CN112508613B - Commodity recommendation method and device, electronic equipment and readable storage medium - Google Patents
Commodity recommendation method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN112508613B CN112508613B CN202011446682.0A CN202011446682A CN112508613B CN 112508613 B CN112508613 B CN 112508613B CN 202011446682 A CN202011446682 A CN 202011446682A CN 112508613 B CN112508613 B CN 112508613B
- Authority
- CN
- China
- Prior art keywords
- click rate
- target user
- predicted
- prediction model
- click
- 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 39
- 238000006243 chemical reaction Methods 0.000 claims abstract description 89
- 238000012549 training Methods 0.000 claims description 42
- 230000006399 behavior Effects 0.000 claims description 29
- 230000008901 benefit Effects 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 10
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims 1
- 230000004927 fusion Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 9
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000000354 decomposition reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 108010033040 Histones Proteins 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity recommendation method, a commodity recommendation device, electronic equipment and a readable storage medium, wherein the commodity recommendation method comprises the following steps: acquiring target user log data, generating a first data set based on the target user log data, and inputting the first data set into the trained click rate prediction model to obtain predicted first click rate; generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate; and recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate. The method utilizes the thought of multi-objective learning, considers the click rate and the conversion rate at the same time, and remarkably improves the recommendation quality; the multi-model fusion is realized, the predicted value of the click rate is used as the characteristic to be input into the conversion rate model, so that not only is the new characteristic constructed, but also the learning result of the click rate model is effectively utilized, the result is transmitted to the conversion rate model, and the generalization capability of the model is improved.
Description
Technical Field
The invention relates to the field of computer distributed processing, in particular to a commodity recommendation method, a commodity recommendation device, electronic equipment and a readable storage medium.
Background
The artificial intelligence technology has been integrated into the life of the social masses, and many internet platforms are presented to quickly help users to find commodities with higher cost performance in order to meet the purchase demands of the users, and personalized recommendation is required to recommend the commodities possibly purchased by the users to the users, so that the Click-Through-Rate (CTR) and Conversion Rate (Conversion Rate, CVR) of the commodities are improved, and the users Click the advertisements to become a Conversion Rate of effectively activating, registering and even paying users. However, when commodity recommendation is performed on some current platforms, user preference is judged by experience of people and manual labels, prediction recommendation based on click rate is performed by some simple linear models or tree models (such as logistic regression and decision trees), the models and the methods have limitations, a great deal of manual labeling is needed for users, the users are easily influenced by personal subjectivity, the accuracy of labels cannot be ensured, meanwhile, a simple machine learning algorithm cannot fully represent attribute characteristics and behavior characteristics of the users, the matching degree of recommended commodities and the users is poor, only the click rate prediction model is considered, the conversion rate is not considered in modeling, so that commodity click rate is high, but the conversion rate is not necessarily high, the recommendation effect is poor, and the experience of the users on the platforms is affected.
Disclosure of Invention
The present invention has been made in view of the above problems, and provides a commodity recommendation method, apparatus, electronic device, and readable storage medium that overcome or at least partially solve the above problems.
According to an aspect of the present invention, there is provided a commodity recommendation method, the method comprising:
acquiring target user log data, generating a first data set based on the target user log data, and inputting the first data set into the trained click rate prediction model to obtain predicted first click rate;
generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate;
and recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate.
Optionally, the click rate prediction model is a LightGBM model capable of realizing distributed gradient promotion based on a Histogram decision tree algorithm, and the conversion rate prediction model is a deep FM model for simultaneously learning low-order and high-order combination features by combining DNN and FM advantages.
Optionally, the trained click rate prediction model is obtained through training in the following manner:
user log data in a first preset time period is obtained, user attribute characteristics, commodity attribute characteristics, user behavior data and labels whether to click or not are determined based on the user log data, a first training set is generated, and a pre-built click rate prediction model is trained by the aid of the first training set, so that the trained click rate prediction model is obtained.
Optionally, the trained conversion rate prediction model is obtained through training in the following manner:
generating a third data set based on the user log data in the second preset time period, and inputting the third data set into the trained click rate prediction model to obtain a predicted second click rate;
generating a second training set based on the user log data, the converted label and the second click rate in the second preset time period, and training a pre-constructed conversion rate prediction model by using the second training set so as to obtain a trained conversion rate prediction model;
wherein the second preset time period is closer to a point of time when recommended than the first preset time period.
Optionally, the recommending the commodity to the target user according to the predicted first click rate and the predicted conversion rate includes:
calculating the product of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the product, and recommending one or more commodities to the target user; or,
and calculating an average value of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the average value, and recommending one or more commodities to the target user.
