CN116418881A - Data intelligent processing method for E-commerce big data cloud edge cooperative transmission - Google Patents
Data intelligent processing method for E-commerce big data cloud edge cooperative transmission Download PDFInfo
- Publication number
- CN116418881A CN116418881A CN202310409600.2A CN202310409600A CN116418881A CN 116418881 A CN116418881 A CN 116418881A CN 202310409600 A CN202310409600 A CN 202310409600A CN 116418881 A CN116418881 A CN 116418881A
- Authority
- CN
- China
- Prior art keywords
- data
- shopping
- behavior
- browsing
- behavior vector
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 38
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims description 26
- 238000004891 communication Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 description 98
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/40—Conversion to or from variable length codes, e.g. Shannon-Fano code, Huffman code, Morse code
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/04—Protocols for data compression, e.g. ROHC
-
- 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)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (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 data intelligent processing method for big data cloud edge cooperative transmission of electronic commerce, which collects behavior data of each user under the shopping flow of any commodity in a preset time length to form a behavior vector; acquiring shopping intention indexes reflected by each behavior vector based on the number of effective elements of the behavior vector and the stay time of a user in a corresponding shopping flow; acquiring potential shopping values according to browsing quantity of similar commodities in historical data of any one behavior vector, shopping intention indexes of the similar commodities and browsing time duration; constructing codes corresponding to each behavior vector according to the potential shopping value by utilizing Huffman codes; the corresponding behavior data is compressed in order of encoding from short to long. According to the invention, the priority of the user behavior is divided through data processing, so that the purchase intention of the user can be accurately analyzed, and valuable data can be timely obtained during cloud-edge cooperative transmission.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a data intelligent processing method for e-commerce big data cloud edge cooperative transmission.
Background
With the gradual convergence of network economy and entity economy, electronic commerce has also emerged as a stage of rapid development and has become an integral part of people's lives. The biggest characteristic of electronic commerce is that everything can be monitored and improved through data, so that big electronic commerce data is a core strategy for future development. The electronic commerce data mainly records the behavior data of the users, potential values are obtained through data analysis, relevant regulation and control are carried out, and a plurality of users are always online at the same time, so that the corresponding behavior data volume is huge, and compression and transmission pressure is huge.
The existing data transmission technology is used for carrying out coding compression on all data, then transmitting the data at the same moment one by one, the transmission efficiency is lower, the transmission pressure is higher, in the transmission mode, the data received by a cloud is disordered, effective data with shopping value cannot be identified, the intelligent degree of data analysis is lower, the data processing requirement of large data of an e-commerce at the present stage cannot be met, a data processing method for predicting buying intention by using user data exists at present, the more common method is used for acquiring buying intention by using user browsing behavior data, but the basis for acquiring the buying intention by using the existing method is single, the analysis result of the buying intention of a user is inaccurate, and the valuable data is not transmitted timely.
Disclosure of Invention
In order to solve the technical problems of inaccurate analysis results of purchasing intent of users and untimely valuable data transmission in the E-commerce big data processing process, the invention provides a data intelligent processing method for E-commerce big data cloud-edge cooperative transmission, which adopts the following technical scheme:
the embodiment of the invention provides a data intelligent processing method for E-commerce big data cloud edge cooperative transmission, which comprises the following steps:
collecting behavior data of each user under the shopping flow of any commodity in a preset time length to form a behavior vector;
acquiring shopping intention indexes reflected by each behavior vector based on the number of effective elements of the behavior vector and the stay time of a user in a corresponding shopping flow; acquiring potential shopping values according to browsing quantity of similar commodities in historical data of any one behavior vector, shopping intention indexes of the similar commodities and browsing time duration;
constructing codes corresponding to each behavior vector according to the potential shopping value by utilizing Huffman codes; and compressing corresponding behavior data according to the sequence from short code to long code and carrying out cloud-edge cooperative transmission.
Further, the shopping intention index obtaining method comprises the following steps:
taking the proportion of the number of the effective elements of each behavior vector in the number of all elements contained in the behavior data as a corresponding effective proportion, and acquiring shopping intention indexes of the corresponding behavior vectors according to the effective proportion and the stay time of the user in the corresponding shopping flow; the effective proportion and the stay time are in positive correlation with the shopping intention index.
Further, the method for acquiring the potential shopping value comprises the following steps:
for any one behavior vector, acquiring shopping intention indexes corresponding to each similar commodity in historical data, summing to obtain historical intention indexes, and weighting and summing the browsing quantity and the historical intention indexes to obtain the purchase probability degree of the corresponding behavior vector;
obtaining browsing similarity based on the difference between the corresponding browsing duration and the minimum value in all browsing durations of each similar commodity;
and taking the normalized result of the ratio of the purchase possibility degree to the browsing similarity degree as the potential shopping value.
Further, the browsing amount obtaining method includes:
and for any one of the behavior vectors, taking the behavior vector in the preset history time before the corresponding shopping flow as the corresponding history data, and acquiring the number of similar commodities browsed by the user in the history data as the browsing quantity.
Further, the method for acquiring the browsing duration from the present time comprises the following steps:
and acquiring the duration between the browsing time of each similar commodity in the historical data and the time of the current shopping flow as the browsing duration.
Further, in the process of acquiring the purchase possibility degree, the browsing amount is weighted to be greater than or equal to the historical intent index.
Further, the composition process of the behavior vector is as follows:
the behavior data comprises at least one of browsing duration, clicking times, customer service communication duration, whether to collect, join in shopping carts and pay, the values of the corresponding data are obtained based on the behavior result of each item of data, and the values of all the data form the behavior vector.
Further, the method for obtaining the number of the effective elements comprises the following steps: and taking the number of non-zero valued data in all data composing the behavior vector as the number of effective elements.
The embodiment of the invention has at least the following beneficial effects:
acquiring behavior data of a user under the shopping flow of any commodity in a preset time period to form a behavior vector, quantifying the behavior of the user when browsing the commodity shopping by the behavior data to form the behavior vector, and representing the preference of the user for each commodity; acquiring shopping intention indexes under the current action vector through the number of effective elements in the action vector and the corresponding stay time, acquiring the possibility of shopping of the user according to the action of the user, quantifying the possibility of shopping into the shopping intention indexes, and reflecting the possibility of shopping of the user under the current action; then, based on the browsing amount, shopping intention index and browsing duration of similar commodities in the historical data of the behavior vector, obtaining potential shopping values, and estimating the possibility of purchasing the similar commodities by a user, namely the potential shopping values, by referring to the browsing condition, shopping possibility and the latest browsing duration of the similar commodities in the historical data; the larger the potential shopping value is, the more likely the user finishes purchasing when encountering similar commodities next time, and the Huffman codes are utilized to construct codes corresponding to each action vector according to the potential shopping value; according to the method, corresponding behavior data are compressed according to the sequence from short to long, the priority of user behaviors is divided according to the potential shopping value through the data processing method, the purchasing intention of a user is accurately analyzed, the user behavior data which are more likely to have shopping behaviors in the future are compressed preferentially and are transmitted in a cloud-edge cooperative mode, valuable data can be transmitted in time during the cloud-edge cooperative transmission, and more benefits are brought to electronic commerce.
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 flow chart of steps of a data intelligent processing method for e-commerce big data cloud edge cooperative transmission according to an embodiment of the present invention;
FIG. 2 is a table of behavior data according to one 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 is a detailed description of specific implementation, structure, characteristics and effects thereof for the data intelligent processing method for e-commerce big data cloud-edge cooperative transmission according to the invention, which is provided by the invention, with reference to 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 specific scheme of the data intelligent processing method for the e-commerce big data cloud edge cooperative transmission provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a step flow chart of a data intelligent processing method for e-commerce big data cloud edge cooperative transmission according to an embodiment of the present invention is shown, the method includes the following steps:
step S001, collecting behavior data of each user under the shopping flow of any commodity in a preset time period to form a behavior vector.
The electronic commerce data mainly records transaction information corresponding to a user, the most important operation data of the user on a certain commodity in the transaction information comprises operation corresponding data such as browsing time length, clicking times, customer service communication time length, collection or not, and a series of data from entering a link to finally purchasing a certain commodity by the user is recorded, and the process is recorded as a shopping flow of the user on the certain commodity.
As an example, in the embodiment of the present invention, the data includes at least one of browsing duration, clicking times, customer service communication duration, collection, shopping cart joining, and payment, and the values of the corresponding data are obtained based on the behavior result of each item of data, and the values of all the data form a behavior vector.
After the electronic commerce data of each user are obtained, the behavior vector of each shopping flow is obtained according to the obtained behavior data and the corresponding behavior result, wherein in the judgment result, the corresponding number is 1, and the corresponding number is 0.
As shown in the behavior data table in FIG. 2, the user ID is A1, the commodity ID is 256454, the first class corresponding to the commodity is 221456, the second class is 35264, the browsing time is 5min, the clicking time is 5, the customer service communication time is 0.6min, the result of collecting is yes, the result of adding shopping cart is yes, the result of paying is yes, and the corresponding behavior vector X is obtained A1 ＝{A1,256454,221456,35264,5,5,0.6,1,1,1}。
Different commodities can obtain a corresponding primary classification standard according to commodity attributes, the primary classification corresponding to the commodities is different from the secondary classification in different electronic commerce platforms, and the relevant platforms have mature classification standards.
As an example, in the embodiment of the present invention, the preset duration is 10 minutes, that is, the data of a certain purchase procedure of a certain user is collected within 10 minutes to form a corresponding behavior vector.
Step S002, based on the number of the effective elements of the behavior vectors and the stay time of the user in the corresponding shopping flow, acquiring shopping intention indexes reflected by each behavior vector; and obtaining potential shopping values according to browsing quantity of similar commodities, shopping intention indexes of the similar commodities and browsing time duration in the historical data of any one behavior vector.
Carrying out subsequent analysis and transmission on data every 10 minutes, wherein in each 10 minutes, behavior vectors formed by behavior data corresponding to a plurality of users exist, part of data in the behavior vectors represent the situation that the users have purchase intention on commodities but behavior is stopped in the purchase process, so that the users have a certain potential value, related products should be continuously recommended to the users, certain distribution characteristics are presented in the behavior data, and the users browse the same commodities or similar commodities in a certain historical time range; in contrast, some users directly complete purchase, and the potential value of the users in the future is relatively low, and the users also present certain distribution characteristics in the behavior data, so that the potential value of the data in the future can be evaluated to a certain extent by analyzing the data distribution characteristics in the behavior data.
The number of non-zero valued data in all the data composing the behavior vector is taken as the number of effective elements.
Taking the proportion of the number of the effective elements of each behavior vector in the number of all elements contained in the behavior data as the corresponding effective proportion, and acquiring shopping intention indexes of the corresponding behavior vectors according to the effective proportion and the stay time of the user in the corresponding shopping flow; the effective proportion and the stay time are in positive correlation with the shopping intention index.
For example, action vector X A1 The number of effective elements in = { a1,256454,221456,35264,5,5,0.6,1,1,1} is 10, and the number of all elements is also 10. The effective ratio obtained is 1.
The more the purchasing behavior of the user passes through in the whole purchasing process, namely, the closer the purchasing behavior is to the successful payment behavior, the more the variables corresponding to the existence values are, namely, the larger the effective proportion is, and the larger the purchasing intention of the corresponding user to the commodity is; the longer the user stays in the overall purchasing flow of the commodity, i.e. the stay time t re The larger the corresponding user's intention to purchase the commodity; namely, the effective proportion and the stay time are in positive correlation with the shopping intention index.
The larger the shopping intention index DI is, the larger the user's intention to purchase the commodity is, but when the user completes the entire purchase flow, i.e., the effective ratio becomes 1, the user has purchased the commodity, the corresponding intention to purchase disappears, i.e., the shopping intention index DI becomes 0.
Thus, when the effective ratio is not 1, the shopping intention index of the corresponding behavior vector is calculated:
wherein DI represents shopping intention index, nor () represents normalization function, M ev Representing the number of effective elements, M gv Indicating the number of all the elements,
representing the effective proportion, ||representing the absolute value, |j +.>
Representing a base number of 10
Logarithm of (2); exp () represents an exponential function based on a natural constant e, t re Indicating the dwell time.
The shopping intention index corresponding to each shopping flow is obtained, and because of certain contingency of the data, the single data cannot accurately measure whether the data corresponding to the shopping flow has future potential value or not, and whether the data has future potential value or not can be evaluated more accurately by combining other data corresponding to the user in the historical data, so that targeted regulation and control are realized.
In the e-commerce data, the behavior data of different users have certain difference, some of the behavior data of the users have future potential values, for example, when a user exits when arriving at a payment operation, the user has potential value of purchasing the commodity in the future, the commodity should be continuously promoted to the user, and the future potential values of the corresponding data of different users are different.
At the data acquisition end, historical data, namely a time sequence table arranged in time sequence, is stored, so that the data distribution characteristics in the historical data can be analyzed to judge whether the user has potential value of purchasing the commodity in the future.
And for any one of the behavior vectors, taking the behavior vector in the preset history time before the corresponding shopping flow as the corresponding history data, and acquiring the number of similar commodities browsed by the user as browsing quantity.
As an example, in the embodiment of the present invention, the preset history period is 5 days, and in other embodiments, the time span of the preset history period may be adjusted according to the actual situation. In the preset historical time before each shopping flow, the more similar commodities are browsed by the user, the stronger the purchasing intention of the user for the similar commodities is, and the higher the degree of contact between the current data and the data in the preset historical time is, the higher the future potential value rate of the corresponding shopping flow is.
Counting the number M of the behavior vectors corresponding to the same secondary classified commodity recorded by the user in a preset history time period s As a browsing volume. The more browsed the greater the future potential value rate of the corresponding shopping flow.
And acquiring the duration between the browsing time of each similar commodity in the historical data and the time of the current shopping flow as the browsing duration.
The corresponding commodities of the behavior vectors are classified into two classes, the commodities under the same class are similar commodities, and the duration between the corresponding moment and the current moment of each behavior vector in the historical data is obtained, namely how long the corresponding similar commodity is separated from the current behavior vector in each browsing of the historical data, and is used as the browsing duration of the corresponding similar commodity.
The more similar commodities are browsed by a user in a short time, the more likely the similar commodities are purchased, namely the shorter the browsing time duration from the present time is, the higher the future potential value rate is.
Based on the method, potential shopping values are obtained according to browsing amounts of similar commodities, shopping intention indexes of the similar commodities and browsing duration in historical data of any one behavior vector.
Specifically, for any one behavior vector, shopping intention indexes corresponding to each similar commodity in the historical data are obtained, the historical intention indexes are obtained through summation, and the browsing amount and the historical intention indexes are weighted and summed to obtain the purchase possibility degree of the corresponding behavior vector; the browsing amount has a weight greater than or equal to the weight of the historical intent index.
The calculation formula of the purchase possibility degree is as follows:
wherein F represents the purchase possibility, W 1 Weights representing browsing amounts, M S Represents the browsing amount, W 2 Weights representing historical intent index, DI i Indicating the shopping intention index of the ith like commodity,
representing historical intent index.
The browsing amount has a greater influence on the purchase possibility than the historical intent index of the like commodity, and thus the browsing amount has a weight greater than or equal to the weight of the historical intent index. As an example, in an embodiment of the present invention, W 1 ＝0.7、W 2 =0.3. The values of the two weights may also be adjusted in other embodiments.
Obtaining browsing similarity based on the difference between the browsing duration corresponding to each similar commodity and the minimum value in all the browsing durations:
wherein D is T Represents the browsing similarity degree, t i Representing the browsing time length, t of the ith similar commodity (i,min) Representing the shortest browsing duration in all the same kind of commodities.
Taking the normalized result of the ratio of the purchase likelihood level to the browse closeness level as the potential shopping value:
where Fpv represents potential shopping value and nor () represents the normalization function.
The more the user browses the same kind of commodity in the history data, namely the browsing amount M s The larger the corresponding user has higher purchase probability for the commodity, the higher the future potential value; the higher the intention index corresponding to the similar secondary commodity browsed by the user, namely the larger the historical intention index, the higher the probability of purchasing by the user, and the higher the corresponding future potential value; the closer the user browses the similar secondary commodity to the current moment, namely the browsing similarity degree D T The smaller the probability of purchasing the commodity, the higher the corresponding future potential value; i.e., the greater the potential shopping value Fpv, the higher the future potential value of the item purchased by the user corresponding to the current behavior vector.
Step S003, constructing codes corresponding to each behavior vector according to the potential shopping value by utilizing Huffman codes; and compressing corresponding behavior data according to the sequence from short code to long code and carrying out cloud-edge cooperative transmission.
Different data have different potential shopping values, huffman codes are coded according to the frequency of the occurrence of the numbers, and similarly, the potential shopping values can be represented by short codes and the potential shopping values are smaller according to the potential shopping values of the action vectors.
Because the behavior vectors with high potential shopping values are represented by short codes, and the relatively lower behavior vectors are represented by long codes, the data with future potential values can be preferentially acquired and analyzed, and then the relevant regulation and control can be carried out in real time when cloud-edge cooperative transmission is carried out, the regulation and control effect is good, so that the behavior data with high potential shopping values represented by the short codes are preferentially transmitted by compressing and cloud-edge cooperative transmission according to the length of the codes.
The data volume of the cooperative transmission of Yun Bian is limited in every 10 minutes, and all the behavior data cannot be transmitted, so that the behavior data with shorter codes is preferentially transmitted, the next 10 minutes of behavior data is corresponding, the coding is continued, the behavior data with the code length smaller than the shortest code length in the last 10 minutes of legacy data is preferentially transmitted, the next 10 minutes of behavior data with shorter codes in the legacy data is transmitted, and the cloud-edge cooperative transmission of the behavior data in every 10 minutes is realized by iterating the process.
By compressing and storing all the behavior data in every 10 minutes according to the size sequence of the potential shopping values, the behavior data of the user can be ordered according to the size sequence of the potential shopping values, higher priority is given to the user data with high potential shopping values, then cloud edge cooperative transmission is carried out according to the encoding length, the behavior vector with high potential shopping values is transmitted preferentially, the transmission efficiency can be improved, and corresponding feedback is timely carried out on the behavior data with high potential shopping values.
In summary, the embodiment of the invention collects the behavior data of each user under the shopping flow of any commodity in the preset time period to form the behavior vector; acquiring shopping intention indexes reflected by each behavior vector based on the number of effective elements of the behavior vector and the stay time of a user in a corresponding shopping flow; acquiring potential shopping values according to browsing quantity of similar commodities in historical data of any one behavior vector, shopping intention indexes of the similar commodities and browsing time duration; constructing codes corresponding to each behavior vector according to the potential shopping value by utilizing Huffman codes; the corresponding behavior data is compressed in order of encoding from short to long. According to the invention, the priority of the user behavior is divided according to the potential shopping value by the data processing method, the purchase intention of the user is accurately analyzed, the user behavior which is more likely to have shopping behavior in the future is compressed preferentially and cloud-edge cooperative transmission is carried out, valuable data can be transmitted in time during the cloud-edge cooperative transmission, and more benefits are brought to the electronic commerce.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (8)
1. The intelligent data processing method for the cloud-edge cooperative transmission of the big data of the electronic commerce is characterized by comprising the following steps of:
collecting behavior data of each user under the shopping flow of any commodity in a preset time length to form a behavior vector;
acquiring shopping intention indexes reflected by each behavior vector based on the number of effective elements of the behavior vector and the stay time of a user in a corresponding shopping flow; acquiring potential shopping values according to browsing quantity of similar commodities in historical data of any one behavior vector, shopping intention indexes of the similar commodities and browsing time duration;
constructing codes corresponding to each behavior vector according to the potential shopping value by utilizing Huffman codes; and compressing corresponding behavior data according to the sequence from short code to long code and carrying out cloud-edge cooperative transmission.
2. The intelligent data processing method for the e-commerce big data cloud edge cooperative transmission of claim 1, wherein the shopping intention index obtaining method is as follows:
taking the proportion of the number of the effective elements of each behavior vector in the number of all elements contained in the behavior data as a corresponding effective proportion, and acquiring shopping intention indexes of the corresponding behavior vectors according to the effective proportion and the stay time of the user in the corresponding shopping flow; the effective proportion and the stay time are in positive correlation with the shopping intention index.
3. The intelligent data processing method for the e-commerce big data cloud edge cooperative transmission of claim 1, wherein the acquisition method of the potential shopping value is as follows:
for any one behavior vector, acquiring shopping intention indexes corresponding to each similar commodity in historical data, summing to obtain historical intention indexes, and weighting and summing the browsing quantity and the historical intention indexes to obtain the purchase probability degree of the corresponding behavior vector;
obtaining browsing similarity based on the difference between the corresponding browsing duration and the minimum value in all browsing durations of each similar commodity;
and taking the normalized result of the ratio of the purchase possibility degree to the browsing similarity degree as the potential shopping value.
4. The intelligent data processing method for e-commerce big data cloud edge cooperative transmission according to claim 3, wherein the browsing amount obtaining method is as follows:
and for any one of the behavior vectors, taking the behavior vector in the preset history time before the corresponding shopping flow as the corresponding history data, and acquiring the number of similar commodities browsed by the user in the history data as the browsing quantity.
5. The intelligent data processing method for the e-commerce big data cloud edge cooperative transmission according to claim 3, wherein the method for acquiring the browsing duration is as follows:
and acquiring the duration between the browsing time of each similar commodity in the historical data and the time of the current shopping flow as the browsing duration.
6. The intelligent data processing method for e-commerce big data cloud edge cooperative transmission according to claim 3, wherein the browsing amount weight is greater than or equal to the historical intent index weight in the purchase possibility degree acquisition process.
7. The intelligent data processing method for the e-commerce big data cloud edge cooperative transmission according to claim 1, wherein the composition process of the behavior vector is as follows:
the behavior data comprises at least one of browsing duration, clicking times, customer service communication duration, whether to collect, join in shopping carts and pay, the values of the corresponding data are obtained based on the behavior result of each item of data, and the values of all the data form the behavior vector.
8. The intelligent data processing method for the e-commerce big data cloud edge cooperative transmission of claim 7, wherein the method for acquiring the number of the effective elements is as follows: and taking the number of non-zero valued data in all data composing the behavior vector as the number of effective elements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310409600.2A CN116418881B (en) | 2023-04-18 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310409600.2A CN116418881B (en) | 2023-04-18 | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116418881A true CN116418881A (en) | 2023-07-11 |
| CN116418881B CN116418881B (en) | 2024-06-04 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720928A (en) * | 2023-08-10 | 2023-09-08 | 量子数科科技有限公司 | Artificial intelligence-based personalized accurate shopping guide method for electronic commerce |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488697A (en) * | 2015-12-09 | 2016-04-13 | 焦点科技股份有限公司 | Potential customer mining method based on customer behavior characteristics |
| CN107742250A (en) * | 2017-12-04 | 2018-02-27 | 深圳春沐源控股有限公司 | The display methods and display system of goods browse record |
| JP2018180928A (en) * | 2017-04-13 | 2018-11-15 | ムーヴ株式会社 | Purchase intention evaluation system and advertisement publication method |
| CN112861003A (en) * | 2021-02-19 | 2021-05-28 | 杭州谐云科技有限公司 | User portrait construction method and system based on cloud edge collaboration |
| CN113674063A (en) * | 2021-08-27 | 2021-11-19 | 卓尔智联(武汉)研究院有限公司 | Shopping recommendation method, shopping recommendation device and electronic equipment |
| WO2022145836A1 (en) * | 2020-12-31 | 2022-07-07 | Samsung Electronics Co., Ltd. | Method and apparatus for processing information |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488697A (en) * | 2015-12-09 | 2016-04-13 | 焦点科技股份有限公司 | Potential customer mining method based on customer behavior characteristics |
| JP2018180928A (en) * | 2017-04-13 | 2018-11-15 | ムーヴ株式会社 | Purchase intention evaluation system and advertisement publication method |
| CN107742250A (en) * | 2017-12-04 | 2018-02-27 | 深圳春沐源控股有限公司 | The display methods and display system of goods browse record |
| WO2022145836A1 (en) * | 2020-12-31 | 2022-07-07 | Samsung Electronics Co., Ltd. | Method and apparatus for processing information |
| CN112861003A (en) * | 2021-02-19 | 2021-05-28 | 杭州谐云科技有限公司 | User portrait construction method and system based on cloud edge collaboration |
| CN113674063A (en) * | 2021-08-27 | 2021-11-19 | 卓尔智联(武汉)研究院有限公司 | Shopping recommendation method, shopping recommendation device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720928A (en) * | 2023-08-10 | 2023-09-08 | 量子数科科技有限公司 | Artificial intelligence-based personalized accurate shopping guide method for electronic commerce |
| CN116720928B (en) * | 2023-08-10 | 2023-10-27 | 量子数科科技有限公司 | Artificial intelligence-based personalized accurate shopping guide method for electronic commerce |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7113932B2 (en) | Artificial intelligence trending system | |
| CN113139857B (en) | Electronic commerce platform merchant store intelligent management method, system, equipment and computer storage medium | |
| CN110796512A (en) | Product information recommendation method and device, storage medium and computer equipment | |
| CN115187344B (en) | Big data-based user preference analysis and identification method | |
| CN111179016A (en) | Electricity sales package recommendation method, equipment and storage medium | |
| CN111798301A (en) | Resource transfer quota determining method, device and system | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN115204985A (en) | Shopping behavior prediction method, device, equipment and storage medium | |
| CN113255908A (en) | Method, neural network model and device for service prediction based on event sequence | |
| CN115659055A (en) | Commodity recommendation method, system, equipment and storage medium based on event sequence | |
| CN116418881B (en) | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission | |
| CN115760202A (en) | Product operation management system and method based on artificial intelligence | |
| CN106651582A (en) | Security transaction risk early warning method and system based on instruction stream toxicity index | |
| CN116418881A (en) | Data intelligent processing method for E-commerce big data cloud edge cooperative transmission | |
| CN112396496B (en) | Intelligent commodity recommendation management system of electronic commerce platform based on cloud computing | |
| CN113077320A (en) | Business opportunity recommendation method based on user behavior acquisition and analysis | |
| Wanchai | Customer churn analysis: A case study on the telecommunication industry of Thailand | |
| CN112488421B (en) | Tracking and predicting method and device for accounts receivable of electric charge | |
| CN115186156A (en) | Fusion method and system of multi-source data | |
| CN114764714A (en) | Risk rating method and device for noble metal leasing transaction | |
| CN113283960A (en) | Vertical e-commerce platform commodity intelligent recommendation method based on big data analysis and cloud computing and cloud service platform | |
| CN105225116A (en) | The recognition methods of transactional operation and server | |
| CN112907308B (en) | Data detection method and device, and computer readable storage medium | |
| CN111768139A (en) | Stock processing method, apparatus, device and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240509 Address after: 410000 third floor, Xiangsu public service platform, No. 329, yinpen South Road, yinpenling street, Yuelu District, Changsha City, Hunan Province Applicant after: Hunan supply and marketing e-commerce Co.,Ltd. Country or region after: China Address before: Room 106, Unit 2, Building 3-7, Lvyuan New District, Jinxi Road, Luyuan District, Changchun City, 130000 Jilin Province Applicant before: Jilin Yuyu Network Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |