CN111798273A - Training method of purchase probability prediction model of product and purchase probability prediction method - Google Patents
Training method of purchase probability prediction model of product and purchase probability prediction method Download PDFInfo
- Publication number
- CN111798273A CN111798273A CN202010620474.1A CN202010620474A CN111798273A CN 111798273 A CN111798273 A CN 111798273A CN 202010620474 A CN202010620474 A CN 202010620474A CN 111798273 A CN111798273 A CN 111798273A
- Authority
- CN
- China
- Prior art keywords
- information
- product
- user
- purchase
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 175
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000006399 behavior Effects 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000007477 logistic regression Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000005034 decoration Methods 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
- 238000011022 operating instruction Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
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
- G06N20/00—Machine learning
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a training method of a purchase probability prediction model of a product and a purchase probability prediction method. The method comprises the following steps: acquiring user information of a training sample user, all historical purchase information, target purchase information in a preset time period and product information of a product corresponding to the historical purchase information; determining first associated characteristic information based on the historical purchase information and the target purchase information; determining second associated characteristic information based on the user information and the product information; determining a training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, and performing model training according to the training sample set to obtain a purchase probability prediction model. The accuracy of the purchase probability prediction through the trained prediction model in the scheme is high, the product recommendation based on the predicted purchase probability has high recommendation accuracy, and the purchase demand of the user can be better met.
Description
Technical Field
The application relates to the field of data processing, in particular to a training method of a purchase probability prediction model of a product and a purchase probability prediction method.
Background
With the rapid development of the financial industry, various financial products are in endless, and in order to facilitate the purchase of the financial products by users, the financial products need to be recommended to the users.
In the prior art, when the financial products are recommended, the product recommendation accuracy is low, and the financial products recommended for the user may not meet the purchase demand of the user, so that the user experience is poor.
Disclosure of Invention
The present application aims to solve at least one of the above technical drawbacks. The technical scheme adopted by the application is as follows:
in a first aspect, an embodiment of the present application provides a method for training a purchase probability prediction model of a product, where the method includes:
acquiring user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information;
determining first associated characteristic information based on the historical purchase information and the target purchase information;
determining second associated characteristic information based on the user information and the product information;
determining a training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information;
and carrying out model training according to the training sample set to obtain a purchase probability prediction model.
Optionally, performing model training according to the training sample set to obtain a purchase probability prediction model, including:
determining purchasing behaviors of training sample users based on the target purchasing information, wherein the purchasing behaviors comprise purchasing products and browsing but not purchasing the products;
taking training samples corresponding to purchasing behaviors of purchased products in a training sample set as positive samples;
taking training samples corresponding to purchasing behaviors of browsed but not purchased products in the training sample set as negative samples;
and carrying out model training based on the positive samples and the negative samples to obtain a purchase probability prediction model.
Optionally, determining the first associated characteristic information based on the historical purchase information and the target purchase information includes:
determining a first product corresponding to the historical purchase information and a second product corresponding to the target purchase information;
and constructing first associated characteristic information based on the first product corresponding to the same training sample user and the second product corresponding to the same training sample user.
Optionally, the user information includes a user portrait label, the product information includes a product label, and determining associated feature information based on the user information and the product information includes:
constructing an associated label of the user portrait label and the product label based on the target purchase information;
and determining the similarity of the associated labels, and determining the associated labels with the similarity meeting the preset conditions and the corresponding similarity values as second associated characteristic information.
Optionally, determining the similarity of the associated tags includes:
constructing a feature vector of an associated label based on a word2vec model and a user portrait label and a product label;
and determining the similarity of the associated labels based on the vector distance of each feature vector.
In a second aspect, an embodiment of the present application provides a method for predicting a purchase probability of a product, where the method includes:
acquiring user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period and product information of a product to be recommended;
determining third associated characteristic information based on the historical purchase information and the target purchase information;
determining fourth associated feature information based on the user information and the product information;
determining a prediction sample set according to the user information, the target purchase information, the third associated characteristic information, the fourth associated characteristic information and the product information;
and inputting the prediction sample set into the purchase probability prediction model trained by the training method to obtain the purchase probability of the product to be recommended by the target user.
Optionally, the method further includes:
and determining a target recommended product based on the purchase probability, and providing the target recommended product to a corresponding target user.
In a third aspect, an embodiment of the present application provides a device for training a purchase probability prediction model of a product, where the device includes:
the basic information acquisition module is used for acquiring user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information;
the first associated information determining module is used for determining first associated characteristic information based on the historical purchasing information and the target purchasing information;
the second associated information determining module is used for determining second associated characteristic information based on the user information and the product information;
the training sample set constructing module is used for determining a training sample set according to the user information, the target purchasing information, the first associated characteristic information, the second associated characteristic information and the product information;
and the model training module is used for carrying out model training according to the training sample set to obtain a purchase probability prediction model.
Optionally, the model training module is specifically configured to:
determining purchasing behaviors of training sample users based on the target purchasing information, wherein the purchasing behaviors comprise purchasing products and browsing but not purchasing the products;
taking training samples corresponding to purchasing behaviors of purchased products in a training sample set as positive samples;
taking training samples corresponding to purchasing behaviors of browsed but not purchased products in the training sample set as negative samples;
and carrying out model training based on the positive samples and the negative samples to obtain a purchase probability prediction model.
Optionally, the first associated information determining module is specifically configured to:
determining a first product corresponding to the historical purchase information and a second product corresponding to the target purchase information;
and constructing first associated characteristic information based on the first product corresponding to the same training sample user and the second product corresponding to the same training sample user.
Optionally, the user information includes a user portrait label, the product information includes a product label, and the second associated information determining module is specifically configured to:
constructing an associated label of the user portrait label and the product label based on the target purchase information;
and determining the similarity of the associated labels, and determining the associated labels with the similarity meeting the preset conditions and the corresponding similarity values as second associated characteristic information.
Optionally, when determining the similarity of the associated tag, the second associated information determining module is specifically configured to:
constructing a feature vector of an associated label based on a word2vec model and a user portrait label and a product label;
and determining the similarity of the associated labels based on the vector distance of each feature vector.
In a fourth aspect, an embodiment of the present application provides an apparatus for predicting a purchase probability of a product, where the apparatus includes:
the basic information acquisition module is used for acquiring user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period and product information of a product to be recommended;
the third association information determining module is used for determining third association characteristic information based on the historical purchase information and the target purchase information;
the fourth associated information determining module is used for determining fourth associated characteristic information based on the user information and the product information;
the prediction sample set construction module is used for determining a prediction sample set according to the user information, the target purchase information, the third associated characteristic information, the fourth associated characteristic information and the product information;
and the prediction module is used for inputting the prediction sample set into the purchase probability prediction model trained by the training method to obtain the purchase probability of the product to be recommended by the target user.
Optionally, the apparatus further comprises:
and the product recommending module is used for determining a target recommended product based on the purchase probability and providing the target recommended product for a corresponding target user.
In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory;
a memory for storing operating instructions;
a processor configured to perform the method as shown in any implementation of the first aspect or any implementation of the second aspect of the present application by calling an operation instruction.
In a sixth aspect, embodiments of the present application provide a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the method shown in any of the embodiments of the first aspect or any of the embodiments of the second aspect of the present application.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
in the scheme provided by the embodiment of the application, the user information of the training sample user, the historical purchase information of all the training sample users, the target purchase information of the training sample user in a preset time period and the product information of the product corresponding to the historical purchase information are obtained, the first associated characteristic information is determined based on the historical purchase information and the target purchase information, the second associated characteristic information is determined based on the user information and the product information, so that a training sample set is determined according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, and the purchase probability prediction model is obtained by performing model training according to the training sample set, the method has high accuracy, so that the accuracy of product recommendation is high when the financial products are recommended based on the prediction result, the purchase requirements of the user can be better met, and the use experience of the user is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic flowchart of a method for training a purchase probability prediction model of a product according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a method for predicting a purchase probability of a product according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a training apparatus for a product purchase probability prediction model according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a device for predicting a purchase probability of a product according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for training a product purchase probability prediction model according to an embodiment of the present application, where as shown in fig. 1, the method mainly includes:
step S110: acquiring user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information;
step S120: determining first associated characteristic information based on the historical purchase information and the target purchase information;
step S130: determining second associated characteristic information based on the user information and the product information;
step S140: determining a training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information;
step S150: and carrying out model training according to the training sample set to obtain a purchase probability prediction model.
In this embodiment of the application, the preset time period may be a time period before and immediately adjacent to the model training, for example, the preset time period may be a time period from a certain preset time to a certain time before the model training. The target purchase information of the training sample user in the preset time period can be understood as the recent purchase information of the training sample user.
In the embodiment of the present application, the purchase information may include information about a financial product purchased by the user, a time and a location of purchasing the financial product, and the like. First associated characteristic information may be constructed based on the historical purchase information and the target purchase information.
In the embodiment of the application, the user information may include basic information of the user and description information such as a user portrait label, and the product information may include related information of the user and description information such as a product label.
In the embodiment of the application, a training sample set can be determined according to user information, target purchase information, first associated feature information, second associated feature information and product information, model training is performed according to the training sample set, and a purchase probability prediction model is obtained.
The training method provided by the embodiment of the application comprises the steps of obtaining user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information, determining first associated characteristic information based on the historical purchase information and the target purchase information, determining second associated characteristic information based on the user information and the product information, determining a training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, performing model training according to the training sample set, and obtaining a purchase probability prediction model, wherein in the scheme, due to the fact that the purchase probability prediction model is trained by combining a plurality of elements, the purchase probability prediction model of the product is predicted by the trained purchase probability prediction model, the method has high accuracy, so that the accuracy of product recommendation is high when the financial products are recommended based on the prediction result, the purchase requirements of the user can be better met, and the use experience of the user is improved.
When model training for purchasing probability prediction is performed according to training sample data, feature preprocessing needs to be performed on the training sample set.
The sample feature data into which the training sample data is converted may include both discrete feature types as well as continuous feature types. And for sample feature data with too sparse discrete features, dimension reduction processing can be performed. For example, for sample feature data with 8-10 feature values for 10 samples, the specific dimension reduction processing method is as follows: setting the preset proportion of the discrete features in the sample as P%, and performing embedding dimensionality reduction when the proportion of the discrete features in the sample is greater than P%. For continuous sample feature data, whether abnormal values exist in the sample feature data or not can be analyzed, that is, a few continuous values are deviated from the sample feature data overall distribution (for example, sample feature data with too large or too small individual values), the sample is compressed to a sample data range or the sample is abandoned, and then continuous feature binning is performed by adopting an equidistant binning mode, an equal frequency binning mode, a clustering binning mode or a tree model binning mode.
In an optional mode of the embodiment of the present application, performing model training according to a training sample set to obtain a purchase probability prediction model includes:
determining purchasing behaviors of training sample users based on the target purchasing information, wherein the purchasing behaviors comprise purchasing products and browsing but not purchasing the products;
taking training samples corresponding to purchasing behaviors of purchased products in a training sample set as positive samples;
taking training samples corresponding to purchasing behaviors of browsed but not purchased products in the training sample set as negative samples;
and carrying out model training based on the positive samples and the negative samples to obtain a purchase probability prediction model.
In the embodiment of the application, when model training is performed, since the purchase probability is predicted, a training sample corresponding to a purchase behavior of clicking to check a product and purchasing the product can be used as a positive sample, a training sample corresponding to a purchase behavior of clicking to check the product but not purchasing the product can be used as a negative sample, and model training is performed based on the positive sample and the negative sample to obtain a purchase probability prediction model.
In an optional manner of the embodiment of the application, determining the first associated feature information based on the historical purchase information and the target purchase information includes:
determining a first product corresponding to the historical purchase information and a second product corresponding to the target purchase information;
and constructing first associated characteristic information based on the first product corresponding to the same training sample user and the second product corresponding to the same training sample user.
In the embodiment of the application, the first product is all the products purchased by the training sample user in all the purchase records. The second product is the product that the training sample user purchased in the recent purchase record. The first associated feature information may be constructed according to a first product corresponding to the same training sample user and a second product corresponding to the same training sample user.
As an example, the target purchase information for a training sample user may be as shown in Table 1.
TABLE 1
| UserId (user id) | Products (Products) |
| 0 | a |
| 1 | b |
| 2 | a |
The target purchase information for the training sample user may be as shown in table 2:
TABLE 2
| UserId (user id) | Products (Products) |
| 0 | h、i、j |
| 1 | k、l |
| 2 | h、w |
The constructed first associated feature information may be as shown in table 3:
TABLE 3
In an optional mode of the embodiment of the application, the user information includes a user portrait label, the product information includes a product label, and the second associated feature information is determined based on the user information and the product information, including:
constructing an associated label of the user portrait label and the product label based on the target purchase information;
and determining the similarity of the associated labels, and determining the associated labels with the similarity meeting the preset conditions and the corresponding similarity values as second associated characteristic information.
In the embodiment of the application, the user information can be a user portrait label, the product information can be a product label, the user portrait label is description information of the user, the product label is description information of the product, the user portrait label corresponding to the user of each purchase record and the product label corresponding to the product are associated, and a constructed associated label can be obtained.
In the embodiment of the application, the similarity between the associated tags may be determined, and the associated tag and the corresponding similarity value of the preset condition that the similarity satisfies are determined as the second associated feature information.
In an optional manner of the embodiment of the present application, determining similarity of associated tags includes:
constructing a feature vector of an associated label based on a word2vec model and a user portrait label and a product label;
and determining the similarity of the associated labels based on the vector distance of each feature vector.
In the embodiment of the application, the feature vectors of the associated labels can be constructed based on a word2vec model, and the similarity between the associated labels is determined by calculating the vector distance between the feature vectors. The associated label with the similarity higher than the first preset value and the corresponding similarity value can be stored in a database, and the similarity value can be used as the weight of the associated label.
In the embodiment of the application, during model training, the associated label with the weight value higher than the second preset value and the weight of the associated label can be extracted from the database as second associated feature information. The second preset value is greater than the first preset value.
In the embodiment of the application, machine learning models such as a gradient boosting iterative decision tree + logistic regression (GBDT + LR), Logistic Regression (LR) or wide-deep can be selected for training to obtain the prediction model.
In the embodiment of the application, the purchase probability prediction model is constructed through machine learning by combining information such as user portrait, user behaviors and product basic characteristics, so that the obtained purchase probability prediction model has higher accuracy in purchase probability prediction.
Fig. 2 is a flowchart illustrating a method for predicting a purchase probability of a product according to an embodiment of the present application, where as shown in fig. 2, the method mainly includes:
step S210: acquiring user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period and product information of a product to be recommended;
step S220: determining third associated characteristic information based on the historical purchase information and the target purchase information;
step S230: determining fourth associated feature information based on the user information and the product information;
step S240: determining a prediction sample set according to the user information, the target purchase information, the third associated characteristic information, the fourth associated characteristic information and the product information;
step S250: and inputting the prediction sample set into a purchase probability prediction model trained by the training method to obtain the purchase probability of the product to be recommended by the target user.
In the embodiment of the application, the third associated feature information may be determined based on the historical purchase information of the target user and the target purchase information. And determining fourth associated characteristic information based on the user information and the product information of the target user.
Specifically, when the third associated feature information is determined, a third product corresponding to all the historical purchase information of the target user and a fourth product corresponding to the target purchase information of the target user within a preset time period may be determined. And then the person constructs third associated characteristic information based on a third product corresponding to the same target sample user and a fourth product corresponding to the same target sample user.
Specifically, in determining the fourth associated feature information, the associated tag may be constructed based on the user portrait tag of the target user and the product tag of the product to be recommended. And determining the similarity of the associated labels, and determining the associated labels with the similarity meeting the preset conditions and the corresponding similarity values as fourth associated characteristic information.
In the embodiment of the application, a prediction sample set can be determined according to the user information, the product information, the third associated feature information and the fourth associated feature information, and the prediction sample set is input into the purchase probability prediction model, so that the purchase probability of the product to be recommended by the target user is obtained.
According to the method provided by the embodiment of the application, the user information of the target user, all historical purchase information of the target user, the target purchase information of the target user in a preset time period and the product information of a product to be recommended are obtained, the third associated characteristic information is determined based on the historical purchase information and the target purchase information, the fourth associated characteristic information is determined based on the user information and the product information, the prediction sample set is determined according to the user information, the target purchase information, the third associated characteristic information, the fourth associated characteristic information and the product information, the prediction sample set is input into the purchase probability prediction model, and therefore the purchase probability of the product to be recommended of the target user is obtained. In the scheme, the purchase probability prediction model is trained by combining multiple elements, so that the accuracy rate is higher when the purchase probability of the product is predicted by the user, the accuracy rate of product recommendation is high when the financial product is recommended based on the prediction result, the purchase demand of the user can be better met, and the use experience of the user is improved.
In an optional manner of the embodiment of the present application, the method further includes:
and determining a target recommended product based on the purchase probability, and providing the target recommended product to a corresponding target user.
According to the method and the device, the products to be recommended with higher purchase probability ranking can be ranked, the products to be recommended with higher purchase probability are selected as the target recommended products to be recommended to the user, and the click rate and the purchase rate of the products recommended to the user can be improved.
Based on the same principle as the method shown in fig. 1, fig. 3 shows a schematic structural diagram of a training device for a purchase probability prediction model of a product provided by an embodiment of the present application, and as shown in fig. 3, the training device 30 may include:
the basic information acquisition module 310 is configured to acquire user information of a training sample user, historical purchase information of all training sample users, target purchase information of the training sample user in a preset time period, and product information of a product corresponding to the historical purchase information;
a first associated information determining module 320, configured to determine first associated feature information based on the historical purchase information and the target purchase information;
a second associated information determining module 330, configured to determine second associated feature information based on the user information and the product information;
a training sample set constructing module 340, configured to determine a training sample set according to the user information, the target purchase information, the first associated feature information, the second associated feature information, and the product information;
and the model training module 350 is configured to perform model training according to the training sample set to obtain a purchase probability prediction model.
The training device provided by the embodiment of the application obtains the user information of the training sample user, the historical purchase information of all the training sample users, the target purchase information of the training sample user in a preset time period and the product information of the product corresponding to the historical purchase information, determines the first associated characteristic information based on the historical purchase information and the target purchase information, determines the second associated characteristic information based on the user information and the product information, determines the training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, performs model training according to the training sample set to obtain the purchase probability prediction model, in the scheme, because the purchase probability prediction model is trained by combining a plurality of elements, the purchase probability prediction model of the product by the user is predicted by the trained purchase probability prediction model, the method has high accuracy, so that the accuracy of product recommendation is high when the financial products are recommended based on the prediction result, the purchase requirements of the user can be better met, and the use experience of the user is improved.
Optionally, the model training module is specifically configured to:
determining purchasing behaviors of training sample users based on the target purchasing information, wherein the purchasing behaviors comprise purchasing products and browsing but not purchasing the products;
taking training samples corresponding to purchasing behaviors of purchased products in a training sample set as positive samples;
taking training samples corresponding to purchasing behaviors of browsed but not purchased products in the training sample set as negative samples;
and carrying out model training based on the positive samples and the negative samples to obtain a purchase probability prediction model.
Optionally, the first associated information determining module is specifically configured to:
determining a first product corresponding to the historical purchase information and a second product corresponding to the target purchase information;
and constructing first associated characteristic information based on the first product corresponding to the same training sample user and the second product corresponding to the same training sample user.
Optionally, the user information includes a user portrait label, the product information includes a product label, and the second associated information determining module is specifically configured to:
constructing an associated label of the user portrait label and the product label based on the target purchase information;
and determining the similarity of the associated labels, and determining the associated labels with the similarity meeting the preset conditions and the corresponding similarity values as second associated characteristic information.