Optionally, the generating the first data set based on the target user log data includes:
determining target user attribute characteristics, recall commodity attribute characteristics and behavior data aiming at recall commodities with corresponding relations based on the target user log data, and combining to form the first data set according to whether a user clicks a label for determining whether to click;
wherein the target user attribute feature comprises at least one of: user attribution, age, gender, registration time, asset size, total browsing duration, total browsing times, purchase times, or total expense;
the recalled commodity refers to a commodity which is browsed, clicked, collected, added into a shopping cart or purchased by a target user, and the attribute characteristics of the recalled commodity comprise at least one of the following: brand, model, type, origin, or location;
the behavioral characteristics for the recall commodity include at least one of: browse, click, collect, join shopping carts, forward, consult, or purchase.
Optionally, the target user is a user who triggers a recall commodity purchase recommendation request; the recalled commodities are commodities in a state of being purchased by the target user so as to control the quantity of the recalled commodities; the behavior data of the recalled commodity is behavior data of a historical user on the recalled commodity.
According to another aspect of the present invention, there is provided a commodity recommendation apparatus, the apparatus comprising:
the click rate determining unit is used for obtaining target user log data, generating a first data set based on the target user log data, and inputting the first data set into the trained click rate prediction model to obtain predicted first click rate;
the conversion rate determining unit is used for generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate;
and the commodity recommending unit is used for recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate.
According to still another aspect of the present invention, there is provided an electronic apparatus including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a method as described in any of the above.
According to a further aspect of the present invention there is provided a computer readable storage medium storing one or more programs which when executed by a processor implement a method as described in any of the above.
From the above, the technical scheme of the invention can obtain the following beneficial effects:
according to the multi-objective learning idea, the click rate and conversion rate double indexes are considered, and the recommended conversion rate is obviously improved. The single-target thought is easy to cause poor recommendation effect, for example, only click rate is considered, so that the click rate is high, the conversion rate is low, or only the conversion rate is considered, the sparsity of data is brought, and the recommendation effect is influenced.
According to the multi-model fusion method, the predicted value of the click rate is used as a characteristic to be input into a conversion rate model, so that on one hand, new effective characteristics are constructed, on the other hand, the result experience learned by the click rate model can be effectively utilized, and the result experience can be transmitted into the conversion rate model, and the generalization capability of the model is improved.
Further, the click rate model is preferably a LightGBM model, the LightGBM is based on a Histone decision tree algorithm, and compared with a pre-dissolved algorithm, the Histone has a plurality of advantages in memory consumption and calculation cost, occupies lower memory, and has lower complexity of data separation; the conversion rate model is preferably a Deep FM model, deep is combined with FM, FM is used for inter-feature low-order combination, deep NN part is used for inter-feature high-order combination, and two methods are combined in a parallel mode, so that the final framework has the following characteristics: pre-training FM is not needed to obtain hidden vectors; no artificial feature engineering is required; the combined characteristics of low order and high order can be learned simultaneously; the FM module and the Deep module share the Feature Embedding part, so that faster training and more accurate training and learning can be realized, and more importantly, unexpected accuracy improvement is obtained by combining the two models.
And the modeling is based on the user attribute, commodity characteristics and user historical behavior data, so that the manual marking process is reduced, and the influence of personal subjective factors on commodity recommendation accuracy is avoided.
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 diagram of a method of recommending items according to one embodiment of the invention;
FIG. 2 is a schematic diagram showing a structure of a commodity recommending apparatus according to an embodiment of the present invention;
FIG. 3 shows a schematic diagram of an electronic device according to one embodiment of the invention;
FIG. 4 illustrates a schematic diagram of a computer-readable storage medium according to one embodiment of the invention;
FIG. 5 shows a flow diagram of click rate acquisition in accordance with one embodiment of the present invention;
FIG. 6 shows a schematic flow diagram of conversion acquisition according to one embodiment of the 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.
FIG. 1 shows a schematic flow diagram of a commodity recommendation method according to one embodiment of the present invention, the method comprising:
s110, acquiring target user log data, and generating a first data set based on the target user log data. The target user log data can be obtained from a distributed website platform or an application platform through buried points, and can obtain user attribute (can be marked as user_id) such as the characteristic data of the affiliated place, age, sex, asset scale, browsing condition and the like from the log data, and further comprises commodity attribute features (can be marked as item_id) which are interested in the user and are to be recommended for recall such as commodity types, brands, models, affiliated places and the like, and behavior data (can be marked as features) of the recall commodity of the user, wherein the behavior data is preferably behavior data of the history user for the recall commodity such as browsing times, browsing time, collecting, shopping cart adding, forwarding, consulting or purchasing times and the like in a certain time period, and can also comprise data such as labels for clicking whether the commodity enters or not, and the data are combined to form a first data set.
And then, inputting the first data set into the trained click rate prediction model to obtain a predicted first click rate.
And S120, generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate.
Of course, the second set of data includes target user attribute features, recall merchandise attribute features, behavioral data, and the like.
It is worth to describe that the second data set includes the first click rate corresponding to the target user, embodies the thought of multi-target learning, and realizes the fusion of the two models, so that the conversion rate prediction model can also react to the click rate.
S130, recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate.
In the step, the recalled commodities are ranked according to the comprehensive level of the first click rate and the conversion rate, and commodity recommendation is carried out to the user according to the ranking condition.
According to the technical scheme, the click rate and the conversion rate are considered by utilizing the thought of multi-target learning, so that the recommendation quality is obviously improved; the multi-model fusion is realized, the predicted value of the click rate is used as the characteristic to be input into the conversion rate model, so that not only is the new characteristic constructed, but also the learning result of the click rate model is effectively utilized, the result is transmitted to the conversion rate model, and the generalization capability of the model is improved.
In a preferred embodiment, the click rate prediction model is a LightGBM model capable of achieving distributed gradient promotion based on a Histogram decision tree algorithm. Light Gradient Boosting Machine (LightGBM) is a distributed gradient promotion (GradientBoosting Decision Tree, GBDT) framework based on decision tree algorithms, open-source by Microsoft Asian institute distributed machine learning toolkit (DMTC) team. It is based on a decision tree algorithm of a Histogram, discretizes continuous floating point features into k discrete values, and constructs a Histogram of width k. The training data is then traversed and the cumulative statistics of each discrete value in the histogram are counted. When the feature selection is carried out, only the optimal segmentation points need to be traversed and searched according to the discrete values of the histogram; compared with the pre-dissolved algorithm, the histogram has a plurality of advantages in memory consumption and calculation cost, occupies lower memory, and has lower complexity of data separation. The following advantages can be obtained based on the histogram advantage: reducing the calculated amount of the segmentation gain; training of further acceleration models by histogram subtraction: the histogram of the leaf node can be obtained by utilizing the subtraction of the histograms of the parent node and the adjacent node of the leaf node in the binary tree, so that the cost is low; the use of the memory is reduced; reducing the communication cost of parallel learning.
And, the LightGBM adopts a leaf-wise growth strategy, and each time a leaf with the maximum splitting gain (generally the maximum data size) is found from all the current leaves, then split and circulate; but a deeper decision tree will grow, resulting in an over-fit, so the LightGBM adds a maximum depth display to the leaf-wise, preventing the over-fit while ensuring high efficiency.
The conversion rate prediction model is a deep FM model which combines DNN and FM advantages and learns low-order and high-order combination characteristics.
Deep FM can be regarded as an algorithm derived from FM, combining Deep with FM, using FM as inter-feature low-order combination, using Deep NN as inter-feature high-order combination, combining two methods in parallel, and enabling the final architecture to have the following characteristics: pre-training FM is not needed to obtain hidden vectors; no artificial feature engineering is required; the combined characteristics of low order and high order can be learned simultaneously; the FM module and the Deep module share Feature Embedding part, which can train faster and train more accurate learning.
The network structure of the Deep FM model firstly divides the Deep FM model into a Deep neural network part and an FM factor decomposition machine part, wherein the Deep neural network part can adopt a fully connected feedforward neural network DNN, the DNN and the FM divide input user characteristics and attribute characteristics into a plurality of characteristic groups, each characteristic group corresponds to an embedding (embedding) vector, wherein a characteristic splicing layer (concat) of the Deep neural network part splices all the embedding vectors, and then a fully connected layer (Fc (relu)) of two layers is added to realize the combination of high-order characteristics; the FM factor decomposition machine performs weighted summation (addition) on input user characteristics, attribute characteristics and other original characteristic inputs, and extracts characteristic combinations through the EMBedding vector inner products of each dimension to realize the combination of low-order characteristics; finally, the output of the Deep neural network and the output of the FM factor decomposition machine are combined to obtain a prediction result (sigmoid).
The optimal embodiment creatively combines the two excellent prediction models, the combined model has better generalization capability than a single model, the idea of integrated learning is adopted, the advantages of multiple models are fully utilized, and the phenomena of larger prediction deviation and overfitting of the single model are avoided.
In a preferred embodiment, as can be seen from fig. 5, the trained click rate prediction model is trained as follows:
acquiring historical user log data in a first preset time period, such as 30 to 60 days recently, determining user attribute characteristics with corresponding relations, commodity attribute characteristics interested by the user and operation data set user behavior data of the commodity performed by the user based on the historical user log data in the time period, marking whether the user clicks the detail of entering the commodity to form a clicked label, combining the labels to generate a first training set, and training a pre-constructed click rate prediction model, such as a LightGBM model, by using the first training set to obtain the trained click rate prediction model.
In a preferred embodiment, as can be seen in connection with fig. 5 and 6, the trained conversion prediction model is trained as follows:
according to fig. 5, a third data set is generated based on the user log data such as the last 30 days in the second preset period, and data items such as user attribute features, commodity attribute features and behavior data may also be included in the third data set, and then the third data set is input into the trained click rate prediction model to obtain a predicted second click rate.
And then, with reference to fig. 6, based on the user log data such as user attribute features, commodity attribute features, behavior data and other data items in the second preset time period, a second training set is generated by splicing and combining the converted labels and the second click rate, and the second training set is utilized to train the pre-constructed conversion rate prediction model, so that a trained conversion rate prediction model is obtained.
Of course, the lengths and intervals of the above-described first and second preset time periods are not limited thereto, and the time periods in which the training purpose can be achieved as long as the conditions are satisfied are all within the protection range, but the conditions that the second preset time period is closer to the point of time when recommended to the target user than the first preset time period need to be satisfied.
In one embodiment, the recommending items to the target user according to the predicted first click through rate and the predicted conversion rate in S130 includes:
calculating the product of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the product, and recommending one or more commodities to the target user; or,
and calculating an average value of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the average value, and recommending one or more commodities to the target user.
Of course, the recommendation may be made to the target user by weighting or by using a certain independent score according to the actual situation.
In some specific embodiments, the generating the first data set based on the target user log data comprises:
determining target user attribute characteristics, recall commodity attribute characteristics and behavior data aiming at recall commodities with corresponding relations based on the target user log data, and combining to form the first data set according to whether a user clicks a label for determining whether to click;
wherein the target user attribute feature comprises at least one of: user attribution, age, gender, registration time, asset size, total browsing duration, total browsing times, purchase times, or total expense; the recalled commodity refers to a commodity which is browsed, clicked, collected, added into a shopping cart or purchased by a target user, and the attribute characteristics of the recalled commodity comprise at least one of the following: brand, model, type, origin, or location; the behavioral characteristics for the recall commodity include at least one of: browse, click, collect, join shopping carts, forward, consult, or purchase.
Further, according to the requirements of training, the following can be determined: the target user is a user triggering a recall commodity purchase recommendation request; the recalled commodities are commodities in a state of being purchased by the target user so as to control the quantity of the recalled commodities; the behavior data for the recalled commodity is behavior data of a historical user for the recalled commodity within, for example, approximately 30-60 days. Under the situation, a model for achieving the aim of predicting the click rate with higher accuracy is easier to obtain.
Fig. 2 shows a schematic structural diagram of a commodity recommendation apparatus 200 according to an embodiment of the present invention, the apparatus 200 including:
the click rate determination unit 210 is adapted to obtain target user log data, and to generate a first data set based on the target user log data. The target user log data can be obtained from a distributed website platform or an application platform through buried points, and can obtain user attribute (marked as user_id) such as belonging location, age, sex, asset size, browsing condition and the like from the log data, and further include commodity attribute features (marked as item_id) which are interested in the user and are to be recommended for recall such as commodity category, brand, model, belonging location and the like, and behavior data (marked as features) of the user on the recalled commodity, wherein the behavior data is preferably behavior data of historical users on the recalled commodity such as browsing times, browsing duration, collection, shopping cart adding, forwarding, consulting or purchasing times and the like in a certain time period, and can also include data such as labels for clicking whether the commodity enters or not, and the data can be combined to form a first data set.
And then, inputting the first data set into the trained click rate prediction model to obtain a predicted first click rate.
The conversion rate determining unit 220 is adapted to generate a second data set based on the target user log data and the first click rate, and input the second data set to a trained conversion rate prediction model to obtain a predicted conversion rate.
The second data set includes target user attribute features, recall merchandise attribute features, behavioral data, and the like.
It is worth to describe that the second data set includes the first click rate corresponding to the target user, embodies the thought of multi-target learning, and realizes the fusion of the two models, so that the conversion rate prediction model can also react to the click rate.
And a commodity recommending unit 230 adapted to recommend a commodity to the target user according to the predicted first click rate and the predicted conversion rate.
In the unit, the recalled commodities are ranked according to the comprehensive level of the first click rate and the conversion rate, and commodity recommendation is carried out to the user according to the ranking condition.
According to the technical scheme, the click rate and the conversion rate are considered by utilizing the thought of multi-target learning, so that the recommendation quality is obviously improved; the multi-model fusion is realized, the predicted value of the click rate is used as the characteristic to be input into the conversion rate model, so that not only is the new characteristic constructed, but also the learning result of the click rate model is effectively utilized, the result is transmitted to the conversion rate model, and the generalization capability of the model is improved.
In a preferred embodiment, the click rate prediction model is a LightGBM model capable of achieving distributed gradient promotion based on a Histogram decision tree algorithm.
The conversion rate prediction model is a deep FM model which combines DNN and FM advantages and learns low-order and high-order combination characteristics.
In a preferred embodiment, referring to fig. 5, in the click rate determination unit 210, the trained click rate prediction model is trained as follows:
acquiring historical user log data in a first preset time period, such as 30 to 60 days recently, determining user attribute characteristics with corresponding relations, commodity attribute characteristics interested by the user and operation data set user behavior data of the commodity performed by the user based on the historical user log data in the time period, marking whether the user clicks the detail of entering the commodity to form a clicked label, combining the labels to generate a first training set, and training a pre-constructed click rate prediction model, such as a LightGBM model, by using the first training set to obtain the trained click rate prediction model.
In a preferred embodiment, as can be seen in connection with fig. 5 and 6, in the conversion determining unit 220, the trained conversion prediction model is trained as follows:
according to fig. 5, a third data set is generated based on the user log data such as the last 30 days in the second preset period, and data items such as user attribute features, commodity attribute features and behavior data may also be included in the third data set, and then the third data set is input into the trained click rate prediction model to obtain a predicted second click rate.
And then, with reference to fig. 6, based on the user log data such as user attribute features, commodity attribute features, behavior data and other data items in the second preset time period, a second training set is generated by splicing and combining the converted labels and the second click rate, and the second training set is utilized to train the pre-constructed conversion rate prediction model, so that a trained conversion rate prediction model is obtained.
In one embodiment, the merchandise recommendation unit 230 is specifically adapted to:
calculating the product of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the product, and recommending one or more commodities to the target user; or,
and calculating an average value of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the average value, and recommending one or more commodities to the target user.
Of course, the recommendation may be made to the target user by weighting or by using a certain independent score according to the actual situation.
In some specific embodiments, the click rate determination unit 210 is specifically adapted to:
determining target user attribute characteristics, recall commodity attribute characteristics and behavior data aiming at recall commodities with corresponding relations based on the target user log data, and combining to form the first data set according to whether a user clicks a label for determining whether to click;
wherein the target user attribute feature comprises at least one of: user attribution, age, gender, registration time, asset size, total browsing duration, total browsing times, purchase times, or total expense; the recalled commodity refers to a commodity which is browsed, clicked, collected, added into a shopping cart or purchased by a target user, and the attribute characteristics of the recalled commodity comprise at least one of the following: brand, model, type, origin, or location; the behavioral characteristics for the recall commodity include at least one of: browse, click, collect, join shopping carts, forward, consult, or purchase.
Further, according to the requirements of training, the following can be determined: the target user is a user triggering a recall commodity purchase recommendation request; the recalled commodities are commodities in a state of being purchased by the target user so as to control the quantity of the recalled commodities; the behavior data for the recalled commodity is behavior data of a historical user for the recalled commodity within, for example, approximately 30-60 days. Under the situation, a model for achieving the aim of predicting the click rate with higher accuracy is easier to obtain.
It should be noted that, the specific implementation manner of each embodiment of the apparatus may be performed with reference to the specific implementation manner of the corresponding embodiment of the method, which is not described herein.
In summary, according to the technical scheme of the invention, first, target user log data is acquired, a first data set is generated based on the target user log data, and the first data set is input into the trained click rate prediction model to obtain a predicted first click rate; then generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate; and finally, recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate. According to the technical scheme, according to the thought of multi-objective learning, the double indexes of click rate and conversion rate are considered, so that the recommended conversion rate is obviously improved; according to the multi-model fusion method, the predicted value of the click rate is used as a characteristic to be input into a conversion rate model, so that on one hand, new effective characteristics are built, on the other hand, the result experience learned by the click rate model can be effectively utilized, and the result experience can be transmitted into the conversion rate model, and the generalization capability of the model is improved.
It should be noted that:
the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with the teachings herein. The required structure for the construction of such devices 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.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in a merchandising recommendation device according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
For example, fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device 300 comprises a processor 310 and a memory 320 arranged to store computer executable instructions (computer readable program code). The memory 320 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 320 has a memory space 330 storing computer readable program code 331 for performing any of the method steps described above. For example, the memory space 330 for storing computer readable program code may include respective computer readable program code 331 for implementing the respective steps in the above method, respectively. The computer readable program code 331 can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium as described for example in fig. 4. Fig. 4 illustrates a schematic structure of a computer-readable storage medium according to an embodiment of the present invention. The computer readable storage medium 400 stores computer readable program code 331 for performing the steps of the method according to the invention, which may be read by the processor 310 of the electronic device 300, which computer readable program code 331, when executed by the electronic device 300, causes the electronic device 300 to perform the steps of the method described above, in particular the computer readable program code 331 stored by the computer readable storage medium may perform the method shown in any of the embodiments described above. The computer readable program code 331 may be compressed in a suitable form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.
Claims (8)
1. A method of recommending goods, the method comprising:
acquiring target user log data, generating a first data set based on the target user log data, and inputting the first data set into a trained click rate prediction model to obtain a predicted first click rate;
generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate;
recommending commodities to the target user according to the predicted first click rate and the predicted conversion rate;
the trained click rate prediction model is obtained through training in the following mode:
acquiring user log data in a first preset time period, determining user attribute characteristics, commodity attribute characteristics, user behavior data and labels whether to click or not according to the user log data, generating a first training set, and training a pre-constructed click rate prediction model by using the first training set so as to obtain the trained click rate prediction model;
the trained conversion rate prediction model is obtained through training in the following way:
generating a third data set based on user log data in a second preset time period, and inputting the third data set into the trained click rate prediction model to obtain a predicted second click rate;
generating a second training set based on the user log data, the converted label and the second click rate in the second preset time period, and training a pre-constructed conversion rate prediction model by using the second training set so as to obtain a trained conversion rate prediction model;
wherein the second preset time period is closer to a point of time when recommended than the first preset time period.
2. The method according to claim 1, wherein the click rate prediction model is a LightGBM model capable of realizing distributed gradient promotion based on a Histogram decision tree algorithm, and the conversion rate prediction model is a deep FM model for learning low-order and high-order combined features simultaneously by combining DNN and FM advantages.
3. The method of any of claims 1-2, wherein the recommending items to the target user based on the predicted first click through rate and the predicted conversion rate comprises:
calculating the product of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the product, and recommending one or more commodities to the target user; or,
and calculating an average value of the predicted first click rate and the predicted conversion rate, sorting the commodities according to the size of the average value, and recommending one or more commodities to the target user.
4. The method of any of claims 1-2, wherein the generating a first data set based on the target user log data comprises:
determining target user attribute characteristics, recall commodity attribute characteristics and behavior data aiming at recall commodities with corresponding relations based on the target user log data, and combining to form the first data set according to whether a user clicks a label for determining whether to click;
wherein the target user attribute feature comprises at least one of: user attribution, age, gender, registration time, asset size, total browsing duration, total browsing times, purchase times, or total expense;
the recalled commodity refers to a commodity which is browsed, clicked, collected, added into a shopping cart or purchased by a target user, and the attribute characteristics of the recalled commodity comprise at least one of the following: brand, model, type, origin, or location;
the behavioral characteristics for the recall commodity include at least one of: browse, click, collect, join shopping carts, forward, consult, or purchase.
5. The method of claim 4, wherein the target user is a user who triggered a recall item purchase recommendation request; the recalled commodities are commodities in a state of being purchased by the target user so as to control the quantity of the recalled commodities; the behavior data of the recalled commodity is behavior data of a historical user on the recalled commodity.
6. A merchandise recommendation apparatus, the apparatus comprising:
the click rate determining unit is used for obtaining target user log data, generating a first data set based on the target user log data, and inputting the first data set into the trained click rate prediction model to obtain predicted first click rate;
the conversion rate determining unit is used for generating a second data set based on the target user log data and the first click rate, and inputting the second data set into a trained conversion rate prediction model to obtain a predicted conversion rate;
a commodity recommending unit that recommends commodities to the target user according to the predicted first click rate and the predicted conversion rate;
in the click rate determination unit, the trained click rate prediction model is obtained through training in the following manner:
acquiring user log data in a first preset time period, determining user attribute characteristics, commodity attribute characteristics, user behavior data and labels whether to click or not according to the user log data, generating a first training set, and training a pre-constructed click rate prediction model by using the first training set so as to obtain the trained click rate prediction model;
in the conversion rate determination unit, the trained conversion rate prediction model is obtained through training in the following manner:
generating a third data set based on user log data in a second preset time period, and inputting the third data set into the trained click rate prediction model to obtain a predicted second click rate;
generating a second training set based on the user log data, the converted label and the second click rate in the second preset time period, and training a pre-constructed conversion rate prediction model by using the second training set so as to obtain a trained conversion rate prediction model;
wherein the second preset time period is closer to a point of time when recommended than the first preset time period.
7. An electronic device, wherein the electronic device comprises: a processor; and a memory arranged to store computer executable instructions which, when executed, cause the processor to perform the method of any of claims 1-5.
8. A computer readable storage medium storing one or more programs which, when executed by a processor, implement the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011446682.0A CN112508613B (en) | 2020-12-09 | 2020-12-09 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011446682.0A CN112508613B (en) | 2020-12-09 | 2020-12-09 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112508613A CN112508613A (en) | 2021-03-16 |
| CN112508613B true CN112508613B (en) | 2024-03-19 |
Family
ID=74971189
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011446682.0A Active CN112508613B (en) | 2020-12-09 | 2020-12-09 | Commodity recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112508613B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065066B (en) * | 2021-03-31 | 2024-05-07 | 北京达佳互联信息技术有限公司 | Prediction method, prediction device, server and storage medium |
| CN113379449B (en) * | 2021-05-31 | 2022-10-04 | 北京达佳互联信息技术有限公司 | Multimedia resource recall method and device, electronic equipment and storage medium |
| CN113689234B (en) * | 2021-08-04 | 2024-03-15 | 华东师范大学 | Platform-related advertisement click rate prediction method based on deep learning |
| CN113610580B (en) * | 2021-08-10 | 2023-09-19 | 平安科技（深圳）有限公司 | Product recommendation method and device, electronic equipment and readable storage medium |
| CN113516522B (en) * | 2021-09-14 | 2022-03-04 | 腾讯科技（深圳）有限公司 | Media resource recommendation method, and training method and device of multi-target fusion model |
| CN114139724A (en) * | 2021-11-30 | 2022-03-04 | 支付宝(杭州)信息技术有限公司 | Method and device for training gain model |
| CN114430504B (en) * | 2022-01-28 | 2023-03-10 | 腾讯科技（深圳）有限公司 | Recommendation method and related device for media content |
| CN115860870A (en) * | 2022-12-16 | 2023-03-28 | 深圳市云积分科技有限公司 | Commodity recommendation method, system and device and readable medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN109684554A (en) * | 2018-12-26 | 2019-04-26 | 腾讯科技（深圳）有限公司 | The determination method and news push method of the potential user of news |
| CN109992710A (en) * | 2019-02-13 | 2019-07-09 | 网易传媒科技（北京）有限公司 | Clicking rate predictor method, system, medium and calculating equipment |
| CN110008399A (en) * | 2019-01-30 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| CN110046952A (en) * | 2019-01-30 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| WO2019169977A1 (en) * | 2018-03-07 | 2019-09-12 | 阿里巴巴集团控股有限公司 | Information conversion rate prediction method and apparatus, and information recommendation method and apparatus |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
| CN110413877A (en) * | 2019-07-02 | 2019-11-05 | 阿里巴巴集团控股有限公司 | A kind of resource recommendation method, device and electronic equipment |
| CN110490637A (en) * | 2019-07-15 | 2019-11-22 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of commodity group |
| CN110851713A (en) * | 2019-11-06 | 2020-02-28 | 腾讯科技（北京）有限公司 | Information processing method, recommendation method and related equipment |
| CN110910201A (en) * | 2019-10-18 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Information recommendation control method and device, computer equipment and storage medium |
| CN111027895A (en) * | 2019-05-16 | 2020-04-17 | 珠海随变科技有限公司 | Stock prediction and behavior data collection method, apparatus, device and medium for commodity |
| CN111080413A (en) * | 2019-12-20 | 2020-04-28 | 深圳市华宇讯科技有限公司 | E-commerce platform commodity recommendation method and device, server and storage medium |
| CN111523044A (en) * | 2020-07-06 | 2020-08-11 | 南京梦饷网络科技有限公司 | Method, computing device, and computer storage medium for recommending target objects |
-
2020
- 2020-12-09 CN CN202011446682.0A patent/CN112508613B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| WO2019169977A1 (en) * | 2018-03-07 | 2019-09-12 | 阿里巴巴集团控股有限公司 | Information conversion rate prediction method and apparatus, and information recommendation method and apparatus |
| CN109684554A (en) * | 2018-12-26 | 2019-04-26 | 腾讯科技（深圳）有限公司 | The determination method and news push method of the potential user of news |
| CN110008399A (en) * | 2019-01-30 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| CN110046952A (en) * | 2019-01-30 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of training method and device, a kind of recommended method and device of recommended models |
| CN109992710A (en) * | 2019-02-13 | 2019-07-09 | 网易传媒科技（北京）有限公司 | Clicking rate predictor method, system, medium and calculating equipment |
| CN111027895A (en) * | 2019-05-16 | 2020-04-17 | 珠海随变科技有限公司 | Stock prediction and behavior data collection method, apparatus, device and medium for commodity |
| CN110298725A (en) * | 2019-05-24 | 2019-10-01 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of grouping of commodities |
| CN110413877A (en) * | 2019-07-02 | 2019-11-05 | 阿里巴巴集团控股有限公司 | A kind of resource recommendation method, device and electronic equipment |
| CN110490637A (en) * | 2019-07-15 | 2019-11-22 | 北京三快在线科技有限公司 | Recommended method, device, electronic equipment and the readable storage medium storing program for executing of commodity group |
| CN110910201A (en) * | 2019-10-18 | 2020-03-24 | 中国平安人寿保险股份有限公司 | Information recommendation control method and device, computer equipment and storage medium |
| CN110851713A (en) * | 2019-11-06 | 2020-02-28 | 腾讯科技（北京）有限公司 | Information processing method, recommendation method and related equipment |
| CN111080413A (en) * | 2019-12-20 | 2020-04-28 | 深圳市华宇讯科技有限公司 | E-commerce platform commodity recommendation method and device, server and storage medium |
| CN111523044A (en) * | 2020-07-06 | 2020-08-11 | 南京梦饷网络科技有限公司 | Method, computing device, and computer storage medium for recommending target objects |
Non-Patent Citations (4)
| Title |
|---|
| 于俊伟译.《数据科学导论 PYTHON语言 原书第3版》.机械工业出版社,2020,第152页. * |
| 基于LightGBM的广告商品平台推荐系统设计与应用;杨正成等;《科技创新与应用》;第12卷(第30期);全文 * |
| 基于序列特征的点击率预测模型;朱思涵;浦剑;;华东师范大学学报(自然科学版)(第04期);全文 * |
| 基于机器学习混合算法的APP广告转化率预测研究;赵杨;袁析妮;陈亚文;武立强;;数据分析与知识发现(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112508613A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112508613B (en) | Commodity recommendation method and device, electronic equipment and readable storage medium | |
| CN110956497B (en) | Method for predicting repeated purchasing behavior of user of electronic commerce platform | |
| CN106651546B (en) | Electronic commerce information recommendation method oriented to smart community | |
| CN112182412B (en) | Method, computing device, and computer storage medium for recommending physical examination items | |
| Lin | Analysis of service satisfaction in web auction logistics service using a combination of fruit fly optimization algorithm and general regression neural network | |
| Li et al. | Customs classification for cross-border e-commerce based on text-image adaptive convolutional neural network | |
| CN109299994B (en) | Recommendation method, device, equipment and readable storage medium | |
| CN107016026B (en) | User tag determination method, information push method, user tag determination device, information push device | |
| CN104268292B (en) | The label Word library updating method of portrait system | |
| CN111784455A (en) | Article recommendation method and recommendation equipment | |
| CN109064285B (en) | Commodity recommendation sequence and commodity recommendation method | |
| CN113256367B (en) | Commodity recommendation method, system, equipment and medium for user behavior history data | |
| CN108921602B (en) | User purchasing behavior prediction method based on integrated neural network | |
| CN110175895B (en) | Article recommendation method and device | |
| CN111461841A (en) | Article recommendation method, device, server and storage medium | |
| JP2020047156A (en) | Commodity recommendation device and program | |
| CN113268656A (en) | User recommendation method and device, electronic equipment and computer storage medium | |
| CN111429161B (en) | Feature extraction method, feature extraction device, storage medium and electronic equipment | |
| CN112150227A (en) | Commodity recommendation method, system, device and medium | |
| Kim et al. | Deep user segment interest network modeling for click-through rate prediction of online advertising | |
| CN113761347A (en) | Commodity recommendation method, commodity recommendation device, storage medium and commodity recommendation system | |
| CN112380449A (en) | Information recommendation method, model training method and related device | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| Zhang et al. | Application of sample balance-based multi-perspective feature ensemble learning for prediction of user purchasing behaviors on mobile wireless network platforms | |
| Parlar et al. | IWD based feature selection algorithm for sentiment analysis |
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 |