CN111143685B - Commodity recommendation method and device - Google Patents
Commodity recommendation method and device Download PDFInfo
- Publication number
- CN111143685B CN111143685B CN201911394281.2A CN201911394281A CN111143685B CN 111143685 B CN111143685 B CN 111143685B CN 201911394281 A CN201911394281 A CN 201911394281A CN 111143685 B CN111143685 B CN 111143685B
- Authority
- CN
- China
- Prior art keywords
- optimization
- model
- individuals
- optimized
- identifiable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000005457 optimization Methods 0.000 claims abstract description 151
- 238000012163 sequencing technique Methods 0.000 claims abstract description 35
- 230000000694 effects Effects 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000003860 storage Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012216 screening Methods 0.000 claims description 13
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000007418 data mining Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000012804 iterative process Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- UBKQRASXZMLQRJ-UHFFFAOYSA-N 2-phenylsulfanylethanamine Chemical compound NCCSC1=CC=CC=C1 UBKQRASXZMLQRJ-UHFFFAOYSA-N 0.000 description 1
- 241001415395 Spea Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000001637 plasma atomic emission spectroscopy Methods 0.000 description 1
- 229920000110 poly(aryl ether sulfone) Polymers 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity recommending method and device, relates to the technical field of data mining, and mainly aims to improve the optimizing effect of a recommending system and simultaneously avoid the complexity of a model structure by performing multi-objective optimization on the model structure and the effect. The main technical scheme of the invention is as follows: acquiring a sample data set according to the transaction data; determining a plurality of targets to be optimized and a plurality of targets to be optimized of a sequencing model in a recommendation system, wherein the targets to be optimized at least comprise a first optimization target and a second optimization target, the first optimization target is a target for representing a model effect, the second optimization target is a target for representing a model structure, and the targets to be optimized are super-parameters of the sequencing model; optimizing a plurality of objects to be optimized by utilizing a multi-objective optimization algorithm based on a sample data set to obtain a plurality of optimization models; integrating the plurality of optimization models into an integrated model according to a preset strategy, and applying the integrated model to the recommendation system.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a commodity recommendation method and device.
Background
In the big data age, the recommendation system can provide personalized recommendation results for different clients, so that the clients can be better served. In particular, in the field of electronic commerce, how to accurately recommend different products to different clients is significant, and along with the explosive growth of the data volume of the internet and the breakthrough of machine learning technology, the construction of an automatic recommendation system becomes a reality.
At present, when a recommendation system is constructed, a model is generally constructed by using a machine learning algorithm, and then a training sample is used for training the model, so that the available recommendation system is obtained. The accuracy of recommending products to users by the recommendation system is mainly reflected by the training effect of the model, so that the model effect is usually optimized for optimizing the recommendation system, and the model becomes more and more complex in the process of optimizing the model effect. The complex model is easy to cause the time consumed by training and predicting the model to be increased, more calculation resources are required to be consumed, and meanwhile, the complex model is easy to cause over fitting, namely, the effect is good when the model is verified off line, but poor performance occurs on line. It follows that further improvements are needed for how the existing recommendation system is optimized.
Disclosure of Invention
In view of the above problems, the present invention provides a method and an apparatus for recommending goods, which mainly aims to improve the optimization effect of a recommendation system and simultaneously avoid complicating the model structure by performing multi-objective optimization on the model structure and the effect.
In order to achieve the above purpose, the present invention mainly provides the following technical solutions:
in one aspect, the invention provides a commodity recommendation method, which specifically includes:
acquiring a sample data set according to the transaction data;
determining a plurality of targets to be optimized and a plurality of targets to be optimized of a sequencing model in a recommendation system, wherein the targets to be optimized at least comprise a first optimization target and a second optimization target, the first optimization target is a target for representing a model effect, the second optimization target is a target for representing a model structure, and the targets to be optimized are super-parameters of the sequencing model;
optimizing the plurality of objects to be optimized by utilizing a multi-objective optimization algorithm based on the sample data set to obtain a plurality of optimization models;
integrating the plurality of optimization models into an integrated model according to a preset strategy, and applying the integrated model to the recommendation system.
In another aspect, the present invention provides a commodity recommendation device, specifically including:
an acquisition unit for acquiring a sample dataset from transaction data;
the system comprises a determining unit, a determining unit and a determining unit, wherein the determining unit is used for determining a plurality of targets to be optimized and a plurality of targets to be optimized of a sequencing model in a recommendation system, the targets to be optimized at least comprise a first optimizing target and a second optimizing target, the first optimizing target is a target for representing a model effect, the second optimizing target is a target for representing a model structure, and the targets to be optimized are super-parameters of the sequencing model;
the optimizing unit is used for optimizing the plurality of objects to be optimized determined by the determining unit by utilizing a multi-objective optimizing algorithm based on the sample data set obtained by the obtaining unit to obtain a plurality of optimizing models;
and the synthesis unit is used for integrating the plurality of optimization models into an integrated model according to a preset strategy and applying the integrated model to the recommendation system.
In another aspect, the present invention provides a storage medium, where the storage medium is used for storing a computer program, where the computer program controls, when running, a device where the storage medium is located to execute the commodity recommendation method described above.
In another aspect, the present invention provides a processor, where the processor is configured to run a program, and the program executes the commodity recommendation method described above when running the program.
By means of the technical scheme, the commodity recommending method and device provided by the invention are mainly used for optimizing the sequencing model in the recommending system in a multi-objective manner, so that the recommending system with a simple structure and high efficiency is constructed, and time consumption, resource consumption, overfitting and other conditions caused by complex model structure are reduced while the recommending accuracy is ensured. In the invention, when a plurality of optimization targets in the sequencing model are determined, the optimization targets are divided and selected at least according to the classification mode of the model effect and the model structure, so that multi-target optimization is performed, and the optimized optimization models are integrated to adapt to different input data to obtain optimal recommendation results.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 shows a flow chart of a commodity recommendation method according to an embodiment of the present invention;
FIG. 2 shows a flowchart of optimizing a plurality of objects to be optimized according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating the integration of multiple optimization models into an integrated model in accordance with an embodiment of the present invention;
FIG. 4 is a block diagram showing a commodity recommending apparatus according to an embodiment of the present invention;
fig. 5 shows a block diagram of another commodity recommendation device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a commodity recommendation method which is mainly applied to optimizing a sequencing model in a recommendation system, so that a recommended result has higher response speed and lower resource occupation while being better and more accurate. The specific steps of the method are shown in fig. 1, and the method comprises the following steps:
101. a sample dataset is obtained from the transaction data.
In general, the transaction data record is data of a user purchasing a commodity, which is taken as a positive sample in the sample data set, and the negative sample in the sample data set is generated based on the positive sample, for example, a correspondence between the user and the commodity without the transaction record is generated as a negative sample.
Sample generation in the sample dataset of this step is illustrated by the following table:
| user number | Product number |
| u1 | p1 |
| u2 | p2 |
| u3 | p3 |
TABLE 1
| User number | Product number | f1 | f2 | f3 | f4 | Identification mark |
| u1 | p1 | 2 | 1 | 3 | 11 | 1 |
| u1 | p2 | 4 | 2 | 5 | 12 | 0 |
| u1 | p3 | 20 | 10 | 15 | 10 | 0 |
| u2 | p1 | 25 | 130 | 12 | 23 | 1 |
| u2 | p2 | 34 | 32 | 13 | 22 | 0 |
| u2 | p3 | 52 | 17 | 15 | 27 | 0 |
| u3 | p1 | 29 | 83 | 32 | 23 | 1 |
| u3 | p2 | 96 | 27 | 36 | 27 | 0 |
| u3 | p3 | 25 | 32 | 35 | 22 | 0 |
TABLE 2
Wherein, transaction data is recorded in table 1, i.e. user u1 purchased product p1, user u2 purchased product p2, user u3 purchased product p3, table 2 is generated based on the transaction data, each row in table 2 is represented as one sample, and table 2 constitutes a sample data set. In table 2, positive and negative attributes for marking the sample are identified, and f1, f2, f3, etc. are used to record the relevant attributes of the sample, such as the number of times the user views the product, the browsing duration, etc.
102. And determining a plurality of targets to be optimized and a plurality of objects to be optimized of the sequencing model in the recommendation system.
Ranking models in recommendation systems are typically built based on ranking targets in multiple dimensions, and therefore optimization of the ranking model, i.e., the ranking targets that build the ranking model, is optimized. In this step, when the sorting model is optimized, a plurality of targets are simultaneously optimized, that is, a plurality of targets to be optimized are determined, and the targets to be optimized are generally preset. Moreover, the optimization of a target is generally related to one or more super-parameters in the ranking model, so that the super-parameters, i.e. a plurality of objects to be optimized, to be optimized in the ranking model are determined at the same time as the target to be optimized is determined.
It should be noted that, in the present invention, the determined plurality of objects to be optimized includes at least a first optimization object and a second optimization object, where the first optimization object is an object representing a model effect, the second optimization object is an object representing a model structure, and the objects to be optimized are super parameters of the ranking model. That is, the object to be optimized determined in the present invention is to select at least one object from two dimensions of the model effect and the model structure as the object to be optimized. By optimizing the method, the sequencing model is ensured to have higher accuracy and simpler structure, so that the response time and the resource consumption of the sequencing model are lower.
The first optimization target comprises, but is not limited to, one or more of recall rate, accuracy and AUC of the sequencing model, wherein the AUC is a common evaluation index of the model, and can objectively reflect the comprehensive prediction capability of positive samples and negative samples and eliminate the influence of sample inclination; the second optimization objective is a model structure determined according to an algorithm employed by a ranking model, for example, when the ranking model is a gradient-lifted tree model (GBDT), the second optimization objective may be a sum of a product of a maximum depth of the tree and a number of tree nodes and all nodes of the tree.
103. And optimizing the plurality of objects to be optimized by utilizing a multi-objective optimization algorithm based on the sample data set to obtain a plurality of optimization models.
Among them, commonly used multi-objective optimization algorithms such as NSGA, PAES, SPEA and NSGA-II and clonal selection algorithms, etc. The selection of different optimization algorithms needs to be determined according to specific application scenarios, and the embodiment of the invention is not limited in detail.
104. Integrating the plurality of optimization models into an integrated model according to a preset strategy, and applying the integrated model to a recommendation system.
The aim of the step is to integrate a plurality of optimization models, and as a result, recommendation prediction can be carried out on different input samples through the combination of different optimization models, so that more accurate recommendation results can be obtained. Thus, the integrated model may also be regarded as a combined model of at least one optimization model selected from a plurality of optimization models for processing for different input data. The specific combination mode needs to be determined according to a preset strategy, such as weighting, averaging and the like.
Based on the embodiment shown in fig. 1, it can be known that the commodity recommendation method provided by the invention mainly performs optimization construction on the ranking model in the recommendation system, performs synchronous optimization on a plurality of optimization targets and corresponding optimization objects of the determined effect and structure dimension according to the acquired sample data set, integrates the obtained plurality of optimization models, so that the constructed ranking model can select optimization models with different combinations for processing according to different inputs, and inputs the optimal ranking result. Because the optimization of the ordering model in the invention is based on the synchronous optimization of the model effect and the two dimensions of the model structure, the optimized ordering model has both effect and structure, realizes that the ordering model with a simpler structure has more ordering effect, and improves the overall processing efficiency of the recommendation system.
Further, with respect to step 103 in the embodiment shown in fig. 1, a preferred embodiment of the present invention is a process for optimizing a plurality of objects to be optimized based on NSGA-II algorithm, and specific steps thereof are shown in fig. 2, including:
201. and carrying out N groups of random assignment on the plurality of objects to be optimized to generate N individuals, thereby forming an initial population.
Wherein, the object to be optimized is a super-parameter of the ranking model determined based on a plurality of objects to be optimized, for example, when the ranking model is a gradient-lifted tree model (GBDT), the super-parameters required to be optimized by the GBDT include: learning rate, sampling rate, maximum number of trees, maximum depth of trees, etc.
202. And iterating the initial population to obtain an iterated individual.
Wherein the number of individuals of the iterative individuals may be greater than N. The iterative process includes conventional selection, crossover, and mutation operations.
203. And screening iterative individuals according to the preset probability trigger, and selecting individuals with the difference of the optimization results of the multiple targets to be optimized greater than a threshold value.
Specific screening methods may include:
first, a random probability value is acquired.
And when the random probability value is less than or equal to the preset probability value, sorting the optimization results corresponding to each target to be optimized by the iterative individuals according to the sequence from high to low.
And finally deleting M iterative individuals sequenced at the last, wherein M is the ratio of the total number of the preset deletions to the total number of targets to be optimized.
According to the above steps, the optimization results of each iteration individual in each target to be optimized are ordered, so as to select the iteration individual which is optimized worst relative to each target to be optimized, and the number of the iteration individuals is controlled to be M. The screening process may refer to the following example steps:
1) Generating a random integer n of [1,100], and when n is less than or equal to lambda (assuming lambda to be 5 according to experience), executing the following steps.
2) Assuming that the number of targets to be optimized is m and t is respectively 1 ,t 2 ,…,t m . Respectively at the ith target t i Ranking is performed on the base of t i The method is applied to the effect after the sorting model. Reject at target t i The last 5 individuals in each target rank will be deleted with the worst α/m% individuals (typically a empirically valued of 20), e.g., m is 4. Of course, the deleting mode is not limited to the ratio of the total number of the preset deletions to the total number of the targets to be optimized, and can also be based onThe importance of the targets is removed by weighting, for example, when m is 2, the first target has a weight of 0.8, and the second target has a weight of 0.2, then, according to the ranking, the last 16 individuals in the first target ranking will be removed, and only the last 4 individuals in the second target ranking will be removed.
The step is to eliminate individuals with obvious defects and accelerate the convergence rate of the iterative process.
204. And sorting the screened iteration individuals according to the optimized result of the sorting model.
Specifically, the ordering process in the NSGA-II algorithm is as follows:
firstly, carrying out rapid non-dominant sorting on the screened iteration individuals, and dividing the iteration individuals into a plurality of layers according to an optimization result of a sorting model. The basic principle of the rapid non-dominant sorting is as follows: selecting all non-dominant individuals in the population, dividing the non-dominant individuals into the same level, wherein the sequence value is 1, namely a first layer, removing the individuals in the first layer, finding new non-dominant individuals in the rest individuals, enabling the sequence value to be 2, and the like until all the individuals in the population are ranked.
Secondly, the crowding degree of iterative individuals in the appointed layer is calculated.
And finally, ordering the iteration individuals in the appointed layer according to the crowding degree.
205. And selecting N iterative individuals with the best optimization results according to the sequences to form a next generation population.
As can be seen from the steps shown in fig. 2, the optimization process is an iterative process of the population, but in fig. 2, only the process from iteration of the primary population to iteration of the secondary population is exemplarily illustrated, and in the practical application process, the iteration needs to be repeated for a plurality of times until an individual meeting the optimization condition exists in the individuals, or at least one individual in the individuals is determined to be an optimization result after the iteration for a designated number of times, and the optimization result is applied to the ranking model, so as to obtain the optimization model. Generally, through the iterative process described above, a plurality of available individuals are obtained, and applying these individuals to the ranking model results in a plurality of optimization models.
Further, based on the embodiments shown in fig. 1 and fig. 2, a preferred embodiment of the present invention is a possible manner described with respect to step 104, that is, integrating a plurality of optimization models, thereby obtaining an integrated model, and specific steps thereof are shown in fig. 3, including:
301. an identifiable interval for each optimization model for all sample data is determined.
The identifiable interval is used for distinguishing whether each optimization model can obtain a valid sequencing result for the sample data.
The specific process of determining the identifiable interval is as follows:
first, the optimization model ranks the ranking results of all sample data from high to low.
And then, determining an identifiable interval, wherein two endpoints of the identifiable interval are a k-th big sorting result and a k-th small sorting result according to the sorting, and k is a preset value.
302. And judging whether the plurality of optimization models are identifiable to the same sample data by utilizing the identifiable interval.
For a sample data, if its ranking result in an optimization model is outside the identifiable interval, i.e., the ranking result is greater than the kth big ranking result or is less than the kth small ranking result, then the sample data is considered to be identifiable by the identifiable interval.
Because each optimization model has a corresponding identifiable interval, for the same sample data, whether the optimization model capable of identifying the sample data exists or not can be judged through the identifiable intervals corresponding to different optimization models.
303. If the identifiable optimization model exists, the ranking result of the integrated model is the ratio of the sum of the ranking results of all identifiable optimization models to the number of identifiable optimization models.
304. If no identifiable optimization model exists, the ranking result of the integrated model is the average value of the ranking results of all the optimization models.
For the description of the above steps, the comparison can be made with the data in the following table:
assume that the samples to be predicted are as shown in table 3:
TABLE 3 Table 3
Assuming that the number of the obtained optimization models is 3, the predicted values of the samples in table 3 are shown in table 4:
TABLE 4 Table 4
Assuming k is 10, then the identifiable interval for model 1 is 0.1-0.7; the identifiable interval of the model 2 is 0.1-0.7; the identifiable interval of model 3 is 0.2-0.8, from which it is known that model 1 is identifiable as sample 1 and sample 8, and model 2 and model 3 are identifiable as sample 1 and sample 7. Based on this, the integration model integrates model 1, model 2 and model 3 according to the preset strategy to obtain the predicted values of the samples, i.e. the sorting result, according to the embodiments of steps 303 and 304, the result is as follows
Table 5 shows:
| sample numbering | f1 | f2 | f3 | f4 | Model 1 | Model 2 | Model 3 | Final prediction result |
| 1 | 21 | 5 | 3 | 66 | 0.1 | 0.1 | 0.2 | (0.1+0.1+0.2)/3 |
| 2 | 2 | 6 | 2 | 72 | 0.3 | 0.3 | 0.5 | (0.3+0.3+0.5)/3 |
| 3 | 3 | 72 | 4 | 20 | 0.2 | 0.4 | 0.4 | (0.2+0.4+0.4)/3 |
| 4 | 52 | 11 | 7 | 21 | 0.4 | 0.3 | 0.6 | (0.4+0.3+0.6)/3 |
| 5 | 6 | 23 | 87 | 4 | 0.5 | 0.5 | 0.7 | (0.5+0.5+0.7)/3 |
| 6 | 27 | 52 | 91 | 8 | 0.6 | 0.6 | 0.3 | (0.6+0.6+0.3)/3 |
| 7 | 14 | 8 | 3 | 4 | 0.4 | 0.7 | 0.8 | (0.7+0.8)/2 |
| 8 | 9 | 4 | 456 | 2 | 0.7 | 0.2 | 0.6 | 0.7/1 |
| 9 | 8 | 2 | 39 | 7 | 0.2 | 0.2 | 0.3 | (0.2+0.2+0.3)/3 |
| 10 | 12 | 22 | 32 | 7 | 0.3 | 0.4 | 0.5 | (0.3+0.4+0.5)/3 |
TABLE 5
It should be noted that the embodiments of the steps 303 and 304 are only exemplary, and different preset strategies may be integrated into different integrated models, for example, a weighted manner may be used to calculate the sorting result in addition to the averaging manner.
As can be seen from the description of fig. 1-3, the commodity recommendation method provided by the invention optimizes the sorting models in the recommendation system, mainly optimizes the effects and structures of the models by using a multi-objective optimization algorithm, integrates a plurality of obtained optimization models so as to be suitable for different input data, optimizes the model structures of the models while improving the model identification accuracy, improves the response speed of the models, reduces the occupation of computing resources, and integrally improves the recommendation result of the recommendation system.
Further, as an implementation of the commodity recommendation method, the embodiment of the invention provides a commodity recommendation device which is mainly used for achieving the purpose of avoiding the complexity of a model structure while improving the optimization effect of a recommendation system by performing multi-objective optimization on the model structure and the effect. For convenience of reading, the details of the foregoing method embodiment are not described one by one in the embodiment of the present apparatus, but it should be clear that the apparatus in this embodiment can correspondingly implement all the details of the foregoing method embodiment. The device is shown in fig. 4, and specifically comprises:
an acquisition unit 41 for acquiring a sample dataset from transaction data;
a determining unit 42, configured to determine a plurality of targets to be optimized and a plurality of targets to be optimized of a ranking model in a recommendation system, where the targets to be optimized at least include a first optimization target and a second optimization target, the first optimization target is a target representing a model effect, the second optimization target is a target representing a model structure, and the targets to be optimized are super parameters of the ranking model;
an optimizing unit 43, configured to optimize the plurality of objects to be optimized determined by the determining unit 42 by using a multi-objective optimization algorithm based on the sample data set obtained by the obtaining unit 41, so as to obtain a plurality of optimization models;
and a synthesizing unit 44, configured to integrate the plurality of optimization models obtained by the optimizing unit 43 into an integrated model according to a preset policy, and apply the integrated model to the recommendation system.
Further, as shown in fig. 5, the optimizing unit 43 includes:
the generating module 431 is configured to perform N groups of random assignments on the multiple objects to be optimized, generate N individuals, and form an initial population;
the iteration module 432 is configured to iterate the initial population obtained by the generation module 431 to obtain iterated individuals, where the number of individuals of the iterated individuals is greater than N;
the screening module 433 is configured to trigger, according to a preset probability, screening the iterative individuals obtained by the iteration module 432, and selecting individuals whose optimization results of the multiple targets to be optimized differ by more than a threshold;
a ranking module 434, configured to rank the iterative individuals screened by the screening module 433 according to the optimization result of the ranking model;
the generating module 431 is further configured to select N iterative individuals with the best optimization results to form a next generation population according to the ranking obtained by the ranking module.
Further, the screening module 433 is further configured to:
acquiring a random probability value;
when the random probability value is smaller than or equal to a preset probability value, sequencing the optimization results corresponding to each target to be optimized by the iterative individuals from high to low;
deleting M iterative individuals sequenced at the last, wherein M is the ratio of the total number of the preset deletions to the total number of targets to be optimized.
Further, the sorting module 434 is further configured to:
carrying out rapid non-dominant sorting on the screened iteration individuals, and dividing the iteration individuals into a plurality of layers according to an optimization result of the sorting model;
calculating the crowding degree of iterative individuals in the appointed layer;
and ordering the iterative individuals in the appointed layer according to the crowding degree.
Further, as shown in fig. 5, the synthesizing unit 44 includes:
a determining module 441, configured to determine an identifiable interval of each optimization model for all sample data, where the identifiable interval is used to distinguish whether the optimization model can obtain a valid sorting result for the sample data;
a judging module 442, configured to judge whether the plurality of optimization models are identifiable to the same sample data by using the identifiable interval determined by the determining module 441;
a synthesis module 443, configured to, if there is an identifiable optimization model, set a ranking result of the integrated model as a ratio of a sum of ranking results of all identifiable optimization models to a number of identifiable optimization models;
the synthesis module 443 is further configured to, if there is no identifiable optimization model, determine that the ranking result of the integrated model is an average value of the ranking results of all the optimization models.
Further, the determining module 441 is further configured to:
sequencing the sequencing results of all sample data from high to low by the optimization model;
and determining an identifiable interval, wherein two endpoints of the identifiable interval are a k-th big sorting result and a k-th small sorting result according to the sorting, and k is a preset value.
Further, the first optimization objective determined by the determining unit 42 is one or more of recall, accuracy, AUC including the ranking model;
the second optimization objective determined by the determining unit 42 is a model structure determined according to an algorithm adopted by the ranking model, and when the ranking model is a gradient-lifting tree model, the second optimization objective is a sum of a product of a maximum depth of a tree and the number of trees and all nodes of the tree.
Further, the embodiment of the invention also provides a storage medium which is used for storing the computer program, wherein the computer program controls equipment where the storage medium is located to execute the commodity recommendation method when running.
In addition, the embodiment of the invention also provides a processor, which is used for running a program, wherein the commodity recommendation method is executed when the program runs.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the methods and apparatus described above may be referenced to one another. In addition, the "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent the merits and merits of the embodiments.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
Furthermore, the memory may include volatile memory, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), in a computer readable medium, the memory including at least one memory chip.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (16)
1. A method of merchandise recommendation, the method comprising:
acquiring a sample data set according to transaction data, wherein the sample data set comprises a positive sample and a negative sample, the positive sample is used for indicating data of a user for purchasing goods, the negative sample is used for indicating data of a user without transaction records with the goods, and the data comprises the times of checking the goods and browsing duration of the user;
determining a plurality of targets to be optimized and a plurality of targets to be optimized of a sequencing model in a recommendation system, wherein the targets to be optimized at least comprise a first optimization target and a second optimization target, the first optimization target is a target for representing a model effect, the second optimization target is a target for representing a model structure, and the targets to be optimized are super-parameters of the sequencing model;
optimizing the plurality of objects to be optimized by utilizing a multi-objective optimization algorithm based on the sample data set to obtain a plurality of optimization models, wherein the multi-objective optimization algorithm is determined according to the application scene of the recommendation system;
determining an identifiable interval of each optimization model on all sample data, wherein the identifiable interval is used for distinguishing whether the optimization model can obtain a valid sequencing result on the sample data;
judging whether the plurality of optimization models are identifiable to the same sample data or not by utilizing the identifiable interval;
integrating the plurality of optimization models corresponding to each sample data into an integrated model according to a preset strategy according to the identifiable condition of each sample data;
and applying the integrated model to the recommendation system, wherein the recommendation system is used for recommending commodities to the user.
2. The method of claim 1, wherein the optimizing the plurality of objects to be optimized using a multi-objective optimization algorithm based on the sample dataset to obtain a plurality of optimization models comprises:
performing N groups of random assignment on the plurality of objects to be optimized to generate N individuals to form an initial population;
iterating the initial population to obtain iterated individuals, wherein the number of the iterated individuals is greater than N;
screening the iterative individuals according to the preset probability trigger, and selecting individuals with the difference of the optimization results of the multiple targets to be optimized larger than a threshold value;
sorting the screened iteration individuals according to the optimization result of the sorting model;
and selecting N iterative individuals with the best optimization results according to the sorting to form a next generation population.
3. The method of claim 2, wherein the iterative individual screening according to a preset probability trigger comprises:
acquiring a random probability value;
when the random probability value is smaller than or equal to a preset probability value, sequencing the optimization results corresponding to each target to be optimized by the iterative individuals from high to low;
deleting M iterative individuals sequenced at the last, wherein M is the ratio of the total number of the preset deletions to the total number of targets to be optimized.
4. The method of claim 2, wherein the ranking the screened iterative individuals by the optimization result of the ranking model comprises:
carrying out rapid non-dominant sorting on the screened iteration individuals, and dividing the iteration individuals into a plurality of layers according to an optimization result of the sorting model;
calculating the crowding degree of iterative individuals in the appointed layer;
and ordering the iterative individuals in the appointed layer according to the crowding degree.
5. The method of claim 1, wherein integrating the plurality of optimization models corresponding to each sample data into an integrated model according to a preset strategy according to the identifiable condition of each sample data, comprises:
if the identifiable optimization model exists, the ranking result of the integrated model is the ratio of the sum of the ranking results of all the identifiable optimization models to the number of the identifiable optimization models;
and if the identifiable optimization model does not exist, the sequencing result of the integrated model is the average value of the sequencing results of all the optimization models.
6. The method of claim 5, wherein the determining an identifiable interval for all sample data for each optimization model comprises:
sequencing the sequencing results of all sample data from high to low by the optimization model;
and determining an identifiable interval, wherein two endpoints of the identifiable interval are a k-th big sorting result and a k-th small sorting result according to the sorting, and k is a preset value.
7. The method of any of claims 1-6, wherein the first optimization objective is to include one or more of recall, accuracy, AUC of the ranking model;
the second optimization target is a model structure determined according to an algorithm adopted by the sorting model, and when the sorting model is a gradient lifting tree model, the second optimization target is the sum of the product of the maximum depth of the tree and the number of the tree and all nodes of the tree.
8. A merchandise recommendation apparatus, the apparatus comprising:
the acquisition unit is used for acquiring a sample data set according to transaction data, wherein the sample data set comprises a positive sample and a negative sample, the positive sample is used for indicating data of a user for purchasing goods, the negative sample is used for indicating the data of the user and the goods without transaction records, and the data comprises the times of checking the goods by the user and browsing duration;
the system comprises a determining unit, a determining unit and a determining unit, wherein the determining unit is used for determining a plurality of targets to be optimized and a plurality of targets to be optimized of a sequencing model in a recommendation system, the targets to be optimized at least comprise a first optimizing target and a second optimizing target, the first optimizing target is a target for representing a model effect, the second optimizing target is a target for representing a model structure, and the targets to be optimized are super-parameters of the sequencing model;
the optimizing unit is used for optimizing the plurality of objects to be optimized determined by the determining unit by utilizing a multi-objective optimizing algorithm based on the sample data set obtained by the obtaining unit to obtain a plurality of optimizing models, and the multi-objective optimizing algorithm is determined according to the application scene of the recommending system;
the synthesis unit is used for determining identifiable intervals of each optimization model on all sample data, and the identifiable intervals are used for distinguishing whether the optimization models can obtain effective sequencing results on the sample data or not; judging whether the plurality of optimization models are identifiable to the same sample data or not by utilizing the identifiable interval; integrating the plurality of optimization models corresponding to each sample data into an integrated model according to a preset strategy according to the identifiable condition of each sample data; and applying the integrated model to the recommendation system, wherein the recommendation system is used for recommending commodities to the user.
9. The apparatus of claim 8, wherein the optimizing unit comprises:
the generation module is used for carrying out N groups of random assignment on the plurality of objects to be optimized, generating N individuals and forming an initial population;
the iteration module is used for iterating the initial population obtained by the generation module to obtain iteration individuals, and the number of the iteration individuals is larger than N;
the screening module is used for triggering the iterative individual screening obtained by the iterative module according to the preset probability and selecting individuals with the difference of the optimization results of the multiple targets to be optimized larger than a threshold value;
the sorting module is used for sorting the iterative individuals screened by the screening module according to the optimization result of the sorting model;
the generation module is also used for selecting N iterative individuals with the best optimization results to form a next generation population according to the sequencing obtained by the sequencing module.
10. The apparatus of claim 9, wherein the screening module is further to:
acquiring a random probability value;
when the random probability value is smaller than or equal to a preset probability value, sequencing the optimization results corresponding to each target to be optimized by the iterative individuals from high to low;
deleting M iterative individuals sequenced at the last, wherein M is the ratio of the total number of the preset deletions to the total number of targets to be optimized.
11. The apparatus of claim 9, wherein the ranking module is further configured to:
carrying out rapid non-dominant sorting on the screened iteration individuals, and dividing the iteration individuals into a plurality of layers according to an optimization result of the sorting model;
calculating the crowding degree of iterative individuals in the appointed layer;
and ordering the iterative individuals in the appointed layer according to the crowding degree.
12. The device according to claim 8, wherein the synthesis unit is specifically configured to:
if the identifiable optimization model exists, the ranking result of the integrated model is the ratio of the sum of the ranking results of all the identifiable optimization models to the number of the identifiable optimization models;
and if the identifiable optimization model does not exist, the sequencing result of the integrated model is the average value of the sequencing results of all the optimization models.
13. The device according to claim 12, wherein the synthesis unit is specifically configured to:
sequencing the sequencing results of all sample data from high to low by the optimization model;
and determining an identifiable interval, wherein two endpoints of the identifiable interval are a k-th big sorting result and a k-th small sorting result according to the sorting, and k is a preset value.
14. The apparatus of any of claims 8-13, wherein the first optimization objective determined by the determination unit is one or more of recall, accuracy, AUC comprising the ranking model;
the second optimization target determined by the determining unit is a model structure determined according to an algorithm adopted by the sorting model, and when the sorting model is a gradient lifting tree model, the second optimization target is the sum of the product of the maximum depth of the tree and the number of the tree and all nodes of the tree.
15. A storage medium for storing a computer program, wherein the computer program when run controls a device in which the storage medium is located to perform the merchandise recommendation method of any one of claims 1-7.
16. A processor for executing a computer program, wherein the computer program when executed performs the merchandise recommendation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394281.2A CN111143685B (en) | 2019-12-30 | 2019-12-30 | Commodity recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394281.2A CN111143685B (en) | 2019-12-30 | 2019-12-30 | Commodity recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111143685A CN111143685A (en) | 2020-05-12 |
| CN111143685B true CN111143685B (en) | 2024-01-26 |
Family
ID=70521787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911394281.2A Active CN111143685B (en) | 2019-12-30 | 2019-12-30 | Commodity recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111143685B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753215B (en) * | 2020-06-28 | 2021-11-02 | 海南大学 | Multi-objective recommendation optimization method and readable medium |
| CN111797318B (en) * | 2020-07-01 | 2024-02-23 | 喜大（上海）网络科技有限公司 | Information recommendation method, device, equipment and storage medium |
| CN113627900A (en) * | 2021-08-10 | 2021-11-09 | 未鲲(上海)科技服务有限公司 | Model training method, device and storage medium |
| CN115145153B (en) * | 2022-07-06 | 2023-03-10 | 广东省十九建建设有限公司 | Intelligent energy-saving control method, system, terminal and medium for building house |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022865A (en) * | 2016-05-10 | 2016-10-12 | 江苏大学 | Goods recommendation method based on scores and user behaviors |
| CN106844637A (en) * | 2017-01-19 | 2017-06-13 | 北京工业大学 | Method is recommended based on the film for just giving cluster to prune improvement multi-objective genetic algorithm |
| CN107256241A (en) * | 2017-05-26 | 2017-10-17 | 北京工业大学 | The film recommendation method for improving multi-objective genetic algorithm is replaced based on grid and difference |
| CN107544981A (en) * | 2016-06-25 | 2018-01-05 | 华为技术有限公司 | Content recommendation method and device |
| WO2018060967A1 (en) * | 2016-09-29 | 2018-04-05 | Inesc Tec - Instituto De Engenharia De Sistemas E Computadores, Tecnologia E Ciência | Big data self-learning methodology for the accurate quantification and classification of spectral information under complex varlability and multi-scale interference |
| CN109614609A (en) * | 2018-11-06 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method for establishing model and device |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN110457545A (en) * | 2019-08-16 | 2019-11-15 | 第四范式（北京）技术有限公司 | The method and device of the parameter of order models in a kind of determining recommender system |
| CN110457329A (en) * | 2019-08-16 | 2019-11-15 | 第四范式（北京）技术有限公司 | A kind of method and device for realizing personalized recommendation |
| CN110559664A (en) * | 2019-09-19 | 2019-12-13 | 湘潭大学 | game hero outgoing recommendation method and system based on multi-objective optimization |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7647293B2 (en) * | 2004-06-10 | 2010-01-12 | International Business Machines Corporation | Detecting correlation from data |
| US20120185330A1 (en) * | 2011-01-14 | 2012-07-19 | Platformation, Inc. | Discovery and Publishing Among Multiple Sellers and Multiple Buyers |
| US20180137219A1 (en) * | 2016-11-14 | 2018-05-17 | General Electric Company | Feature selection and feature synthesis methods for predictive modeling in a twinned physical system |
| EP3584717A1 (en) * | 2017-08-01 | 2019-12-25 | Samsung Electronics Co., Ltd. | Electronic device and method for providing search result thereof |
| CN108108821B (en) * | 2017-12-29 | 2022-04-22 | Oppo广东移动通信有限公司 | Model training method and device |
-
2019
- 2019-12-30 CN CN201911394281.2A patent/CN111143685B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022865A (en) * | 2016-05-10 | 2016-10-12 | 江苏大学 | Goods recommendation method based on scores and user behaviors |
| CN107544981A (en) * | 2016-06-25 | 2018-01-05 | 华为技术有限公司 | Content recommendation method and device |
| WO2018060967A1 (en) * | 2016-09-29 | 2018-04-05 | Inesc Tec - Instituto De Engenharia De Sistemas E Computadores, Tecnologia E Ciência | Big data self-learning methodology for the accurate quantification and classification of spectral information under complex varlability and multi-scale interference |
| CN106844637A (en) * | 2017-01-19 | 2017-06-13 | 北京工业大学 | Method is recommended based on the film for just giving cluster to prune improvement multi-objective genetic algorithm |
| CN107256241A (en) * | 2017-05-26 | 2017-10-17 | 北京工业大学 | The film recommendation method for improving multi-objective genetic algorithm is replaced based on grid and difference |
| CN109614609A (en) * | 2018-11-06 | 2019-04-12 | 阿里巴巴集团控股有限公司 | Method for establishing model and device |
| CN109977283A (en) * | 2019-03-14 | 2019-07-05 | 中国人民大学 | A kind of the tourism recommended method and system of knowledge based map and user's footprint |
| CN110457545A (en) * | 2019-08-16 | 2019-11-15 | 第四范式（北京）技术有限公司 | The method and device of the parameter of order models in a kind of determining recommender system |
| CN110457329A (en) * | 2019-08-16 | 2019-11-15 | 第四范式（北京）技术有限公司 | A kind of method and device for realizing personalized recommendation |
| CN110559664A (en) * | 2019-09-19 | 2019-12-13 | 湘潭大学 | game hero outgoing recommendation method and system based on multi-objective optimization |
Non-Patent Citations (9)
| Title |
|---|
| A Study on the Impacts of Maintenance Duration on Dynamic Grouping Modeling and Optimization of Multicomponent Systems;Hai-Canh Vu et.al.;IEEE Transactions on Reliability ( Volume: 67, Issue: 3, September 2018);全文 * |
| Hai-Canh Vu et.al..A Study on the Impacts of Maintenance Duration on Dynamic Grouping Modeling and Optimization of Multicomponent Systems.《IEEE Transactions on Reliability ( Volume: 67, Issue: 3, September 2018)》.2018,全文. * |
| Lambda架构下基于用户行为的机构知识库推荐系统建设研究;邱煜炎;;中国教育信息化(第07期);全文 * |
| 唐真.基于hadoop的推荐系统设计与实现.《中国优秀硕士学位论文全文数据库 (信息科技辑) 》.2014,全文. * |
| 基于 hadoop 的推荐 系统设计与实现;唐真;中国优秀硕士学位论文全 文数据库 (信息科技辑);全文 * |
| 基于Spark的并行化协同深度推荐模型;贾晓光;;计算机工程与应用(第14期);全文 * |
| 基于用户特征的文献个性化推荐系统研究;肖诗伯;郭秀英;;网络新媒体技术(04);全文 * |
| 贾晓光 ; .基于Spark的并行化协同深度推荐模型.计算机工程与应用.2018,(14),全文. * |
| 邱煜炎 ; .Lambda架构下基于用户行为的机构知识库推荐系统建设研究.中国教育信息化.2019,(07),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111143685A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143685B (en) | Commodity recommendation method and device | |
| CN107292186B (en) | Model training method and device based on random forest | |
| CN102855259B (en) | Parallelization of massive data clustering analysis | |
| CN105718490A (en) | Method and device for updating classifying model | |
| CN110570111A (en) | Enterprise risk prediction method, model training method, device and equipment | |
| CN110717535B (en) | Automatic modeling method and system based on data analysis processing system | |
| CN108629436B (en) | Method and electronic equipment for estimating warehouse goods picking capacity | |
| CN108540988B (en) | Scene division method and device | |
| CN106534302A (en) | Multi-task demand service combination method and system | |
| CN112396428B (en) | User portrait data-based customer group classification management method and device | |
| CN114490786B (en) | Data sorting method and device | |
| CN107066328A (en) | The construction method of large-scale data processing platform | |
| CN107193940A (en) | Big data method for optimization analysis | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| CN116226468B (en) | Service data storage management method based on gridding terminal | |
| CN114968028A (en) | Method, apparatus, and medium for dynamically changing menu layout based on user behavior analysis | |
| CN107103095A (en) | Method for computing data based on high performance network framework | |
| CN111145066A (en) | Method and system for determining urban physical sign portrait based on infinite hierarchical data structure | |
| CN113538020B (en) | Method and device for acquiring association degree of group of people features, storage medium and electronic device | |
| CN114339859B (en) | Method and device for identifying WiFi potential users of full-house wireless network and electronic equipment | |
| CN116228483B (en) | Learning path recommendation method and device based on quantum drive | |
| CN117974923A (en) | Method and device for determining three-dimensional modeling data, storage medium and electronic equipment | |
| US20220083905A1 (en) | Framework for providing improved predictive model | |
| CN116563644A (en) | Fluorescent image classification method and device, storage medium and electronic equipment | |
| CN117893309A (en) | User grade determining method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |