WO2021189976A1 - 一种产品信息推送方法、装置、设备及存储介质 - Google Patents
一种产品信息推送方法、装置、设备及存储介质 Download PDFInfo
- Publication number
- WO2021189976A1 WO2021189976A1 PCT/CN2020/136326 CN2020136326W WO2021189976A1 WO 2021189976 A1 WO2021189976 A1 WO 2021189976A1 CN 2020136326 W CN2020136326 W CN 2020136326W WO 2021189976 A1 WO2021189976 A1 WO 2021189976A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vector
- product
- feature
- fusion
- sub
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Definitions
- This application relates to the field of data analysis, and in particular to a method, device, equipment and storage medium for pushing product information.
- the traditional product recommendation system judges the product that the user will buy next by analyzing the user's product historical purchase and consulting situation by the salesperson.
- manual product recommendation methods a large amount of labor is required, which increases labor costs and at the same time brings a poor user experience. Due to the large number of users, manual recommendation methods can no longer meet the needs of current users, and intelligent product automatic recommendation solutions have also emerged.
- This application provides a method for pushing product information, and the method includes:
- product information of at least one product to be recommended is sent to the target user terminal.
- This application also provides a product information push device, the device includes:
- a data acquisition module for acquiring user characteristic information from a target user terminal, the user characteristic information including numerical characteristics and sub-type characteristics;
- a data processing module configured to perform data preprocessing on the numerical feature and the sub-category feature to construct a fusion vector
- the vector processing module is used to process the fusion vector based on the deep neural network sub-model in the product recommendation model to obtain a deep feature vector, and perform processing on the fusion vector based on the cross neural network sub-model in the product recommendation model Processing to get the cross feature vector;
- the score prediction module is configured to construct a fusion feature vector according to the depth feature vector and the cross feature vector, and predict the respective recommendation scores of several products to be recommended according to the fusion feature vector;
- the product recommendation module is configured to send the product information of at least one product to be recommended to the target user terminal according to the respective recommendation scores of the products to be recommended.
- the application also provides a computer device, the computer device includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and realizes when the computer program is executed The following steps:
- product information of at least one product to be recommended is sent to the target user terminal.
- the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the following steps:
- product information of at least one product to be recommended is sent to the target user terminal.
- FIG. 1 is a schematic flowchart of a method for pushing product information according to an embodiment of the present application
- Figure 2 is a schematic diagram of a scenario of a product information push method applied to a server
- FIG. 3 is a schematic diagram of a sub-process of performing data preprocessing on the numerical feature and the sub-type feature in FIG. 1 to construct a fusion vector;
- FIG. 4 is a schematic block diagram of the structure of a product recommendation model provided by an embodiment of the present application.
- FIG. 5 is a schematic flowchart of a product recommendation model training process provided by an embodiment of the present application.
- FIG. 6 is a schematic block diagram of a product information pushing device provided by an embodiment of the present application.
- FIG. 7 is a schematic block diagram of another product information pushing device provided by an embodiment of the present application.
- FIG. 8 is a schematic block diagram of the structure of a computer device according to an embodiment of the present application.
- the embodiments of the present application provide a method, device, computer equipment, and storage medium for pushing product information.
- the product information push method can be applied to a server, and is used for processes such as pushing suitable product information for the user according to the user characteristic information of the user, so as to improve the accuracy of product recommendation.
- the product information push method is used for the server; the server can be an independent server or a server cluster.
- the following embodiments will introduce in detail the product information push method applied to the server.
- FIG. 1 is a schematic flowchart of a method for pushing product information according to an embodiment of the present application.
- Figure 2 is a schematic diagram of a scenario of a product information push method applied to a server.
- the product information push method specifically includes: Step S101 to Step S105.
- Step S101 Obtain user characteristic information from a target user terminal, where the user characteristic information includes numerical characteristics and sub-type characteristics.
- the user characteristic information may include the user's vehicle information.
- the user can input vehicle information on the terminal he uses, and then the terminal sends the vehicle information to the server.
- the vehicle information input interface can be displayed on the terminal; the user can input vehicle information on the input interface, and then the terminal sends the vehicle information to the server.
- the vehicle information may include purchase price, number of seats, exhaust steam volume, agency code, broker code, agent code, car dealer code, vehicle family, brand, nature, vehicle type, new energy vehicle logo , Gender of the owner of the driving license, etc.
- the purchase price, the number of seats, and the amount of exhaust steam are quantitative values, so vehicle information such as the purchase price, number of seats, and amount of exhaust steam can be determined as numerical features.
- Step S102 Perform data preprocessing on the numerical feature and the sub-category feature to construct a fusion vector.
- the data preprocessing of the numerical feature and the sub-category feature to construct a fusion vector specifically includes: step S1021 to step S1023.
- Step S1021 Perform standardization processing on the numerical feature to obtain numerical data corresponding to the numerical feature.
- the numerical features are normalized by a max-min normalization method.
- Max-min normalization is also called dispersion standardization, which is a linear transformation of the original data, so that the result value is mapped to [0, 1].
- the purchase price of a preset vehicle is 1.1 million RMB and the minimum value is 100,000 RMB
- the purchase price in the vehicle information obtained from the target user terminal is 300,000 RMB
- the numerical data obtained is 0.2.
- the numerical characteristics are standardized so that the numerical data corresponding to the numerical characteristics satisfy a normal distribution.
- the purchase price, the number of seats, and the exhaust steam volume in the vehicle information are standardized, and the corresponding numerical data obtained are D1, D2, and D3, respectively.
- Step S1022 Perform vectorization processing on the sub-type feature to obtain a sub-type vector corresponding to the sub-type feature.
- the server pre-stores a mapping table of the sub-type characteristics and the sub-type vectors, and the sub-type vectors corresponding to the sub-type characteristics can be obtained by looking up the table.
- the sub-type feature is vectorized based on the vector embedding layer in the product recommendation model to obtain the sub-type vector corresponding to the sub-type feature.
- the vector embedding layer learns the correspondence between the sub-type features and the sub-type vectors in the training samples, so that the corresponding sub-type vectors can be determined according to the sub-type features.
- the agency code, broker code, agent code, car dealer code, and car series in the vehicle information are respectively vectorized, and the sub-type vectors E1, E2, E3, E4, and E5 are obtained accordingly.
- Step S1023 Construct a fusion vector according to the numerical data and the classification vector.
- the numerical data and the sub-type vector are spliced end to end as the input vector of the product recommendation model.
- the fusion vector is represented as D1, D2, D3, E1, E2, E3, E4, E5.
- the fusion vector constructed according to the numerical data and the sub-type vector because the user's numerical characteristics and relevant information of the sub-type characteristics are retained at the same time, such as purchase price, number of seats, exhaust steam volume, agency code, broker code , Agent code, car dealer code, car family, brand, nature, vehicle type, new energy vehicle logo, driving license owner’s gender, etc., can better integrate more types of user attributes to participate in decision-making, so as to obtain more Accurate portraits of user interests. Recommending products for users based on user interest portraits can improve the accuracy of product recommendations.
- the method before constructing a fusion vector based on the numerical data and the sub-type vector, the method further includes the following steps:
- the product category information is obtained from the target user terminal, and the product category information is vectorized to obtain the product category vector corresponding to the product category information.
- the user also enters the category of the product that needs to be recommended in the target user terminal, so that the server can obtain product category information according to the user's input, such as auto insurance, which can be life insurance, auto insurance, etc.
- auto insurance which can be life insurance, auto insurance, etc.
- the performing vectorization processing on the product category information to obtain the product category vector corresponding to the product category information specifically includes the following steps: obtaining the difference between the preset product category information and the product category vector Mapping relationship data; performing vectorization processing on the product category information according to the mapping relationship data to obtain a product category vector corresponding to the product category information.
- the server pre-stores a mapping table of product category information and product category vectors, and the product category vector corresponding to the product category information can be obtained by looking up the table.
- the performing vectorization processing on the product category information to obtain the product category vector corresponding to the product category information specifically includes the following steps: performing vectorization processing on the product based on the vector embedding layer in the product recommendation model
- the category information is vectorized to obtain the corresponding product category vector.
- the vector embedding layer learns the corresponding relationship between the product category information and the product category vector in the training sample, so that the corresponding product category vector can be determined according to the product category information.
- the constructing a fusion vector according to the numerical data and the classification vector specifically includes the following steps:
- a fusion vector is constructed.
- the product category information obtained from the target user terminal is auto insurance
- the product category vector corresponding to the auto insurance is F1
- the numerical data, the sub-type vector, and the product category vector are spliced head to tail to construct a fusion vector, that is, as The input vector of the product recommendation model, for example, the fusion vector is represented as D1, D2, D3, E1, E2, E3, E4, E5, F1.
- the fusion vector constructed, because in addition to retaining the user’s numerical characteristics and sub-type characteristics related information, it also retains product category information, which can be used in the user On the basis of the interest profile, according to the corresponding category characteristics of the product, further analyze the products that users may be interested in, so as to improve the accuracy of product recommendation.
- the method before constructing a fusion vector based on the numerical data and the sub-type vector, the method further includes the following steps:
- the product that the user has purchased is obtained from the customer database, and the historical product purchase record corresponding to the user is generated.
- the target user is a renewal user, and the target user has purchased more auto insurance types in history, it is also more likely to continue to purchase the auto insurance types next time.
- the attention (self-attention) mechanism is used to rank the importance of insurance types. If the user has purchased more types of auto insurance in the history, the type of insurance will get a higher score.
- the result processed by the attention mechanism can be used as the input of the product recommendation model, so that the prediction of the model can be optimized by using the attention mechanism.
- the constructing a fusion vector according to the numerical data and the classification vector specifically includes the following steps:
- a fusion vector is constructed.
- the product category information obtained from the target user terminal is auto insurance
- the product category vector corresponding to auto insurance is F1
- the purchase record vector corresponding to the historical product purchase record is G1
- the numerical data, the category vector, and the product category vector and/or the purchase record vector are spliced from the beginning to the end as the input vector of the product recommendation model.
- the fusion vector can be expressed as D1, D2, D3, E1, E2, E3, E4, E5, F1, G1, Or D1, D2, D3, E1, E2, E3, E4, E5, G1.
- Step S103 Process the fusion vector based on the deep neural network sub-model in the product recommendation model to obtain a deep feature vector, and process the fusion vector based on the cross neural network sub-model in the product recommendation model to obtain Cross feature vector.
- the product recommendation model includes a deep neural network sub-model deep network and a cross neural network sub-model cross network.
- the core idea of crossover network is to apply explicit feature crossover in an effective way.
- the crossover network is composed of crossover layers, and each crossover layer has the following formula:
- X l and X l+1 are column vectors, respectively representing the output of the cross layer from the lth layer and the (l+1)th layer
- X 0 is the preset vector
- W l and b l are the lth layer.
- the connection parameter between the two cross layers of the layer and the (l+1)th layer, f() represents feature crossing, which is used to fit the residual of the output of this layer and the output of the previous layer, namely X l The residual of +1 -X l.
- the deep network is a fully connected feedforward neural network, and each deep layer has the following formula:
- h l and h l+1 are the output of the hidden layer of the lth layer and the (l+1)th layer, respectively, and W l and b l are the two layers of the lth layer and the (l+1)th layer.
- the connection parameter between the deep layers, f() represents the activation function—ReLU function.
- the product recommendation model is obtained by jointly training the cross network cross network and the deep neural network deep network, which not only retains the ability of the deep neural network deep network to capture complex feature combinations, but also in the cross network cross network, each layer has feature cross feature crossing, can learn cross features, and does not require manual feature engineering. Therefore, the recommended model of this product has a small memory, is very efficient when learning features of a specific order combination, and the additional complexity introduced is also minimal.
- Step S104 Construct a fusion feature vector according to the depth feature vector and the cross feature vector, and predict the respective recommendation scores of several products to be recommended based on the fusion feature vector.
- the cross feature vector output by the cross neural network sub-model in the product recommendation model is X l+1
- the depth feature vector output by the deep neural network sub-model is h l+1
- the depth in the product recommendation model The outputs of the neural network sub-model deep network and the cross neural network sub-model cross network are spliced to obtain a fusion feature vector, which can be expressed as X l+1 , h l+1 , for example.
- the product recommendation model further includes a logistic regression sub-model, and the logistic regression sub-model includes a linear network layer and a sigmoid activation layer.
- the fusion feature vector is input into the logistic regression sub-model, and the linear network layer processes the fusion feature vector to obtain an output vector containing several elements.
- the several elements have a one-to-one correspondence with several products to be recommended, wherein the several elements are in a proportional relationship with the recommended scores of the products to be recommended, that is, the larger the element corresponding to a product to be recommended, the larger the product to be recommended The higher the recommended score for the product.
- the output vector of the linear network layer is passed through the sigmoid activation function to calculate the recommended score corresponding to each product to be recommended, so that the recommended score can be processed as a value between 0 and 1.
- Step S105 Send product information of at least one product to be recommended to the target user terminal according to the respective recommendation scores of the plurality of products to be recommended.
- the product to be recommended with the largest recommended score may be determined as the target product, and then product information of the target product, such as the auto insurance agreement, price, etc., is obtained, and then the product information is sent to the target user terminal.
- product information of the target product such as the auto insurance agreement, price, etc.
- the sending product information of at least one product to be recommended to the target user terminal according to the respective recommendation scores of the products to be recommended includes the following steps:
- the product to be recommended is sent to the target user terminal.
- the lowest recommended score can be preset, such as 0.75, if the recommended score of the product to be recommended is greater than 0.75, the product information of the product to be recommended is sent to the target user terminal; if there is no product to be recommended If the recommended score is greater than 0.75, the product information corresponding to the product to be recommended with the largest recommended score is sent to the target user terminal.
- the product information pushing method further includes a training process of a product recommendation model, for example, it may include step 201 to step S206.
- the training process of the product recommendation model can be implemented by a terminal or a server; the product recommendation model obtained after the training can be deployed on the terminal or server used to implement the product information pushing method of the foregoing embodiment.
- Step 201 Obtain training sample data.
- the training sample data includes product information of several users and products of interest, and the product information includes numerical features and sub-type features.
- the product information includes the user's vehicle information
- the vehicle information includes purchase price, number of seats, exhaust steam volume, agency code, broker code, agent code, car dealer code, car series, brand, nature of belonging, and vehicle type , New energy vehicle logo, gender of owner of driving license, etc.
- the purchase price, the number of seats, and the amount of exhaust steam are quantitative values, so vehicle information such as the purchase price, number of seats, and exhaust amount can be determined as numerical features.
- Step 202 Perform standardization processing on the numerical feature to obtain numerical data corresponding to the numerical feature, and perform vectorization processing on the sub-type feature to obtain a sub-type vector corresponding to the sub-type feature.
- the numerical features are normalized by a max-min normalization method. The reason is that if the data difference between multiple features is large, the convergence speed will be very slow. In the model involving distance calculation, if the numerical difference between multiple features is large, then the effect of the feature with a small value on the distance will be Very small, it will affect the accuracy of the model.
- the sub-type features are randomly initialized to obtain the corresponding sub-type vector, and the sub-type vector is updated during the model training process.
- L2 regularization is used to process sub-type features, so that model complexity and instability are reduced in the process of model training and learning, so as to avoid the risk of overfitting.
- a corresponding auto insurance type feature vector is initialized, and the sub-type variable is used to express the auto insurance type information, and the initial dimension of the feature of the sub-type variable is 10 dimensions.
- the eigenvector values of the sub-types are updated, and the initial eigenvalues are between 0 and 0.001.
- the model training has the fastest convergence speed.
- the purchase price, the number of seats, and the exhaust steam volume in the vehicle information of a certain user in the training sample data are standardized, and the numerical data are correspondingly obtained as D1, D2, and D3, and the user’s vehicle information is
- the agency code, broker code, agent code, car dealer code, and car series are respectively vectorized, and the sub-type vectors E1, E2, E3, E4, and E5 are obtained accordingly.
- Step 203 Construct a fusion vector according to the user's numerical data and the classification vector.
- the numerical data and the sub-type vector are spliced end to end as the input vector of the product recommendation model.
- the fusion vector is represented as D1, D2, D3, E1, E2, E3, E4, E5.
- Step 204 Input the fusion vector of the user into the deep neural network sub-model and the cross neural network sub-model in the product recommendation model, respectively, to obtain a deep feature vector and a cross feature vector.
- the output cross feature vector is X l+1 ; the user's fusion vector is input to the product After recommending the deep neural network sub-model in the model, the output depth feature vector is h l+1 .
- Step 205 Construct a fusion feature vector according to the depth feature vector of the user and the cross feature vector, and predict the respective recommendation scores of several products to be recommended based on the fusion feature vector.
- the cross feature vector output by the cross neural network sub-model in the product recommendation model is X l+1
- the depth feature vector output by the deep neural network sub-model is h l+1
- the depth in the product recommendation model The outputs of the neural network sub-model deep network and the cross neural network sub-model cross network are spliced to obtain a fusion feature vector, which can be expressed as X l+1 , h l+1 , for example.
- the product recommendation model further includes a logistic regression sub-model, wherein the logistic regression sub-model includes a linear network layer and a sigmoid activation layer.
- the fusion feature vector is input into the logistic regression sub-model, and the linear network layer processes the fusion feature vector to obtain an output vector containing several elements.
- the output vector of the linear network layer is passed through the sigmoid activation function to calculate the recommended score corresponding to each product to be recommended, so that the recommended score can be processed as a value between 0 and 1.
- Step 206 Calculate a loss value according to the respective recommendation scores of the plurality of products to be recommended corresponding to the user and the product of interest of the user, and adjust the model parameters of the product recommendation model according to the loss value.
- the acquired data set is divided into a training data set, a verification data set, and a test data set.
- the training data set is used for model training
- the verification data set is used for model selection
- the test data set is used for model testing.
- the training problem can be treated as a dual problem or a dual problem.
- the non-dual problem is that in the constructed positive and negative sample pairs, if the user purchases some types of insurance, the sample of the insurance is a positive sample, then We label this type of insurance as 1, and if some insurance types are not purchased, and the sample of this type of insurance is a negative sample, then we will label these types of insurance as 0.
- each sample pair corresponds to a positive sample and a negative sample.
- a sorting problem we make the score of the positive sample higher than the negative sample in the training process of the model to achieve the sorting effect of the model.
- the deep neural network is first calculated.
- the number of deep neural network layers can be adjusted as needed. For example, a two-layer linear neural network is selected, and each neural network layer corresponds to a weight and a bias. Bias, during model training, the weight and Bias values are updated.
- the dimension of the hidden layer can be adjusted as needed, such as setting the dimension of the hidden layer to 50.
- the final input dimension of the model is 100.
- the output layer dimension of the middle layer is set to 50, and the input layer dimension is set to 10, and the output layer dimension can be adjusted as needed.
- the model can learn feature information in the deep sense.
- the Batch Normalization mechanism in the deep neural network, can be selectively used.
- the input value distribution will shift and approach the upper and lower ends of the value range.
- Batch Normalization uses certain normalization methods to force the distribution of the input values of each layer of neural network back to the standard normal distribution with a mean of 0 and a variance of 1, making the distribution back to a nonlinear function more sensitive to the input
- the loss function can be changed greatly, such as the gradient becomes larger, so as to avoid the problem of the disappearance of the gradient.
- the larger the gradient can speed up the convergence speed of the model and increase the training speed.
- the cross neural network mechanism in order to learn the cross information between the features, is used.
- the number of cross neural network layers can be adjusted as needed.
- the implementation mechanism of the cross neural network is based on the previous one each time.
- the result of the layer cross neural network is multiplied by a matrix of the same dimension, and the output result of the previous layer cross neural network and a corresponding offset are added at the same time.
- an optimizer is selected for model training, where the optimizer can be selected, such as the sgd optimizer, and the learning rate of the optimizer can be adjusted according to actual needs to improve the model training effect.
- the sgd optimizer has the characteristics of fast training speed and not easy to fall into the local optimal solution.
- a dynamic learning rate scheme can be used in the product recommendation model. For example, for every 100 training iterations of the model, the learning rate is attenuated by 10 times. The purpose of setting the dynamic learning rate is to make the model more accessible to the optimal solution.
- the product information push method provided by the foregoing embodiment obtains user characteristic information from a target terminal, and the user characteristic information includes numerical characteristics and sub-type characteristics.
- the numerical characteristics and sub-type characteristics are processed separately to obtain a fusion vector.
- the deep neural network sub-model and the cross neural network sub-model in the pre-trained product recommendation model process the fusion vector to obtain the deep feature vector and the cross feature vector, and construct the fusion feature vector according to the deep feature vector and the cross feature vector.
- the fusion feature vector predicts the respective recommendation scores of several products to be recommended, and finally, according to the respective recommendation scores of the recommended products, sends the product information of at least one product to be recommended to the target user terminal, which can integrate more types User attributes participate in decision-making, thereby improving the accuracy of product recommendations.
- FIG. 6 is a schematic block diagram of a product information pushing device provided by an embodiment of the present application, and the product information pushing device is used to execute the aforementioned product information pushing method.
- the product information pushing device can be configured in a server or a terminal.
- the server can be an independent server or a server cluster.
- the terminal can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device.
- the product information pushing device 300 includes: a data acquisition module 301, a data processing module 302, a vector processing module 303, a score prediction module 304, and a product recommendation module 305.
- the data acquisition module 301 is configured to acquire user characteristic information from a target user terminal, where the user characteristic information includes numerical characteristics and sub-type characteristics.
- the data processing module 302 is configured to perform data preprocessing on the numerical feature and the sub-category feature to construct a fusion vector.
- the data processing module 302 includes a standardized processing sub-module 3021, a vectorization processing sub-module 3022 and a data fusion sub-module 3023.
- the standardization processing sub-module 3021 is used to perform standardization processing on the numerical features to obtain the numerical data corresponding to the numerical features;
- the vectorization processing sub-module 3022 is used to vectorize the sub-type features Through processing, the sub-type vector corresponding to the sub-type feature is obtained;
- the data fusion sub-module 3023 is configured to construct a fusion vector according to the numerical data and the sub-type vector.
- the vector processing module 303 is configured to process the fusion vector based on the deep neural network sub-model in the product recommendation model to obtain a deep feature vector, and perform processing on the fusion vector based on the cross neural network sub-model in the product recommendation model Process to get the cross feature vector.
- the score prediction module 304 is configured to construct a fusion feature vector according to the depth feature vector and the cross feature vector, and predict the respective recommendation scores of several products to be recommended according to the fusion feature vector.
- the product recommendation module 305 is configured to send product information of at least one product to be recommended to the target user terminal according to the respective recommendation scores of the products to be recommended.
- the product recommendation module 305 includes a product judgment sub-module 3051 and a product push sub-module 3052.
- the product judgment sub-module 3051 is used to judge whether the recommended score of the product to be recommended is greater than a preset threshold; the product push sub-module 3052 is used to send the product to be recommended with the recommended score greater than the preset threshold to the target User terminal.
- the product information push device 300 includes a model optimization module for obtaining training sample data, the training sample data includes product information of a number of users and products of interest, and the product information includes numerical features and scores.
- Type feature standardize the numeric feature to obtain the numeric data corresponding to the numeric feature, and vectorize the sub-category feature to obtain the sub-category vector corresponding to the sub-category feature;
- the user’s numerical data and classification vectors are used to construct a fusion vector; the user’s fusion vector is input into the deep neural network sub-model and the cross neural network sub-model in the product recommendation model, respectively, to obtain the deep feature vector and cross Feature vector; construct a fusion feature vector according to the depth feature vector of the user and the cross feature vector, and predict the respective recommendation scores of several products to be recommended according to the fusion feature vector; according to the user’s corresponding The respective recommendation scores of a number of products to be recommended and the loss value of the user's product of interest are calculated, and the model parameters of the product recommendation
- the above-mentioned product information pushing device may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in FIG. 8.
- FIG. 8 is a schematic block diagram of a structure of a computer device provided by an embodiment of the present application.
- the computer equipment can be a server or a terminal.
- the computer device includes a processor, a memory, and a network interface connected through a system bus, where the memory may be volatile or non-volatile.
- the non-volatile storage medium can store an operating system and a computer program.
- the computer program includes program instructions, and when the program instructions are executed, the processor can execute any method for pushing product information.
- the processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.
- the internal memory provides an environment for the operation of the computer program in the non-volatile storage medium.
- the processor can execute any product information push method.
- the network interface is used for network communication, such as sending assigned tasks.
- FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
- the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
- the processor may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), and application specific integrated circuits (Application Specific Integrated Circuits). Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
- the general-purpose processor may be a microprocessor or the processor may also be any conventional processor.
- the processor is used to run a computer program stored in a memory to implement the following steps:
- product information of at least one product to be recommended is sent to the target user terminal.
- the processor when the processor implements the data preprocessing of the numerical feature and the sub-category feature to construct a fusion vector, the processor is used to implement:
- a fusion vector is constructed according to the numerical data and the classification vector.
- the processor is further configured to implement:
- the constructing a fusion vector according to the numerical data and the classification vector includes:
- a fusion vector is constructed.
- the processor when the processor implements the vectorization processing on the product category information to obtain the product category vector corresponding to the product category information, the processor is configured to implement:
- mapping relationship data vectorization processing is performed on the product category information to obtain a product category vector corresponding to the product category information.
- the processor before the processor implements the construction of a fusion vector based on the numerical data and the classification vector, the processor is configured to implement:
- the constructing a fusion vector according to the numerical data and the classification vector includes:
- a fusion vector is constructed.
- the processor is used to realize that when the processor realizes that the product information of at least one product to be recommended is sent to the target user terminal according to the respective recommendation scores of the several products to be recommended :
- the product to be recommended is sent to the target user terminal.
- the processor when the processor implements the product information pushing method, it is further configured to implement:
- training sample data includes product information of several users and products of interest, and the product information includes numerical features and sub-type features;
- a loss value is calculated according to the respective recommendation scores of the plurality of products to be recommended corresponding to the user and the product of interest of the user, and the model parameters of the product recommendation model are adjusted according to the loss value.
- the embodiments of the present application also provide a computer-readable storage medium, and the computer-readable storage medium may be volatile or non-volatile.
- the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the processor executes the program instructions to implement any product information push method provided in the embodiments of the present application.
- the computer-readable storage medium may be the internal storage unit of the computer device described in the foregoing embodiment, for example, the hard disk or memory of the computer device.
- the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk equipped on the computer device, a smart memory card (Smart Media Card, SMC), and a Secure Digital (SD) ) Card, Flash Card, etc.
- a plug-in hard disk equipped on the computer device such as a smart memory card (Smart Media Card, SMC), and a Secure Digital (SD) ) Card, Flash Card, etc.
- SD Secure Digital
- the product information pushing device, storage medium, and computer equipment provided in the foregoing embodiments obtain user characteristic information from the target terminal, and the user characteristic information includes numerical characteristics and sub-type characteristics, and the numerical characteristics and sub-type characteristics are processed separately,
- To obtain the fusion vector use the deep neural network sub-model and the cross neural network sub-model in the pre-trained product recommendation model to process the fusion vector to obtain the deep feature vector and the cross feature vector, which are constructed according to the deep feature vector and the cross feature vector Fusion feature vectors, thereby predicting the respective recommendation scores of several products to be recommended according to the fusion feature vector, and finally sending the product information of at least one product to be recommended to the target user terminal according to the respective recommendation scores of the recommended products, More types of user attributes can be integrated to participate in decision-making, thereby improving the accuracy of product recommendations.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种产品信息推送方法、装置、设备及存储介质,所述方法包括:从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征(S101);对所述数值型特征和所述分类型特征进行数据预处理以构造融合向量(S102);基于产品推荐模型中的深度神经网络子模型对融合向量进行处理得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对融合向量进行处理得到交叉特征向量(S103);根据深度特征向量和交叉特征向量构造融合特征向量,并根据融合特征向量预测若干待推荐产品各自的推荐分值(S104);根据待推荐产品的推荐分值,将待推荐产品发送给所述目标终端(S105)。可以融合更多种类的用户属性参与决策,以提高产品推荐的准确率。
Description
本申请要求于2020年03月25日提交中国专利局、申请号为CN202010220066.7、名称为“一种产品信息推送方法、装置、设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及数据分析领域,尤其涉及一种产品信息推送方法、装置、设备及存储介质。
传统的产品推荐系统通过业务员对用户产品历史购买情况以及咨询情况作分析来判断用户接下来购买的产品。对于人工推荐产品的方式,需要抽入大量的人工,增加了人力成本开支,同时会给用户带来较差的体验。由于用户数量之多,人工推荐的方式已经不能满足当前用户的需要,智能化产品自动推荐方案也因此产生。
现有的智能化产品自动推荐方案,一般通过大数据分析确定用户属性与产品属性之间的关联度,然后根据用户属性和产品属性及其关联度,确定用户可能感兴趣的产品。但是可以参与决策的用户属性的种类有限,在推荐决策过程中会遗漏较多的参考信息,从而确定的产品可能不是用户真正感兴趣,导致推荐准确率较低。
因此,如何提高产品推荐的准确率成为亟待解决的问题。
发明内容
本申请提供了一种产品信息推送方法,所述方法包括:
从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;
对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;
基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;
根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
本申请还提供了一种产品信息推送装置,所述装置包括:
数据获取模块,用于从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;
数据处理模块,用于对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;
向量处理模块,用于基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;
分值预测模块,用于根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
产品推荐模块,用于根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
本申请还提供了一种计算机设备,所述计算机设备包括存储器和处理器;所述存储器用于存储计算机程序;所述处理器,用于执行所述计算机程序并在执行所述计算机程序时实现如下步骤:
从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;
对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;
基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;
根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
本申请还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时使所述处理器实现如下步骤:
从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;
对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;
基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;
根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
为了更清楚地说明本申请实施例技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种产品信息推送方法的示意流程图;
图2为应用于服务器的产品信息推送方法的场景示意图;
图3为图1中对所述数值型特征和所述分类型特征进行数据预处理以构造融合向量的子流程示意图;
图4是本申请实施例提供的一种产品推荐模型的结构示意性框图;
图5是本申请实施例提供的一种产品推荐模型训练过程的示意流程图;
图6是本申请实施例提供的一种产品信息推送装置的示意性框图;
图7是本申请实施例提供的另一种产品信息推送装置的示意性框图;
图8是本申请一实施例提供的一种计算机设备的结构示意性框图。
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
附图中所示的流程图仅是示例说明,不是必须包括所有的内容和操作/步骤,也不是必须按所描述的顺序执行。例如,有的操作/步骤还可以分解、组合或部分合并,因此实际执行的顺序有可能根据实际情况改变。
应当理解,在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样,除非上下文清楚地指明其它情况,否则单数形式的“一”、“一个”及“该”意在包括复数形式。
还应当理解,在本申请说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合,并且包括这些组合。
本申请的实施例提供了一种产品信息推送方法、装置、计算机设备及存储介质。该产品信息推送方法可应用于服务器中,用于根据用户的用户特征信息为用户推送适合的产品信息等过程,以提高产品推荐的准确率。
例如,产品信息推送方法用于服务器;服务器可以为独立的服务器,也可以为服务器集群。以下实施例将以应用于服务器的产品信息推送方法进行详细介绍。
下面结合附图,对本申请的一些实施方式作详细说明。在不冲突的情况下,下述的实施例及实施例中的特征可以相互组合。
请参阅图1,图1是本申请实施例提供的一种产品信息推送方法的示意流程图。
如图2所示为应用于服务器的产品信息推送方法的场景示意图。
如图1和图2所示,该产品信息推送方法,具体包括:步骤S101至步骤S105。
步骤S101、从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征。
示例性地,用户特征信息可以包括用户的车辆信息。在一些实施方式中,用户可以在其使用的终端上输入车辆信息,然后终端将车辆信息发送给服务器。
示例性地,用户在终端上点击产品推荐的按钮,则终端上可以显示车辆信息输入界面;用户可以在该输入界面输入车辆信息,然后终端将车辆信息发送给服务器。
在一些实施方式中,车辆信息可以包括购置价、座位数、排汽量、机构代码、经纪人代码、代理人代码、车商编码、车系、品牌、所属性质、车辆种类、新能源车标志、行驶证车主性别等。
其中,购置价、座位数、排汽量是量化的数值,因此可以将购置价、座位数、排汽量等车辆信息确定为数值型特征。机构代码、经纪人代码、代理人代码、车商编码、车系、品牌、所属性质、车辆种类、新能源车标志、行驶证车主性别等不适量化的特征,例如可以以数字和/或字母代码表示,因此可以将这些特征确定为分类型特征。
步骤S102、对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量。
由于所述数值型特征和所述分类型特征为不同的数据类型,因此,需要使用不同的预处理方法分别对所述数值型特征和所述分类型特征进行处理。
在一些实施例中,请参考图3,所述对所述数值型特征和所述分类型特征进行数据预处理以构造融合向量,具体包括:步骤S1021至步骤S1023。
步骤S1021、对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据。
在一些实施方式中,通过max-min归一化方法对所述数值型特征进行标准化处理。
max-min归一化也称为离差标准化,是对原始数据的线性变换,使结果值映射到[0,1]之间。转换函数如下:x’=(x-min)÷(max-min)。其中,max表示数值型特征的最大值、min表示数值型特征的最小值,x表示从目标用户终端获取的车辆信息中的数值型特征的数值,x’表示数值型特征对应的数值数据。
例如,预设车辆的购置价的最大值为110万人民币,最小值为10万人民币,则若从目标用户终端获取的车辆信息中的购置价为30万人民币,则该购置价进行标准化处理后得到的数值数据为0.2。
在另一些实施方式中,对所述数值型特征进行标准化处理,使所述数值型特征对应的数值数据满足正态分布。
示例性地,该标准化处理的转化函数可以表示为:x’=(x-μ)÷σ,其中μ表示数值型特征样本数据的均值,σ表示数值型特征样本数据的标准差,x表示从目标用户终端获取的车辆信息中的数值型特征的数值,x’表示数值型特征对应的数值数据。
通过对数值型特征进行标准化处理,可以避免由于不同数值型特征数值差异过大,导致的在数值型特征较小时产品推荐的准确性较差的问题;通过标准化处理将差异很大的数值型 特征的数值压缩至较小的范围,即可以保持不同数值型特征的数值之间的差异,也缩小了不同数值型特征的数值之间的差异,使得产品信息推送方法可以在更多的场景下保持足够的精度。
示例性地,车辆信息中的购置价、座位数、排汽量进行标准化处理,相应的得到数值数据分别为D1、D2、D3。
步骤S1022、对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量。
在一些实施例中,服务器预先存储有分类型特征和分类型向量的映射表,可以通过查表得到分类型特征对应的分类型向量。
在另一些实施方式中,基于产品推荐模型中的向量嵌入层对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量。通过模型训练的产品推荐模型,向量嵌入层学习到了训练样本中分类型特征和分类型向量的对应关系,从而可以根据分类型特征确定对应的分类型向量。
示例性地,对车辆信息中的机构代码、经纪人代码、代理人代码、车商编码、车系分别进行向量化处理,相应地得到分类型向量E1、E2、E3、E4、E5。
步骤S1023、根据所述数值数据和所述分类型向量构造融合向量。
在一些实施例中,通过将所述数值数据和所述分类型向量首尾拼接,作为产品推荐模型的输入向量。示例性地,融合向量表示为D1、D2、D3、E1、E2、E3、E4、E5。
根据所述数值数据和所述分类型向量构造的融合向量,由于同时保留了用户的数值型特征和分类型特征的相关信息,如购置价、座位数、排汽量、机构代码、经纪人代码、代理人代码、车商编码、车系、品牌、所属性质、车辆种类、新能源车标志、行驶证车主性别等,可以更好地融合更多种类的用户属性参与决策,从而得出更为精准的用户兴趣画像。基于用户兴趣画像为用户推荐产品,可提高产品推荐的精确率。在一些实施例中,所述根据所述数值数据和所述分类型向量构造融合向量之前,还包括以下步骤:
从所述目标用户终端获取产品类别信息,对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量。
示例性地,用户在目标用户终端还输入需要推荐的产品的类别,从而服务器可以根据用户输入获取产品类别信息,如车险险种,可以为寿险、车险等。
在一些实施例中,所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量,具体包括以下步骤:获取预设的产品类别信息与产品类别向量之间的映射关系数据;根据所述映射关系数据,对所述产品类别信息进行向量化处理,以得到所述产品类别信息对应的产品类别向量。服务器预先存储有产品类别信息和产品类别向量的映射表,可以通过查表得到产品类别信息对应的产品类别向量。
在另一些实施例中,所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量,具体包括以下步骤:基于产品推荐模型中的向量嵌入层对所述产品类别信息进行向量化处理,得到对应的产品类别向量。通过模型训练的产品推荐模型,向量嵌入层学习到了训练样本中产品类别信息和产品类别向量的对应关系,从而可以根据产品类别信息确定对应的产品类别向量。
在一些实施例中,所述根据所述数值数据和所述分类型向量构造融合向量,具体包括以下步骤:
根据所述数值数据、所述分类型向量以及所述产品类别向量,构造融合向量。
示例性地,从目标用户终端获取产品类别信息为车险,车险对应的产品类别向量为F1,将所述数值数据、所述分类型向量和所述产品类别向量首尾拼接,构造融合向量,即作为产品推荐模型的输入向量,如融合向量表示为D1、D2、D3、E1、E2、E3、E4、E5、F1。
根据所述数值数据、所述分类型向量以及所述产品类别向量,构造的融合向量,由于除了保留了用户的数值型特征和分类型特征的相关信息,还保留了产品类别信息,可以在用户 兴趣画像的基础上,根据产品对应的类别特性,进一步分析用户可能感兴趣的产品,从而提高产品推荐的准确率。
在一些实施例中,所述根据所述数值数据和所述分类型向量构造融合向量之前,还包括以下步骤:
获取所述目标用户终端对应的历史产品购买记录,对所述历史产品购买记录进行自注意力机制处理,得到所述历史产品购买记录对应的购买记录向量。
示例性地,根据目标用户终端的用户信息,从客户数据库获取该用户曾购买过的产品,生成该用户对应的历史产品购买记录。
若该目标用户为续保用户,且该目标用户历史购买较多的车险险种,在下次车险险种购买时继续购买该险种的可能性也较大。在续保用户车险险种推荐中,可以根据历史产品购买记录视为情况对每种险种的重要性进行评估。因此,对于续保用户,根据历史车险险种购买记录,采用attention(自注意力)机制,进行险种重要性排序。用户历史购买的某种车险险种较多,则该险种会获得较高的评分。同时,可以将attention机制处理后的结果作为产品推荐模型的输入,从而可以通过使用attention机制以使得模型的预测达到最优效果。
在一些实施例中,所述根据所述数值数据和所述分类型向量构造融合向量,具体包括以下步骤:
根据所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量,构造融合向量。
示例性地,从目标用户终端获取产品类别信息为车险,车险对应的产品类别向量为F1,所述历史产品购买记录对应的购买记录向量为G1,将所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量首尾拼接,作为产品推荐模型的输入向量,如融合向量可以表示为D1、D2、D3、E1、E2、E3、E4、E5、F1、G1,或者为D1、D2、D3、E1、E2、E3、E4、E5、G1。
步骤S103、基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量。
在一些实施例中,如图4所示,产品推荐模型包括深度神经网络子模型deep network和交叉神经网络子模型cross network。其中,交叉网络的核心思想是以有效的方式应用显式特征交叉。交叉网络由交叉层组成,每个交叉层具有以下公式:
其中,X
l、X
l+1为列向量,分别表示来自第l层和第(l+1)层的交叉层cross layer的输出,X
0为预设向量,W
l、b
l为第l层和第(l+1)层这两个交叉层cross layer之间的连接参数,f()表示特征交叉feature crossing,用于拟合该层输出和上一层输出的残差,即X
l+1-X
l的残差。
由于交叉网络的参数数目少,从而限制了模型的能力。为了捕获高阶非线性交叉,在所述产品推荐模型中平行引入了一个深度网络。深度网络就是一个全连接的前馈神经网络,每个深度层具有如下公式:
h
l+1=f(W
lH
l+b
l)
其中,h
l、h
l+1分别是第l层和第(l+1)层的隐藏层hidden layer的输出,W
l、b
l为第l层和第(l+1)层这两个深度层deep layer之间的连接参数,f()表示激活函数—ReLU function。
产品推荐模型通过联合(jointly)训练交叉网络cross network和深度神经网络deep network得到,既保留了深度神经网络deep network捕获复杂特征组合的能力,同时交叉网络cross network中,每一层都有特征交叉feature crossing,能够学习交叉特征,并不需要人工特征工程。因此,该产品推荐模型内存较小,在学习特定阶数组合特征的时候效率非常高,并且引入的额外的复杂度也是微乎其微的。
步骤S104、根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值。
示例性地,所述产品推荐模型中的交叉神经网络子模型输出的交叉特征向量为X
l+1,深度神经网络子模型输出的深度特征向量为h
l+1,将产品推荐模型中的深度神经网络子模型deep network和交叉神经网络子模型cross network的输出进行拼接,得到融合特征向量,例如可以表示为X
l+1,h
l+1。
在一些实施例中,所述产品推荐模型还包括逻辑回归子模型,所述逻辑回归子模型包括线性网络层和sigmoid激活层。
将该融合特征向量输入所述逻辑回归子模型,线性网络层根据融合特征向量处理得到包含若干元素的输出向量。示例性地,所述若干元素与若干待推荐产品一一对应,其中,所述若干元素与待推荐产品的推荐分值成正比关系,即一待推荐产品对应的元素越大,则该待推荐产品对应的推荐分值越高。
示例性地,将线性网络层的输出向量,经过sigmoid激活函数,计算出各个待推荐产品对应的推荐分值,从而可以将推荐分值处理为0到1之间的数值。
步骤S105、根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
示例性地,可以将推荐分值最大的待推荐产品确定为目标产品,然后获取该目标产品的产品信息,如该车险的协议、价格等,之后将该产品信息发送给所述目标用户终端。
在一些实施例中,所述根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端,包括以下步骤:
若有所述待推荐产品的推荐分值大于预设阈值,则将所述待推荐产品发送给所述目标用户终端。
可预设最低的推荐分值,如0.75,若有所述待推荐产品的推荐分值大于0.75,则将所述待推荐产品的产品信息发送给所述目标用户终端;若没有待推荐产品的推荐分值大于0.75,则将推荐分值最大的待推荐产品对应的产品信息发送给所述目标用户终端。
在一些实施例中,请参考图5,所述产品信息推送方法,还包括产品推荐模型的训练过程,例如可以包括步骤201至步骤S206。
可以理解的,产品推荐模型的训练过程可以由终端或服务器执行实现;训练结束后得到的产品推荐模型可以部署在用于实现前述实施例的产品信息推送方法的终端或服务器。
步骤201、获取训练样本数据,所述训练样本数据包括若干用户的产品信息以及感兴趣产品,且所述产品信息包括数值型特征和分类型特征。
所述产品信息包括用户的车辆信息,所述车辆信息包括购置价、座位数、排汽量、机构代码、经纪人代码、代理人代码、车商编码、车系、品牌、所属性质、车辆种类、新能源车标志、行驶证车主性别等。其中,购置价、座位数、排汽量是量化的数值,因此可以将购置价、座位数、排汽量等车辆信息确定为数值型特征。机构代码、经纪人代码、代理人代码、车商编码、车系、品牌、所属性质、车辆种类、新能源车标志、行驶证车主性别等不适量化的特征,例如可以以数字和/或字母代码表示,因此可以将这些特征确定为分类型特征。
步骤202、对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据,并对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量。
在一些实施方式中,通过max-min归一化方法对所述数值型特征进行标准化处理。原因在如果多个特征之间数据差异较大,收敛速度就会很慢,在涉及到距离计算的模型中,若多个特征之间数值差异较大,那么数值小的特征对距离的影响则很小,会影响模型的精度。
分类型特征进行随机初始化处理得到对应的分类型向量,同时在模型训练过程中,会对分类型向量进行更新。示例性地,运用L2正则化对分类型特征进行处理,使得在模型训练学习过程中降低模型复杂度和不稳定程度,从而避免过拟合的风险。
示例性地,对每个车险险种初始化一个对应的车险险种特征向量,采用分类型变量来表 达车险险种信息,分类型变量的特征的初始化维度为10维。同时在模型训练过程中,会对分类型特征向量值进行更新,初始化特征值在0到0.001之间。当特征值在0到0.001之间时,模型训练收敛速度最快。
示例性地,对训练样本数据中某个用户的车辆信息中的购置价、座位数、排汽量进行标准化处理,相应地得到数值数据分别为D1、D2、D3,且该用户的车辆信息中的机构代码、经纪人代码、代理人代码、车商编码、车系分别进行向量化处理,相应的得到分类型向量E1、E2、E3、E4、E5。
步骤203、根据所述用户的数值数据和分类型向量构造融合向量。
在一些实施例中,通过将所述数值数据和所述分类型向量首尾拼接,作为产品推荐模型的输入向量。示例性地,融合向量表示为D1、D2、D3、E1、E2、E3、E4、E5。
步骤204、将所述用户的所述融合向量分别输入所述产品推荐模型中的深度神经网络子模型和交叉神经网络子模型,各自得到深度特征向量和交叉特征向量。
示例性地,将所述用户的所述融合向量输入至产品推荐模型中的交叉神经网络子模型后,输出的交叉特征向量为X
l+1;将所述用户的所述融合向量输入至产品推荐模型中的深度神经网络子模型后,输出的深度特征向量为h
l+1。
步骤205、根据所述用户的所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值。
示例性地,所述产品推荐模型中的交叉神经网络子模型输出的交叉特征向量为X
l+1,深度神经网络子模型输出的深度特征向量为h
l+1,将产品推荐模型中的深度神经网络子模型deep network和交叉神经网络子模型cross network的输出进行拼接,得到融合特征向量,例如可以表示为X
l+1,h
l+1。
在一些实施例中,产品推荐模型还包括逻辑回归子模型,其中,所述逻辑回归子模型包括线性网络层和sigmoid激活层。将该融合特征向量输入所述逻辑回归子模型,线性网络层根据融合特征向量处理得到包含若干元素的输出向量。将线性网络层的输出向量,经过sigmoid激活函数,计算出各个待推荐产品对应的推荐分值,从而可以将推荐分值处理为0到1之间的数值。
步骤206、根据所述用户对应的所述若干待推荐产品各自的推荐分值,以及所述用户的感兴趣产品计算损失值,根据所述损失值调整所述产品推荐模型的模型参数。
在一些实施方式中,将获取的数据集划分为训练数据集、校验数据集和测试数据集。训练数据集用于模型训练,校验数据集用于模型的选择,测试数据集用于模型的测试。
在一些实施方式中,可以将训练的问题处理为对非偶问题或者对偶问题,非对偶问题为在构造的正负样本对中,如果用户购买了些类险种,该险种样本为正样本,则我们将该类险种打标签为1,如果没有购买些类险种,该险种样本为负样本,则我们将些类险种打标签为0。而对偶问题中,每个样本对中对应一个正样本和一个负样本,作为排序问题,我们在模型的训练过程中,令正样本的得分高于负样本,以达到模型的排序效果。
在一些实施方式中,模型训练过程中,首先经过深度神经网络计算,深度神经网络层数可根据需要进行调整,如选用两层的线性神经网络,每层神经网络层对应一个权重weight和偏置Bias,在模型训练中,会对weight和Bias值进行更新。隐藏层维度大小可根据需要进行调整,如将隐藏层维度设置为50。模型的最终输入维度100维,为了使得模型达到理想的效果,因此将中间层输出层维度设置为50,输入层维度大小设置为10,其中输出层维度大小可根据需要进行调整。经过深度神经网络,模型可以学习到深度意义上的特征信息。
在一些实施方式中,在深度神经网络中,可选择性使用Batch Normalization机制,神经网络在训练过程中,随着深度加深,输入值分布会发生偏移,向取值区间上下两端靠近。为了解决这一问题,Batch Normalization通过一定的规范化手段,把每层神经网络输入值的分布强行拉回到均值为0方差为1的标准正态分布,使得分布回到非线性函数对输入比较敏感的区域,并且使得损失函数能发生较大的变化,如梯度变大,从而避免梯度消失问题。 同时梯度变大能加快模型收敛速度,提高训练速度。
在一些实施方式中,模型训练过程中,为了学习到特征之间的交叉信息,使用到了交叉神经网络机制,交叉神经网络层数可根据需要调整,交叉神经网络的实现机制是每次根据上一层交叉神经网络的结果,乘以一个同等维度的矩阵,同时加上上一层交叉神经网络的输出结果以及一个对应的偏置。
示例性地,选用优化器进行模型训练,其中优化器可选择,如sgd优化器,可根据实际所需对优化器的学习率进行调整从而提高模型训练效果。sgd优化器具有训练速度快,不容易陷入局部最优解的特性。
示例性地,在所述产品推荐模型中可采用动态学习率方案,如模型每训练迭代100轮,学习率衰减10倍。设置动态学习率的目的是为了使得模型更接进最优解。
上述实施例提供的产品信息推送方法,通过从目标终端获取用户特征信息,该用户特征信息包括数值型特征和分类型特征,对数值型特征和分类型特征分别进行处理,以得到融合向量,利用预先训练好的产品推荐模型中的深度神经网络子模型和交叉神经网络子模型分别对融合向量进行处理得到深度特征向量和交叉特征向量,根据深度特征向量和交叉特征向量构造融合特征向量,从而根据所述融合特征向量预测若干待推荐产品各自的推荐分值,最后根据推荐产品各自对应的推荐分值,将至少一个所述待推荐产品的产品信息发送至目标用户终端,可以融合更多种类的用户属性参与决策,从而提高产品推荐的准确率。
请参阅图6,图6是本申请的实施例还提供一种产品信息推送装置的示意性框图,该产品信息推送装置用于执行前述的产品信息推送方法。其中,该产品信息推送装置可以配置于服务器或终端中。
其中,服务器可以为独立的服务器,也可以为服务器集群。该终端可以是手机、平板电脑、笔记本电脑、台式电脑、个人数字助理和穿戴式设备等电子设备。
如图6所示,产品信息推送装置300包括:数据获取模块301、数据处理模块302、向量处理模块303、分值预测模块304和产品推荐模块305。
数据获取模块301,用于从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征。
数据处理模块302,用于对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量。
其中,如图7所示,数据处理模块302包括标准化处理子模块3021、向量化处理子模块3022和数据融合子模块3023。
具体地,标准化处理子模块3021,用于对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据;向量化处理子模块3022,用于对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;数据融合子模块3023,用于根据所述数值数据和所述分类型向量构造融合向量。
向量处理模块303,用于基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量。
分值预测模块304,用于根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值。
产品推荐模块305,用于根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
其中,如图7所示,产品推荐模块305包括产品判断子模块3051和产品推送子模块3052。
具体地,产品判断子模块3051,用于判断是否有待推荐产品的推荐分值大于预设阈值;产品推送子模块3052,用于将推荐分值大于预设阈值的待推荐产品发送给所述目标用户终端。
产品信息推送装置300包括模型优化模块,所述模型优化模块用于:获取训练样本数据,所述训练样本数据包括若干用户的产品信息以及感兴趣产品,且所述产品信息包括数值型特 征和分类型特征;对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据,并对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述用户的数值数据和分类型向量构造融合向量;将所述用户的所述融合向量分别输入所述产品推荐模型中的深度神经网络子模型和交叉神经网络子模型,各自得到深度特征向量和交叉特征向量;根据所述用户的所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述用户对应的所述若干待推荐产品各自的推荐分值,以及所述用户的感兴趣产品计算损失值,根据所述损失值调整所述产品推荐模型的模型参数。
需要说明的是,所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,上述描述的产品信息推送装置和各模块的具体工作过程,可以参考前述产品信息推送方法实施例中的对应过程,在此不再赘述。
上述的产品信息推送装置可以实现为一种计算机程序的形式,该计算机程序可以在如图8所示的计算机设备上运行。
请参阅图8,图8是本申请实施例提供的一种计算机设备的结构示意性框图。该计算机设备可以是服务器或终端。
参阅图8,该计算机设备包括通过系统总线连接的处理器、存储器和网络接口,其中,存储器可以是易失性的,也可以是非易失性的。
非易失性存储介质可存储操作系统和计算机程序。该计算机程序包括程序指令,该程序指令被执行时,可使得处理器执行任意一种产品信息推送方法。
处理器用于提供计算和控制能力,支撑整个计算机设备的运行。
内存储器为非易失性存储介质中的计算机程序的运行提供环境,该计算机程序被处理器执行时,可使得处理器执行任意一种产品信息推送方法。
该网络接口用于进行网络通信,如发送分配的任务等。本领域技术人员可以理解,图8中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的计算机设备的限定,具体的计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
应当理解的是,处理器可以是中央处理单元(Central Processing Unit,CPU),该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中,通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
其中,在一个实施例中,所述处理器用于运行存储在存储器中的计算机程序,以实现如下步骤:
从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;
对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;
基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;
根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
在一个实施例中,所述处理器在实现所述对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量时,用于实现:
对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据;
对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;
根据所述数值数据和所述分类型向量构造融合向量。
在一个实施例中,所述处理器在实现所述根据所述数值数据和所述分类型向量构造融合向量之前,还用于实现:
从所述目标用户终端获取产品类别信息,对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量;
所述根据所述数值数据和所述分类型向量构造融合向量,包括:
根据所述数值数据、所述分类型向量以及所述产品类别向量,构造融合向量。
在一个实施例中,所述处理器在实现所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量时,用于实现:
获取预设的产品类别信息与产品类别向量之间的映射关系数据;
根据所述映射关系数据,对所述产品类别信息进行向量化处理,以得到所述产品类别信息对应的产品类别向量。
在一个实施例中,所述处理器在实现所述根据所述数值数据和所述分类型向量构造融合向量之前,用于实现:
获取所述目标用户终端对应的历史产品购买记录,对所述历史产品购买记录进行自注意力机制处理,得到所述历史产品购买记录对应的购买记录向量;
所述根据所述数值数据和所述分类型向量构造融合向量,包括:
根据所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量,构造融合向量。
在一个实施例中,所述处理器在实现所述根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端时,用于实现:
若有所述待推荐产品的推荐分值大于预设阈值,则将所述待推荐产品发送给所述目标用户终端。
在一个实施例中,所述处理器在实现所述产品信息推送方法时,还用于实现:
获取训练样本数据,所述训练样本数据包括若干用户的产品信息以及感兴趣产品,且所述产品信息包括数值型特征和分类型特征;
对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据,并对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;
根据所述用户的数值数据和分类型向量构造融合向量;
将所述用户的所述融合向量分别输入所述产品推荐模型中的深度神经网络子模型和交叉神经网络子模型,各自得到深度特征向量和交叉特征向量;
根据所述用户的所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;
根据所述用户对应的所述若干待推荐产品各自的推荐分值,以及所述用户的感兴趣产品计算损失值,根据所述损失值调整所述产品推荐模型的模型参数。
本申请的实施例中还提供一种计算机可读存储介质,所述计算机可读存储介质可以是易失性的,也可以是非易失性的。所述计算机可读存储介质存储有计算机程序,所述计算机程序中包括程序指令,所述处理器执行所述程序指令,实现本申请实施例提供的任一项产品信息推送方法。
其中,所述计算机可读存储介质可以是前述实施例所述的计算机设备的内部存储单元,例如所述计算机设备的硬盘或内存。所述计算机可读存储介质也可以是所述计算机设备的外部存储设备,例如所述计算机设备上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。
前述实施例提供的产品信息推送装置、存储介质、计算机设备,通过从目标终端获取用户特征信息,该用户特征信息包括数值型特征和分类型特征,对数值型特征和分类型特征分别进行处理,以得到融合向量,利用预先训练好的产品推荐模型中的深度神经网络子模型和 交叉神经网络子模型分别对融合向量进行处理得到深度特征向量和交叉特征向量,根据深度特征向量和交叉特征向量构造融合特征向量,从而根据所述融合特征向量预测若干待推荐产品各自的推荐分值,最后根据推荐产品各自对应的推荐分值,将至少一个所述待推荐产品的产品信息发送至目标用户终端,可以融合更多种类的用户属性参与决策,从而提高产品推荐的准确率。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到各种等效的修改或替换,这些修改或替换都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以权利要求的保护范围为准。
Claims (20)
- 一种产品信息推送方法,其中,包括:从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
- 如权利要求1所述的产品信息推送方法,其中,所述对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量,包括:对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据;对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述数值数据和所述分类型向量构造融合向量。
- 如权利要求1所述的产品信息推送方法,其中,所述根据所述数值数据和所述分类型向量构造融合向量之前,还包括:从所述目标用户终端获取产品类别信息,对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量,构造融合向量。
- 如权利要求3所述的产品信息推送方法,其中,所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量,包括:获取预设的产品类别信息与产品类别向量之间的映射关系数据;根据所述映射关系数据,对所述产品类别信息进行向量化处理,以得到所述产品类别信息对应的产品类别向量。
- 如权利要求1至4中任一项所述的产品信息推送方法,其中,所述根据所述数值数据和所述分类型向量构造融合向量之前,还包括:获取所述目标用户终端对应的历史产品购买记录,对所述历史产品购买记录进行自注意力机制处理,得到所述历史产品购买记录对应的购买记录向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量,构造融合向量。
- 如权利要求1所述的产品信息推送方法,其中,所述根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端,包括:若有所述待推荐产品的推荐分值大于预设阈值,则将所述待推荐产品发送给所述目标用户终端。
- 如权利要求1所述的产品信息推送方法,其中,还包括:获取训练样本数据,所述训练样本数据包括若干用户的产品信息以及感兴趣产品,且所述产品信息包括数值型特征和分类型特征;对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据,并对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述用户的数值数据和分类型向量构造融合向量;将所述用户的所述融合向量分别输入所述产品推荐模型中的深度神经网络子模型和交叉神经网络子模型,各自得到深度特征向量和交叉特征向量;根据所述用户的所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述用户对应的所述若干待推荐产品各自的推荐分值,以及所述用户的感兴趣产品计算损失值,根据所述损失值调整所述产品推荐模型的模型参数。
- 一种产品信息推送装置,其中,包括:数据获取模块,用于从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;数据处理模块,用于对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;向量处理模块,用于基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;分值预测模块,用于根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;产品推荐模块,用于根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
- 一种计算机设备,其中,所述计算机设备包括存储器和处理器;所述存储器用于存储计算机程序;所述处理器,用于执行所述计算机程序并在执行所述计算机程序时实现如下步骤:从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
- 如权利要求9所述的计算机设备,其中,所述对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量,包括:对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据;对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述数值数据和所述分类型向量构造融合向量。
- 如权利要求9所述的计算机设备,其中,在执行所述计算机程序时还实现如下步骤:从所述目标用户终端获取产品类别信息,对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量,构造融合向量。
- 如权利要求11所述的计算机设备,其中,所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量,包括:获取预设的产品类别信息与产品类别向量之间的映射关系数据;根据所述映射关系数据,对所述产品类别信息进行向量化处理,以得到所述产品类别信息对应的产品类别向量。
- 如权利要求9至12中任一项所述的计算机设备,其中,在执行所述计算机程序时还实现如下步骤:获取所述目标用户终端对应的历史产品购买记录,对所述历史产品购买记录进行自注意 力机制处理,得到所述历史产品购买记录对应的购买记录向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量,构造融合向量。
- 如权利要求9所述的计算机设备,其中,所述根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端,包括:若有所述待推荐产品的推荐分值大于预设阈值,则将所述待推荐产品发送给所述目标用户终端。
- 如权利要求9所述的计算机设备,其中,在执行所述计算机程序时还实现如下步骤:获取训练样本数据,所述训练样本数据包括若干用户的产品信息以及感兴趣产品,且所述产品信息包括数值型特征和分类型特征;对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据,并对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述用户的数值数据和分类型向量构造融合向量;将所述用户的所述融合向量分别输入所述产品推荐模型中的深度神经网络子模型和交叉神经网络子模型,各自得到深度特征向量和交叉特征向量;根据所述用户的所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述用户对应的所述若干待推荐产品各自的推荐分值,以及所述用户的感兴趣产品计算损失值,根据所述损失值调整所述产品推荐模型的模型参数。
- 一种计算机可读存储介质,其中,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时使所述处理器实现如下步骤:从目标用户终端获取用户特征信息,所述用户特征信息包括数值型特征和分类型特征;对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量;基于产品推荐模型中的深度神经网络子模型对所述融合向量进行处理,得到深度特征向量,并基于所述产品推荐模型中的交叉神经网络子模型对所述融合向量进行处理,得到交叉特征向量;根据所述深度特征向量和所述交叉特征向量构造融合特征向量,并根据所述融合特征向量预测若干待推荐产品各自的推荐分值;根据所述若干待推荐产品各自的推荐分值,将至少一个所述待推荐产品的产品信息发送给所述目标用户终端。
- 如权利要求16所述的计算机可读存储介质,其中,所述对所述数值型特征和所述分类型特征进行数据预处理,以构造融合向量,包括:对所述数值型特征进行标准化处理,得到所述数值型特征对应的数值数据;对所述分类型特征进行向量化处理,得到所述分类型特征对应的分类型向量;根据所述数值数据和所述分类型向量构造融合向量。
- 如权利要求16所述的计算机可读存储介质,其中,在执行所述计算机程序时还实现如下步骤:从所述目标用户终端获取产品类别信息,对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量,构造融合向量。
- 如权利要求18所述的计算机可读存储介质,其中,所述对所述产品类别信息进行向量化处理,得到所述产品类别信息对应的产品类别向量,包括:获取预设的产品类别信息与产品类别向量之间的映射关系数据;根据所述映射关系数据,对所述产品类别信息进行向量化处理,以得到所述产品类别信 息对应的产品类别向量。
- 如权利要求16至19中任一项所述的计算机可读存储介质,其中,在执行所述计算机程序时还实现如下步骤:获取所述目标用户终端对应的历史产品购买记录,对所述历史产品购买记录进行自注意力机制处理,得到所述历史产品购买记录对应的购买记录向量;所述根据所述数值数据和所述分类型向量构造融合向量,包括:根据所述数值数据、所述分类型向量以及所述产品类别向量和/或所述购买记录向量,构造融合向量。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010220066.7 | 2020-03-25 | ||
| CN202010220066.7A CN111553759A (zh) | 2020-03-25 | 2020-03-25 | 一种产品信息推送方法、装置、设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021189976A1 true WO2021189976A1 (zh) | 2021-09-30 |
Family
ID=72003754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/136326 Ceased WO2021189976A1 (zh) | 2020-03-25 | 2020-12-15 | 一种产品信息推送方法、装置、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111553759A (zh) |
| WO (1) | WO2021189976A1 (zh) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114520826A (zh) * | 2021-12-31 | 2022-05-20 | 珠海华发金融科技研究院有限公司 | 跨平台信息匹配方法、装置及云端智能机器人 |
| CN114581196A (zh) * | 2022-03-10 | 2022-06-03 | 广州华多网络科技有限公司 | 商品排序处理方法及其装置、设备、介质、产品 |
| CN114741592A (zh) * | 2022-04-02 | 2022-07-12 | 天元大数据信用管理有限公司 | 一种基于多模型融合的产品推荐方法、设备及介质 |
| CN115017992A (zh) * | 2022-06-10 | 2022-09-06 | Oppo广东移动通信有限公司 | 行为事件的处理方法、服务推送方法、装置和服务器 |
| CN115204984A (zh) * | 2022-07-25 | 2022-10-18 | 中国工商银行股份有限公司 | 业务产品推送方法、装置、计算机设备和存储介质 |
| CN115238189A (zh) * | 2022-08-10 | 2022-10-25 | 平安科技(深圳)有限公司 | 基于多元数据融合的精准推荐方法、装置、设备及介质 |
| CN115293130A (zh) * | 2022-08-09 | 2022-11-04 | 中国平安人寿保险股份有限公司 | 金融数据监控方法、装置、设备及介质 |
| CN115438802A (zh) * | 2022-09-28 | 2022-12-06 | 微梦创科网络科技(中国)有限公司 | 信息处理方法、装置、计算机设备及存储介质 |
| CN115982425A (zh) * | 2022-12-14 | 2023-04-18 | 达观数据(苏州)有限公司 | 推荐模型训练、推荐方法、装置、电子设备及存储介质 |
| CN116089745A (zh) * | 2021-11-01 | 2023-05-09 | 腾讯科技(深圳)有限公司 | 信息推荐方法、装置、电子设备及计算机可读存储介质 |
| CN116467521A (zh) * | 2023-04-25 | 2023-07-21 | 中国工商银行股份有限公司 | 账户推荐模型的训练方法、账户推荐方法、装置和设备 |
| CN116662556A (zh) * | 2023-08-02 | 2023-08-29 | 天河超级计算淮海分中心 | 一种融合用户属性的文本数据处理方法 |
| WO2023241207A1 (zh) * | 2022-06-13 | 2023-12-21 | 腾讯科技(深圳)有限公司 | 一种数据处理方法、装置、设备、计算机可读存储介质及计算机程序产品 |
| CN117609620A (zh) * | 2023-11-29 | 2024-02-27 | 广州方舟信息科技有限公司 | 一种医药商品信息推送方法、装置、电子设备和存储介质 |
| CN117952724A (zh) * | 2024-03-21 | 2024-04-30 | 烟台大学 | 基于知识图谱和神经网络的物品推荐方法、系统和设备 |
| CN118035859A (zh) * | 2024-04-15 | 2024-05-14 | 普益智慧云科技(成都)有限公司 | 一种用户画像构建方法、系统、计算机设备和存储介质 |
| CN118484602A (zh) * | 2024-06-13 | 2024-08-13 | 上海极豆新能源科技有限公司 | 推荐方法、装置、车辆和计算机可读存储介质 |
| CN118521343A (zh) * | 2024-07-24 | 2024-08-20 | 支付宝(杭州)信息技术有限公司 | 转化预测模型训练方法及装置 |
| CN119624584A (zh) * | 2024-12-02 | 2025-03-14 | 中国平安人寿保险股份有限公司 | 产品推荐方法和装置、电子设备及存储介质 |
| CN120494905A (zh) * | 2025-04-29 | 2025-08-15 | 智睿互动网络技术(北京)有限公司 | 一种基于大数据的数字化营销系统 |
Families Citing this family (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111553759A (zh) * | 2020-03-25 | 2020-08-18 | 平安科技(深圳)有限公司 | 一种产品信息推送方法、装置、设备及存储介质 |
| CN112231550B (zh) * | 2020-09-11 | 2024-05-17 | 重庆誉存大数据科技有限公司 | 一种信贷金融产品推荐处理方法及装置 |
| CN112163963B (zh) * | 2020-09-27 | 2024-04-02 | 中国平安财产保险股份有限公司 | 业务推荐方法、装置、计算机设备和存储介质 |
| CN113781139B (zh) * | 2020-10-19 | 2024-08-20 | 北京沃东天骏信息技术有限公司 | 物品推荐方法、物品推荐装置、设备和介质 |
| CN112163165B (zh) * | 2020-10-21 | 2024-05-17 | 腾讯科技(深圳)有限公司 | 信息推荐方法、装置、设备及计算机可读存储介质 |
| CN112307341A (zh) * | 2020-11-02 | 2021-02-02 | 沈阳民航东北凯亚有限公司 | 航班推送方法及装置 |
| CN112417760B (zh) * | 2020-11-20 | 2023-01-17 | 哈尔滨工程大学 | 基于竞争混合网络的舰船控制方法 |
| CN112765482B (zh) * | 2020-12-23 | 2026-03-10 | 微民保险代理有限公司 | 产品投放方法、装置、设备及计算机可读介质 |
| CN114926192A (zh) * | 2021-02-01 | 2022-08-19 | 腾讯科技(深圳)有限公司 | 一种信息处理方法、装置及计算机可读存储介质 |
| CN112949824A (zh) * | 2021-02-07 | 2021-06-11 | 北京淇瑀信息科技有限公司 | 一种基于神经网络的多输出多任务特征评估方法、装置和电子设备 |
| CN112990584B (zh) * | 2021-03-19 | 2022-08-02 | 山东大学 | 一种基于深度强化学习的自动生产决策系统及方法 |
| CN113159201B (zh) * | 2021-04-28 | 2023-04-25 | 上海德衡数据科技有限公司 | 基于云边缘计算智能融合信息的方法、装置及云端服务器 |
| CN113159927A (zh) * | 2021-04-30 | 2021-07-23 | 中国银行股份有限公司 | 一种客户标签的确定方法及装置 |
| CN113298121B (zh) * | 2021-04-30 | 2023-08-18 | 上海淇玥信息技术有限公司 | 基于多数据源建模的消息发送方法、装置和电子设备 |
| CN113298661B (zh) * | 2021-07-28 | 2021-11-05 | 北京芯盾时代科技有限公司 | 一种基于人工智能的产品推荐方法、装置及电子设备 |
| CN113672803B (zh) * | 2021-08-02 | 2025-01-28 | 杭州网易云音乐科技有限公司 | 推荐方法、装置、计算设备及存储介质 |
| CN113610580B (zh) * | 2021-08-10 | 2023-09-19 | 平安科技(深圳)有限公司 | 产品推荐方法、装置、电子设备及可读存储介质 |
| CN115935047B (zh) * | 2021-08-19 | 2026-02-10 | 腾讯科技(深圳)有限公司 | 内容推送方法、装置及存储介质 |
| CN115905680A (zh) * | 2021-09-29 | 2023-04-04 | 华为技术有限公司 | 一种推荐方法及相关装置 |
| CN113946763B (zh) * | 2021-10-25 | 2025-08-19 | 北京爱奇艺科技有限公司 | 一种推荐信息排序方法、装置、电子设备及介质 |
| CN113868542B (zh) * | 2021-11-25 | 2022-03-11 | 平安科技(深圳)有限公司 | 基于注意力模型的推送数据获取方法、装置、设备及介质 |
| CN114565432A (zh) * | 2022-02-28 | 2022-05-31 | 广东技术师范大学 | 一种基于图嵌入方式的用户个性化产品推荐方法及系统 |
| CN114969521B (zh) * | 2022-05-16 | 2025-11-14 | 深圳市欢太科技有限公司 | 对象推荐模型的训练方法、推荐方法、装置及电子设备 |
| CN115034847A (zh) * | 2022-05-25 | 2022-09-09 | 山东大学 | 基于深度学习的产品推荐方法、系统、存储介质及设备 |
| CN114971866A (zh) * | 2022-06-07 | 2022-08-30 | 平安银行股份有限公司 | 基于人工智能的授信额度管控方法、装置、设备及介质 |
| CN115238193A (zh) * | 2022-08-22 | 2022-10-25 | 中国国际金融股份有限公司 | 金融产品推荐方法和装置、计算设备以及计算机存储介质 |
| CN115470413A (zh) * | 2022-10-18 | 2022-12-13 | 中国工商银行股份有限公司 | 推荐对象的确定方法、装置及计算机可读存储介质 |
| CN116719993B (zh) * | 2023-05-31 | 2026-03-24 | 上海期智研究院 | 一种基于存内处理的个性化推荐系统 |
| CN118761825B (zh) * | 2024-09-05 | 2024-11-15 | 中免日上互联科技有限公司 | 一种推荐系统的神经网络模型数据处理方法和装置 |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140651A (zh) * | 2006-09-04 | 2008-03-12 | 腾讯科技(深圳)有限公司 | 一种展示对象的排序方法及系统 |
| CN101551825A (zh) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | 基于属性描述的个性化影片推荐系统及方法 |
| US20180158078A1 (en) * | 2016-12-05 | 2018-06-07 | Institute For Information Industry | Computer device and method for predicting market demand of commodities |
| CN108985830A (zh) * | 2018-07-05 | 2018-12-11 | 北京邮电大学 | 基于异质信息网络的推荐评分方法、装置 |
| CN109710768A (zh) * | 2019-01-10 | 2019-05-03 | 西安交通大学 | 一种基于mimo递归神经网络的纳税人行业两层级分类方法 |
| CN109977151A (zh) * | 2019-03-28 | 2019-07-05 | 北京九章云极科技有限公司 | 一种数据分析方法及系统 |
| CN110119477A (zh) * | 2019-05-14 | 2019-08-13 | 腾讯科技(深圳)有限公司 | 一种信息推送方法、装置和存储介质 |
| CN111553759A (zh) * | 2020-03-25 | 2020-08-18 | 平安科技(深圳)有限公司 | 一种产品信息推送方法、装置、设备及存储介质 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263821B (zh) * | 2019-05-29 | 2020-08-14 | 阿里巴巴集团控股有限公司 | 交易特征生成模型的训练、交易特征的生成方法和装置 |
| CN110458649B (zh) * | 2019-07-11 | 2025-06-27 | 北京三快在线科技有限公司 | 信息推荐方法、装置、电子设备及可读存储介质 |
| CN110888911A (zh) * | 2019-10-11 | 2020-03-17 | 平安科技(深圳)有限公司 | 样本数据处理方法、装置、计算机设备及存储介质 |
-
2020
- 2020-03-25 CN CN202010220066.7A patent/CN111553759A/zh active Pending
- 2020-12-15 WO PCT/CN2020/136326 patent/WO2021189976A1/zh not_active Ceased
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101140651A (zh) * | 2006-09-04 | 2008-03-12 | 腾讯科技(深圳)有限公司 | 一种展示对象的排序方法及系统 |
| CN101551825A (zh) * | 2009-05-15 | 2009-10-07 | 中国科学技术大学 | 基于属性描述的个性化影片推荐系统及方法 |
| US20180158078A1 (en) * | 2016-12-05 | 2018-06-07 | Institute For Information Industry | Computer device and method for predicting market demand of commodities |
| CN108985830A (zh) * | 2018-07-05 | 2018-12-11 | 北京邮电大学 | 基于异质信息网络的推荐评分方法、装置 |
| CN109710768A (zh) * | 2019-01-10 | 2019-05-03 | 西安交通大学 | 一种基于mimo递归神经网络的纳税人行业两层级分类方法 |
| CN109977151A (zh) * | 2019-03-28 | 2019-07-05 | 北京九章云极科技有限公司 | 一种数据分析方法及系统 |
| CN110119477A (zh) * | 2019-05-14 | 2019-08-13 | 腾讯科技(深圳)有限公司 | 一种信息推送方法、装置和存储介质 |
| CN111553759A (zh) * | 2020-03-25 | 2020-08-18 | 平安科技(深圳)有限公司 | 一种产品信息推送方法、装置、设备及存储介质 |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116089745B (zh) * | 2021-11-01 | 2025-12-12 | 腾讯科技(深圳)有限公司 | 信息推荐方法、装置、电子设备及计算机可读存储介质 |
| CN116089745A (zh) * | 2021-11-01 | 2023-05-09 | 腾讯科技(深圳)有限公司 | 信息推荐方法、装置、电子设备及计算机可读存储介质 |
| CN114520826B (zh) * | 2021-12-31 | 2024-04-05 | 珠海华发金融科技研究院有限公司 | 跨平台信息匹配方法、装置及云端智能机器人 |
| CN114520826A (zh) * | 2021-12-31 | 2022-05-20 | 珠海华发金融科技研究院有限公司 | 跨平台信息匹配方法、装置及云端智能机器人 |
| CN114581196A (zh) * | 2022-03-10 | 2022-06-03 | 广州华多网络科技有限公司 | 商品排序处理方法及其装置、设备、介质、产品 |
| CN114741592A (zh) * | 2022-04-02 | 2022-07-12 | 天元大数据信用管理有限公司 | 一种基于多模型融合的产品推荐方法、设备及介质 |
| CN114741592B (zh) * | 2022-04-02 | 2024-09-20 | 天元大数据信用管理有限公司 | 一种基于多模型融合的产品推荐方法、设备及介质 |
| CN115017992A (zh) * | 2022-06-10 | 2022-09-06 | Oppo广东移动通信有限公司 | 行为事件的处理方法、服务推送方法、装置和服务器 |
| CN115017992B (zh) * | 2022-06-10 | 2025-08-01 | Oppo广东移动通信有限公司 | 行为事件的处理方法、服务推送方法、装置和服务器 |
| WO2023241207A1 (zh) * | 2022-06-13 | 2023-12-21 | 腾讯科技(深圳)有限公司 | 一种数据处理方法、装置、设备、计算机可读存储介质及计算机程序产品 |
| CN115204984A (zh) * | 2022-07-25 | 2022-10-18 | 中国工商银行股份有限公司 | 业务产品推送方法、装置、计算机设备和存储介质 |
| CN115293130A (zh) * | 2022-08-09 | 2022-11-04 | 中国平安人寿保险股份有限公司 | 金融数据监控方法、装置、设备及介质 |
| CN115238189A (zh) * | 2022-08-10 | 2022-10-25 | 平安科技(深圳)有限公司 | 基于多元数据融合的精准推荐方法、装置、设备及介质 |
| CN115238189B (zh) * | 2022-08-10 | 2025-04-29 | 平安科技(深圳)有限公司 | 基于多元数据融合的精准推荐方法、装置、设备及介质 |
| CN115438802A (zh) * | 2022-09-28 | 2022-12-06 | 微梦创科网络科技(中国)有限公司 | 信息处理方法、装置、计算机设备及存储介质 |
| CN115982425A (zh) * | 2022-12-14 | 2023-04-18 | 达观数据(苏州)有限公司 | 推荐模型训练、推荐方法、装置、电子设备及存储介质 |
| CN116467521A (zh) * | 2023-04-25 | 2023-07-21 | 中国工商银行股份有限公司 | 账户推荐模型的训练方法、账户推荐方法、装置和设备 |
| CN116662556B (zh) * | 2023-08-02 | 2023-10-20 | 天河超级计算淮海分中心 | 一种融合用户属性的文本数据处理方法 |
| CN116662556A (zh) * | 2023-08-02 | 2023-08-29 | 天河超级计算淮海分中心 | 一种融合用户属性的文本数据处理方法 |
| CN117609620A (zh) * | 2023-11-29 | 2024-02-27 | 广州方舟信息科技有限公司 | 一种医药商品信息推送方法、装置、电子设备和存储介质 |
| CN117952724A (zh) * | 2024-03-21 | 2024-04-30 | 烟台大学 | 基于知识图谱和神经网络的物品推荐方法、系统和设备 |
| CN118035859B (zh) * | 2024-04-15 | 2024-06-11 | 普益智慧云科技(成都)有限公司 | 一种用户画像构建方法、系统、计算机设备和存储介质 |
| CN118035859A (zh) * | 2024-04-15 | 2024-05-14 | 普益智慧云科技(成都)有限公司 | 一种用户画像构建方法、系统、计算机设备和存储介质 |
| CN118484602A (zh) * | 2024-06-13 | 2024-08-13 | 上海极豆新能源科技有限公司 | 推荐方法、装置、车辆和计算机可读存储介质 |
| CN118521343A (zh) * | 2024-07-24 | 2024-08-20 | 支付宝(杭州)信息技术有限公司 | 转化预测模型训练方法及装置 |
| CN119624584A (zh) * | 2024-12-02 | 2025-03-14 | 中国平安人寿保险股份有限公司 | 产品推荐方法和装置、电子设备及存储介质 |
| CN120494905A (zh) * | 2025-04-29 | 2025-08-15 | 智睿互动网络技术(北京)有限公司 | 一种基于大数据的数字化营销系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553759A (zh) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021189976A1 (zh) | 一种产品信息推送方法、装置、设备及存储介质 | |
| Ala’raj et al. | Modelling customers credit card behaviour using bidirectional LSTM neural networks | |
| CN108133418A (zh) | 实时信用风险管理系统 | |
| US11921821B2 (en) | System and method for labelling data for trigger identification | |
| CN111062444A (zh) | 信用风险预测方法、系统、终端及存储介质 | |
| US11144938B2 (en) | Method and system for predictive modeling of consumer profiles | |
| US20210356920A1 (en) | Information processing apparatus, information processing method, and program | |
| CN118014693A (zh) | 会员商品推送方法、装置、系统、电子设备及存储介质 | |
| CN117291633A (zh) | 基于动态模型配置的企业生产运营管理系统及其方法 | |
| CN116029760A (zh) | 消息推送方法、装置、计算机设备和存储介质 | |
| US20250022055A1 (en) | Systems and methods for data monitoring | |
| US11586520B2 (en) | Automated data linkages across datasets | |
| CA3196321A1 (en) | A computer-implemented method for deriving a data processing and inference pipeline | |
| CN113111957A (zh) | 基于特征去噪的防伪方法、装置、设备、产品及介质 | |
| Louati et al. | Embedding channel pruning within the CNN architecture design using a bi-level evolutionary approach: H. Louati et al. | |
| US20240185369A1 (en) | Biasing machine learning model outputs | |
| US12406183B2 (en) | Accelerated model training from disparate and heterogeneous sources using a meta-database | |
| CN115222119A (zh) | 一种银行账号存款预测方法 | |
| CN115345248A (zh) | 一种面向深度学习的数据去偏方法及装置 | |
| Harikrishna et al. | Credit scoring using support vector machine: a comparative analysis | |
| HK40032024A (zh) | 一种产品信息推送方法、装置、设备及存储介质 | |
| CN112052903A (zh) | 多标签处理任务训练样本构建方法、设备及介质 | |
| US20250117688A1 (en) | Bootstrapped simulated data for model simulation and selection | |
| US20230359704A1 (en) | Centralized repository and data sharing hub for establishing model sufficiency | |
| US20230401416A1 (en) | Leveraging multiple disparate machine learning model data outputs to generate recommendations for the next best action |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20927287 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20927287 Country of ref document: EP Kind code of ref document: A1 |