocoding service is ensured to be accurate, if the conversion fails, the address is marked as an invalid address, and an error log is recorded for subsequent processing;
s32, presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
Presetting a reasonable matching distance range according to service requirements and network point coverage, setting an initialization matching distance to be 1 km, setting a matching distance step length to be 500 meters and setting a maximum matching distance to be 5 km in the embodiment, calculating the geographical distance between a registration address of a newly opened enterprise and the network point position of each business network point by using a HAVERSINE formula or other geographical distance calculation methods, and matching a network point list of the newly opened enterprise in the current matching distance range, if the matching result is null, increasing the matching distance step length until the maximum matching distance is reached, thereby obtaining a matching network point set;
s33, clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain a matched clustering result, and obtaining an optimal network point list according to the matched clustering result, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
S331, extracting business information of corresponding stock enterprises (stock versus public clients) from the network points of the matched network point set, wherein the business information comprises enterprise scale, industry classification, registered capital and the like, and preferably, the extracted data also comprises network point IDs and corresponding public client information;
Performing standardization processing on the extracted business information by using z-score standardization or min-max standardization so as to eliminate dimension differences among different features;
S332, determining an optimal clustering number K by using a contour coefficient method specifically comprises the following steps:
Setting a range of K values, for example from 2 to 10, preparing for multi-round clustering to find out the optimal K value, clustering the standardized business information by using a K-Means algorithm for each K value, calculating and recording the contour coefficient corresponding to each K value;
the profile coefficients measure the compactness and the separation degree of the clustering result, the larger the value is, the better the clustering effect is, so that the profile coefficients under different K values are compared, and the K value with the largest profile coefficient is selected as the optimal clustering number K of the K-Means algorithm;
S333, clustering the matching network point set through a K-Means clustering algorithm specifically comprises the following steps:
Operating a K-Means clustering algorithm by using the optimal clustering number K, and carrying out clustering analysis on the standardized business information to obtain a plurality of clustering centers;
s334, carrying out standardized processing on business information (such as registered capital, industry classification and the like) of the newly opened enterprises, namely the characteristics of the newly opened enterprises, according to a basic snapshot information base of the business network points, so that the standardized processing is comparable with standardized data of the stock enterprises;
calculating the Euclidean distance between the standardized characteristics of each newly opened enterprise and the clustering center of each stock enterprise, obtaining a matched clustering result, and sequencing the matched clustering results in a sequence from small to large;
s34, calculating and obtaining a website scoring index corresponding to the website in the optimal website list according to the business website basic snapshot information base and the newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
s341, busyness of public service;
In the embodiment, the average waiting time length of the queuing machine for calling the number of the public business reflects the busyness of the node for the public business, the longer the average waiting time length is, the more the node for the public business is, the more the node for the business is, the efficiency of the business handling of a new opening enterprise at the node is affected, the more the average handling time length is, the more the node for the public business is, but the longer the waiting time is, the more the counter for the public business is, the number of the counter for the public business is, namely the number of the counter for the public business is directly affected, thereby reducing the waiting time;
In summary, the embodiment calculates the busyness of the public service in consideration of a time length factor, a service quantity factor and a counter quantity factor, wherein the time length factor is expressed as an average waiting time/a maximum acceptable waiting time of the queuing machine for the public service, the service quantity factor is expressed as a daily average transacting quantity/a maximum daily transacting quantity of the public service, and the counter quantity factor is expressed as 1/a counter quantity, so that the busyness of the public service is expressed as:
For public service busyness= (average waiting time of queuing machine for public service number/maximum acceptable waiting time) ×ω 1 + (daily number for public service/maximum daily number for public service) ×ω 2 + (1/daily number for public counter) ×ω 3;
Wherein omega 1、ω2 and omega 3 are weights corresponding to a time length factor, a service quantity factor and a counter quantity factor respectively, and the weights are set according to actual requirements;
s342, distance priority;
Obtaining a distance priority based on a physical distance from a newly opened enterprise to a business website, and influencing daily operation convenience of the enterprise by the physical distance, wherein preferably, the closer the distance is, the higher the convenience of business handling of the enterprise is generally;
Therefore, using HAVERSINE formula or other geographical distance calculation method, the actual geographical distance between the two is calculated according to the registered address of the newly opened business and the longitude and latitude coordinate data of the business point position in the best point list, and in order to convert the actual geographical distance into a uniform scoring range (such as between 0 and 1), in this embodiment, the calculated actual geographical distance is normalized, expressed as:
Normalized distance = 1- (actual geographic distance/maximum acceptable distance);
Preferably, in order to more comprehensively evaluate the convenience of the distance, when calculating the distance priority, traffic conditions around the business network points, such as the accessibility of public transportation facilities, road congestion conditions and the like, can be considered, and by taking the traffic conditions as influencing factors, a traffic condition score is allocated to each business network point according to the accessibility of public transportation, the traffic congestion conditions and the like, wherein the score range of the traffic condition score is between 0 and 1, and 1 represents the optimal traffic condition:
comprehensive distance priority = normalized distance x traffic status score;
S343, stock business matching priority;
In this embodiment, the matching clustering result in step S334 is converted into a priority score, specifically, the calculated euclidean distance, i.e. the similarity value is converted into a priority score, and the higher the score is, the higher the matching priority is expressed as:
matching priority = 1/(1+euclidean distance);
s35, determining a node score index weight according to the user requirement, calculating a node comprehensive score according to the node score index weight and the node score index, and taking the node with the highest node comprehensive score as the best matching node;
the net point composite score is expressed as:
Dot composite score = omega ' 1 + distance priority omega ' 2 + matching priority omega ' 3 for common traffic busyness;
Wherein ω '1、ω'2 and ω' 3 are weights corresponding to the public traffic busyness, the distance priority and the matching priority respectively;
the net point with the highest net point comprehensive score in the best net point list is used as the best matching net point;
S4, pushing the newly opened enterprise information data set to a client manager of the corresponding best matching network point automatically in a specified time period by using a Quartz timing tool, and enabling the client manager to conduct a corresponding marketing activity;
preferably, the client manager of the best matching network point can select to manually return the information data set of the newly opened enterprise, redistribute the newly opened enterprise to the list to be distributed, and re-match the rest of the best matching network points;
S5, constructing a data circulation link corresponding to the steps S1-S4, ensuring updating frequency and transmission timeliness of business opportunity data of a newly opened enterprise, realizing a tracking mechanism and operation blood margin monitoring according to the data circulation link, and tracking and monitoring a new customer data network point pushing method, wherein the tracking mechanism is specifically based on a big data cloud platform operation and maintenance center module, manually re-running an off-line calculation operation flow to be used for re-calculating data of a certain past time period, and re-executing a data processing task of a certain specific service date or batch before the system, and the operation blood margin monitoring is specifically used for monitoring the operation condition of upstream and downstream operations and rapidly positioning the external dependence of the operation.
Example 2
The embodiment provides an application system for configuring dynamic forms in a workflow engine based on conventions, wherein the system comprises a data acquisition module, a geographic position coding module, a distance calculation and lattice matching module and a result output module, wherein:
The data acquisition module is used for acquiring related information of business points from an API (application program interface) of an external system and creating a basic snapshot information base of the business points;
the geographic position coding module is used for converting the website position in the basic snapshot information base of the business website and the registered address in the information data set of the newly opened business into structured longitude and latitude coordinate data by using an API (application program interface) of the public map service, and transmitting the structured longitude and latitude coordinate data to the distance calculation and website matching module;
the distance calculation and dot matching module is internally provided with an intelligent matching algorithm for obtaining the best matching dot of a newly opened enterprise, and the intelligent matching algorithm is specifically:
presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain matched clustering results, and obtaining an optimal network point list according to the matched clustering results, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
Calculating and obtaining a website scoring index corresponding to a website in an optimal website list according to a business website basic snapshot information base and a newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
Determining a website scoring index weight according to the user requirement, calculating website comprehensive scores according to the website scoring index weight and the website scoring index, and taking the website with the highest website comprehensive score as the best matching website;
the result output module is used for pushing the newly opened enterprise information data set to a client manager of a corresponding best matching network point, and the client manager performs a corresponding marketing activity;
Preferably, the system in this embodiment is obtained by modularized design based on a JAVA micro-service architecture, a quantiz timing tool is arranged in the system, automatic work of a data acquisition module, a geographic position coding module, a distance calculation and mesh point matching module and a result output module is realized by combining the quantiz timing tool and a big data cloud platform intelligent scheduling component, a data circulation link corresponding to the automatic work is constructed, and a tracking mechanism and operation blood-edge monitoring are realized based on the data circulation link.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (10)
1. The website marketing method based on intelligent matching of geographic data and newly opened enterprise information is characterized by comprising the following steps:
acquiring information of a new enterprise of an external system at regular time, and carrying out data preprocessing on the information of the new enterprise to acquire a data set of the information of the new enterprise;
Based on a business website basic snapshot information base and a newly opened enterprise information data set, an intelligent matching algorithm is utilized to obtain an optimal matching website of the newly opened enterprise;
and pushing the newly opened enterprise information data set to a client manager of the corresponding best matching network point, and carrying out a corresponding marketing activity by the client manager.
2. The website marketing method based on intelligent matching geographic data and newly-opened business information according to claim 1, wherein the business website related information comprises website numbers, website names, website positions, website types, website feature business types, website employee numbers, average waiting time of queuing machines for calling public business numbers, average number of public business transactions per day, number of public counters and number of foreign exchange counters, and the newly-opened business information comprises legal representatives, establishment time, registration names, registration addresses, registration amounts, industry types and operation ranges.
3. The website marketing method based on intelligent matching geographic data and newly opened business information according to claim 2, wherein the method for obtaining the best matching website of the newly opened business by using the intelligent matching algorithm based on the business website basic snapshot information base and the newly opened business information data set is specifically as follows:
converting the website position in the business website basic snapshot information base and the registration address in the newly opened business information data set into structured longitude and latitude coordinate data;
presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain matched clustering results, and obtaining an optimal network point list according to the matched clustering results, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
Calculating and obtaining a website scoring index corresponding to a website in an optimal website list according to a business website basic snapshot information base and a newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
And determining a website score index weight according to the user requirement, calculating website comprehensive scores according to the website score index weight and the website score index, and taking the website with the highest website comprehensive score as the best matching website.
4. The website marketing method based on intelligent matching geographic data and newly-opened business information according to claim 3, wherein the website position in a basic snapshot information base of the business website and the registered address in the newly-opened business information data set are converted into structured longitude and latitude coordinate data, specifically, the website position of the business website and the registered address of the newly-opened business are converted into longitude and latitude coordinate data by using a geographic coding service, and the converted longitude and latitude coordinate data are stored in a structured data table, wherein the longitude and latitude coordinate data comprise ID data, longitude and latitude.
5. The website marketing method based on intelligent matching geographic data and newly opened enterprise information according to claim 4, wherein the preset matching distance range, and the obtaining of the matching website set according to the longitude and latitude coordinate data corresponding to the registration address, the longitude and latitude coordinate data corresponding to the website position and the matching distance range is specifically:
And calculating the geographical distance between the registration address of the newly opened enterprise and the site position of each business site by using a HAVERSINE formula, matching the site list of the newly opened enterprise in the current matching distance range, and if the matching result is empty, increasing the matching distance step until the maximum matching distance is reached, thereby obtaining a matching network site set.
6. The website marketing method based on intelligent matching geographic data and newly opened enterprises information according to claim 5, wherein the clustering method is characterized in that the matching network point set is used for clustering the corresponding stock enterprises, and the newly opened enterprises are used for characteristic matching in the clustering center to obtain matching clustering results, and the method is specifically as follows:
Extracting business information of corresponding stock enterprises from the network points of the matching network point set, wherein the business information comprises enterprise scale, industry classification and registered capital;
Setting a range of K values, and finding out an optimal K value through multi-round clustering, wherein the multi-round clustering is specifically to cluster standardized business information by using a K-Means algorithm for each K value; comparing the profile coefficients under different K values, and selecting the K value with the maximum profile coefficient as the optimal clustering number K of the K-Means algorithm;
Taking the optimal clustering number K as a K value of a K-Means clustering algorithm, and carrying out clustering analysis on the standardized business information to obtain a plurality of clustering centers;
The method comprises the steps of calculating Euclidean distance between normalized business information of each newly opened enterprise and a clustering center of each stock enterprise, obtaining a matched clustering result, sequencing the matched clustering results in a sequence from small to large, distributing the newly opened enterprises to clusters corresponding to the clustering center with the forefront of the sequenced matched clustering result, extracting dot information corresponding to all the stock enterprises in the clusters, and obtaining an optimal dot list.
7. The website marketing method based on intelligent matching geographic data and newly-opened enterprise information according to claim 5, wherein the website scoring index corresponding to the website in the best website list is obtained by calculation according to a basic snapshot information base of business website and a newly-opened enterprise information data set, and the website scoring index comprises busyness of public business, distance priority and matching priority of stock and business, specifically comprises the following steps:
According to the average waiting time of queuing machines in a basic snapshot information base of business network points for calling public service, the daily handling quantity of public service and the expressions of time length factors, service quantity factors and counter quantity factors obtained for the number of public counters, and according to the time length factors, the service quantity factors and the counter quantity factors, calculating the busyness of the public service, and expressing the busyness of the public service as follows in the formula:
For public service busyness= (average waiting time of queuing machine for public service number/maximum acceptable waiting time) ×ω 1 + (daily number for public service/maximum daily number for public service) ×ω 2 + (1/daily number for public counter) ×ω 3;
wherein omega 1、ω2 and omega 3 are weights corresponding to a time length factor, a service quantity factor and a counter quantity factor respectively, wherein the time length factor is expressed as average waiting time/maximum acceptable waiting time of a queuing machine for public service call numbers in a formula, the service quantity factor is expressed as daily average transacting quantity/maximum daily average transacting quantity of public service in a formula, and the counter quantity factor is expressed as 1/daily counter quantity in a formula;
Calculating the actual geographic distance between the registered address of the newly opened enterprise and longitude and latitude coordinate data corresponding to the business site position in the optimal site list, and carrying out standardization processing on the calculated actual geographic distance, wherein the actual geographic distance is expressed as follows in a formula:
Normalized distance = 1- (actual geographic distance/maximum acceptable distance);
Taking the standardized distance as a distance priority;
converting the matching clustering result into matching priority, and expressing the matching priority as follows:
matching priority = 1/(1+euclidean distance);
the net point composite score is expressed as:
Dot composite score = omega ' 1 + distance priority omega ' 2 + matching priority omega ' 3 for common traffic busyness;
Wherein ω '1、ω'2 and ω' 3 are weights corresponding to the common traffic busyness, the distance priority, and the matching priority, respectively.
8. The website marketing method based on intelligent matching geographic data and newly-opened business information according to claim 7, wherein the newly-opened business information data set is pushed to a client manager of a corresponding best matching website, the client manager of the best matching website selects whether to manually return the newly-opened business information data set according to the actual situation of the website, if the newly-opened business information data set is returned, the newly-opened business is redistributed to a list to be distributed, and the best matching website except the current best matching website is re-matched.
9. The website marketing system based on intelligent matching geographic data and newly-opened enterprise information is characterized by comprising a data acquisition module, a geographic position coding module, a distance calculation and website matching module and a result output module, wherein:
The data acquisition module is used for acquiring related information of business points from an API (application program interface) of an external system and creating a basic snapshot information base of the business points;
the geographic position coding module is used for converting the website position in the basic snapshot information base of the business website and the registered address in the information data set of the newly opened business into structured longitude and latitude coordinate data by using an API (application program interface) of the public map service, and transmitting the structured longitude and latitude coordinate data to the distance calculation and website matching module;
the distance calculation and dot matching module is internally provided with an intelligent matching algorithm for obtaining the best matching dot of a newly opened enterprise, and the intelligent matching algorithm is specifically:
presetting a matching distance range, and obtaining a matching network point set according to longitude and latitude coordinate data corresponding to the registration address, longitude and latitude coordinate data corresponding to the network point position and the matching distance range;
clustering the corresponding stock enterprises of the matched network point set through a K-Means clustering algorithm, and performing characteristic matching on the clustering centers of the stock enterprises of the newly opened enterprises to obtain matched clustering results, and obtaining an optimal network point list according to the matched clustering results, wherein the K-Means clustering algorithm determines an optimal clustering number K by using a contour coefficient method;
Calculating and obtaining a website scoring index corresponding to a website in an optimal website list according to a business website basic snapshot information base and a newly opened enterprise information data set, wherein the website scoring index comprises busyness of public business, distance priority and stock business matching priority;
Determining a website scoring index weight according to the user requirement, calculating website comprehensive scores according to the website scoring index weight and the website scoring index, and taking the website with the highest website comprehensive score as the best matching website;
the result output module is used for pushing the newly opened enterprise information data set to a client manager of the corresponding best matching network point, and the client manager performs a corresponding marketing activity.
10. The website marketing system based on intelligent matching geographic data and newly-opened enterprise information according to claim 9, wherein the system is obtained by modularized design based on a JAVA micro-service architecture, a Quartz timing tool is arranged inside the system, automatic work of a data acquisition module, a geographic position coding module, a distance calculation and website matching module and a result output module is realized by combining the Quartz timing tool with a big data cloud platform intelligent scheduling component, a data circulation link corresponding to the automatic work is constructed, and a tracking mechanism and operation blood-edge monitoring are realized based on the data circulation link.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411675572.XA CN119624604B (en) | 2024-11-21 | 2024-11-21 | Net point marketing method based on intelligent matching geographic data and newly opened enterprise information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411675572.XA CN119624604B (en) | 2024-11-21 | 2024-11-21 | Net point marketing method based on intelligent matching geographic data and newly opened enterprise information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119624604A true CN119624604A (en) | 2025-03-14 |
| CN119624604B CN119624604B (en) | 2025-09-23 |
Family
ID=94885938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411675572.XA Active CN119624604B (en) | 2024-11-21 | 2024-11-21 | Net point marketing method based on intelligent matching geographic data and newly opened enterprise information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119624604B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060161599A1 (en) * | 2004-10-19 | 2006-07-20 | Rosen James S | System and method for location based matching and promotion |
| US20080027841A1 (en) * | 2002-01-16 | 2008-01-31 | Jeff Scott Eder | System for integrating enterprise performance management |
| WO2009145472A1 (en) * | 2008-04-05 | 2009-12-03 | 주식회사 타스테크 | System and method of calculating the location suitability index and sales rank of a small business shop |
| CN113409081A (en) * | 2021-06-16 | 2021-09-17 | 建信金融科技有限责任公司 | Information processing method and device |
| CN115169859A (en) * | 2022-06-30 | 2022-10-11 | 交通银行股份有限公司 | Intelligent distribution control method based on marketing task |
-
2024
- 2024-11-21 CN CN202411675572.XA patent/CN119624604B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080027841A1 (en) * | 2002-01-16 | 2008-01-31 | Jeff Scott Eder | System for integrating enterprise performance management |
| US20060161599A1 (en) * | 2004-10-19 | 2006-07-20 | Rosen James S | System and method for location based matching and promotion |
| WO2009145472A1 (en) * | 2008-04-05 | 2009-12-03 | 주식회사 타스테크 | System and method of calculating the location suitability index and sales rank of a small business shop |
| CN113409081A (en) * | 2021-06-16 | 2021-09-17 | 建信金融科技有限责任公司 | Information processing method and device |
| CN115169859A (en) * | 2022-06-30 | 2022-10-11 | 交通银行股份有限公司 | Intelligent distribution control method based on marketing task |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119624604B (en) | 2025-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459985B (en) | Identification information processing method and device | |
| US8768914B2 (en) | System and method for searching and matching databases | |
| CN108876034B (en) | Improved Lasso + RBF neural network combination prediction method | |
| CN119444363B (en) | Automatic order dispatching method and system for hotels | |
| CN113641654B (en) | Marketing treatment rule engine method based on real-time event | |
| CN120087691A (en) | A housekeeping platform order distribution system based on big data analysis | |
| CN117829494A (en) | Intelligent service heat line work order identification and distribution platform based on domain knowledge graph | |
| CN113627997A (en) | Data processing method, device, electronic device and storage medium | |
| CN119962934A (en) | A dynamic inventory scheduling method and system based on ERP system | |
| CN119624604B (en) | Net point marketing method based on intelligent matching geographic data and newly opened enterprise information | |
| US20210117886A1 (en) | Data Preparation Method Related to Data Utilization and Data Utilization System | |
| CN115935076A (en) | Travel service information pushing method and system based on artificial intelligence | |
| CN115293792A (en) | A screening system to improve the success rate of business expansion | |
| CN113672800A (en) | Recommended method and storage medium for real-name authentication of natural person users | |
| CN109919811B (en) | Insurance agent culture scheme generation method based on big data and related equipment | |
| KR102790498B1 (en) | System and method for collecting business information and computer program for the same | |
| CN119474234B (en) | Data element processing method, device, electronic device and storage medium | |
| CN119336958B (en) | Method, device, equipment and medium for screening data items of railway freight data | |
| CN112199583B (en) | Network public opinion information intelligent processing method and system based on multi-rule association analysis | |
| CN114661779A (en) | Computing and analysis methods, systems and storage media for specific persons | |
| CN118798510A (en) | Work order scheduling method, device, equipment and medium | |
| CN118333559A (en) | Business process automatic circulation method based on transducer model | |
| CN120011358A (en) | A method and device for building a customer information model in the insurance industry | |
| CN120410664A (en) | Order processing flow monitoring method, device, equipment and storage medium | |
| CN120047002A (en) | Method and system for managing endowment dining-assisting platform based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |