CN117853152B - Business marketing data processing system based on multiple channels - Google Patents
Business marketing data processing system based on multiple channels Download PDFInfo
- Publication number
- CN117853152B CN117853152B CN202410262538.3A CN202410262538A CN117853152B CN 117853152 B CN117853152 B CN 117853152B CN 202410262538 A CN202410262538 A CN 202410262538A CN 117853152 B CN117853152 B CN 117853152B
- Authority
- CN
- China
- Prior art keywords
- data
- multidimensional
- service data
- preference
- service
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 claims description 20
- 238000013507 mapping Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 230000006835 compression Effects 0.000 description 4
- 238000007906 compression Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a business marketing data processing system based on multiple channels, which relates to the technical field of data processing.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a business marketing data processing system based on multiple channels.
Background
Business marketing data processing refers to the process of collecting, collating, analyzing and applying data related to marketing business. This includes collecting various relevant data such as customer information, market trends, sales data, competitor intelligence, etc., and processing with tools and methods so that the business can better make marketing decisions and implement marketing strategies.
The prior business marketing data technology has the following defects:
data quality: the quality of the data may affect the accuracy and reliability of the analysis. Incomplete, inaccurate data may cause errors in the analysis results, thereby affecting the accuracy of the decision.
Data integration and standardization: integrating data from different sources and normalizing the data is a challenge. The format and structure of the data in the different systems may be different, requiring a great deal of effort to integrate and transform the data.
Data overload: the large amount of data can complicate analysis and sometimes even overload the information, making it difficult to extract useful information from the large amount of data.
Therefore, how to improve the processing efficiency of the business marketing data while guaranteeing the quality of the business marketing data is a difficult point of the prior art, and a business marketing data processing system based on multiple channels is provided for the purpose.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a business marketing data processing system based on multiple channels.
In order to achieve the above object, the present invention provides the following technical solutions:
a business marketing data processing system based on multiple channels comprises a cloud computing platform, wherein the cloud computing platform is in communication connection with a business data acquisition module, a business data arrangement module, a preference condition analysis module and a business recommendation module;
The service data acquisition module is provided with a lower layer data acquisition chain and an upper layer data arrangement node, and is used for acquiring the multidimensional service data of the data source and integrating the multidimensional service data to generate a multidimensional service data set;
The service data arrangement module is used for carrying out data content standardization processing on the multidimensional service data set;
The preference condition analysis module is used for establishing a multi-dimensional coordinate system, converting multi-dimensional service data in a multi-dimensional service data set into corresponding multi-dimensional data coordinates and mapping the corresponding multi-dimensional data coordinates on the multi-dimensional coordinate system, setting a preference attraction distance and a coordinate density threshold, dividing a plurality of temporary preference relation clusters from each multi-dimensional data coordinate according to the coordinate density threshold and the preference attraction distance, judging whether the center coordinate distance of two adjacent temporary preference relation clusters is smaller than or equal to the respective space radius, establishing a space preference relation cluster according to a judgment result, and establishing a preference analysis network according to the space preference relation clusters;
the service recommendation module is used for inputting the multidimensional service data of each data source into the preference analysis network, and further generating and executing multidimensional service recommendation decisions of each data source.
Further, the lower layer data acquisition chain consists of a plurality of data acquisition nodes and is used for acquiring multidimensional service data of each data source;
The upper layer data arrangement node is connected with a plurality of lower layer data acquisition chains for acquiring the same type of data source, further collects and integrates the multidimensional service data acquired by the connected lower layer data acquisition chains to generate a multidimensional service data set, and sends the multidimensional service data sets of different types to the service data arrangement module.
Further, the collecting process of the multidimensional service data includes:
Setting a plurality of upper layer data arrangement nodes and lower layer data acquisition chains, wherein a business data acquisition module sends the lower layer data acquisition chains to each data source, and sets an identity number for the data source;
the data source receives and installs a lower data acquisition chain, and then the lower data acquisition chain confirms the positions of all data ports of the data source, obtains the data source types of the corresponding data sources, and sets the positions of the data ports as data acquisition nodes;
The data source types comprise off-line malls, on-line malls and advertisement platforms, and further the lower layer data acquisition chain sends the data source type of the data source to the service data acquisition module;
the business data acquisition module distributes a lower layer data acquisition chain positioned in the same data source type to the position below the same upper layer data arrangement node;
Each time the data source carries out communication data interaction, each data acquisition node in the lower layer data acquisition chain acquires corresponding data interaction content, so as to obtain corresponding service data, and marks the identity number of the corresponding data source, wherein the types of the service data comprise sales service data, customer service data and advertisement service data.
Further, the generating process of the multidimensional service data set includes:
the upper layer data arrangement node integrates the multidimensional service data of the same type of data sources to obtain a multidimensional service data set, and the service data acquisition module sends the multidimensional service data set to the service data arrangement module.
Further, the process of performing data content standardization processing on the multidimensional service data set includes:
all the business data of the same type are traversed in parallel, the data content formats of all the business data are obtained according to the traversing result, the data content formats are compared with each other, and the standard data content format of the corresponding type of business data is established according to the comparison result;
Overlapping and mapping the standard data content format and the corresponding type of service data, wherein the difference between the standard data content format and the corresponding type of service data is within 5%, and no operation is performed;
otherwise, marking the part which is different from the standard data content format in the corresponding service data, and further adjusting the marked part by the service data sorting module until the difference degree between all the service data and the corresponding standard data content format is within 5%.
Further, the partitioning process of the temporary preference relation cluster includes:
The preference condition analysis module establishes a plurality of multidimensional coordinate systems, extracts all service data from the multidimensional service data set, and further converts each type of service data into multidimensional data coordinate points according to the numerical data in each service data;
Mapping multidimensional data coordinate points corresponding to the same type of service data on the same multidimensional coordinate system, and setting a preferential attraction distance and a coordinate density threshold;
For any one multidimensional data coordinate point on the multidimensional coordinate system, if the density of the multidimensional data coordinate point in the preferred attraction distance range is greater than or equal to a coordinate density threshold value by taking the multidimensional data coordinate point as the center, establishing a temporary preferred relation cluster so that the coordinate density in the temporary preferred relation cluster is equal to the coordinate density threshold value, otherwise, neglecting the temporary preferred relation cluster;
And then a plurality of mutually intersected temporary preference relation clusters are divided on a multi-dimensional coordinate system according to the coordinate density threshold value.
Further, the establishing process of the preference analysis network includes:
Acquiring the center coordinate distance of each adjacent temporary preference relation cluster, if the center coordinate distance of each adjacent two temporary preference relation clusters is smaller than or equal to the respective space radius, merging the adjacent two temporary preference relation clusters to establish a space preference relation cluster, so that the space preference relation clusters contain the two temporary preference relation clusters at the same time, otherwise, not performing any operation;
Repeating the operation until two adjacent temporary preference relation clusters are not available for merging;
for the temporary preference relation clusters which are not added with any spatial preference relation clusters, the preference condition analysis module converts the temporary preference relation clusters into the spatial preference relation clusters, establishes a preference analysis network, marks the corresponding data source identity numbers of the spatial preference relation clusters corresponding to all types of service data, and inputs the data source identity numbers to the preference analysis network.
Further, the generating process of the multi-dimensional service recommendation decision includes:
The service recommendation module inputs the multidimensional service data of each data source into a preference analysis network, and matches corresponding spatial preference relation clusters according to the identity numbers carried by the multidimensional service data;
matching corresponding multidimensional data coordinate points in the space preference relation cluster according to the multidimensional service data, and marking the multidimensional data coordinate points in the temporary preference data relation cluster where the corresponding multidimensional data coordinates are positioned as core association points, and marking other multidimensional data coordinate points in the space preference relation cluster as edge association points;
The service recommendation module invokes multidimensional service data of the core association points and the edge association points, extracts sales service data, customer service data and advertisement service data in the multidimensional service data, and establishes multidimensional service recommendation decisions according to the multidimensional service data corresponding to the core association points and the edge association points in a ratio of 7:3.
Compared with the prior art, the invention has the beneficial effects that:
the invention is used for collecting the multidimensional service data of the data source by arranging the upper layer data arrangement node and the lower layer data acquisition chain, integrating the multidimensional service data to generate the multidimensional service data set, and carrying out data content standardization processing on the multidimensional service data sets of different types, thereby effectively improving the data quality of the service data and providing data assurance for the subsequent service data processing;
Establishing a multi-dimensional coordinate system, converting multi-dimensional business data in a multi-dimensional business data set into corresponding multi-dimensional data coordinates and mapping the corresponding multi-dimensional data coordinates on the multi-dimensional coordinate system, setting a preferential attraction distance and a coordinate density threshold, dividing a plurality of temporary preferential relation clusters from each multi-dimensional data coordinate according to the coordinate density threshold and the preferential attraction distance, judging whether the center coordinate distance of two adjacent temporary preferential relation clusters is smaller than or equal to the respective space radius, and establishing a space preferential relation cluster according to a judging result, thereby improving the processing efficiency and accuracy of the business data.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.
Fig. 1 is a schematic diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, based on the examples herein, which are within the scope of the invention as defined by the claims, will be within the scope of the invention as defined by the claims.
As shown in fig. 1, a business marketing data processing system based on multiple channels comprises a cloud computing platform, wherein the cloud computing platform is in communication connection with a business data acquisition module, a business data arrangement module, a preference condition analysis module and a business recommendation module;
The service data acquisition module is provided with a plurality of upper layer data arrangement nodes and a lower layer data acquisition chain, wherein the lower layer data acquisition chain is arranged in each type of data source, and consists of a plurality of data acquisition nodes and is used for acquiring multidimensional service data of the data source;
The upper layer data arrangement node is connected with a plurality of lower layer data acquisition chains for acquiring the same type of data source, so as to collect and integrate multidimensional service data acquired by the connected lower layer data acquisition chains to generate corresponding multidimensional service data sets, and the multidimensional service data sets of different types are sent to the service data arrangement module;
the service data arrangement module is used for carrying out data content standardization processing on different types of multidimensional service data sets, and further sending the processed multidimensional service data sets to the preference condition analysis module;
the preference condition analysis module is used for establishing a multi-dimensional coordinate system, converting multi-dimensional service data in multi-dimensional service data sets of different types into corresponding multi-dimensional data coordinates and mapping the corresponding multi-dimensional data coordinates on the multi-dimensional coordinate system, setting a preference attraction distance and a coordinate density threshold, dividing a plurality of temporary preference relation clusters from each multi-dimensional data coordinate according to the coordinate density threshold and the preference attraction distance, judging whether the center coordinate distance of two adjacent temporary preference relation clusters is smaller than or equal to the respective space radius, merging the two temporary preference relation clusters according to a judgment result to generate a space preference relation cluster, repeating the operation until the two temporary preference relation clusters cannot be merged, further obtaining a plurality of space preference relation clusters, and establishing a preference analysis network according to the space preference relation clusters;
the service recommendation module is used for inputting the multidimensional service data of each data source into the preference analysis network, and further generating and executing multidimensional service recommendation decisions of each data source.
Further, the working principle of the present invention is illustrated by the following examples:
The business data acquisition module is provided with K upper layer data arrangement nodes and L lower layer data acquisition chains, wherein K and L are natural numbers larger than 0, and K is smaller than L;
each data source and the user side are in communication connection with the cloud computing platform through the service data acquisition module, so that the cloud computing platform collects each data source, uses an IP address when in communication connection, and sends the IP address to the service data acquisition module;
According to the IP address, the service data acquisition module confirms the identity with the corresponding data source, if the identity is confirmed successfully, the service data acquisition module sends a lower layer data acquisition chain to the corresponding data source, and an identity number is set for the data source;
The data source receives and installs a lower data acquisition chain, and then the lower data acquisition chain confirms the positions of all data ports of the data source, and further obtains the data source types of the corresponding data sources, and sets the positions of the data ports as data acquisition nodes;
the data source types comprise off-line malls, on-line malls, advertisement platforms and the like, and further the lower layer data acquisition chain sends the data source type of the data source to the service data acquisition module;
The business data acquisition module distributes a lower layer data acquisition chain positioned in the same data source class to the position below the same upper layer data arrangement node;
Each time the data source performs communication data interaction, each data acquisition node in the lower layer data acquisition chain acquires corresponding data interaction content, so as to obtain corresponding service data, and marks the identity number of the corresponding data source;
The types of the business data comprise sales business data, customer business data and advertisement business data, wherein the sales business data comprises sales volume, order volume, transaction time and other information of each commodity, the customer business data comprises customer information, commodity purchase condition, advertisement browsing condition and other information of each customer, and the advertisement business data comprises advertisement click volume, advertisement conversion rate and other information of each type of advertisement;
the upper layer data arrangement node integrates the multidimensional service data of the same type of data sources to obtain a multidimensional service data set, and the service data acquisition module sends the multidimensional service data set to the service data arrangement module.
Further, after the service data sorting module set receives the multidimensional service data set, classifying the types of the service data in the multidimensional service data set;
All the business data of the same type are traversed in parallel, the data content formats of all the business data are obtained according to the traversal, the data content formats are compared with each other, if the difference between the two data content formats is within 5%, the comparison of the two data content formats is judged to be successful, and otherwise, the comparison is judged to be unsuccessful;
selecting the data content format with the largest number of successful comparison times as the standard data content format of the corresponding type of service data;
Overlapping and mapping the standard data content format and the corresponding type of service data, wherein the difference between the standard data content format and the corresponding type of service data is within 5%, and no operation is performed;
otherwise, marking the part of the corresponding service data with the format different from that of the standard data content, and then adjusting the different parts by the service data sorting module until the difference between all the service data and the corresponding standard data content format is within 5%;
the following illustrates the process of the service data arrangement module for content adjustment of service data:
The service data of the same type are compared with each other, so that the standard data content format of the service data of the same type is obtained, wherein the standard data content format is as follows: setting labels for non-conforming business data within 100 text characters, 18 digits and … … through a standard data content format, for example, if the number of text characters in first column data with one business data is greater than 105, performing lossless compression on adjacent text characters in the first column data in the business data by a business data sorting module according to an LZW algorithm, judging that the number of text characters in the compressed first column data is greater than 105, and repeating the operation until the number of text characters in the first column data is less than or equal to 105 if the number of compressed text characters is still greater than 105;
it should be noted that, the LZW algorithm is a lossless dictionary compression algorithm, which uses repeated occurrence of character strings to implement compression, dynamically updates a dictionary to improve compression efficiency, and only needs to use the same dictionary and coding rules to restore an original text when decompressing;
When all the services in the multidimensional service data set complete data content standardization, the service data arrangement module sends the multidimensional service data set to the preference condition analysis module.
Further, the preference condition analysis module establishes a plurality of multidimensional coordinate systems, extracts all service data from the multidimensional service data set, and further converts each type of service data into multidimensional data coordinate points according to numerical data in each service data, wherein the multidimensional data coordinate points can be represented as (data 1,……,datan), data represents the numerical data, and n is a natural number greater than 0;
Mapping multidimensional data coordinate points corresponding to the same type of service data on the same multidimensional coordinate system, and setting a preferential attraction distance and a coordinate density threshold;
For any one multidimensional data coordinate point on the multidimensional coordinate system, if the density of the multidimensional data coordinate point in the preferred attraction distance range is greater than or equal to a coordinate density threshold value by taking the multidimensional data coordinate point as the center, establishing a temporary preferred relation cluster so that the coordinate density in the temporary preferred relation cluster is equal to the coordinate density threshold value, otherwise, neglecting;
It should be noted that the temporary preference relation cluster is spherical, where the space radius of the temporary preference relation cluster is equal to the distance from the center to the farthest multidimensional coordinate data, and the space radius of the temporary preference relation cluster is less than or equal to the preference attraction distance;
Dividing a multi-dimensional coordinate system into a plurality of mutually-intersected temporary preference relation clusters according to the coordinate density threshold value, and calculating the center coordinate distance of each adjacent temporary preference relation cluster;
If the center coordinate distance of two adjacent temporary preference relation clusters is smaller than or equal to the respective space radius, merging the two adjacent temporary preference relation clusters to establish a space preference relation cluster, so that the space preference relation cluster simultaneously contains the two temporary preference relation clusters, otherwise, not performing any operation;
Repeating the operation until two adjacent temporary preference relation clusters are not combinable;
meanwhile, the temporary preference relation clusters which are not added with any spatial preference relation clusters are converted into the spatial preference relation clusters by the preference condition analysis module;
It should be noted that, for the multidimensional space coordinate points not added with any temporary preference relation cluster and space preference relation cluster, the preference condition analysis module directly eliminates the multidimensional space coordinate points.
Further, a preference analysis network is established according to a DBSCAN algorithm, the spatial preference relation clusters corresponding to all types of service data are labeled with the identity numbers of the corresponding data sources and then input into the preference analysis network, and meanwhile, the preference analysis network is sent to the service recommendation module by the preference condition analysis module;
The service recommendation module inputs the multidimensional service data of each data source into a preference analysis network, and matches corresponding spatial preference relation clusters according to the identity numbers carried by the multidimensional service data;
Matching corresponding multidimensional data coordinate points in the spatial preference relation cluster according to the multidimensional service data, and marking the multidimensional data coordinate points in the temporary preference relation cluster where the corresponding multidimensional data coordinates are located as core association points, and marking other multidimensional data coordinate points in the spatial preference relation cluster as edge association points;
The service recommendation module invokes multidimensional service data of the core association points and the edge association points, extracts sales service data, customer service data and advertisement service data in the multidimensional service data, and establishes multidimensional service recommendation decisions according to the multidimensional service data corresponding to the core association points and the edge association points in a ratio of 7:3;
It should be noted that the DBSCAN algorithm is a density-based clustering algorithm for finding clusters of points having a relatively high density and capable of identifying noisy points. The algorithm can group points with sufficient density into one cluster and distinguish noise points.
The establishment process of the multidimensional service recommendation decision comprises the following steps:
Extracting the types and corresponding sales volume of various commodities from various sales service data, client service data and advertisement service data, commodity purchase status and advertisement browsing volume of various clients, and advertisement click volume of various advertisements;
Setting corresponding commodity recommendation weights according to sales of various commodities, for example, if the sales of a certain type of commodity is 100, the commodity recommendation weight is 100;
Further, the commodity recommendation weight of each commodity is proportionally adjusted according to the corresponding core association point or the edge association point, for example, the commodity recommendation weight of a certain commodity is 100, if the commodity recommendation weight of the certain commodity corresponds to the core association point, the commodity recommendation weight is 100 x 0.7, and if the commodity recommendation weight of the certain commodity corresponds to the edge association point, the commodity recommendation weight of the certain commodity is 100 x 0.3;
By adopting the same method, setting corresponding advertisement recommendation weights according to advertisement click quantity of advertisements and corresponding core association points or edge association points thereof, and setting user commodity recommendation weights and user advertisement recommendation weights according to commodity purchase conditions of users and advertisement browsing quantity;
Adding the commodity recommendation weights of the users of the commodities of the same category and the commodity recommendation weights according to the proportion of 1:1 to obtain commodity recommendation weights alpha of the corresponding commodities in the corresponding data sources;
Adding the user advertisement recommendation weights of the advertisements of the same kind and the advertisement recommendation weights according to the proportion of 1:1 to obtain advertisement recommendation weights of the corresponding advertisements in the corresponding data sources;
Adding commodity recommendation weights of all commodities to obtain a total advertisement recommendation weight beta, and further obtaining commodity recommendation duty ratio p of each type of commodity, wherein p=alpha/beta;
The advertisement recommendation duty ratio of each type of advertisement is obtained by adopting the same method;
and generating a multidimensional service recommendation decision corresponding to the data source according to the commodity recommendation proportion of all types of commodities and the advertisement recommendation proportion of all types of advertisements, and sending the multidimensional service recommendation decision to the corresponding data source for execution.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (1)
1. The business marketing data processing system based on the multiple channels comprises a cloud computing platform, and is characterized in that the cloud computing platform is in communication connection with a business data acquisition module, a business data arrangement module, a preference condition analysis module and a business recommendation module;
The service data acquisition module is provided with an upper data arrangement node and a lower data acquisition chain and is used for acquiring multidimensional service data of a data source and integrating the multidimensional service data to generate a multidimensional service data set;
The lower layer data acquisition chain consists of a plurality of data acquisition nodes and is used for acquiring multidimensional service data of each data source;
The upper layer data arrangement node is connected with a plurality of lower layer data acquisition chains for acquiring the same type of data source, so as to collect and integrate multidimensional service data acquired by the connected lower layer data acquisition chains to generate a multidimensional service data set, and the multidimensional service data sets of different types are sent to a service data arrangement module;
The multi-dimensional business data acquisition process comprises the following steps:
setting a plurality of upper layer data sorting nodes and lower layer data acquisition chains, wherein a business data acquisition module sends the lower layer data acquisition chains to each data source, and sets an identity number for each data source;
The data source receives and installs a lower data acquisition chain, the lower data acquisition chain confirms the positions of all data ports of the data source, so as to obtain the data source types of the corresponding data sources, and the positions of the data ports are set as data acquisition nodes;
The data source types comprise off-line malls, on-line malls and advertisement platforms, and further the lower layer data acquisition chain sends the data source type of the data source to the service data acquisition module;
the business data acquisition module distributes a lower layer data acquisition chain positioned in the same data source type to the position below the same upper layer data arrangement node;
Each time a data source performs communication data interaction, each data acquisition node in a lower layer data acquisition chain acquires corresponding data interaction content, so as to obtain corresponding service data, and marks the identity number of the corresponding data source, wherein the types of the service data comprise sales service data, customer service data and advertisement service data;
The service data arrangement module is used for carrying out data content standardization processing on the multidimensional service data set;
The process of carrying out data content standardization processing on the multidimensional service data set comprises the following steps:
all the business data of the same type are traversed in parallel, the data content formats of all the business data are obtained according to the traversing result, the data content formats are compared with each other, and the standard data content format of the corresponding type of business data is established according to the comparison result;
Overlapping and mapping the standard data content format and the corresponding type of service data, wherein the difference between the standard data content format and the corresponding type of service data is within 5%, and no operation is performed;
Otherwise, marking the part which is different from the standard data content format in the corresponding service data, and then adjusting the marked part by the service data sorting module until the difference between all the service data and the corresponding standard data content format is within 5%;
The preference condition analysis module is used for establishing a multi-dimensional coordinate system, converting multi-dimensional service data in a multi-dimensional service data set into corresponding multi-dimensional data coordinates and mapping the corresponding multi-dimensional data coordinates on the multi-dimensional coordinate system, setting a preference attraction distance and a coordinate density threshold, dividing a plurality of temporary preference relation clusters from each multi-dimensional data coordinate according to the coordinate density threshold and the preference attraction distance, judging whether the center coordinate distance of two adjacent temporary preference relation clusters is smaller than or equal to the respective space radius, establishing a space preference relation cluster according to a judgment result, and establishing a preference analysis network according to the space preference relation clusters;
The partitioning process of the temporary preference relation cluster comprises the following steps:
The preference condition analysis module establishes a plurality of multidimensional coordinate systems, extracts all service data from the multidimensional service data set, and further converts each type of service data into multidimensional data coordinate points according to the numerical data in each service data;
Mapping multidimensional data coordinate points corresponding to the same type of service data on the same multidimensional coordinate system, and setting a preferential attraction distance and a coordinate density threshold;
For any one multidimensional data coordinate point on the multidimensional coordinate system, if the density of the multidimensional data coordinate point in the preferred attraction distance range is greater than or equal to a coordinate density threshold value by taking the multidimensional data coordinate point as the center, establishing a temporary preferred relation cluster so that the coordinate density in the temporary preferred relation cluster is equal to the coordinate density threshold value, otherwise, neglecting the temporary preferred relation cluster;
dividing a plurality of mutually-intersected temporary preference relation clusters on a multi-dimensional coordinate system according to the coordinate density threshold;
the establishment process of the preference analysis network comprises the following steps:
Acquiring the center coordinate distance of each adjacent temporary preference relation cluster, if the center coordinate distance of each adjacent two temporary preference relation clusters is smaller than or equal to the respective space radius, merging the adjacent two temporary preference relation clusters to establish a space preference relation cluster, so that the space preference relation clusters contain the two temporary preference relation clusters at the same time, otherwise, not performing any operation;
Repeating the operation until two adjacent temporary preference relation clusters are not available for merging;
for the temporary preference relation clusters which are not added with any spatial preference relation clusters, the preference condition analysis module converts the temporary preference relation clusters into the spatial preference relation clusters, establishes a preference analysis network, marks the corresponding data source identity numbers of the spatial preference relation clusters corresponding to all types of service data, and inputs the spatial preference relation clusters into the preference analysis network;
the service recommendation module is used for inputting the multidimensional service data of each data source into the preference analysis network, so as to generate and execute multidimensional service recommendation decisions of each data source;
the generation process of the multidimensional service recommendation decision comprises the following steps:
The service recommendation module inputs the multidimensional service data of each data source into a preference analysis network, and matches corresponding spatial preference relation clusters according to the identity numbers carried by the multidimensional service data;
matching corresponding multidimensional data coordinate points in the space preference relation cluster according to the multidimensional service data, and marking the multidimensional data coordinate points in the temporary preference data relation cluster where the corresponding multidimensional data coordinates are positioned as core association points, and marking other multidimensional data coordinate points in the space preference relation cluster as edge association points;
The service recommendation module invokes multidimensional service data of the core association points and the edge association points, extracts sales service data, customer service data and advertisement service data in the multidimensional service data, and establishes multidimensional service recommendation decisions according to the multidimensional service data corresponding to the core association points and the edge association points in a ratio of 7:3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410262538.3A CN117853152B (en) | 2024-03-07 | 2024-03-07 | Business marketing data processing system based on multiple channels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410262538.3A CN117853152B (en) | 2024-03-07 | 2024-03-07 | Business marketing data processing system based on multiple channels |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117853152A CN117853152A (en) | 2024-04-09 |
| CN117853152B true CN117853152B (en) | 2024-05-17 |
Family
ID=90538755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410262538.3A Active CN117853152B (en) | 2024-03-07 | 2024-03-07 | Business marketing data processing system based on multiple channels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117853152B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101197876A (en) * | 2006-12-06 | 2008-06-11 | 中兴通讯股份有限公司 | Method and system for multi-dimensional analysis of message service data |
| CN108696597A (en) * | 2018-05-29 | 2018-10-23 | 阿里巴巴集团控股有限公司 | The method and apparatus for pushing marketing message |
| CN110287415A (en) * | 2019-06-26 | 2019-09-27 | 海南车智易通信息技术有限公司 | A kind of content recommendation method, device and calculate equipment |
| WO2020001096A1 (en) * | 2018-06-29 | 2020-01-02 | 京东方科技集团股份有限公司 | Commodity recommendation method and commodity recommendation device |
| CN111340601A (en) * | 2020-03-30 | 2020-06-26 | 贝壳技术有限公司 | Commodity information recommendation method and device, electronic equipment and storage medium |
| CN111382217A (en) * | 2018-12-29 | 2020-07-07 | 北京奇虎科技有限公司 | Destination recommendation method and device |
| CN111401936A (en) * | 2020-02-26 | 2020-07-10 | 中国人民解放军战略支援部队信息工程大学 | Recommendation method based on comment space and user preference |
| KR102183143B1 (en) * | 2020-05-20 | 2020-11-25 | 이창욱 | Method and apparatus for determining recommended color of the target product based on big data |
| CN112132217A (en) * | 2020-09-23 | 2020-12-25 | 广西大学 | Classification type data clustering method based on intra-cluster dissimilarity |
| CN113656709A (en) * | 2021-08-24 | 2021-11-16 | 东北大学 | Interpretable interest point recommendation method fusing knowledge graph and time sequence characteristics |
| CN113779395A (en) * | 2021-09-10 | 2021-12-10 | 粒子文化科技集团(杭州)股份有限公司 | Media asset recommendation method, device, system, electronic device and storage medium |
| CN113886709A (en) * | 2021-10-29 | 2022-01-04 | 平安银行股份有限公司 | Recommendation method, device and equipment for business products and storage medium |
| CN116385048A (en) * | 2023-06-06 | 2023-07-04 | 山东政信大数据科技有限责任公司 | Intelligent marketing method and system for agricultural products |
| CN116703485A (en) * | 2023-08-04 | 2023-09-05 | 山东创亿智慧信息科技发展有限责任公司 | Advertisement accurate marketing method and system based on big data |
| CN116975539A (en) * | 2023-08-16 | 2023-10-31 | 杭州火奴数据科技有限公司 | Marketing data storage management system based on clustering algorithm |
| CN117035948A (en) * | 2023-10-10 | 2023-11-10 | 山东唐和智能科技有限公司 | Task intelligent processing method and system based on big data |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100997541B1 (en) * | 2008-10-08 | 2010-11-30 | 인하대학교 산학협력단 | The method and apparatus for image recommendation based on user profile using feature based collaborative filtering to resolve new item recommendation |
| JP5744660B2 (en) * | 2010-08-26 | 2015-07-08 | キヤノン株式会社 | Data search result display method, data search result display device, and program |
| CN114022205A (en) * | 2021-11-05 | 2022-02-08 | 国网江苏省电力有限公司营销服务中心 | Power consumer payment channel preference matching method and system based on improved clustering method |
-
2024
- 2024-03-07 CN CN202410262538.3A patent/CN117853152B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101197876A (en) * | 2006-12-06 | 2008-06-11 | 中兴通讯股份有限公司 | Method and system for multi-dimensional analysis of message service data |
| CN108696597A (en) * | 2018-05-29 | 2018-10-23 | 阿里巴巴集团控股有限公司 | The method and apparatus for pushing marketing message |
| WO2020001096A1 (en) * | 2018-06-29 | 2020-01-02 | 京东方科技集团股份有限公司 | Commodity recommendation method and commodity recommendation device |
| CN111382217A (en) * | 2018-12-29 | 2020-07-07 | 北京奇虎科技有限公司 | Destination recommendation method and device |
| CN110287415A (en) * | 2019-06-26 | 2019-09-27 | 海南车智易通信息技术有限公司 | A kind of content recommendation method, device and calculate equipment |
| CN111401936A (en) * | 2020-02-26 | 2020-07-10 | 中国人民解放军战略支援部队信息工程大学 | Recommendation method based on comment space and user preference |
| CN111340601A (en) * | 2020-03-30 | 2020-06-26 | 贝壳技术有限公司 | Commodity information recommendation method and device, electronic equipment and storage medium |
| KR102183143B1 (en) * | 2020-05-20 | 2020-11-25 | 이창욱 | Method and apparatus for determining recommended color of the target product based on big data |
| CN112132217A (en) * | 2020-09-23 | 2020-12-25 | 广西大学 | Classification type data clustering method based on intra-cluster dissimilarity |
| CN113656709A (en) * | 2021-08-24 | 2021-11-16 | 东北大学 | Interpretable interest point recommendation method fusing knowledge graph and time sequence characteristics |
| CN113779395A (en) * | 2021-09-10 | 2021-12-10 | 粒子文化科技集团(杭州)股份有限公司 | Media asset recommendation method, device, system, electronic device and storage medium |
| CN113886709A (en) * | 2021-10-29 | 2022-01-04 | 平安银行股份有限公司 | Recommendation method, device and equipment for business products and storage medium |
| CN116385048A (en) * | 2023-06-06 | 2023-07-04 | 山东政信大数据科技有限责任公司 | Intelligent marketing method and system for agricultural products |
| CN116703485A (en) * | 2023-08-04 | 2023-09-05 | 山东创亿智慧信息科技发展有限责任公司 | Advertisement accurate marketing method and system based on big data |
| CN116975539A (en) * | 2023-08-16 | 2023-10-31 | 杭州火奴数据科技有限公司 | Marketing data storage management system based on clustering algorithm |
| CN117035948A (en) * | 2023-10-10 | 2023-11-10 | 山东唐和智能科技有限公司 | Task intelligent processing method and system based on big data |
Non-Patent Citations (4)
| Title |
|---|
| A collaborative filtering recommendation algorithm based on a bee colony K-means clustering model;Li Yan-juan;Computer Engineering and Science;20190601;第41卷(第6期);第113-121页 * |
| 在线学习资源推荐综述;董永峰;计算机应用;20230630;第43卷(第6期);第1655-1663页 * |
| 数据挖掘中聚类算法综述;刘维;;江苏商论;20180720(第07期);第122-127页 * |
| 精准・互动――数字传播时代广告公司业务模式的重构;姚曦;李斐飞;;新闻大学;20170215(01);第116-124页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117853152A (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021017679A1 (en) | Address information parsing method and apparatus, system and data acquisition method | |
| CN106296059B (en) | Method and equipment for determining delivery network points | |
| CN107145516B (en) | Text clustering method and system | |
| CN101605126A (en) | A kind of method and system of multi-protocol data Classification and Identification | |
| CN102693299A (en) | System and method for parallel video copy detection | |
| CN108090332A (en) | A kind of air control method that behavioural analysis is logged in based on user | |
| CN107704868A (en) | Tenant group clustering method based on Mobile solution usage behavior | |
| CN104268247A (en) | Master data imputation method based on fuzzy analytic hierarchy process | |
| CN117853152B (en) | Business marketing data processing system based on multiple channels | |
| CN110347827A (en) | Event Distillation method towards isomery text operation/maintenance data | |
| CN114491187A (en) | Intelligent natural resource monitoring integrated system | |
| CN113706263A (en) | Electronic commerce system based on cloud platform | |
| CN115146653B (en) | Dialogue scenario construction method, device, equipment and storage medium | |
| CN108268478A (en) | A kind of unbalanced dataset feature selection approach and device based on ur-CAIM algorithms | |
| CA2556353A1 (en) | Method and apparatus for information factoring | |
| CN115757935A (en) | Big data pushing method and system applying computer intelligence | |
| CN110968570A (en) | Distributed big data mining system facing E-commerce platform | |
| CN111737371B (en) | Data flow detection classification method and device capable of dynamically predicting | |
| CN114519343A (en) | 95598-based repeated incoming call preprocessing method, device, equipment and storage medium | |
| US20020194052A1 (en) | Method and system for analyzing application needs of an entity | |
| CN114385899A (en) | User group accurate identification system and method based on big data analysis | |
| CN112308419A (en) | Data processing method, device, equipment and computer storage medium | |
| WO2015029158A1 (en) | Data conversion device, data conversion method, and data conversion program | |
| CN112445939A (en) | Social network group discovery system, method and storage medium | |
| CN110572403A (en) | web safety monitoring system and method thereof |
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 | ||
| GR01 | Patent grant |