CN117668368A - E-commerce data pushing method and system based on big data - Google Patents
E-commerce data pushing method and system based on big data Download PDFInfo
- Publication number
- CN117668368A CN117668368A CN202311739427.9A CN202311739427A CN117668368A CN 117668368 A CN117668368 A CN 117668368A CN 202311739427 A CN202311739427 A CN 202311739427A CN 117668368 A CN117668368 A CN 117668368A
- Authority
- CN
- China
- Prior art keywords
- analysis
- node
- data
- service data
- real
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 117
- 238000010223 real-time analysis Methods 0.000 claims abstract description 93
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000007418 data mining Methods 0.000 claims abstract description 32
- 230000003993 interaction Effects 0.000 claims abstract description 22
- 238000005065 mining Methods 0.000 claims abstract description 16
- 238000000611 regression analysis Methods 0.000 claims description 40
- 238000004140 cleaning Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013144 data compression Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000011156 evaluation Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Abstract
According to the big data-based e-commerce data pushing method and system, the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition is calculated through the condition description possibility; combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition; and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result. According to the method and the device, analysis and mining processing can be carried out according to the pushing condition of the electronic commerce data corresponding to each node in the washed business data, so that the interest direction of a user can be accurately obtained, data pushing is carried out, pushing effect can be improved, and benefits are improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an electronic commerce data pushing method and system based on big data.
Background
Electronic commerce generally refers to a novel business operation mode for realizing online shopping of consumers, online transaction and online electronic payment among merchants, various business activities, transaction activities, financial activities and related comprehensive service activities based on client/server application modes in a global and wide-ranging business trade activities in an internet open network environment.
Many e-commerce data are pushed to a user on a network, and the phenomenon that the user cannot be recommended to the user in an interesting manner is likely to be bad, the situation that the user feels dislike when pushing things which are not needed by the user is likely to occur, and how to push e-commerce data to improve the interest of the user is a technical problem which is difficult to overcome at present.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides an electronic commerce data pushing method and system based on big data.
In a first aspect, there is provided a method for pushing electronic commerce data based on big data, the method comprising: acquiring electronic commerce service data to be processed, wherein the electronic commerce service data is service data in a first interaction state; cleaning the electronic commerce service data to obtain cleaned service data; for each node in the washed service data, carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node; calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition through the condition description possibility; combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition; and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result.
In an independent embodiment, the calculating the push efficiency of the node from the real-time analysis case to the specified analysis case by describing the possibility through the case includes:
comparing the situation description possibilities of the nodes on the real-time analysis situation and the appointed analysis situation respectively; and setting the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition according to the comparison processing result and the appointed constraint requirement.
It can be appreciated that when the situation describes the possibility, the problem of inaccurate comparison processing is improved, so that the pushing efficiency of the node from the real-time analysis situation to the specified analysis situation can be accurately calculated.
In an independent embodiment, the setting the push efficiency of the node from the real-time analysis case to the specified analysis case according to the comparison processing result and the specified constraint requirement includes: when the situation description probability of the node on the real-time analysis situation is larger than the situation description probability of the node on the appointed analysis situation, setting the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation by combining the appointed constraint requirement; when the situation description probability of the node on the real-time analysis situation is not more than the situation description probability of the node on the appointed analysis situation, the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation is set to be an appointed value.
It can be understood that the problem of analysis anomalies is improved when comparing the processing result with the specified constraint requirements, so that the push efficiency of the node from the real-time analysis situation to the specified analysis situation can be accurately set.
In an independent embodiment, the calculating the push efficiency of the node from the real-time analysis case to the specified analysis case by describing the possibility through the case includes:
calculating a state difference between the real-time analysis condition and the specified analysis condition; and when the state difference meets the specified difference requirement, calculating the pushing efficiency of the node loaded from the real-time analysis condition to the specified analysis condition according to the condition description possibility.
It can be appreciated that the problem of inaccuracy of the difference is improved by describing the possibility of the situation, so that the pushing efficiency of the node from the real-time analysis situation to the specified analysis situation can be accurately calculated.
In an independently implemented embodiment, the real-time analysis case includes element sub-states in not less than one direction; the specified analysis case includes element sub-states in not less than one direction; combining the pushing efficiency, determining the e-commerce data pushing situation of the node under the real-time analysis condition includes: determining, for each direction, from specified analysis cases, adjacent specified business information description contents of real-time analysis cases in the direction, wherein element sub-states of the adjacent specified analysis cases in the direction are different from element sub-states of the real-time analysis cases in the direction, the element sub-states of the adjacent specified analysis cases in a reference direction are identical to the element sub-states of the real-time analysis cases in the reference direction, and the reference direction is other directions except the direction; the state analysis possibility of the real-time analysis condition of the node in the direction is determined through the pushing efficiency of the node loaded from the real-time analysis condition to the corresponding adjacent appointed analysis condition;
and splicing the state analysis possibility of the real-time analysis condition of the node in each direction to obtain the electronic commerce data pushing condition of the node under the real-time analysis condition.
It will be appreciated that the real-time analysis case includes element sub-states in not less than one direction; the specified analysis case includes element sub-states in not less than one direction; when the pushing efficiency is combined, the problem of inaccurate pushing efficiency is solved, so that the electronic commerce data pushing condition of the node under the real-time analysis condition can be accurately determined.
In an independent embodiment, the mining processing is performed on the cleaned service data according to the e-commerce data pushing situation corresponding to each node in the cleaned service data, generating a service data mining result in a second interaction state, and determining the e-commerce data pushing result according to the service data mining result includes: the cleaning business data is mined according to the pushing condition of the electronic business data corresponding to each node in the cleaning business data, so as to obtain the processed business data; and determining the processed service data as new cleaned service data, returning to the step of executing the description possibility through the condition, calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition, generating a service data mining result in a second interaction state, and determining an electronic commerce data pushing result according to the service data mining result.
It can be understood that the problem of inaccurate mining is improved when the cleaning service data is mined according to the electronic commerce data pushing condition corresponding to each node in the cleaned service data, so that the service data mining result in the second interaction state can be accurately generated, and the electronic commerce data pushing result is determined according to the service data mining result.
In an independent embodiment, the cleaning the e-commerce service data to obtain cleaned service data includes: the electronic commerce service data is cleaned through a service data processing thread, so that cleaned service data are obtained; the regression analysis of the situation description possibility corresponding to each specified analysis situation on the node by combining the real-time business information description content of the node aiming at each node in the washed business data comprises the following steps: and carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node aiming at each node in the washed business data through the business data processing thread.
It can be appreciated that when the electronic commerce service data is cleaned, the problem of inaccurate cleaning is solved, so that the cleaned service data can be accurately obtained.
In an independent embodiment, before the electronic commerce service data is cleaned by the service data processing thread to obtain cleaned service data, the method further includes: obtaining configuration data, wherein the configuration data comprises no less than one service data example; cleaning the service data examples by designating service data processing threads to obtain cleaned example service data; determining regression analysis state possibility weights corresponding to all nodes in the cleaned example business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise regression analysis condition description possibilities corresponding to all specified analysis conditions on the nodes; and debugging the appointed business data processing thread through the regression analysis state possibility weight and the appointed state possibility weight to obtain the configured business data processing thread.
It can be understood that the electronic commerce service data is cleaned by the service data processing thread, and the service data processing thread is optimized before the cleaned service data is obtained, so that the cleaning accuracy can be improved.
In an independent embodiment, the cleaning the e-commerce service data to obtain cleaned service data includes: splicing the e-commerce service data and the service influence data to obtain spliced service data; and carrying out service data compression processing on the spliced service data to obtain the washed service data.
It can be understood that when the electronic commerce service data is cleaned, the interference affecting the service data is reduced, so that the cleaned service data can be accurately obtained.
In an independent embodiment, the regression analysis of the situation description probability corresponding to each specified analysis situation on the node by combining the real-time business information description content of the node for each node in the post-cleaning business data includes: determining regression analysis state possibility weights corresponding to all nodes in the washed business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise situation description possibilities corresponding to all undetermined specified analysis situations on the nodes; and extracting the situation description possibility corresponding to each specified analysis situation on the node from the regression analysis state possibility weight according to the state positioning information corresponding to the specified analysis situation.
It can be understood that, for each node in the service data after cleaning, the probability weight can be reliably determined, and the accuracy of the situation description probability can be improved.
In a second aspect, an electronic commerce data push system based on big data is provided, including a processor and a memory in communication with each other, where the processor is configured to read a computer program from the memory and execute the computer program to implement the method described above.
The electronic commerce data pushing method and system based on big data can obtain electronic commerce service data to be processed, wherein the electronic commerce service data is service data in a first interaction state; cleaning the electronic commerce service data to obtain cleaned service data; for each node in the washed service data, carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node; calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition through the condition description possibility; combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition; and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result. According to the method and the device, analysis and mining processing can be carried out according to the pushing condition of the electronic commerce data corresponding to each node in the washed business data, so that the interest direction of a user can be accurately obtained, data pushing is carried out, pushing effect can be improved, and benefits are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an electronic commerce data pushing method based on big data according to an embodiment of the present application.
Description of the embodiments
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, an electronic commerce data pushing method based on big data is shown, and the method may include the following technical solutions described in steps 101-106.
101. And obtaining electronic commerce service data to be processed, wherein the electronic commerce service data is service data in a first interaction state.
The e-commerce service data may be any service data, for example, may be product information, for example: the user who likes playing the game recommends relevant game information, recommends novel information which likes looking at novel, and the like, and the method and the device can analyze the information in combination with the hobbies and interests of the user, so that data pushing is performed. By the electronic commerce data pushing method based on big data, the service data mining result related to the electronic commerce service data can be generated.
102. And cleaning the electronic commerce service data to obtain cleaned service data.
For example, some crawler information or malicious software may exist in the e-commerce business data, and the data needs to be cleared, so that a user is prevented from having bad experience. Optionally, in this embodiment, the step of "performing cleaning processing on the e-commerce service data to obtain cleaned service data" may include: splicing the e-commerce service data and the service influence data to obtain spliced service data; and carrying out service data compression processing on the spliced service data to obtain the washed service data.
For example, the splicing processing of the e-commerce service data and the service influence data may be to splice the e-commerce service data and the service influence data, and then perform service data compression processing on the spliced service data to obtain the cleaned service data.
103. And carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on each node by combining the real-time business information description content of the node aiming at each node in the washed business data.
By way of example, regression analysis may be understood as prediction.
The real-time analysis condition is an element value of the node in real time, and specifically may include element values in three directions. The specified analysis case may include the real-time analysis case itself and other analysis cases other than the real-time analysis case.
Optionally, in this embodiment, the step of "regression analyzing, for each node in the post-cleaning service data, the situation description likelihood corresponding to each specified analysis situation on the node in combination with the real-time business information description content of the node" may include: determining regression analysis state possibility weights corresponding to all nodes in the washed business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise situation description possibilities corresponding to all undetermined specified analysis situations on the nodes; and extracting the situation description possibility corresponding to each specified analysis situation on the node from the regression analysis state possibility weight according to the state positioning information corresponding to the specified analysis situation.
The distribution of situation description possibilities corresponding to each undetermined specified analysis situation in the specified state possibility weight can be arranged according to the size of the analysis situation, the specified analysis situation can determine state positioning information of the specified analysis situation based on the size of the analysis situation, and the state positioning information is specifically, namely, the distribution positioning of the situation description possibilities in the specified state possibility weight.
Optionally, in this embodiment, the step of "performing cleaning processing on the e-commerce service data to obtain cleaned service data" may include: the electronic commerce service data is cleaned through a service data processing thread, so that cleaned service data are obtained;
the step of performing regression analysis on the situation description probability corresponding to each specified analysis situation on the node by combining the real-time business information description content of the node for each node in the washed business data may include: and carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node aiming at each node in the washed business data through the business data processing thread.
It will be appreciated that the traffic data processing thread may be part of the spawned thread described above.
Optionally, in this embodiment, before the step of "performing cleaning processing on the e-commerce service data through the service data processing thread to obtain cleaned service data", the method further includes: obtaining configuration data, wherein the configuration data comprises no less than one service data example; cleaning the service data examples by designating service data processing threads to obtain cleaned example service data; determining regression analysis state possibility weights corresponding to all nodes in the cleaned example business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise regression analysis condition description possibilities corresponding to all specified analysis conditions on the nodes; and debugging the appointed business data processing thread through the regression analysis state possibility weight and the appointed state possibility weight to obtain the configured business data processing thread.
The service data example may be any service data. Specifically, the specified state likelihood weight may be a case description likelihood that corresponds to each specified analysis case, exhibiting a gaussian distribution.
The configuration process may be to calculate a capability evaluation result between the regression analysis state likelihood weight corresponding to the node and the designated state likelihood weight, debug parameters of the designated service data processing thread, and optimize parameters of the designated service data processing thread based on the capability evaluation result, so that the regression analysis state likelihood weight approaches to the designated state likelihood weight, and obtain the configured service data processing thread. Specifically, the capability evaluation result between the regression analysis state likelihood weight and the specified state likelihood weight may be made smaller than a specified value, which may be set according to the actual situation.
104. And calculating the pushing efficiency of the node from the real-time analysis condition to the specified analysis condition through the condition description possibility.
Optionally, in this embodiment, the step of "describing the possibility by the case, calculating the push efficiency of the node from the real-time analysis case to the specified analysis case" may include: calculating a state difference between the real-time analysis condition and the specified analysis condition; and when the state difference meets the specified difference requirement, calculating the pushing efficiency of the node loaded from the real-time analysis condition to the specified analysis condition according to the condition description possibility.
Wherein, specifically, the real-time analysis case may include element sub-states in X directions; the specified analysis case includes element sub-states in the X directions. The state difference between the real-time analysis case and the specified analysis case may be a sum of state sub-differences in X directions, and the state sub-difference in each direction may specifically be a difference between an element sub-state of the real-time analysis case in the direction and an element sub-state of the specified analysis case in the direction.
Optionally, in this embodiment, the step of "describing the possibility by the case, calculating the push efficiency of the node from the real-time analysis case to the specified analysis case" may include: comparing the situation description possibilities of the nodes on the real-time analysis situation and the appointed analysis situation respectively; and setting the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition according to the comparison processing result and the appointed constraint requirement.
Wherein, through the comparison processing, the situation description possibility of the real-time analysis situation and the size of the situation description possibility of the specified analysis situation can be determined.
Optionally, in this embodiment, the step of "setting, according to the comparison processing result and the specified constraint requirement, the push efficiency of the node from the real-time analysis case to the specified analysis case" may include: when the situation description probability of the node on the real-time analysis situation is larger than the situation description probability of the node on the appointed analysis situation, setting the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation by combining the appointed constraint requirement; when the situation description probability of the node on the real-time analysis situation is not more than the situation description probability of the node on the appointed analysis situation, the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation is set to be an appointed value.
105. And combining the pushing efficiency to determine the pushing condition of the e-commerce data of the node under the real-time analysis condition.
Optionally, in this embodiment, the real-time analysis case includes element sub-states in not less than one direction; the specified analysis case includes element sub-states in not less than one direction;
the step of determining the e-commerce data pushing situation of the node under the real-time analysis condition by combining the pushing efficiency may include: determining, for each direction, from specified analysis cases, adjacent specified business information description contents of real-time analysis cases in the direction, wherein element sub-states of the adjacent specified analysis cases in the direction are different from element sub-states of the real-time analysis cases in the direction, the element sub-states of the adjacent specified analysis cases in a reference direction are identical to the element sub-states of the real-time analysis cases in the reference direction, and the reference direction is other directions except the direction; the state analysis possibility of the real-time analysis condition of the node in the direction is determined through the pushing efficiency of the node loaded from the real-time analysis condition to the corresponding adjacent appointed analysis condition; and splicing the state analysis possibility of the real-time analysis condition of the node in each direction to obtain the electronic commerce data pushing condition of the node under the real-time analysis condition.
The real-time analysis condition may include element sub-states in X directions, and the specified analysis condition may also include element sub-states in X directions.
The method for splicing the state analysis possibility of the real-time analysis condition of the node in each direction is various, for example, the splicing method can be a function processing method such as addition.
106. And mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result.
Optionally, in this embodiment, the step of "performing, by using the e-commerce data pushing conditions corresponding to each node in the cleaned service data, mining processing on the cleaned service data to generate a service data mining result in the second interaction state, and determining the e-commerce data pushing result according to the service data mining result" may include: the cleaning business data is mined according to the pushing condition of the electronic business data corresponding to each node in the cleaning business data, so as to obtain the processed business data; and determining the processed service data as new cleaned service data, returning to the step of executing the description possibility through the condition, calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition, generating a service data mining result in a second interaction state, and determining an electronic commerce data pushing result according to the service data mining result.
Specifically, the service data size of each processed service data obtained in the circulation process is the same as that of the service data after washing at the beginning, and the service data mining result is consistent with that of the service data after washing.
As can be seen from the above, the present embodiment may obtain electronic commerce service data to be processed, where the electronic commerce service data is service data in the first interaction state; cleaning the electronic commerce service data to obtain cleaned service data; for each node in the washed service data, carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node; calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition through the condition description possibility; combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition; and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result. According to the method and the device, analysis and mining processing can be carried out according to the pushing condition of the electronic commerce data corresponding to each node in the washed business data, so that the interest direction of a user can be accurately obtained, data pushing is carried out, pushing effect can be improved, and benefits are improved.
The embodiment of the application provides an electronic commerce data pushing method based on big data, and the specific flow of the electronic commerce data pushing method based on big data can be as follows.
On the basis of the above, there is provided an electronic commerce data pushing device based on big data, the device comprising:
the data acquisition module is used for acquiring electronic commerce service data to be processed, wherein the electronic commerce service data is service data in a first interaction state;
the data cleaning module is used for cleaning the electronic commerce service data to obtain cleaned service data;
the possibility determining module is used for carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node aiming at each node in the washed business data;
the situation analysis module is used for calculating the pushing efficiency of the node from the real-time analysis situation to the appointed analysis situation according to the situation description possibility;
the pushing condition determining module is used for determining the electronic commerce data pushing condition of the node under the real-time analysis condition by combining the pushing efficiency;
the data pushing module is used for carrying out mining processing on the cleaned business data according to the electronic business data pushing conditions corresponding to the nodes in the cleaned business data, generating a business data mining result in a second interaction state, and determining the electronic business data pushing result according to the business data mining result.
On the basis of the above, an e-commerce data push system based on big data is shown, comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute the computer program to implement the method described above.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the above scheme, electronic commerce service data to be processed can be obtained, where the electronic commerce service data is service data in the first interaction state; cleaning the electronic commerce service data to obtain cleaned service data; for each node in the washed service data, carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node; calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition through the condition description possibility; combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition; and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result. According to the method and the device, analysis and mining processing can be carried out according to the pushing condition of the electronic commerce data corresponding to each node in the washed business data, so that the interest direction of a user can be accurately obtained, data pushing is carried out, pushing effect can be improved, and benefits are improved.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
Claims (10)
1. An electronic commerce data pushing method based on big data is characterized by comprising the following steps:
acquiring electronic commerce service data to be processed, wherein the electronic commerce service data is service data in a first interaction state;
cleaning the electronic commerce service data to obtain cleaned service data;
for each node in the washed service data, carrying out regression analysis on the situation description possibility corresponding to each appointed analysis situation on the node by combining the real-time business information description content of the node;
calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition through the condition description possibility;
combining the pushing efficiency, and determining the pushing condition of the e-commerce data of the node under the real-time analysis condition;
and mining the cleaned business data according to the pushing condition of the e-commerce data corresponding to each node in the cleaned business data, generating a business data mining result in a second interaction state, and determining the pushing result of the e-commerce data according to the business data mining result.
2. The method of claim 1, wherein said calculating, by said case description likelihood, a push efficiency of said node loading from said real-time analysis case to said specified analysis case comprises:
comparing the situation description possibilities of the nodes on the real-time analysis situation and the appointed analysis situation respectively;
and setting the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition according to the comparison processing result and the appointed constraint requirement.
3. The method according to claim 2, wherein said setting the push efficiency of the node from the real-time analysis case to the specified analysis case according to the comparison processing result and the specified constraint requirement comprises:
when the situation description probability of the node on the real-time analysis situation is larger than the situation description probability of the node on the appointed analysis situation, setting the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation by combining the appointed constraint requirement;
when the situation description probability of the node on the real-time analysis situation is not more than the situation description probability of the node on the appointed analysis situation, the pushing efficiency of the node loaded from the real-time analysis situation to the appointed analysis situation is set to be an appointed value.
4. The method of claim 1, wherein said calculating, by said case description likelihood, a push efficiency of said node loading from said real-time analysis case to said specified analysis case comprises:
calculating a state difference between the real-time analysis condition and the specified analysis condition;
and when the state difference meets the specified difference requirement, calculating the pushing efficiency of the node loaded from the real-time analysis condition to the specified analysis condition according to the condition description possibility.
5. The method of claim 1, wherein the real-time analysis case includes element sub-states in not less than one direction; the specified analysis case includes element sub-states in not less than one direction; combining the pushing efficiency, determining the e-commerce data pushing situation of the node under the real-time analysis condition includes:
determining, for each direction, from specified analysis cases, adjacent specified business information description contents of real-time analysis cases in the direction, wherein element sub-states of the adjacent specified analysis cases in the direction are different from element sub-states of the real-time analysis cases in the direction, the element sub-states of the adjacent specified analysis cases in a reference direction are identical to the element sub-states of the real-time analysis cases in the reference direction, and the reference direction is other directions except the direction;
the state analysis possibility of the real-time analysis condition of the node in the direction is determined through the pushing efficiency of the node loaded from the real-time analysis condition to the corresponding adjacent appointed analysis condition;
and splicing the state analysis possibility of the real-time analysis condition of the node in each direction to obtain the electronic commerce data pushing condition of the node under the real-time analysis condition.
6. The method of claim 1, wherein the mining the cleaned service data according to the e-commerce data pushing condition corresponding to each node in the cleaned service data to generate a service data mining result in a second interaction state, and determining the e-commerce data pushing result according to the service data mining result comprises:
the cleaning business data is mined according to the pushing condition of the electronic business data corresponding to each node in the cleaning business data, so as to obtain the processed business data;
and determining the processed service data as new cleaned service data, returning to the step of executing the description possibility through the condition, calculating the pushing efficiency of the node from the real-time analysis condition to the appointed analysis condition, generating a service data mining result in a second interaction state, and determining an electronic commerce data pushing result according to the service data mining result.
7. The method of claim 1, wherein the performing the cleaning process on the e-commerce service data to obtain cleaned service data comprises: the electronic commerce service data is cleaned through a service data processing thread, so that cleaned service data are obtained; the regression analysis of the situation description possibility corresponding to each specified analysis situation on the node by combining the real-time business information description content of the node aiming at each node in the washed business data comprises the following steps: through the service data processing thread, carrying out regression analysis on situation description possibility corresponding to each appointed analysis situation on each node by combining real-time business information description content of each node in the cleaned service data;
the method comprises the steps of carrying out cleaning treatment on the electronic commerce service data through a service data processing thread, and before obtaining the cleaned service data, further comprising:
obtaining configuration data, wherein the configuration data comprises no less than one service data example; cleaning the service data examples by designating service data processing threads to obtain cleaned example service data;
determining regression analysis state possibility weights corresponding to all nodes in the cleaned example business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise regression analysis condition description possibilities corresponding to all specified analysis conditions on the nodes;
and debugging the appointed business data processing thread through the regression analysis state possibility weight and the appointed state possibility weight to obtain the configured business data processing thread.
8. The method of claim 1, wherein the performing the cleaning process on the e-commerce service data to obtain cleaned service data comprises:
splicing the e-commerce service data and the service influence data to obtain spliced service data;
and carrying out service data compression processing on the spliced service data to obtain the washed service data.
9. The method according to claim 1, wherein the regression analysis of the situation description probability corresponding to each specified analysis situation on the node in combination with the real-time business information description content of the node for each node in the post-cleaning business data comprises:
determining regression analysis state possibility weights corresponding to all nodes in the washed business data by combining real-time business information description contents of the nodes, wherein the regression analysis state possibility weights comprise situation description possibilities corresponding to all undetermined specified analysis situations on the nodes;
and extracting the situation description possibility corresponding to each specified analysis situation on the node from the regression analysis state possibility weight according to the state positioning information corresponding to the specified analysis situation.
10. A big data based e-commerce data pushing system comprising a processor and a memory in communication with each other, said processor being adapted to read a computer program from said memory and execute it to implement the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311739427.9A CN117668368A (en) | 2023-12-18 | 2023-12-18 | E-commerce data pushing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311739427.9A CN117668368A (en) | 2023-12-18 | 2023-12-18 | E-commerce data pushing method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117668368A true CN117668368A (en) | 2024-03-08 |
Family
ID=90078769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311739427.9A Pending CN117668368A (en) | 2023-12-18 | 2023-12-18 | E-commerce data pushing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117668368A (en) |
-
2023
- 2023-12-18 CN CN202311739427.9A patent/CN117668368A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11537607B2 (en) | Automated sequential site navigation | |
| Hewamalage et al. | Forecast evaluation for data scientists: common pitfalls and best practices | |
| US11783324B2 (en) | Resource sharing method, apparatus, and device | |
| Piscitelli et al. | Design space pruning through hybrid analysis in system-level design space exploration | |
| CN111507543A (en) | Model training method and device for predicting business relation between entities | |
| US10225272B2 (en) | Ordered correction of application based on dependency topology | |
| US11775412B2 (en) | Machine learning models applied to interaction data for facilitating modifications to online environments | |
| US10846210B1 (en) | Automation of platform release | |
| US20210365555A1 (en) | A method and system for detecting and preventing issues in smart contracts based on historical behavior analysis | |
| US10198761B2 (en) | Intelligently determining buying online and picking up in store based on commute patterns of connections in a social network and store parameters | |
| Fabra et al. | Log-based session profiling and online behavioral prediction in E–Commerce websites | |
| Grohmann et al. | Detecting parametric dependencies for performance models using feature selection techniques | |
| Bale et al. | Web scraping approaches and their performance on modern websites | |
| US20180052759A1 (en) | Performance metric contextualization in a distributed computing environment | |
| Wang et al. | A detection method for abnormal transactions in e-commerce based on extended data flow conformance checking | |
| CN110347887A (en) | Obtain the method and device of business scenario time series data | |
| Ricós et al. | Distributed state model inference for scriptless GUI testing | |
| CN117370767A (en) | User information evaluation method and system based on big data | |
| CN117668368A (en) | E-commerce data pushing method and system based on big data | |
| Mankodi et al. | Performance prediction from simulation systems to physical systems using machine learning with transfer learning and scaling | |
| JP2021197089A (en) | Output device, output method, and output program | |
| Boussif et al. | Tuning the diagnoser-based approach for diagnosability analysis of finite automata | |
| CN113542047B (en) | Abnormal request detection method and device, electronic equipment and computer readable medium | |
| US11729247B2 (en) | Systems and methods for decentralized detection of software platforms operating on website pages | |
| US7536427B2 (en) | Comparing process sizes |
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 |