CN110956492A - Commodity pushing method based on big data science and dynamic weight adjustment - Google Patents
Commodity pushing method based on big data science and dynamic weight adjustment Download PDFInfo
- Publication number
- CN110956492A CN110956492A CN201911102713.8A CN201911102713A CN110956492A CN 110956492 A CN110956492 A CN 110956492A CN 201911102713 A CN201911102713 A CN 201911102713A CN 110956492 A CN110956492 A CN 110956492A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- matrix
- model
- generating
- 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
Classifications
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
The invention discloses a commodity pushing method and a system based on big data science and dynamic weight adjustment, wherein the method comprises the following steps: generating a user commodity matrix according to the scores of the commodities by the users; generating preference information of the user according to the commodity matrix of the user; constructing a constraint model and an independent scoring model according to the commodity matrix and the preference information of the user; generating a commodity scoring predicted value based on a dynamic weight adjusting method according to the constraint model and the independent scoring model; and carrying out commodity pushing according to the commodity scoring predicted value. According to the method, the scores of the commodities are predicted through the constraint model and the independent score model, the global information and the local information can be considered at the same time, the predicted results can be adjusted according to actual conditions, and the effect is stable; in addition, when the commodity score is predicted, the dynamic weight adjusting method is adopted, so that the accuracy of the prediction result is greatly improved, and the method can be widely applied to the technical field of deep learning.
Description
Technical Field
The invention relates to the technical field of deep learning, in particular to a commodity pushing method and a commodity pushing system based on big data science and dynamic weight adjustment.
Background
With the rapid development of the internet era, online transactions have gradually merged into the lives of people, and are realized through online transaction platforms, which need to maintain and update commodity-related information, and thus occupy a large amount of resources, such as storage space of a server, network bandwidth, and the like. In fact, many customers who browse the information related to the commodity in the trading platform can certainly have no buying intention, and very detailed commodity-related happiness and table are provided for the customers, so that resources are wasted, and the trading cost is increased.
In order to solve this problem, a system which is reasonable in design, ensures efficiency, and can push goods from a large amount of data according to the specific situation of the user is indispensable.
Disclosure of Invention
To solve the above technical problems, the present invention aims to: the commodity pushing method and system based on big data science and dynamic weight adjustment are high in accuracy and stable in effect.
On one hand, the technical scheme adopted by the invention is as follows:
the commodity pushing method based on big data science and dynamic weight adjustment comprises the following steps:
generating a user commodity matrix according to the scores of the commodities by the users;
generating preference information of the user according to the commodity matrix of the user;
constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user;
generating a commodity scoring predicted value based on a dynamic weight adjusting method according to the constraint model and the independent scoring model;
and carrying out commodity pushing according to the commodity scoring predicted value.
Further, the step of generating the preference information of the user according to the commodity matrix of the user comprises the following steps:
calculating a user commodity matrix to generate a first result, wherein the first result comprises a commodity coexistence matrix and a user coexistence matrix;
and extracting information of the operation result of the commodity matrix of the user through the web log to obtain the preference information of the user.
Further, the step of constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user comprises the following steps:
solving the first result by a matrix decomposition method to obtain a second result;
solving the second result through the regularized singular value to obtain a third result;
and constructing a constraint model and an independent scoring model according to the third result.
Further, the step of constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user further comprises the following steps:
and establishing the multi-view neural network through the constraint model and the independent scoring model.
Further, the step of establishing the multi-view neural network through the constraint model and the independent scoring model comprises the following steps:
inputting the real-time solution of the constraint model into a full-connection layer for first training;
inputting the real-time solution of the independent scoring model into the convolutional layer for second training;
inputting the historical solution of the constraint model into a full-connection layer for third training;
inputting the historical solution of the independent scoring model into the convolutional layer for fourth training;
and establishing the multi-view neural network according to the results of the first training, the second training, the third training and the fourth training.
Further, the step of generating a commodity score predicted value based on a dynamic weight adjustment method according to the constraint model and the independent score model comprises the following steps:
generating a first prediction component by a multi-view neural network;
generating a second prediction component by the user preference information;
generating a third prediction component by a nearest neighbor classification algorithm;
respectively configuring the weights of the first prediction component, the second prediction component and the third prediction component based on a dynamic weight adjustment mechanism;
and generating a commodity score predicted value through the first prediction component, the second prediction component and the third prediction component according to the weight configuration result.
Further, the step of pushing the commodities according to the commodity score predicted value comprises the following steps:
generating a commodity sequence set according to the commodity matrix of the user;
calculating the support degree of each commodity sequence in the commodity sequence set, and acquiring a first commodity sequence with the support degree being greater than a first threshold value;
taking the first commodity sequence as a current commodity sequence, and generating a commodity sequence matrix according to the first commodity sequence and the current commodity sequence;
calculating the support degree of each commodity sequence in the commodity sequence matrix;
judging whether the commodity sequence matrix has the commodity sequence support degree larger than a first threshold value, if so, taking all the commodity sequences larger than the first threshold value as current commodity sequences, and returning to execute the step of generating the commodity sequence matrix according to the first commodity sequence and the current commodity sequences; otherwise, executing the next step;
and screening the commodity sequence with the support degree larger than a second threshold value in the commodity matrix, and taking the commodity sequence as a commodity pushing result.
The technical scheme adopted by the other aspect of the invention is as follows:
commodity push system based on big data science and dynamic weight adjustment includes:
the first generation module is used for generating a user commodity matrix according to the scores of the user on the commodities;
the model building module is used for building a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user;
the prediction module is used for generating a commodity scoring prediction value based on a dynamic weight adjustment method according to the constraint model and the independent scoring model;
and the pushing module is used for pushing the commodities according to the commodity scoring predicted value.
The technical scheme adopted by the other aspect of the invention is as follows:
commodity push system based on big data science and dynamic weight adjustment includes:
at least one processor;
when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement the commodity pushing method based on big data science and dynamic weight adjustment.
The invention has the beneficial effects that: the method predicts the scores of the commodities through the constraint model and the independent scoring model, compared with the existing BP neural network model and the decision tree model, the method can simultaneously consider global information and local information, can adjust the predicted results according to actual conditions, and has stable effect; in addition, when the commodity score is predicted, the dynamic weight adjusting method is adopted, and the accuracy of the prediction result is greatly improved.
Detailed Description
The invention will be further explained and illustrated with reference to specific examples. The step numbers in the embodiments of the present invention are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.
As a deep learning method, the Multi-view Neural Networks (Multi-view Neural Networks) have the characteristics of full connection layers and convolution layers, have the advantage of higher prediction speed than that of the BP Neural Networks, and can effectively overcome the technical obstacle of pushing considering the contradiction between local information and global information.
In order to avoid various defects of the prior art, the invention applies the characteristics of big data science, preprocesses data in a targeted manner, and introduces a multi-view neural network, wherein the network is supported by two models, namely: a Constraint Model (CM) and an Independent scoring Model (RIM) consider global information and local information at the same time, a method based on historical data and content is used for participating in modeling, then a method for dynamically adjusting weight is used for adjusting a result of Model prediction, and the pushing of commodities and commodity paths to users is realized in cooperation with data mining science.
The embodiment of the invention provides a commodity pushing method based on big data science and dynamic weight adjustment, which comprises the following steps:
s1, generating a user commodity matrix according to the scores of the commodities by the users;
specifically, the invention obtains the value of each commodity of each user under a certain commodity classification according to the database of the online education system, wherein the lowest point is assumed to be 0, the highest point is assumed to be 5, if the user does not pass a certain commodity, the value is recorded as a null value, and the data are filled into a user-commodity matrix.
S2, generating preference information of the user according to the user commodity matrix;
further as a preferred embodiment of step S2, the step S2 includes the steps of:
s21, operating the user commodity matrix to generate a first result, wherein the first result comprises a commodity coexistence matrix and a user coexistence matrix;
and S22, extracting information from the operation result of the commodity matrix of the user through the web log to obtain the preference information of the user.
S3, constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user;
further as a preferred embodiment of step S3, the step S3 includes the steps of:
s31, solving the first result through a matrix decomposition method to obtain a second result;
s32, solving the second result through the regularized singular value to obtain a third result;
and S33, constructing a constraint model and an independent scoring model according to the third result.
And S34, establishing the multi-view neural network through the constraint model and the independent scoring model.
Further as a preferred embodiment of step S34, the step S34 includes the steps of:
s341, inputting the real-time solution of the constraint model into a full connection layer for first training;
s342, inputting the real-time solution of the independent scoring model into the convolutional layer for second training;
s343, inputting the historical solution of the constraint model into a full-connection layer for third training;
s344, inputting the historical solution of the independent scoring model into the convolutional layer for fourth training;
and S345, establishing the multi-view neural network according to the results of the first training, the second training, the third training and the fourth training.
S4, generating a commodity score predicted value based on a dynamic weight adjustment method according to the constraint model and the independent score model;
further as a preferred embodiment, the step S4 includes the steps of:
s41, generating a first prediction component through a multi-view neural network;
s42, generating a second prediction component through the user preference information;
s43, providing a general S44, and configuring the weights of the first prediction component, the second prediction component and the third prediction component based on a dynamic weight adjusting mechanism; generating a third prediction component by a nearest neighbor classification algorithm;
and S45, generating a commodity grade predicted value through the first prediction component, the second prediction component and the third prediction component according to the weight configuration result.
And S5, pushing commodities according to the commodity score prediction value.
Further as a preferred embodiment of step S5, the step S5 includes the steps of:
s51, generating a commodity sequence set according to the user commodity matrix;
s52, calculating the support degree of each commodity sequence in the commodity sequence set, and acquiring a first commodity sequence with the support degree larger than a first threshold value;
s53, taking the first commodity sequence as a current commodity sequence, and calculating the support degree of each commodity sequence in the commodity sequence matrix according to the first commodity sequence and the current commodity sequence S54;
s55, judging whether the commodity sequence support degree in the commodity sequence matrix is larger than a first threshold value, if so, taking all commodity sequences larger than the first threshold value as first commodity sequences, and returning to execute the step S53; otherwise, go to step S56;
and S56, screening the commodity sequence with the support degree larger than a second threshold value in the commodity matrix, and taking the commodity sequence as a commodity pushing result.
Claims (9)
1. The commodity pushing method based on big data science and dynamic weight adjustment is characterized by comprising the following steps: the method comprises the following steps:
generating a user commodity matrix according to the scores of the commodities by the users;
generating preference information of the user according to the commodity matrix of the user;
constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user;
generating a commodity scoring predicted value based on a dynamic weight adjusting method according to the constraint model and the independent scoring model;
and carrying out commodity pushing according to the commodity scoring predicted value.
2. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 1, wherein: the step of generating the preference information of the user according to the commodity matrix of the user comprises the following steps:
calculating a user commodity matrix to generate a first result, wherein the first result comprises a commodity coexistence matrix and a user coexistence matrix;
and extracting information of the operation result of the commodity matrix of the user through the web log to obtain the preference information of the user.
3. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 2, wherein: the step of constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user is included
The method comprises the following steps:
solving the first result by a matrix decomposition method to obtain a second result;
solving the second result through the regularized singular value to obtain a third result;
and constructing a constraint model and an independent scoring model according to the third result.
4. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 3, wherein: the step of constructing a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user, and the step of constructing the constraint model and the independent scoring model
The method comprises the following steps:
and establishing the multi-view neural network through the constraint model and the independent scoring model.
5. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 4, wherein: the step of establishing the multi-view neural network through the constraint model and the independent scoring model comprises the following steps:
inputting the real-time solution of the constraint model into a full-connection layer for first training;
inputting the real-time solution of the independent scoring model into the convolutional layer for second training;
inputting the historical solution of the constraint model into a full-connection layer for third training;
inputting the historical solution of the independent scoring model into the convolutional layer for fourth training;
and establishing the multi-view neural network according to the results of the first training, the second training, the third training and the fourth training.
6. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 4, wherein: the step of generating the commodity score predicted value based on the dynamic weight adjustment method according to the constraint model and the independent score model comprises the following steps:
generating a first prediction component by a multi-view neural network;
generating a second prediction component by the user preference information;
generating a third prediction component by a nearest neighbor classification algorithm;
respectively configuring the weights of the first prediction component, the second prediction component and the third prediction component based on a dynamic weight adjustment mechanism;
and generating a commodity score predicted value through the first prediction component, the second prediction component and the third prediction component according to the weight configuration result.
7. The commodity pushing method based on big data science and dynamic weight adjustment according to claim 1, wherein: the step of pushing the commodities according to the commodity score predicted value comprises the following steps:
generating a commodity sequence set according to the commodity matrix of the user;
calculating the support degree of each commodity sequence in the commodity sequence set, and acquiring a first commodity sequence with the support degree being greater than a first threshold value;
taking the first commodity sequence as a current commodity sequence, and generating a commodity sequence matrix according to the first commodity sequence and the current commodity sequence;
calculating the support degree of each commodity sequence in the commodity sequence matrix;
judging whether the commodity sequence matrix has the commodity sequence support degree larger than a first threshold value, if so, taking all the commodity sequences larger than the first threshold value as current commodity sequences, and returning to execute the step of generating the commodity sequence matrix according to the first commodity sequence and the current commodity sequences; otherwise, executing the next step;
and screening the commodity sequence with the support degree larger than a second threshold value in the commodity matrix, and taking the commodity sequence as a commodity pushing result.
8. Commodity push system based on big data science and dynamic weight adjustment, its characterized in that: the method comprises the following steps:
the first generation module is used for generating a user commodity matrix according to the scores of the user on the commodities;
the second generation module is used for generating preference information of the user according to the commodity matrix of the user;
the model building module is used for building a constraint model and an independent scoring model according to the commodity matrix of the user and the preference information of the user;
the prediction module is used for generating a commodity scoring prediction value based on a dynamic weight adjustment method according to the constraint model and the independent scoring model;
and the pushing module is used for pushing the commodities according to the commodity scoring predicted value.
9. Commodity push system based on big data science and dynamic weight adjustment, its characterized in that: the method comprises the following steps:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, the at least one program causes the at least one processor to implement the commodity pushing method based on big data science and dynamic weight adjustment according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911102713.8A CN110956492A (en) | 2019-11-13 | 2019-11-13 | Commodity pushing method based on big data science and dynamic weight adjustment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911102713.8A CN110956492A (en) | 2019-11-13 | 2019-11-13 | Commodity pushing method based on big data science and dynamic weight adjustment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110956492A true CN110956492A (en) | 2020-04-03 |
Family
ID=69977444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911102713.8A Pending CN110956492A (en) | 2019-11-13 | 2019-11-13 | Commodity pushing method based on big data science and dynamic weight adjustment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110956492A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112488355A (en) * | 2020-10-28 | 2021-03-12 | 华为技术有限公司 | Method and device for predicting user rating based on graph neural network |
-
2019
- 2019-11-13 CN CN201911102713.8A patent/CN110956492A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112488355A (en) * | 2020-10-28 | 2021-03-12 | 华为技术有限公司 | Method and device for predicting user rating based on graph neural network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20140279739A1 (en) | Resolving and merging duplicate records using machine learning | |
US9159027B2 (en) | Adaptive experimentation method and system | |
US20060184482A1 (en) | Adaptive decision process | |
CN114721833B (en) | Intelligent cloud coordination method and device based on platform service type | |
Guo et al. | An energy sensitive computation offloading strategy in cloud robotic network based on ga | |
US20230031522A1 (en) | Recommendation method and apparatus based on automatic feature grouping | |
CN116915686B (en) | Heterogeneous multi-edge cloud collaborative micro-service deployment and routing joint optimization method and system | |
Makridakis et al. | The accuracy of machine learning (ML) forecasting methods versus statistical ones: extending the results of the M3-Competition | |
CN101616074A (en) | Multicast routing optimization method based on quantum evolution | |
CN110956492A (en) | Commodity pushing method based on big data science and dynamic weight adjustment | |
Li et al. | A hierarchy weighting similarity measure to improve user-based collaborative filtering algorithm | |
US20230224225A1 (en) | Method and system for link prediction in large multiplex networks | |
CN115150335B (en) | Optimal flow segmentation method and system based on deep reinforcement learning | |
CN115022231B (en) | Optimal path planning method and system based on deep reinforcement learning | |
CN101894063A (en) | Method and device for generating test program for verifying function of microprocessor | |
CN109271371B (en) | Spark-based distributed multi-layer big data analysis processing model | |
Koesdwiady et al. | Methods to improve multi-step time series prediction | |
JP6562851B2 (en) | Yield prediction device and yield prediction method | |
Friese et al. | Weighted ensembles in model-based global optimization | |
KR102251139B1 (en) | A missing value correction system using machine learning and data augmentation | |
CN114596054A (en) | Service information management method and system for digital office | |
Ye et al. | ILBPS: An Integrated Optimization Approach Based on Adaptive Load-Balancing and Heuristic Path Selection in SDN | |
US20100049665A1 (en) | Basel adaptive segmentation heuristics | |
US11604966B1 (en) | Generative adversarial network optimization | |
Zhou | Cloud platform based on mobile internet service opportunistic drive and application aware data mining |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200403 |