CN116226893A - Client marketing information management system based on Internet of things - Google Patents
Client marketing information management system based on Internet of things Download PDFInfo
- Publication number
- CN116226893A CN116226893A CN202310512600.5A CN202310512600A CN116226893A CN 116226893 A CN116226893 A CN 116226893A CN 202310512600 A CN202310512600 A CN 202310512600A CN 116226893 A CN116226893 A CN 116226893A
- Authority
- CN
- China
- Prior art keywords
- value
- marketing
- neighborhood
- tag
- label value
- 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
- 238000000034 method Methods 0.000 claims abstract description 55
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 62
- 230000000694 effects Effects 0.000 abstract description 17
- 238000012545 processing Methods 0.000 abstract description 3
- 238000009826 distribution Methods 0.000 description 12
- 238000007726 management method Methods 0.000 description 8
- 230000002776 aggregation Effects 0.000 description 6
- 238000004220 aggregation Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Bioethics (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a client marketing information management system based on the Internet of things, which comprises the following components: the data acquisition module is used for acquiring the tag value and marketing coding data of the marketing information of the client of the Internet of things; the data preprocessing module is used for correcting the label value according to the difference condition of the label value in the neighborhood of the label value, the density degree of the label value in the neighborhood and the uniformity degree of the difference of the label value in the neighborhood to obtain a preferable label value; and the data encryption module is used for clustering the marketing coded data according to the preferred label value, and encrypting the marketing coded data corresponding to the preferred label value in the clustering process to obtain the encrypted marketing data corresponding to the preferred label value. The invention greatly ensures the safety of the information and improves the effect of encrypting the marketing information.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a client marketing information management system based on the Internet of things.
Background
The internet of things is a network which combines various things or information by utilizing a local network or the internet of things to realize informatization, and along with the development of internet of things technology, the internet of things informatization is applied to more and more fields, for example, different areas and different personnel can be connected into an informatization network by utilizing the internet of things in the product marketing process, and marketing conditions corresponding to different clients at different times are unified managed. At this time, a large amount of client information and marketing information exist in the internet of things information, wherein the client information and the marketing information comprise private data related to personal privacy, so in order to ensure the security of the client marketing information, it is important to encrypt the information when the client marketing information is managed.
In the management method for the marketing information of the clients, the data are scrambled or replaced directly through the relation between the information by utilizing the existing algorithm so as to realize the encryption of the information, and the marketing data in each marketing operation are difficult to encrypt through the relation between the data because of the independent existence of the marketing data, so that the encryption effect of the marketing data is poor.
Meanwhile, marketing data of each marketing operation is searched by utilizing the distribution dense relation of time corresponding to the marketing data, and information encryption is realized in the searching process. However, there may be some time distributions corresponding to the marketing data that are more distributed, resulting in omission of the search process and poor encryption effect of the marketing data.
Disclosure of Invention
In order to solve the technical problem of poor encryption effect of the prior marketing information, the invention aims to provide a client marketing information management system based on the Internet of things, and the adopted technical scheme is as follows:
the data acquisition module is used for acquiring the tag value and marketing coding data of the marketing information of the client of the Internet of things;
the data preprocessing module is used for correcting the label value according to the difference condition of the label value in the neighborhood of the label value, the density degree of the label value in the neighborhood and the uniformity degree of the difference of the label value in the neighborhood to obtain a preferable label value;
and the data encryption module is used for clustering the marketing coded data according to the preferred label value, and encrypting the marketing coded data corresponding to the preferred label value in the clustering process to obtain the encrypted marketing data corresponding to the preferred label value.
Preferably, the correcting the label value according to the difference condition of the label value in the neighborhood of the label value, the density of the label value in the neighborhood and the uniformity of the difference of the label value in the neighborhood to obtain the preferred label value specifically includes:
for any one tag value, a first correction coefficient is obtained according to the difference condition of the tag values in the neighborhood of the tag value; obtaining a second correction coefficient according to the density of the label values in the neighborhood of the label values; obtaining a third correction coefficient according to the uniformity degree of the difference of the label values in the neighborhood of the label value; obtaining the correction degree according to the second correction coefficient and the third correction coefficient; the second correction coefficient and the third correction coefficient are in positive correlation with the correction degree; the product of the first correction coefficient and the correction degree is taken as a preferred label value.
Preferably, the obtaining the first correction coefficient according to the difference of the label values in the neighborhood of the label values specifically includes:
forming a tag value sequence by tag values of all the client marketing information of the Internet of things, marking any tag value as a target tag value, and forming a neighborhood of the target tag value by taking the target tag value as a center and a window with a preset length in the tag value sequence;
respectively acquiring the difference between each label value in the neighborhood and the target label value at the left side of the target label value in the neighborhood of the target label value to obtain a negative direction difference, and marking the sum of all the negative direction differences as the negative direction degree of the target label value;
respectively acquiring differences between each tag value in the neighborhood and the target tag value on the right side of the target tag value in the neighborhood of the target tag value to obtain positive direction differences, and marking the sum of all the positive direction differences as the positive direction degree of the target tag value;
if the positive direction degree of the target label value is greater than the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a first preset value; the first preset value is a negative number;
if the positive direction degree of the target label value is smaller than or equal to the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a second preset value, and the second preset value is a positive number.
Preferably, the method for obtaining the negative direction difference specifically includes:
the absolute value of the difference between each label value in the neighborhood and the target label value is marked as negative direction difference at the left side of the target label value in the neighborhood of the target label value;
the method for acquiring the positive direction difference comprises the following steps:
and marking the absolute value of the difference between each label value in the neighborhood and the target label value as a positive direction difference on the right side of the target label value in the neighborhood of the target label value.
Preferably, the obtaining the second correction coefficient according to the density of the label values in the neighborhood of the label values specifically includes:
obtaining the maximum value of the total number of the tag values contained in the neighborhood of all the tag values;
for the target tag value, calculating the ratio of the number of all tag values in the neighborhood of the target tag value to the maximum value to obtain a characteristic ratio of the target tag value, and obtaining a second correction coefficient of the target tag value according to the characteristic ratio; the feature ratio and the second feature coefficient are in negative correlation.
Preferably, the obtaining the third correction coefficient according to the uniformity degree of the difference of the label values in the neighborhood of the label values specifically includes:
in the neighborhood of the target label value, marking any label value in the neighborhood as a selected neighborhood label value, calculating the average value of the absolute value of the difference value between the selected neighborhood label value and the label values at two adjacent sides of the selected neighborhood label value, and marking the average value as the difference degree of the selected neighborhood label value;
and calculating the absolute value of the difference value between the difference degrees of every two arbitrary label values in the neighborhood of the target label value, and taking the average value of the absolute value of the difference values between the difference degrees of all arbitrary two label values in the neighborhood of the target label value as a third correction coefficient of the target label value.
Preferably, the clustering of the marketing-coded data according to the preferred tag value is specifically: and clustering the marketing coded data according to the preferred label value by using a mean shift clustering algorithm.
Preferably, in the clustering process, encrypting marketing coded data corresponding to the preferred tag value to obtain encrypted marketing data corresponding to the preferred tag value, which specifically includes:
in the clustering process, marking the preferred label value corresponding to the center point data as a center label value, and marking the preferred label value in the preset range corresponding to the center label value as an adjacent label value;
and for any one central tag value, using marketing coding data corresponding to the central tag value as template coding data, and encrypting marketing coding data corresponding to the adjacent tag value according to the difference between the template coding data and marketing coding data corresponding to the adjacent tag value to obtain encrypted marketing data corresponding to the adjacent tag value.
Preferably, encrypting the marketing code data corresponding to the adjacent tag value according to the difference between the template code data and the marketing code data corresponding to the adjacent tag value to obtain encrypted marketing data corresponding to the adjacent tag value, which specifically includes:
marking marketing coded data corresponding to any adjacent tag value as selected coded data, aligning the left end of the template coded data with the selected coded data, performing first exclusive-or operation on the selected coded data, sliding the marketing coded data obtained after the first exclusive-or operation leftwards according to a set step length, performing second exclusive-or operation on the marketing coded data obtained after the first exclusive-or operation according to the template coded data, and pushing the marketing coded data until the right end of the template coded data is aligned with the right end of the selected coded data, and stopping the exclusive-or operation until the encrypted marketing data corresponding to the selected coded data is obtained.
Preferably, the tag value and the marketing coding data of the client marketing information of the internet of things are specifically:
the method comprises the steps of converting time data and marketing data in the client marketing information of the Internet of things into binary coded data, converting the binary coded data corresponding to the time data into decimal data, taking the decimal data corresponding to the time data corresponding to each marketing operation as a label value corresponding to each marketing operation, and taking the binary coded data corresponding to the marketing data corresponding to each marketing operation as marketing coded data.
The embodiment of the invention has at least the following beneficial effects:
according to the method, firstly, the label value and marketing coding data of the client marketing information of the Internet of things are obtained, the label value is used as a label of the marketing coding data, then the label value is corrected according to the difference condition of the label value in the neighborhood of the label value, the density degree of the label value in the neighborhood and the uniformity degree of the difference of the label value in the neighborhood to obtain a preferable label value, and the difference condition, the density degree and the uniformity degree of the difference of the label value in the neighborhood of the label value are considered; and finally, clustering the marketing coded data according to the preferred label values, and encrypting the marketing coded data corresponding to the preferred label values in the clustering process to obtain the encrypted marketing data corresponding to the preferred label values, namely, encrypting the marketing data for a plurality of times by utilizing the clustering relation among the preferred label values, so that the current encryption cannot be broken by violence, the safety of the information is greatly ensured, and the effect of encrypting the marketing information is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of a client marketing information management system based on the Internet of things of the present invention;
FIG. 2 is a schematic diagram of an encryption process for marketing coded data in an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a client marketing information management system based on the internet of things according to the invention, which is provided by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the client marketing information management system based on the Internet of things provided by the invention with reference to the accompanying drawings.
Examples:
referring to fig. 1, a system block diagram of a client marketing information management system based on the internet of things according to an embodiment of the present invention is shown, the system includes: the system comprises a data acquisition module, a data preprocessing module and a data encryption module.
And the data acquisition module is used for acquiring the tag value and marketing coding data of the marketing information of the client of the Internet of things.
In this embodiment, the original marketing data of different customers in different areas is used as the original marketing data to be processed, specifically, the original marketing data refers to time information, customer information and marketing amount information in each marketing operation, and an implementer can set according to specific implementation scenarios.
Since the time information, the customer information and the marketing amount information are different types of data generated by each marketing operation, in order to facilitate the subsequent unified encryption of the data, the marketing data needs to be processed in a unified data form. In this embodiment, the time information, the client information and the marketing amount information in each marketing operation are respectively processed by huffman coding, so as to obtain binary coded data corresponding to the information.
Based on the above, each marketing operation corresponds to a set of original marketing data, and in order to distinguish the original marketing data corresponding to each marketing operation, the data needs to be subjected to label distinction, and the label value of the marketing information of the client of the Internet of things is obtained. In this embodiment, since the time data format corresponding to each marketing operation is single, and the length of the binary coded data corresponding to each marketing operation is short, at the same time, the time data corresponding to different marketing operations has a certain correlation.
Therefore, the embodiment determines the tag value of the corresponding marketing operation according to the time information corresponding to each marketing operation, converts the time data and the marketing data in the marketing information of the client of the internet of things into binary coded data, converts the binary coded data corresponding to the time data into decimal data, takes the decimal data corresponding to the time data corresponding to each marketing operation as the tag value corresponding to each marketing operation, and takes the binary coded data corresponding to the marketing data corresponding to each marketing operation as the marketing coded data.
Specifically, binary coded data corresponding to time information is converted into decimal data, decimal time data corresponding to marketing operations is used as a label value of the corresponding marketing operations, and binary coded data of other marketing data corresponding to the marketing operations are recorded as marketing coded data.
In this embodiment, the binary coded data corresponding to the customer information and the binary coded data corresponding to the marketing amount information are ordered according to a set rule or randomly, the binary coded data corresponding to the customer information is added to the rear of the binary coded data corresponding to the marketing amount information, and a space is not left in the middle, so that one long coded data is formed, namely the marketing coded data. The implementer may set according to a specific implementation scenario such that the binary-coded data corresponding to each marketing data is added to the back of the binary-coded data corresponding to the marketing amount information.
It should be noted that, the client performs one marketing operation, so that time data corresponding to one marketing operation can be obtained, and then one marketing operation corresponds to a tag value of one time, and two or more marketing data corresponding to one marketing operation are marketing coded data. The time for each marketing operation by the customer is not evenly distributed, i.e. the time interval between two adjacent marketing operations by the customer is not exactly the same, but the time corresponding to the marketing operation has a certain correlation.
The data preprocessing module is used for correcting the label value according to the difference condition of the label values in the neighborhood of the label value, the density degree of the label values in the neighborhood and the uniformity degree of the difference of the label values in the neighborhood to obtain the optimal label value.
It should be noted that, because the time corresponding to the marketing operation has a certain aggregation, the time relationship between marketing operations is reflected, and then each marketing operation can be confused according to the time information corresponding to the marketing operation, so as to realize the hidden encryption of the marketing information. Therefore, in this embodiment, the marketing coded data corresponding to each marketing operation is clustered based on the tag value, so that the aggregation feature of the tag value of each marketing operation can be determined.
In this embodiment, the marketing data is required to be clustered by using a mean shift clustering algorithm, and in the clustering process, mean shift is performed for more times, and encryption of the data is realized in the mean shift process of each time. When the drift amount is smaller, a plurality of drift processes exist at corresponding points, so that marketing is encrypted for a plurality of times, and the encryption effect is improved.
However, in practice, because the label value size relationship of each marketing operation is uncertain, the spatial distribution aggregation relationship of the label values has a large difference, so that there may be more outliers which participate in the drifting process less, even do not participate in the drifting, so that the encryption effect is poor or encryption is not performed, so that in order to ensure the encryption integrity and the better encryption effect, the distribution of the label values needs to be corrected before encryption, the aggregation and the distribution uniformity of the label values are improved, so that the label values participate in the drifting process for many times corresponding to marketing information, the encryption effect of the corresponding marketing information is improved, and meanwhile, the fact that the outlier label values do not participate in the drifting process is avoided, namely, the information is not encrypted is avoided, and the integrity of information encryption is improved.
In the mean shift process, the number of the label values participating in the shift process is directly related to the space density degree of the label values, the higher the density degree of the label values is, the smaller the shift amount is, the more the label values participating in the shift process are, and meanwhile, the higher the distribution density uniformity degree of the label values is, the smaller the shift amount is, and the more the label values participating in the shift process are.
Based on the above, the label value is corrected to obtain the preferred label value according to the difference condition of the label value in the neighborhood of the label value, the density degree of the label value in the neighborhood and the uniformity degree of the difference of the label value in the neighborhood,
specifically, for any one tag value, a first correction coefficient is obtained according to the difference condition of the tag values in the neighborhood of the tag value.
In this embodiment, the tag value is time information corresponding to the marketing data, so that the tag value in the neighborhood of the tag value may be understood as another tag value that is closer to the tag value in time. Based on the label value, the label value of all the internet of things client marketing information is formed into a label value sequence, any one label value is recorded as a target label value, and a window with a preset length is formed into a neighborhood of the target label value by taking the target label value as the center in the label value sequence.
In this embodiment, the tag value is time information corresponding to the marketing data, that is, represents occurrence time of the marketing operation, so that the arrangement order of the tag values in the tag value sequence is time sequence of occurrence of the marketing operation. Further, in this embodiment, the window with the preset length is a window formed by a preset time length, that is, the preset time length has a value of 11 time lengths, and the implementer can set according to a specific implementation scenario.
For example, when the time corresponding to the target tag value is the marketing operation occurring at the nth time, and the target tag value is taken as the time center, the neighborhood of the target tag value is the time length range from the nth-5 time to the (n+5) th time, and the tag value in the neighborhood of the target tag value is the tag value corresponding to the marketing operation occurring in the time length range from the nth-5 time to the (n+5) th time.
Respectively acquiring the difference between each label value in the neighborhood and the target label value at the left side of the target label value in the neighborhood of the target label value to obtain a negative direction difference, and marking the sum of all the negative direction differences as the negative direction degree of the target label value; respectively acquiring differences between each tag value in the neighborhood and the target tag value on the right side of the target tag value in the neighborhood of the target tag value to obtain positive direction differences, and marking the sum of all the positive direction differences as the positive direction degree of the target tag value; if the positive direction degree of the target label value is greater than the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a first preset value; the first preset value is a negative number; if the positive direction degree of the target label value is smaller than or equal to the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a second preset value, and the second preset value is a positive number.
It should be noted that the occurrence time of the marketing operation is not uniformly distributed, that is, the number of tag values existing on the left side and the right side of the target tag value may be different or the same in the neighborhood of the target tag value, and the direction in which the target tag value may drift in the subsequent mean shift process is obtained by analyzing the difference between the tag values on the left side and the right side of the target tag value in the neighborhood and the target tag.
In this embodiment, the method for obtaining the negative direction difference specifically includes: the absolute value of the difference between each label value in the neighborhood and the target label value is marked as negative direction difference at the left side of the target label value in the neighborhood of the target label value; the method for acquiring the positive direction difference comprises the following steps: and marking the absolute value of the difference between each label value in the neighborhood and the target label value as a positive direction difference on the right side of the target label value in the neighborhood of the target label value. The negative direction difference characterizes the difference between the left label value and the target label value of the target label value in the neighborhood, and the positive direction difference characterizes the difference between the right label value and the target label value of the target label value in the neighborhood.
In this embodiment, the first preset value is-1, the second preset value is 1, and the practitioner can set according to the specific implementation scenario. Specifically, if the positive direction degree of the target label value is greater than the negative direction degree, it is indicated that the difference condition on the right side of the target label value in the neighborhood is greater than the difference condition on the left side, and further it is indicated that the direction corresponding to the target label value should be on the left side when the target label value is subjected to mean shift in the subsequent process, so that the corresponding first correction coefficient takes a negative value. Otherwise, the direction corresponding to the target label value is the right side of the target label value when the target label value is subjected to mean shift later, so that the value of the corresponding first correction coefficient is a positive number.
And obtaining a second correction coefficient according to the density of the label values in the neighborhood of the label values, wherein the second correction coefficient reflects the density of the label values. Specifically, the maximum value of the total number of tag values contained in the neighborhood of all tag values is obtained; for the target tag value, calculating the ratio of the number of all tag values in the neighborhood of the target tag value to the maximum value to obtain a characteristic ratio of the target tag value, and obtaining a second correction coefficient of the target tag value according to the characteristic ratio; the feature ratio and the second feature coefficient are in negative correlation.
And obtaining a third correction coefficient according to the uniformity degree of the difference of the label values in the neighborhood of the label values, wherein the third correction coefficient reflects the distribution density uniformity degree of the label values. In the neighborhood of the target label value, marking any label value in the neighborhood as a selected neighborhood label value, calculating the average value of the absolute value of the difference value between the selected neighborhood label value and the label values at two adjacent sides of the selected neighborhood label value, and marking the average value as the difference degree of the selected neighborhood label value; and calculating the absolute value of the difference value between the difference degrees of every two arbitrary label values in the neighborhood of the target label value, and taking the average value of the absolute value of the difference values between the difference degrees of all arbitrary two label values in the neighborhood of the target label value as a third correction coefficient of the target label value.
Finally, obtaining the correction degree according to the second correction coefficient and the third correction coefficient; the second correction coefficient and the third correction coefficient are in positive correlation with the correction degree; taking the product of the first correction coefficient and the correction degree as the preferred label value, in this embodiment, taking the ith label value as the target label value as an example, the calculation formula of the preferred label value corresponding to the target label value may be expressed as:
wherein,,representing the preferred tag value corresponding to the ith tag value,/-tag value>First correction coefficient corresponding to the ith tag value,/->Representing the number of tag values contained in the i-th tag value neighborhood,/and>maximum value representing the number of tag values in the neighborhood of all tag values,/->Representing the degree of difference corresponding to the v label value in the i label value neighborhood,/for>Indicating the degree of difference corresponding to the ith tag value in the ith tag value neighborhood, i.e./I>And->Each representing the degree of variance of the selected neighborhood tag values.
The first correction coefficient takes a negative value, which indicates that the difference condition of the right side of the target label value in the neighborhood is larger than the difference condition of the left side, and further indicates that the direction corresponding to the target label value is left side when the target label value is subjected to mean shift in the follow-up process. Otherwise, the value of the first correction coefficient is positive, which indicates that the direction corresponding to the target label value is the right side of the target label value when the target label value is subjected to mean shift in the follow-up process.
For the second correction factor, +.>The ratio of the number of the label values contained in the i-th label value neighborhood is represented, the higher the value of the i-th label value is, the lower the value of the i-th label value is corrected, namely the lower the value of the corresponding second correction coefficient is, and the lower the value of the corresponding corrected preferred label value is.
For the third correction factor, +.>And->All reflect the difference between the selected label value in the neighborhood and the label values around it, so as to analyze the difference between each label value in the neighborhood, when->When the value of (a) is larger, the difference between the difference degrees corresponding to the label values is larger, and the dense average around the ith label value is further illustratedThe smaller the degree of uniformity, the larger the value of the i-th label value corrected, i.e. the larger the value of the corresponding third correction coefficient, the larger the value of the corresponding corrected preferred label value.
According to the method, the label value is corrected to obtain the optimal label value, the aggregation and the distribution uniformity of the label value are improved, so that the label value corresponding to the marketing information can participate in the drifting process for multiple times in the follow-up process, the encryption effect of the corresponding marketing information is improved, meanwhile, the situation that the outlier label value does not participate in the drifting process is avoided, namely, the information is not encrypted is avoided, and the integrity of information encryption is improved.
And the data encryption module is used for clustering the marketing coded data according to the preferred label value, and encrypting the marketing coded data corresponding to the preferred label value in the clustering process to obtain the encrypted marketing data corresponding to the preferred label value.
Each marketing operation independently exists, and the corresponding time of each marketing operation has the characteristics of clustering and dispersing, so that the relation between data generated by each marketing operation can be determined through the time of the marketing operation, and the independent marketing data is encrypted through the relation between each marketing operation.
The data relationship corresponding to the marketing operation is determined based on time distribution, and at the moment, mean shift clustering is firstly carried out based on the time corresponding to the marketing operation, so that the relationship between marketing data corresponding to the marketing operation is determined. The present invention encrypts the marketing data corresponding to each marketing operation based on the above characteristics because the drift vector is easily determined from the region point and the center point during the drift, but a single vector cannot be determined from the drift vector.
In this embodiment, since the number of clusters cannot be determined according to the preferred label value, and the mean shift clustering algorithm does not need to set the number of clusters in advance, the marketing coded data is clustered according to the preferred label value by using the mean shift clustering algorithm. The number of initial center points related to the mean shift is 20, the radius of a circle required by the mean shift is 10, all the initial center points are uniformly distributed in all the preferable label value spaces, and an implementer can set according to specific implementation scenes.
It should be noted that, the mean shift process is mainly represented by moving the center point by using the relationship between the data points and the center point in the circular area, and involves the vector relationship between all the data points and the center point in the circular area corresponding to the center point. In the clustering process, marketing coding data corresponding to the preferred label value is encrypted, and encrypted marketing data corresponding to the preferred label value is obtained.
Based on the method, marketing data corresponding to the center point is fixed, and meanwhile, difference analysis encryption operation is carried out on the marketing data corresponding to all data points in the circular area corresponding to the center point and the marketing data corresponding to the center point. Meanwhile, because the marketing data corresponding to the data points in the circular area are various marketing information, the coding length of the marketing data is far longer than that of the marketing data corresponding to the central point, so that the marketing data corresponding to the data points in the circular area are slid relative to the marketing data corresponding to the central point in order to completely hide the marketing data, and multiple difference analysis encryption operations are carried out, so that the effect of encrypting the marketing data is better.
Specifically, in the clustering process, the preferred label value corresponding to the center point data is marked as a center label value, and the preferred label value in the preset range corresponding to the center label value is marked as an adjacent label value; in this embodiment, the preset range is in a circular area with the center point data as the center and the circular radius length as the radius, where the value of the circular radius length is 10, and the implementer can set according to the specific implementation scenario.
And for any one central tag value, using marketing coding data corresponding to the central tag value as template coding data, and encrypting marketing coding data corresponding to the adjacent tag value according to the difference between the template coding data and marketing coding data corresponding to the adjacent tag value to obtain encrypted marketing data corresponding to the adjacent tag value. The marketing code data corresponding to any adjacent tag value is recorded as selected code data, the left end of the template code data is aligned with the selected code data, the first exclusive-or operation is carried out on the selected code data, the marketing code data obtained after the first exclusive-or operation slides leftwards according to a set step length, the marketing code data obtained after the first exclusive-or operation is carried out on the marketing code data according to the template code data, and the second exclusive-or operation is carried out, so that the exclusive-or operation is stopped until the right end of the template code data is aligned with the right end of the selected code data, and the encrypted marketing data corresponding to the selected code data is obtained.
For example, a center tag value corresponds to a marketing code of 011011, i.e., a template code of 011011, and a neighboring tag value corresponds to a marketing code of 1101101001, i.e., a selected code of 1101101001, in a circular region corresponding to the center tag value. As shown in fig. 2, fig. 2 is a schematic diagram illustrating an encryption process of marketing coded data according to an embodiment of the present invention, wherein,encoding data 011011 for templates, < >>For the selected encoded data 1101101001, the left end of the template encoded data is aligned with the left end of the selected encoded data, and the first exclusive-or operation is performed on the selected encoded data to obtain marketing encoded data 1011011001 obtained after the first exclusive-or operation, and the marketing encoded data obtained after the first exclusive-or operation is slid to the left according to a set step length, in this embodiment, the value of the set step length is 2, and an implementer can set according to a specific implementation scenario. Namely, after the marketing code data obtained after the first exclusive-or operation slides leftwards by a step length of 2, performing a second exclusive-or operation on the marketing code data obtained after the first exclusive-or operation according to the template code data to obtain marketing code data 1010110101 obtained after the second exclusive-or operation, wherein the template code data 011011 is not aligned with the right end of the selected code data 1101101001 at this time, so that sliding encryption processing still needs to be performed on the selected template data, namely, after the marketing code data obtained after the second exclusive-or operation slides leftwards by a step length of 2, obtaining marketing code data obtained after the second exclusive-or operation according to the code dataAnd (3) performing the third exclusive-or operation to obtain marketing coded data 1010101110 obtained after the third exclusive-or operation, and after the marketing coded data is encrypted by the third exclusive-or operation, the template coded data 011011 is aligned with the right end of the selected coded data 1101101001, so that the marketing coded data obtained after the third exclusive-or operation at this time is the encrypted marketing data corresponding to the adjacent tag value.
Meanwhile, it should be noted that, the drift amount in the mean shift process is determined by the positions of the data points in the circular area corresponding to the center point, when the drift amount is smaller, more data points participate in multiple shifts, that is, after the center point is shifted for a certain time in the clustering process, the encrypted marketing coded data possibly exists in the corresponding circular area, at this time, the encrypted marketing data in the circular area is used as the original coded data, and the sliding exclusive or encryption operation is continuously performed on the original coded data, so that multiple encryption on the marketing data according to the preferred label value is realized, and the encryption effect is better.
The marketing coding data corresponding to the central tag value is an encryption key, the marketing coding data corresponding to the adjacent tag value is plaintext information in a round area corresponding to the central tag value, and the result of the exclusive-or operation is the encrypted marketing data adjacent to the tag value, namely ciphertext information. When the drift process is participated for a plurality of times, the encrypted marketing data obtained by the exclusive or encryption operation corresponding to the last drift process is the final ciphertext information.
In order to ensure the integrity of the information, when the encrypted marketing data is stored, the corresponding tag value and the preferred tag value are used as the additional ciphertext to be stored together with the encrypted information. And the preferred label value participates in a multiple-drift process to encrypt marketing information corresponding to the preferred label value for multiple times, so that the encryption effect is effectively improved. Meanwhile, the marketing data encrypted for many times are gathered and distributed on the time sequence, so that the marketing data is relatively important, namely the encryption effect of important information can be improved to a certain extent in the current encryption process.
In summary, the method and the device utilize the time distribution dense relation corresponding to each marketing operation to further determine the relation between marketing data corresponding to each marketing operation, thereby facilitating encryption of marketing information and improving encryption effect. In the mean shift clustering process, the marketing data is encrypted for a plurality of times by utilizing the relation among the optimal label values, so that the current encryption cannot be cracked by violence, and the safety of the information is greatly ensured. Meanwhile, the distribution of the tag values is required to be corrected before encryption, the aggregation and the distribution uniformity of the tag values are improved, the tag values are enabled to participate in the drifting process for a plurality of times corresponding to the marketing information, the encryption effect of the corresponding marketing information is improved, meanwhile, the fact that the outlier tag values do not participate in the drifting process is avoided, namely, the information is prevented from being encrypted, and therefore the integrity of information encryption is improved.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the scope of the embodiments of the present application, and are intended to be included within the scope of the present application.
Claims (10)
1. Client marketing information management system based on the internet of things, which is characterized in that the system comprises:
the data acquisition module is used for acquiring the tag value and marketing coding data of the marketing information of the client of the Internet of things;
the data preprocessing module is used for correcting the label value according to the difference condition of the label value in the neighborhood of the label value, the density degree of the label value in the neighborhood and the uniformity degree of the difference of the label value in the neighborhood to obtain a preferable label value;
and the data encryption module is used for clustering the marketing coded data according to the preferred label value, and encrypting the marketing coded data corresponding to the preferred label value in the clustering process to obtain the encrypted marketing data corresponding to the preferred label value.
2. The system of claim 1, wherein the modifying the tag value to obtain the preferred tag value according to a difference of tag values in a neighborhood of the tag value, a density of tag values in the neighborhood, and a uniformity of the difference of tag values in the neighborhood comprises:
for any one tag value, a first correction coefficient is obtained according to the difference condition of the tag values in the neighborhood of the tag value; obtaining a second correction coefficient according to the density of the label values in the neighborhood of the label values; obtaining a third correction coefficient according to the uniformity degree of the difference of the label values in the neighborhood of the label value; obtaining the correction degree according to the second correction coefficient and the third correction coefficient; the second correction coefficient and the third correction coefficient are in positive correlation with the correction degree; the product of the first correction coefficient and the correction degree is taken as a preferred label value.
3. The system for managing marketing information of clients based on the internet of things according to claim 2, wherein the obtaining the first correction coefficient according to the difference of the tag values in the neighborhood of the tag values is specifically:
forming a tag value sequence by tag values of all the client marketing information of the Internet of things, marking any tag value as a target tag value, and forming a neighborhood of the target tag value by taking the target tag value as a center and a window with a preset length in the tag value sequence;
respectively acquiring the difference between each label value in the neighborhood and the target label value at the left side of the target label value in the neighborhood of the target label value to obtain a negative direction difference, and marking the sum of all the negative direction differences as the negative direction degree of the target label value;
respectively acquiring differences between each tag value in the neighborhood and the target tag value on the right side of the target tag value in the neighborhood of the target tag value to obtain positive direction differences, and marking the sum of all the positive direction differences as the positive direction degree of the target tag value;
if the positive direction degree of the target label value is greater than the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a first preset value; the first preset value is a negative number;
if the positive direction degree of the target label value is smaller than or equal to the negative direction degree, the value of the first correction coefficient corresponding to the target label value is a second preset value, and the second preset value is a positive number.
4. The system for managing marketing information of clients based on the internet of things according to claim 3, wherein the method for acquiring the negative direction difference is specifically as follows:
the absolute value of the difference between each label value in the neighborhood and the target label value is marked as negative direction difference at the left side of the target label value in the neighborhood of the target label value;
the method for acquiring the positive direction difference comprises the following steps:
and marking the absolute value of the difference between each label value in the neighborhood and the target label value as a positive direction difference on the right side of the target label value in the neighborhood of the target label value.
5. The system for managing marketing information of clients based on the internet of things according to claim 3, wherein the obtaining the second correction coefficient according to the density of the tag values in the neighborhood of the tag values is specifically as follows:
obtaining the maximum value of the total number of the tag values contained in the neighborhood of all the tag values;
for the target tag value, calculating the ratio of the number of all tag values in the neighborhood of the target tag value to the maximum value to obtain a characteristic ratio of the target tag value, and obtaining a second correction coefficient of the target tag value according to the characteristic ratio; the feature ratio and the second feature coefficient are in negative correlation.
6. The system for managing marketing information of clients based on the internet of things according to claim 3, wherein the obtaining the third correction coefficient according to the uniformity of the difference of the tag values in the neighborhood of the tag values is specifically:
in the neighborhood of the target label value, marking any label value in the neighborhood as a selected neighborhood label value, calculating the average value of the absolute value of the difference value between the selected neighborhood label value and the label values at two adjacent sides of the selected neighborhood label value, and marking the average value as the difference degree of the selected neighborhood label value;
and calculating the absolute value of the difference value between the difference degrees of every two arbitrary label values in the neighborhood of the target label value, and taking the average value of the absolute value of the difference values between the difference degrees of all arbitrary two label values in the neighborhood of the target label value as a third correction coefficient of the target label value.
7. The marketing information management system based on the internet of things client of claim 1, wherein the clustering of the marketing-coded data according to the preferred tag value is specifically: and clustering the marketing coded data according to the preferred label value by using a mean shift clustering algorithm.
8. The system for managing marketing information of clients based on the internet of things according to claim 1, wherein in the clustering process, the marketing coding data corresponding to the preferred tag value is encrypted to obtain the encrypted marketing data corresponding to the preferred tag value, and the system specifically comprises:
in the clustering process, marking the preferred label value corresponding to the center point data as a center label value, and marking the preferred label value in the preset range corresponding to the center label value as an adjacent label value;
and for any one central tag value, using marketing coding data corresponding to the central tag value as template coding data, and encrypting marketing coding data corresponding to the adjacent tag value according to the difference between the template coding data and marketing coding data corresponding to the adjacent tag value to obtain encrypted marketing data corresponding to the adjacent tag value.
9. The system of claim 1, wherein the encrypting the marketing code data corresponding to the proximity tag value according to the difference between the template code data and the marketing code data corresponding to the proximity tag value to obtain the encrypted marketing data corresponding to the proximity tag value, specifically comprises:
marking marketing coded data corresponding to any adjacent tag value as selected coded data, aligning the left end of the template coded data with the selected coded data, performing first exclusive-or operation on the selected coded data, sliding the marketing coded data obtained after the first exclusive-or operation leftwards according to a set step length, performing second exclusive-or operation on the marketing coded data obtained after the first exclusive-or operation according to the template coded data, and pushing the marketing coded data until the right end of the template coded data is aligned with the right end of the selected coded data, and stopping the exclusive-or operation until the encrypted marketing data corresponding to the selected coded data is obtained.
10. The system for managing marketing information of clients based on the internet of things according to claim 1, wherein the tag value and the marketing coding data of the obtained marketing information of the clients based on the internet of things are specifically:
the method comprises the steps of converting time data and marketing data in the client marketing information of the Internet of things into binary coded data, converting the binary coded data corresponding to the time data into decimal data, taking the decimal data corresponding to the time data corresponding to each marketing operation as a label value corresponding to each marketing operation, and taking the binary coded data corresponding to the marketing data corresponding to each marketing operation as marketing coded data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310512600.5A CN116226893B (en) | 2023-05-09 | 2023-05-09 | Client marketing information management system based on Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310512600.5A CN116226893B (en) | 2023-05-09 | 2023-05-09 | Client marketing information management system based on Internet of things |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116226893A true CN116226893A (en) | 2023-06-06 |
CN116226893B CN116226893B (en) | 2023-08-01 |
Family
ID=86587725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310512600.5A Active CN116226893B (en) | 2023-05-09 | 2023-05-09 | Client marketing information management system based on Internet of things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116226893B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116502107A (en) * | 2023-06-21 | 2023-07-28 | 杭州端点网络科技有限公司 | Data intelligent operation platform supply chain data processing system based on artificial intelligence |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102523241A (en) * | 2012-01-09 | 2012-06-27 | 北京邮电大学 | Method and device for classifying network traffic on line based on decision tree high-speed parallel processing |
CN103824128A (en) * | 2014-02-24 | 2014-05-28 | 华南理工大学 | Method for scale prediction of regional distributed type comprehensive energy-supply system |
WO2014091252A1 (en) * | 2012-12-14 | 2014-06-19 | Omarco Network Solutions Limited | Improvements relating to identifier authentication |
CN107590020A (en) * | 2017-07-14 | 2018-01-16 | 同济大学 | A kind of trusted computing method based on differentiation coding and sentence signature |
CN108304969A (en) * | 2018-01-30 | 2018-07-20 | 东南大学 | A kind of development zone planned land use scale forecast method based on space efficiency |
CN111159258A (en) * | 2019-12-31 | 2020-05-15 | 科技谷(厦门)信息技术有限公司 | Customer clustering implementation method based on cluster analysis |
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 |
CN114064453A (en) * | 2021-10-12 | 2022-02-18 | 华南理工大学 | Software test case automatic generation method based on clustering and evolutionary algorithm |
CN114629701A (en) * | 2022-03-11 | 2022-06-14 | 娄底职业技术学院 | Information display system based on information encryption |
CN115333735A (en) * | 2022-10-11 | 2022-11-11 | 浙江御安信息技术有限公司 | Safe data transmission method |
CN116029394A (en) * | 2023-03-29 | 2023-04-28 | 季华实验室 | Self-adaptive text emotion recognition model training method, electronic equipment and storage medium |
-
2023
- 2023-05-09 CN CN202310512600.5A patent/CN116226893B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102523241A (en) * | 2012-01-09 | 2012-06-27 | 北京邮电大学 | Method and device for classifying network traffic on line based on decision tree high-speed parallel processing |
WO2014091252A1 (en) * | 2012-12-14 | 2014-06-19 | Omarco Network Solutions Limited | Improvements relating to identifier authentication |
CN103824128A (en) * | 2014-02-24 | 2014-05-28 | 华南理工大学 | Method for scale prediction of regional distributed type comprehensive energy-supply system |
CN107590020A (en) * | 2017-07-14 | 2018-01-16 | 同济大学 | A kind of trusted computing method based on differentiation coding and sentence signature |
CN108304969A (en) * | 2018-01-30 | 2018-07-20 | 东南大学 | A kind of development zone planned land use scale forecast method based on space efficiency |
CN111159258A (en) * | 2019-12-31 | 2020-05-15 | 科技谷(厦门)信息技术有限公司 | Customer clustering implementation method based on cluster analysis |
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 |
CN114064453A (en) * | 2021-10-12 | 2022-02-18 | 华南理工大学 | Software test case automatic generation method based on clustering and evolutionary algorithm |
CN114629701A (en) * | 2022-03-11 | 2022-06-14 | 娄底职业技术学院 | Information display system based on information encryption |
CN115333735A (en) * | 2022-10-11 | 2022-11-11 | 浙江御安信息技术有限公司 | Safe data transmission method |
CN116029394A (en) * | 2023-03-29 | 2023-04-28 | 季华实验室 | Self-adaptive text emotion recognition model training method, electronic equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
HASSAN KHAN: "Designing a cluster-based covert channel to evade disk investigation and forensics", 《COMPUTERS & SECURITY》, vol. 30, no. 2011, pages 35 - 49, XP028128337, DOI: 10.1016/j.cose.2010.10.005 * |
曹计昌;邓祯;: "基于旋转编码模板匹配的烟支计数识别", 计算机辅助设计与图形学学报, no. 08, pages 1 - 6 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116502107A (en) * | 2023-06-21 | 2023-07-28 | 杭州端点网络科技有限公司 | Data intelligent operation platform supply chain data processing system based on artificial intelligence |
CN116502107B (en) * | 2023-06-21 | 2023-09-01 | 杭州端点网络科技有限公司 | Data intelligent operation platform supply chain data processing system based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN116226893B (en) | 2023-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI670621B (en) | Information encryption and decryption method and device | |
CN115272502B (en) | Software research and development data security management method based on code conversion | |
CN116226893B (en) | Client marketing information management system based on Internet of things | |
CN106875325B (en) | Searchable image encryption algorithm | |
CN116226471B (en) | Data storage method for homeland resource planning | |
CN115150818B (en) | Communication transmission encryption method based on artificial intelligence | |
CN116522300B (en) | Intelligent management system for electronic seal | |
CN115567329B (en) | Data security encryption method for network information | |
CN116071164B (en) | Digital asset tracing method based on blockchain management | |
CN115460382A (en) | Security and protection engineering monitoring data safety transmission method | |
CN111191255A (en) | Information encryption processing method, server, terminal, device and storage medium | |
CN114640523A (en) | Computer data security encryption algorithm and system | |
Sun et al. | [Retracted] Face Security Authentication System Based on Deep Learning and Homomorphic Encryption | |
CN117596346A (en) | Cloud data encryption transmission method and device | |
CN115292739B (en) | Data management method of metal mold design system | |
CN116825259A (en) | Medical data management method based on Internet of things | |
Zhang et al. | A fast visually meaningful image encryption algorithm based on compressive sensing and joint diffusion and scrambling | |
CN111008276B (en) | Complete entity relationship extraction method and device | |
CN112883389A (en) | Reversible desensitization algorithm supporting feature preservation | |
Yan et al. | Secret image sharing based on error-correcting codes | |
CN117040913B (en) | Cloud resource sharing data security transmission method and system | |
CN117034367B (en) | Electronic seal key management method | |
US20230171092A1 (en) | System and Method for Secure Detection of Similarity and Dissimilarity of Events | |
CN118250402B (en) | Artificial intelligence control method and device based on big data | |
CN111159761B (en) | Model training method and device |
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 |