Optionally, when determining the similarity of the associated tag, the second associated information determining module is specifically configured to:
constructing a feature vector of an associated label based on a word2vec model and a user portrait label and a product label;
and determining the similarity of the associated labels based on the vector distance of each feature vector.
It is understood that the above modules of the training device in the present embodiment have functions of implementing the corresponding steps of the training method in the embodiment shown in fig. 1. The function can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above. The modules can be software and/or hardware, and each module can be implemented independently or by integrating a plurality of modules. For the functional description of each module of the training apparatus, reference may be specifically made to the corresponding description of the training method in the embodiment shown in fig. 1, and details are not repeated here.
Based on the same principle as the method shown in fig. 2, fig. 4 shows a schematic structural diagram of a prediction apparatus for a purchase probability of a product according to an embodiment of the present application, and as shown in fig. 4, the prediction apparatus 40 may include:
a basic information obtaining module 410, configured to obtain user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period, and product information of a product to be recommended;
a third associated information determining module 420, configured to determine third associated feature information based on the historical purchase information and the target purchase information;
a fourth associated information determining module 430, configured to determine fourth associated feature information based on the user information and the product information;
the prediction sample set constructing module 440 is configured to determine a prediction sample set according to the user information, the target purchase information, the third associated feature information, the fourth associated feature information, and the product information;
the prediction module 450 is configured to input the prediction sample set into the purchase probability prediction model trained by the training method, so as to obtain the purchase probability of the product to be recommended by the target user.
According to the prediction device provided by the embodiment of the application, the user information of the target user, the all historical purchase information of the target user, the target purchase information of the target user in a preset time period and the product information of a product to be recommended are obtained, the third associated characteristic information is determined based on the historical purchase information and the target purchase information, the fourth associated characteristic information is determined based on the user information and the product information, the prediction sample set is determined according to the user information, the target purchase information, the third associated characteristic information, the fourth associated characteristic information and the product information, the prediction sample set is input into the purchase probability prediction model, and therefore the purchase probability of the product to be recommended of the target user is obtained. In the scheme, the purchase probability prediction model is trained by combining multiple elements, so that the accuracy rate is higher when the purchase probability of the product is predicted by the user, the accuracy rate of product recommendation is high when the financial product is recommended based on the prediction result, the purchase demand of the user can be better met, and the use experience of the user is improved.
Optionally, the apparatus further comprises:
and the product recommending module is used for determining a target recommended product based on the purchase probability and providing the target recommended product for a corresponding target user.
It is understood that the above modules of the prediction apparatus in the present embodiment have functions of implementing the corresponding steps of the prediction method in the embodiment shown in fig. 2. The function can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above. The modules can be software and/or hardware, and each module can be implemented independently or by integrating a plurality of modules. For the functional description of each module of the prediction apparatus, reference may be specifically made to the corresponding description of the prediction method in the embodiment shown in fig. 2, and details are not repeated here.
The embodiment of the application provides an electronic device, which comprises a processor and a memory;
a memory for storing operating instructions;
and the processor is used for executing the training or prediction method provided by any embodiment of the application by calling the operation instruction.
As an example, fig. 5 shows a schematic structural diagram of an electronic device to which an embodiment of the present application is applicable, and as shown in fig. 5, the electronic device 2000 includes: a processor 2001 and a memory 2003. Wherein the processor 2001 is coupled to a memory 2003, such as via a bus 2002. Optionally, the electronic device 2000 may also include a transceiver 2004. It should be noted that the transceiver 2004 is not limited to one in practical applications, and the structure of the electronic device 2000 is not limited to the embodiment of the present application.
The processor 2001 is applied to the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 2004 may include a receiver and a transmitter, and the transceiver 2004 is applied to the embodiments of the present application to implement the functions of the electronic device of the embodiments of the present application to communicate with other devices when executed.
The Processor 2001 may be a CPU (Central Processing Unit), general Processor, DSP (Digital Signal Processor), ASIC (Application specific integrated Circuit), FPGA (Field Programmable Gate Array) or other Programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 2001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs and microprocessors, and the like.
The Memory 2003 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically erasable programmable Read Only Memory), a CD-ROM (Compact disk Read Only Memory) or other optical disk storage, optical disk storage (including Compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
Optionally, the memory 2003 is used for storing application program code for performing the disclosed aspects, and is controlled in execution by the processor 2001. The processor 2001 is configured to execute application program code stored in the memory 2003 to implement the training or prediction method provided in any of the embodiments of the present application.
The electronic device provided by the embodiment of the application is applicable to any embodiment of the method, and is not described herein again.
Compared with the prior art, the embodiment of the application provides the electronic equipment, the user information of the training sample user, the historical purchase information of all the training sample users, the target purchase information of the training sample user in a preset time period and the product information of the product corresponding to the historical purchase information are obtained, the first associated characteristic information is determined based on the historical purchase information and the target purchase information, the second associated characteristic information is determined based on the user information and the product information, so that the training sample set is determined according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, the model training is carried out according to the training sample set, the purchase probability prediction model is obtained, in the scheme, because the purchase probability prediction model is trained by combining a plurality of elements, the purchase probability prediction model of the product is predicted by the trained purchase probability prediction model, the method has high accuracy, so that the accuracy of product recommendation is high when the financial products are recommended based on the prediction result, the purchase requirements of the user can be better met, and the use experience of the user is improved.
The present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the training or prediction method shown in the above method embodiments.
The computer-readable storage medium provided in the embodiments of the present application is applicable to any of the embodiments of the foregoing method, and is not described herein again.
Compared with the prior art, the embodiment of the application provides a computer-readable storage medium, by obtaining user information of a training sample user, historical purchase information of all training sample users, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information, determining first associated characteristic information based on the historical purchase information and the target purchase information, determining second associated characteristic information based on the user information and the product information, thereby determining a training sample set according to the user information, the target purchase information, the first associated characteristic information, the second associated characteristic information and the product information, performing model training according to the training sample set, and obtaining a purchase probability prediction model, in the scheme, since the purchase probability prediction model is trained by combining a plurality of elements, the purchase probability prediction model of the product by the user is predicted by the trained purchase probability prediction model, the method has high accuracy, so that the accuracy of product recommendation is high when the financial products are recommended based on the prediction result, the purchase requirements of the user can be better met, and the use experience of the user is improved.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (11)
1. A method for training a purchase probability prediction model of a product, comprising:
acquiring user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information;
determining first associated characteristic information based on the historical purchase information and the target purchase information;
determining second associated feature information based on the user information and the product information;
determining a training sample set according to the user information, the target purchasing information, the first associated characteristic information, the second associated characteristic information and the product information;
and carrying out model training according to the training sample set to obtain a purchase probability prediction model.
2. The method of claim 1, wherein the model training according to the training sample set to obtain a purchase probability prediction model comprises:
determining purchasing behavior of the training sample user based on the target purchasing information, the purchasing behavior including purchasing the product and browsing but not purchasing the product;
taking training samples corresponding to the purchasing behavior of the purchased product in the training sample set as positive samples;
taking training samples in the training sample set corresponding to the purchasing behavior of browsing but not purchasing the product as negative samples;
and carrying out model training based on the positive sample and the negative sample to obtain a purchase probability prediction model.
3. The method of claim 1, wherein determining first associated characteristic information based on the historical purchase information and the target purchase information comprises:
determining a first product corresponding to the historical purchase information and a second product corresponding to the target purchase information;
and constructing first associated characteristic information based on the first product corresponding to the same training sample user and the second product corresponding to the same training sample user.
4. The method of claim 1, wherein the user information comprises a user portrait label, wherein the product information comprises a product label, and wherein determining second associated characteristic information based on the user information and the product information comprises:
constructing an associated label of the user representation label and the product label based on the target purchase information;
and determining the similarity of the associated labels, and determining the associated labels with the similarity meeting preset conditions and the corresponding similarity values as second associated characteristic information.
5. The method of claim 4, wherein determining the similarity of the associated labels comprises:
constructing a feature vector of the associated label based on the word2vec model and the user portrait label and the product label;
and determining the similarity of the associated labels based on the vector distance of each feature vector.
6. A method for predicting a purchase probability of a product, comprising:
acquiring user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period and product information of a product to be recommended;
determining third associated feature information based on the historical purchase information and the target purchase information;
determining fourth associated feature information based on the user information and the product information;
determining a prediction sample set according to the user information, the target purchase information, the third associated feature information, the fourth associated feature information and the product information;
inputting the prediction sample set into a purchase probability prediction model trained by the training method of any one of claims 1-5 to obtain the purchase probability of the target user for the product to be recommended.
7. The method of claim 6, further comprising:
and determining a target recommended product based on the purchase probability, and providing the target recommended product to a corresponding target user.
8. An apparatus for training a purchase probability prediction model of a product, comprising:
the basic information acquisition module is used for acquiring user information of a training sample user, all historical purchase information of the training sample user, target purchase information of the training sample user in a preset time period and product information of a product corresponding to the historical purchase information;
a first associated information determining module, configured to determine first associated feature information based on the historical purchase information and the target purchase information;
a second associated information determination module for determining second associated feature information based on the user information and the product information;
a training sample set constructing module, configured to determine a training sample set according to the user information, the target purchase information, the first associated feature information, the second associated feature information, and the product information;
and the model training module is used for carrying out model training according to the training sample set to obtain a purchase probability prediction model.
9. An apparatus for predicting a purchase probability of a product, comprising:
the basic information acquisition module is used for acquiring user information of a target user, all historical purchase information of the target user, target purchase information of the target user in a preset time period and product information of a product to be recommended;
a third associated information determination module, configured to determine third associated feature information based on the historical purchase information and the target purchase information;
a fourth associated information determination module for determining fourth associated feature information based on the user information and the product information;
a prediction sample set constructing module, configured to determine a prediction sample set according to the user information, the target purchase information, the third associated feature information, the fourth associated feature information, and the product information;
a prediction module, configured to input the prediction sample set into a purchase probability prediction model trained by the training method according to any one of claims 1 to 5, and obtain a purchase probability of the target user for the product to be recommended.
10. An electronic device comprising a processor and a memory;
the memory is used for storing operation instructions;
the processor is used for executing the method of any one of claims 1-7 by calling the operation instruction.
11. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010620474.1A CN111798273A (en) | 2020-07-01 | 2020-07-01 | Training method of purchase probability prediction model of product and purchase probability prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010620474.1A CN111798273A (en) | 2020-07-01 | 2020-07-01 | Training method of purchase probability prediction model of product and purchase probability prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111798273A true CN111798273A (en) | 2020-10-20 |
Family
ID=72809840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010620474.1A Pending CN111798273A (en) | 2020-07-01 | 2020-07-01 | Training method of purchase probability prediction model of product and purchase probability prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111798273A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308669A (en) * | 2020-10-29 | 2021-02-02 | 深圳大学 | Commodity recommendation method and device, storage medium and terminal equipment |
| CN112308686A (en) * | 2020-11-26 | 2021-02-02 | 江苏科源网络技术有限公司 | Intelligent recommendation method |
| CN112598472A (en) * | 2020-12-25 | 2021-04-02 | 中国工商银行股份有限公司 | Product recommendation method, device, system, medium and program product |
| CN112651804A (en) * | 2020-12-28 | 2021-04-13 | 中国联合网络通信集团有限公司 | Contract machine recommendation method and system |
| CN112927040A (en) * | 2021-02-23 | 2021-06-08 | 四川享宇金信金融科技有限公司 | Intelligent recommendation method for financial service platform |
| CN113112326A (en) * | 2021-04-02 | 2021-07-13 | 北京沃东天骏信息技术有限公司 | User identification method, method for displaying data to user and related device |
| CN113129080A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Data processing method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113592551A (en) * | 2021-07-31 | 2021-11-02 | 广州小鹏汽车科技有限公司 | Method, device and equipment for analyzing and processing behavior data of vehicle purchasing user |
| CN113627728A (en) * | 2021-07-09 | 2021-11-09 | 国网冀北电力有限公司物资分公司 | Method and device for calculating product quantity |
| CN113763019A (en) * | 2021-01-28 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | User information management method and device |
| CN114022246A (en) * | 2021-11-05 | 2022-02-08 | 平安科技（深圳）有限公司 | Product information pushing method and device, terminal equipment and storage medium |
| CN115828107A (en) * | 2023-01-09 | 2023-03-21 | 深圳市云积分科技有限公司 | Model training method and device based on offline environment |
| CN115880076A (en) * | 2022-04-20 | 2023-03-31 | 北京中关村科金技术有限公司 | Trusted product recommendation method, device and storage medium |
| CN116205376A (en) * | 2023-04-27 | 2023-06-02 | 北京阿帕科蓝科技有限公司 | Behavior prediction method, training method and device of behavior prediction model |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025565A (en) * | 2016-01-29 | 2017-08-08 | 北京京东尚科信息技术有限公司 | A kind of method and system for improving e-commerce website conversion ratio |
| CN107563859A (en) * | 2017-08-31 | 2018-01-09 | 深圳前海弘稼科技有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN108154420A (en) * | 2017-12-26 | 2018-06-12 | 泰康保险集团股份有限公司 | Products Show method and device, storage medium, electronic equipment |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109242631A (en) * | 2018-09-17 | 2019-01-18 | 平安科技（深圳）有限公司 | Product intelligent recommended method, server and storage medium |
| CN110147502A (en) * | 2019-04-12 | 2019-08-20 | 平安科技（深圳）有限公司 | Products Show method, apparatus, medium and server based on big data analysis |
| US20190347708A1 (en) * | 2018-01-10 | 2019-11-14 | Beijing Sensetime Technology Development Co., Ltd | Methods and apparatuses for deep learning-based recommendation, electronic devices, and media |
-
2020
- 2020-07-01 CN CN202010620474.1A patent/CN111798273A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107025565A (en) * | 2016-01-29 | 2017-08-08 | 北京京东尚科信息技术有限公司 | A kind of method and system for improving e-commerce website conversion ratio |
| CN107563859A (en) * | 2017-08-31 | 2018-01-09 | 深圳前海弘稼科技有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN108154420A (en) * | 2017-12-26 | 2018-06-12 | 泰康保险集团股份有限公司 | Products Show method and device, storage medium, electronic equipment |
| US20190347708A1 (en) * | 2018-01-10 | 2019-11-14 | Beijing Sensetime Technology Development Co., Ltd | Methods and apparatuses for deep learning-based recommendation, electronic devices, and media |
| CN108337316A (en) * | 2018-02-08 | 2018-07-27 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109242631A (en) * | 2018-09-17 | 2019-01-18 | 平安科技（深圳）有限公司 | Product intelligent recommended method, server and storage medium |
| CN110147502A (en) * | 2019-04-12 | 2019-08-20 | 平安科技（深圳）有限公司 | Products Show method, apparatus, medium and server based on big data analysis |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308669A (en) * | 2020-10-29 | 2021-02-02 | 深圳大学 | Commodity recommendation method and device, storage medium and terminal equipment |
| CN112308669B (en) * | 2020-10-29 | 2023-10-31 | 深圳大学 | Commodity recommendation method and device, storage medium and terminal equipment |
| CN112308686A (en) * | 2020-11-26 | 2021-02-02 | 江苏科源网络技术有限公司 | Intelligent recommendation method |
| CN112598472A (en) * | 2020-12-25 | 2021-04-02 | 中国工商银行股份有限公司 | Product recommendation method, device, system, medium and program product |
| CN112598472B (en) * | 2020-12-25 | 2024-02-13 | 中国工商银行股份有限公司 | Product recommendation method, device, system, medium and program product |
| CN112651804A (en) * | 2020-12-28 | 2021-04-13 | 中国联合网络通信集团有限公司 | Contract machine recommendation method and system |
| CN112651804B (en) * | 2020-12-28 | 2023-07-07 | 中国联合网络通信集团有限公司 | Recommendation method and recommendation system of contract machine |
| CN113763019A (en) * | 2021-01-28 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | User information management method and device |
| CN112927040A (en) * | 2021-02-23 | 2021-06-08 | 四川享宇金信金融科技有限公司 | Intelligent recommendation method for financial service platform |
| CN113112326A (en) * | 2021-04-02 | 2021-07-13 | 北京沃东天骏信息技术有限公司 | User identification method, method for displaying data to user and related device |
| CN113129080A (en) * | 2021-05-13 | 2021-07-16 | 北京大米科技有限公司 | Data processing method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| CN113627728A (en) * | 2021-07-09 | 2021-11-09 | 国网冀北电力有限公司物资分公司 | Method and device for calculating product quantity |
| CN113627728B (en) * | 2021-07-09 | 2024-03-15 | 国网冀北电力有限公司物资分公司 | Method and device for calculating product quantity |
| CN113592551A (en) * | 2021-07-31 | 2021-11-02 | 广州小鹏汽车科技有限公司 | Method, device and equipment for analyzing and processing behavior data of vehicle purchasing user |
| CN114022246A (en) * | 2021-11-05 | 2022-02-08 | 平安科技（深圳）有限公司 | Product information pushing method and device, terminal equipment and storage medium |
| CN114022246B (en) * | 2021-11-05 | 2023-08-11 | 平安科技（深圳）有限公司 | Product information pushing method and device, terminal equipment and storage medium |
| CN115880076A (en) * | 2022-04-20 | 2023-03-31 | 北京中关村科金技术有限公司 | Trusted product recommendation method, device and storage medium |
| CN115828107A (en) * | 2023-01-09 | 2023-03-21 | 深圳市云积分科技有限公司 | Model training method and device based on offline environment |
| CN116205376A (en) * | 2023-04-27 | 2023-06-02 | 北京阿帕科蓝科技有限公司 | Behavior prediction method, training method and device of behavior prediction model |
| CN116205376B (en) * | 2023-04-27 | 2023-10-17 | 北京阿帕科蓝科技有限公司 | Behavior prediction method, training method and device of behavior prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111798273A (en) | Training method of purchase probability prediction model of product and purchase probability prediction method | |
| CN110866181B (en) | Resource recommendation method, device and storage medium | |
| CN111523976B (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| CN108510402A (en) | Insurance kind information recommendation method, device, computer equipment and storage medium | |
| CN110008397B (en) | Recommendation model training method and device | |
| CN113255370B (en) | Industry type recommendation method, device, equipment and medium based on semantic similarity | |
| CN114119058B (en) | User portrait model construction method, device and storage medium | |
| CN112613938B (en) | Model training method and device and computer equipment | |
| CN111275205B (en) | Virtual sample generation method, terminal equipment and storage medium | |
| CN113220657B (en) | Data processing method and device and computer equipment | |
| CN110147502B (en) | Product recommendation method, device, medium and server based on big data analysis | |
| CN108205580A (en) | A kind of image search method, device and computer readable storage medium | |
| CN114443958A (en) | Recommendation method, recommendation system and recommendation system training method | |
| CN113592605A (en) | Product recommendation method, device, equipment and storage medium based on similar products | |
| CN110851708B (en) | Negative sample extraction method, device, computer equipment and storage medium | |
| CN111161009B (en) | Information pushing method, device, computer equipment and storage medium | |
| CN110837596B (en) | Intelligent recommendation method and device, computer equipment and storage medium | |
| CN115705383A (en) | Sequence recommendation algorithm, system, terminal and medium based on graph neural network time sequence feature extraction | |
| CN111598638A (en) | Click rate determination method, device and equipment | |
| CN111429232A (en) | Product recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN109886299B (en) | User portrait method and device, readable storage medium and terminal equipment | |
| CN113837846B (en) | Commodity recommendation method, commodity recommendation device, computer equipment and storage medium | |
| CN112488863B (en) | Dangerous seed recommendation method and related equipment in user cold start scene | |
| CN113420214B (en) | Electronic transaction object recommendation method, device and equipment | |
| CN112651804B (en) | Recommendation method and recommendation system of contract machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220919 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |