CN110737834A - Business object recommendation method and device, storage medium and computer equipment - Google Patents
Business object recommendation method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN110737834A CN110737834A CN201910973183.8A CN201910973183A CN110737834A CN 110737834 A CN110737834 A CN 110737834A CN 201910973183 A CN201910973183 A CN 201910973183A CN 110737834 A CN110737834 A CN 110737834A
- Authority
- CN
- China
- Prior art keywords
- text
- business
- target
- objects
- service
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 239000013598 vector Substances 0.000 claims abstract description 262
- 238000012549 training Methods 0.000 claims abstract description 24
- 230000001960 triggered effect Effects 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 25
- 238000011176 pooling Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 13
- 239000000284 extract Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000009467 reduction Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 235000021419 vinegar Nutrition 0.000 description 5
- 239000000052 vinegar Substances 0.000 description 5
- 230000004913 activation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 235000011194 food seasoning agent Nutrition 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a service object recommendation method, a device, a storage medium and computer equipment, wherein the method comprises the steps of obtaining a text vector of a triggered target service object, obtaining text vectors of other service objects except the target service object, determining the text vectors of the target service object and the other service objects according to an object type recognition model obtained through training, determining a service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputting the service object to be recommended.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a storage medium, and a computer device for recommending service objects.
Background
In the conventional internet technology, a website publishes a business object for a user who logs in the website to search and browse, and performs subsequent processing operations with respect to a specific business object. Taking a shopping website as an example, a business object is a commodity issued by a seller, and a user logging in the shopping website searches and browses the commodity, collects and purchases interested commodities, and the like; taking news websites as an example, the business objects are news published by publishers, users who log in the news websites search and browse the news, and comment and forward interested news.
When a user searches or browses business objects, the website can recommend business objects that the user may be interested in to the user, so that the user can quickly find out the business objects needed by the user from the recommended business objects, for example, a shopping website can push commodities similar to the commodities searched or browsed by the user, an information website can push news similar to the news searched or browsed by the user, a resource website such as video, music, books and the like can push resources similar to the resources searched or browsed by the user, a social account similar to the social account searched or browsed by the user and Feed stream information similar to the Feed stream information searched or browsed by the user, and the like.
Disclosure of Invention
Based on this, it is necessary to provide service object recommendation methods, apparatuses, storage media, and computer devices for solving the problem that the operation process of the conventional service object recommendation method is complicated.
A method for recommending business objects, the method comprising:
acquiring a text vector of a triggered target service object;
acquiring text vectors of other business objects except the target business object, wherein the text vectors of the business objects are determined according to an object class identification model obtained by training, and the business objects comprise the target business object and the other business objects;
and determining a service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputting the service object to be recommended.
apparatus for recommending business objects, the apparatus comprising:
the acquisition module is used for acquiring the text vector of the triggered target business object;
the acquiring module is further configured to acquire text vectors of other business objects except the target business object, where the text vectors of the business objects are determined according to an object class identification model obtained through training, and the business objects include the target business object and the other business objects;
and the determining module is used for determining the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects and outputting the service object to be recommended.
storage medium having stored thereon computer-executable instructions that, when executed by a processor, cause the processor to perform the steps of a method for recommending business objects.
computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which, when executed by the processor, cause the processor to perform the steps of a method of recommending business objects.
The method, the device, the storage medium and the computer equipment for recommending the business objects acquire the text vectors of the triggered target business objects, acquire the text vectors of other business objects except the target business objects, determine the business objects to be recommended according to the text vectors of the target business objects and the text vectors of the other business objects, and output the business objects to be recommended, wherein the text vectors of the target business objects and the other business objects are determined according to the trained object type identification model.
Drawings
Fig. 1 is an internal structural diagram of a terminal for implementing a recommendation method for a service object in embodiments;
FIG. 2 is a flow chart illustrating a method for recommending business objects in embodiments;
FIG. 3 is a block diagram of the structure of an object class identification model in embodiments;
FIG. 4 is a block diagram of the structure of an object class identification model in another embodiments;
FIG. 5 is a block diagram of the structure of an object class identification model in still another embodiments;
FIG. 6 is a diagram illustrating the result of recommending business objects in embodiments;
FIG. 7 is a schematic diagram of the function of the embedded layer in embodiments;
FIG. 8 is a schematic diagram of the operation of convolutional layers in an embodiment;
FIG. 9 is a schematic representation of the function of the pooling layer in the examples;
FIG. 10 is a flow chart illustrating a method for recommending business objects in another embodiments;
FIG. 11 is a flowchart illustrating a method for recommending business objects in further embodiments;
FIG. 12 is a block diagram showing the structure of a service object recommendation apparatus in embodiments;
FIG. 13 is a block diagram of a recommendation device for business objects in another embodiments;
fig. 14 is an internal structural view of a computer device in embodiments.
Detailed Description
For purposes of making the present application more readily apparent, the technical solutions and advantages thereof, reference is now made to the following detailed description taken in conjunction with the accompanying drawings and examples, it being understood that the specific examples described herein are for purposes of illustration only and are not intended to limit the application.
Fig. 1 is a schematic diagram of an internal structure of an embodiments of a terminal, as shown in fig. 1, the terminal includes a processor, a nonvolatile storage medium, an internal memory, a network interface, a display screen, and an input device, which are connected through a system bus, where the nonvolatile storage medium of the terminal stores an operating system, and further stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor can implement a method for recommending service objects.
Those skilled in the art will appreciate that the configuration shown in fig. 1 is a block diagram of only a portion of the configuration relevant to the present application, and does not constitute a limitation on the terminal to which the present application is applied, and that a particular terminal may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
As shown in FIG. 2, in embodiments, business object recommendation methods are provided.
Referring to fig. 2, this embodiment mainly exemplifies that the method is applied to the terminal in fig. 1, and the method for recommending a service object specifically includes the following steps:
s202, acquiring the text vector of the triggered target business object.
The business objects can be commodities on the shelves of shopping websites, news published by information websites, videos published by video websites, music on the shelves of music websites, books uploaded by book websites, account numbers of social networking websites, Feed streams and the like.
The text vector is text information representing the business object in a vector mode, and the vector used for representing can be a low-dimensional vector. The text information is information related to the business object, such as a title, a keyword, a brief summary, a summary, etc. of the business object. The text vectors can represent the distance of the relationship between the service objects, and the closer the relationship between the service objects is, the smaller the vector distance between the corresponding text vectors is. Taking a business object as a commodity as an example, the vector distance between the text vector of the skirt and the text vector of the trousers is closer than the vector distance between the text vector of the skirt and the text vector of the necklace.
Specifically, a text vector of the target business object is determined according to the trained object class identification model. The object type identification model can identify the type of the business object, in the identification process, the object type identification model generates a text vector of text information of the business object first, and then determines the type of the business object according to the text vector of the business object, so that the text vector of the business object can reflect the relation between the business objects. And testing the trained object type recognition model, wherein the classification accuracy of the object type recognition model to the text information of the business object can reach 92%, which shows that the text vector of the business object determined according to the object type recognition model can accurately represent the semantics of the text information of the business object.
The category of the business object can be characterized by the characteristics of the kind, source and the like of the business object.
The types of the business objects are types which are divided according to the properties of the business objects, the types can comprise snacks, drinks, beverages, grain and oil, subsidiary food, clothes, personal care, household kitchenware, household cleaning, toys for mother and baby, household electrical appliances, medical care, beauty and skin care, pet life and the like by taking the business objects as commodities, and the types can be divided by the fields of the business objects, such as science and technology, finance, military, sports, entertainment, automobiles, housing property, fashion, education, travel, games and the like by taking account numbers or Feed streams of the business objects as examples.
The source of the business object refers to information related to the generation of the business object. Taking the business object as a commodity, the sources may include: production location, production manufacturer, brand, etc.; taking business objects as news, videos, music, books, account numbers of social network sites or Feed streams as examples, the categories may include: publishers, authors, etc.
In particular, the object class identification model may be a neural network model. As shown in FIG. 3, the object class recognition model may include an input layer, a hidden layer, and an output layer, and the connection between the input layer and the hidden layer is established in sequence, and finally the connection between the hidden layer and the output layer is established.
In embodiments, as shown in fig. 4, the object class recognition model may include an input layer, an embedded layer, a hidden layer, and a classifier, wherein the input layer is configured to receive an input sparse matrix of a business object and send the sparse matrix of the business object to the embedded layer, the embedded layer performs a dimensionality reduction operation on the input sparse matrix of the business object to obtain a dense matrix and send the dense matrix to the hidden layer, the hidden layer extracts a distinctive feature based on the input dense matrix and sends the extracted feature to the classifier, and the classifier calculates a probability that the business object belongs to each class, thereby achieving a classification purpose.
In embodiments, as shown in fig. 5, the hidden layer may include a convolutional layer, a pooling layer, and a full-link layer, where the convolutional layer initially extracts features on the input dense matrix to obtain convolutional feature vectors, the pooling layer performs a dimensionality reduction operation on the convolutional feature vectors output by the convolutional layer and further performs steps to extract features to obtain pooled feature vectors, and the full-link layer merges or samples the feature vectors obtained by processing the convolutional layer and the pooling layer to extract discriminative features.
The object class identification model can be obtained through text information of the sample business object and class training to which the sample business object belongs, and the sample business object refers to a business object used for training the object class identification model. The method comprises the steps of marking text information of a sample business object by the class to which the sample business object belongs, inputting the marked text information of the sample business object into an object class identification model, and training the object class identification model in a back propagation mode to enable the identification result of the object class identification model to approach the mark of the sample business object, so that the object class identification model learns mapping between the text information of the sample business object and the class to which the sample business object belongs.
In embodiments, the method for obtaining the text vector of the target business object corresponding to the user operation behavior may be to obtain a matching relationship between a pre-stored business object and the text vector, and to find the text vector of the target business object corresponding to the user operation behavior according to the matching relationship, where the matching relationship is established according to the business object and the text vector of the business object determined by the object type recognition model.
In another embodiments, the manner of obtaining the text vector of the target service object corresponding to the user operation behavior may be to obtain text information of the target service object corresponding to the user operation behavior, and input the text information of the target service object into the object class identification model to obtain the text vector of the target service object.
S204, obtaining text vectors of other business objects except the target business object, wherein the text vectors of the business objects are determined according to the trained object type recognition model, and the business objects comprise the target business object and the other business objects.
The other business objects refer to objects that are not selected as operation targets by the user operation behavior, for example, goods that are not clicked by the user in the shopping website are the other business objects.
Specifically, text vectors of other business objects are determined according to the trained object class recognition model.
In embodiments, the manner of obtaining the text vector of the other business object corresponding to the user operation behavior may be to obtain a matching relationship between a pre-stored business object and the text vector, and to find the text vector of the other business object corresponding to the user operation behavior according to the matching relationship, where the matching relationship is established according to the business object and the text vector of the business object determined by the object type recognition model.
In another embodiments, the text vectors of other business objects corresponding to the user operation behavior may be obtained by obtaining text information of other business objects corresponding to the user operation behavior, and inputting the text information of other business objects into the object class identification model to obtain text vectors of other business objects, specifically, inputting the text information of other business objects into the object class identification model to obtain text vectors of other business objects output by a preset layer in a hidden layer of the object class identification model, where the preset layer may be any layers in the hidden layer, and optionally, the preset layer is a last -layer fully-connected layer.
S206, determining the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputting the service object to be recommended.
Specifically, the method for determining the service object to be recommended according to the text vector of the target service object and the text vectors of other service objects may be: and acquiring the similarity between the text vector of the target business object and the text vectors of other business objects, and determining the business object to be recommended in the other business objects according to the similarity.
In embodiments, the similarity between the text vector of the target business object and the text vectors of other business objects can be determined by the vector distance between the text vector of the target business object and the text vectors of other business objects.
The vector distance is inversely proportional to the similarity, that is, the smaller the vector distance between the text vector of the target service object and the text vectors of other service objects is, the greater the similarity between the text vector of the target service object and the text vectors of other service objects is. Specifically, the vector distance between the text vector of the target service object and the text vectors of other service objects can be characterized by euclidean distance, cosine similarity, and the like.
In embodiments, the manner of determining the business object to be recommended among other business objects according to the similarity may be to sort the other business objects by using the similarity, and determine the business object to be recommended according to the sorting result.
Specifically, after the similarity between the text vector of the target business object and the text vectors of other business objects is obtained, the text vectors are sorted from large to small according to the similarity, or sorted from small to large according to the similarity. And according to the sequencing result, selecting other service objects with preset quantity according to the sequence of the similarity from big to small, and taking the selected other service objects as the service objects to be recommended.
As shown in fig. 6, taking a business object as an example of a commodity, when a user clicks a target commodity "shanxi mature vinegar", respectively determining a text vector of the target commodity and text vectors of other commodities through an object type identification model, obtaining similarity between the text vector of the target commodity and the text vectors of the other commodities, sorting the other commodities by using the similarity, and selecting ten other commodities in the order of similarity from large to small to recommend the user. As can be seen from fig. 6, the goods recommended to the user are not limited to vinegar, but are recommended in a larger category, namely seasoning, so that the business objects are recommended in the dimension of category, and the recommended business objects have relevance to the target objects.
The method for recommending the service object provided by this embodiment obtains the text vector of the triggered target service object, obtains the text vectors of other service objects except the target service object, determines the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputs the service object to be recommended, wherein the text vectors of the target service object and the other service objects are determined according to the object type recognition model obtained by training.
In embodiments, the obtaining the text vector of the target service object corresponding to the user operation behavior includes obtaining a matching relationship between a pre-stored service object and a text vector, where the matching relationship is established according to the service object and the text vector of the service object determined by the object type identification model, and searching the text vector of the target service object corresponding to the user operation behavior according to the matching relationship.
Specifically, a text vector of a business object is determined in advance through an object type identification model obtained through training, and the business object and the text vector of the business object are stored in an associated mode, so that the text vector of the target business object is directly called according to the target business object during application, and therefore complicated operation processes such as word segmentation operation and word frequency statistics are avoided.
According to the recommendation method for the service object, the text vector of the target service object is searched through the matching relation according to the target service object, so that a complicated operation process is avoided.
In embodiments, the obtaining the text vector of the target service object corresponding to the user operation behavior includes obtaining text information of the target service object corresponding to the user operation behavior, and inputting the text information of the target service object into the object type identification model to obtain the text vector of the target service object.
Specifically, an object class recognition model is obtained through pre-training, and text information of the target business object is input into the object class recognition model, so that a text vector of the target business object can be obtained.
In particular, the object class identification model may be a neural network model. As shown in FIG. 3, the object class recognition model may include an input layer, a hidden layer, and an output layer, and the connection between the input layer and the hidden layer is established in sequence, and finally the connection between the hidden layer and the output layer is established.
In embodiments, as shown in fig. 4, the object class recognition model may include an input layer, an embedded layer, a hidden layer, and a classifier, wherein the input layer is configured to receive an input sparse matrix of a business object and send the sparse matrix of the business object to the embedded layer, the embedded layer performs a dimensionality reduction operation on the input sparse matrix of the business object to obtain a dense matrix and send the dense matrix to the hidden layer, the hidden layer extracts a distinctive feature based on the input dense matrix and sends the extracted feature to the classifier, and the classifier calculates a probability that the business object belongs to each class, thereby achieving a classification purpose.
In embodiments, as shown in fig. 5, the hidden layer may include a convolutional layer, a pooling layer, and a full-link layer, where the convolutional layer initially extracts features on the input dense matrix to obtain convolutional feature vectors, the pooling layer performs a dimensionality reduction operation on the convolutional feature vectors output by the convolutional layer and further performs steps to extract features to obtain pooled feature vectors, and the full-link layer merges or samples the feature vectors obtained by processing the convolutional layer and the pooling layer to extract discriminative features.
The text information of the target business object is input into the object type identification model, and a text vector of the target business object output by a preset layer in a hidden layer of the object type identification model is obtained, wherein the preset layer can be any layer in the hidden layer, and optionally, the preset layer is a last full-connection layer.
According to the service object recommendation method provided by the embodiment, the text information of the target service object is input into the object type identification model, so that the text vector of the target service object can be obtained, and a complicated operation process is avoided.
In embodiments, the object type identification model includes a hidden layer, and the inputting the text information of the target business object into the object type identification model to obtain the text vector of the target business object includes inputting the text information of the target business object into the object type identification model to obtain the text vector of the target business object output by a preset layer in the hidden layer.
Before inputting the text information of the business object into the object type identification model, the text information of the business object needs to be preprocessed, namely, the numerical representation of the text information of the business object is obtained, so that the text information of the business object is converted into a language which can be understood by a computer. The numerical representation of the textual information of the business object may be determined by means of a pre-constructed mapping table.
Before training the object type recognition model, collecting text information of sample business objects, splitting each word in the text information of all the sample business objects into a set, and performing deduplication operation on repeated words in the set, respectively giving identification marks to each word in the set, and storing each word in association with the corresponding identification mark to obtain a mapping table between the words and the identification marks, wherein in embodiments, the identification marks can be integer values, such as 0, 1, 2 and the like, for example, seven words in the set, namely, a surface, a bar, a square, a convenience, a surface, a woman and a package, and the mapping table can be { surface: 0, bar: 1, square: 2, convenience: 3, surface: 4, woman: 5 and package: 6 }.
The sparse matrix can be in the form of A × B, wherein A is the total number of words in a set, B is the dimensionality of a vector corresponding to the words, and the dimensionality of the vector can be set according to practical application, such as 32, 64, 128, 256 and the like.
In particular, the object class identification model may be a neural network model. As shown in FIG. 3, the object class recognition model may include an input layer, a hidden layer, and an output layer, and the connection between the input layer and the hidden layer is established in sequence, and finally the connection between the hidden layer and the output layer is established.
In embodiments, as shown in FIG. 4, the object class recognition model may include an input layer, an embedding layer, a hidden layer, and a classifier, where the classifier implements an output function.
Specifically, the input layer is configured to receive an input sparse matrix of the business object and send the sparse matrix of the business object to the embedding layer.
The embedded layer maps the vectors of the sparse matrix corresponding to each word of the text information of the business object into the short vectors with fixed length, and specifically maps all the words in the text information of the business object into dense matrices.
And selecting an activation function for each node of the hidden layer, wherein the activation function is a function which is enhanced by steps after summing the inputs of each path, and the activation function is ReLU, Tanh or Sigmoid.
The classifier calculates the probability that the business object belongs to each category, thereby achieving the purpose of classification.
In embodiments, the hidden layer can include convolutional layer, pooling layer and full-link layer, wherein the number of convolutional layer, pooling layer and full-link layer can be set according to the practical application, and in embodiments, as shown in fig. 5, convolutional layers, pooling layers and two full-link layers are selected.
Specifically, the convolutional layer preliminarily extracts features on an input dense matrix to obtain convolutional feature vectors, the pooling layer performs dimensionality reduction on the convolutional feature vectors output by the convolutional layer and further performs steps to extract the features to obtain pooling feature vectors, and the full-link layer merges or samples the feature vectors obtained by processing the convolutional layer and the pooling layer to extract distinctive features.
The text information of the target business object is input into the object type identification model, and a text vector of the target business object output by a preset layer in a hidden layer of the object type identification model is obtained, wherein the preset layer can be any layer in the hidden layer, and optionally, the preset layer is a last full-connection layer.
In the method for recommending a service object provided by this embodiment, the object class identification model extracts the features of the target service object layer by layer, so that the text vector of the target service object obtained by the object class identification model fully considers the class to which the service object belongs and the semantics of the text information thereof.
In embodiments, the hidden layer includes a full-connection layer, and the inputting the text information of the target business object into the object class recognition model to obtain the text vector of the target business object output by a preset layer in the hidden layer includes inputting the text information of the target business object into the object class recognition model to obtain the text vector of the target business object output by the last full-connection layer in the hidden layer.
As shown in FIG. 8, the extraction method of the convolutional layer is to slide the feature detector in small regions and small regions on the input dense matrix, and calculate the dot product by using the feature detector to obtain the convolutional feature vector.
The feature detector is a matrix vector of m × n, and the values of m and n can be set according to practical application. For the same dense matrix, feature detectors of different m × n will generate different convolution feature vectors. The more feature detectors that are used, the more features the convolutional layer extracts. The convolution feature vector is controlled by three parameters: depth (depth), step size (stride), and zero-padding (zero-padding). The depth refers to the number of feature detectors used in convolution operation, the step size refers to the number of vectors passed by the feature detectors in the sliding direction during each sliding, and the zero padding refers to padding with zero values at the edges of the input dense matrix, so that the edges of the input dense matrix can be filtered.
The pooling layer performs dimension reduction on the convolution feature vectors output by the convolutional layer, and further steps of feature extraction to obtain pooled feature vectors, the pooling can be realized by maximum pooling, average pooling, addition pooling and the like, as shown in fig. 9, the pooling layer reduces the convolution feature vectors and simplifies the calculation complexity, and in addition steps of feature extraction are performed based on the convolution feature vectors .
The fully connected layer combines or samples the feature vectors obtained by processing the convolutional layer and the pooling layer to extract distinctive features, the neurons between the layers of the fully connected layer are connected in a fully connected mode, and at least fully connected layers are included in the object type identification model.
Specifically, the text information of the target service object is input into the object type identification model, a text vector output by the last full-link layer of the object type identification model is obtained, and the text vector is used as the text vector of the target service object.
In the method for recommending a service object provided by this embodiment, the object class identification model extracts the features of the target service object layer by layer, so that the text vector of the target service object obtained by the object class identification model fully considers the class to which the service object belongs and the semantics of the text information thereof.
In embodiments, the determining a service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects includes obtaining similarity between the text vector of the target service object and the text vectors of the other service objects, and determining the service object to be recommended in the other service objects according to the similarity.
Specifically, the business object to be recommended can be determined in other business objects through the similarity between the text vector of the target business object and the text vectors of other business objects.
In embodiments, the similarity between the text vector of the target business object and the text vectors of other business objects can be characterized by the vector distance between the text vector of the target business object and the text vectors of other business objects.
According to the method for recommending the service object, the service object to be recommended is determined in other service objects according to the similarity between the text vector of the target service object and the text vectors of other service objects, and the accuracy of recommending the service object is improved.
In embodiments, the obtaining the similarity between the text vector of the target business object and the text vectors of the other business objects includes obtaining a vector distance between the text vector of the target business object and the text vectors of the other business objects, and characterizing the similarity between the text vector of the target business object and the text vectors of the other business objects by using the vector distance.
The vector distance is inversely proportional to the similarity, that is, the smaller the vector distance between the text vector of the target service object and the text vectors of other service objects is, the greater the similarity between the text vector of the target service object and the text vectors of other service objects is.
Specifically, the vector distance between the text vector of the target service object and the text vectors of other service objects can be characterized by euclidean distance, cosine similarity, and the like. The Euclidean distance can be used for measuring the absolute distance between two individuals in the vector space, and the cosine similarity measures the difference between the two individuals by using the cosine value of the included angle between the two vectors in the vector space.
According to the service object recommendation method provided by the embodiment, the similarity between the text vector of the target service object and the text vectors of other service objects is represented by the vector distance, so that the accuracy of service object recommendation is improved.
In embodiments, the determining the to-be-recommended service object among the other service objects according to the similarity includes sorting the other service objects by using the similarity, and determining the to-be-recommended service object according to a sorting result.
Specifically, after the similarity between the text vector of the target business object and the text vectors of other business objects is obtained, the text vectors are sorted from large to small according to the similarity, or sorted from small to large according to the similarity.
The method for recommending the business object provided by this embodiment ranks other business objects by using the similarity, so as to accurately select the recommended business object.
In embodiments, the determining the service objects to be recommended according to the sorting result includes selecting a preset number of the other service objects according to the sorting result, and taking the selected other service objects as the service objects to be recommended, wherein the preset number of the other service objects is in a descending order of the similarity.
The preset number can be set according to practical application, such as 5, 8, 10, and the like.
As shown in fig. 6, taking the business object as an example of a commodity, when the user clicks the target commodity "shanxi mature vinegar", 10 other commodities are selected in the order of similarity from large to small and recommended to the user.
In the method for recommending a service object provided in this embodiment, a preset number of other service objects are selected as service objects to be recommended according to the sequence of similarity from large to small, so as to accurately select the recommended service object.
In embodiments, the training method of the object class identification model includes obtaining text information of a sample business object and a class to which the sample business object belongs, and training the object class identification model in a back propagation manner according to the text information of the sample business object and the class to which the sample business object belongs.
The selection range of the sample business object is , and taking the business object as a commodity as an example, the sample business object can be commodities of all shopping websites on the market.
The object class identification model can be obtained through text information of the sample business object and class training of the sample business object. The text information of the sample business object is marked by the category to which the sample business object belongs, and the marked text information of the sample business object is input into the object category identification model, so that the identification result of the object category identification model approaches the mark of the sample business object, and the object category identification model learns the mapping between the text information of the sample business object and the category to which the sample business object belongs.
Specifically, training the object class recognition model in a back propagation manner includes: when the probability that the sample business object belongs to each category is obtained, comparing the probability with the mark of the sample business object to obtain an error; calculating the gradient of the error according to the weight of the object class identification model by using a back propagation algorithm; and updating the parameters of the object class identification model by using a gradient descent algorithm so as to minimize the error of the output of the object class identification model. The parameters of the object class identification model may include the weight of each junction, the deviation value of each node itself, and the value of the matrix vector of the feature detector.
According to the recommendation method for the business object provided by the embodiment, the object class identification model is trained in a back propagation mode according to the text information of the sample business object and the class to which the sample business object belongs, so that the object class identification model can more accurately understand the class to which the business object belongs and the semantics of the text information of the business object.
As shown in fig. 10, in specific embodiments, the method for recommending a business object includes the following steps:
s1002, inputting the triggered text information of the target business object into the trained object type recognition model to obtain a text vector of the target business object output by the last layers of full connection layers of the object type recognition model;
s1004, inputting text information of other business objects except the target business object into the object type identification model to obtain text vectors of the other business objects output by the last layers of full connection layers of the object type identification model;
s1006, obtaining a vector distance between the text vector of the target service object and the text vectors of the other service objects, and representing similarity between the text vector of the target service object and the text vectors of the other service objects by using the vector distance;
s1008, sorting the other business objects by using the similarity, selecting a preset number of the other business objects according to the sequence of the similarity from big to small, and taking the selected other business objects as business objects to be recommended;
and S1010, outputting the service object to be recommended.
The method for recommending the service object provided by this embodiment obtains the text vector of the triggered target service object, obtains the text vectors of other service objects except the target service object, determines the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputs the service object to be recommended, wherein the text vectors of the target service object and the other service objects are determined according to the object type recognition model obtained by training.
As shown in fig. 11, in specific embodiments, the method for recommending a business object includes the following steps:
s1102, inputting the triggered title of the target commodity into the trained object type identification model to obtain the text vector of the target commodity output by the last layers of full connection layers of the object type identification model;
s1104, inputting titles of other commodities except the target commodity into the object type identification model to obtain text vectors of the other commodities output by a last layer full-link layer of the object type identification model;
s1106, obtaining the vector distance between the text vector of the target commodity and the text vectors of the other commodities, and representing the similarity between the text vector of the target commodity and the text vectors of the other commodities by using the vector distance;
s1108, the similarity is used for sorting the other commodities, ten other commodities are selected according to the sequence of the similarity from big to small, and the selected ten other commodities are used as commodities to be recommended;
and S1111, outputting the to-be-recommended commodity.
As shown in fig. 6, when the user clicks the target commodity "shanxi mature vinegar", the text vector of the target commodity and the text vectors of other commodities are respectively determined through the object type identification model, the similarity between the text vector of the target commodity and the text vectors of other commodities is obtained, the other commodities are sorted by using the similarity, and ten other commodities are selected according to the sequence of the similarity from large to small and recommended to the user. As can be seen from fig. 6, the goods recommended to the user are not limited to vinegar, but are recommended in a larger category, namely seasoning, so that the business objects are recommended in the dimension of category, and the recommended business objects have relevance to the target objects.
The method for recommending the service object, provided by this embodiment, includes obtaining a text vector of a triggered target commodity, obtaining text vectors of commodities other than the target commodity, determining the commodity to be recommended according to the text vector of the target commodity and the text vectors of the commodities other than the target commodity, and outputting the commodity to be recommended, where the text vectors of the target commodity and the commodities other than the target commodity are determined according to an object type recognition model obtained through training.
It should be understood that although the steps in the flowcharts of fig. 2, 10 and 11 are shown in sequence as indicated by arrows, the steps are not necessarily performed in the sequence indicated by the arrows, unless explicitly stated herein, the steps may be performed in other sequences, and at least part of the steps in fig. 2, 10 and 11 may include multiple sub-steps or phases, which are not necessarily performed at the same time , but may be performed at different times, and the order of performance of the sub-steps or phases may not necessarily be performed in sequence, but may be performed alternately or alternatively with at least part of the sub-steps or phases of other steps or other steps .
As shown in FIG. 12, in embodiments, the recommendation apparatus 1200 for business objects is provided and includes an obtaining module 1202 and a determining module 1204.
An obtaining module 1202, configured to obtain a text vector of a triggered target service object;
the obtaining module 1202 is further configured to obtain text vectors of other business objects except the target business object, where the text vectors of the business objects are determined according to an object class identification model obtained through training, and the business objects include the target business object and the other business objects;
a determining module 1204, configured to determine a service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and output the service object to be recommended.
The recommending device 1200 for the business object obtains the text vector of the triggered target business object, obtains the text vectors of other business objects except the target business object, determines the business object to be recommended according to the text vector of the target business object and the text vectors of the other business objects, and outputs the business object to be recommended, wherein the text vectors of the target business object and the other business objects are determined according to the object type identification model obtained through training.
In embodiments, the obtaining module 1202 is further configured to obtain a matching relationship between a pre-stored service object and a text vector, where the matching relationship is established according to the service object and the text vector of the service object determined by the object type identification model, and search for the text vector of the target service object corresponding to the user operation behavior according to the matching relationship.
In embodiments, the obtaining module 1202 is further configured to obtain text information of a target service object corresponding to the user operation behavior, and input the text information of the target service object into the object type identification model to obtain a text vector of the target service object.
In embodiments, the object class identification model includes a hidden layer, and the obtaining module 1202 is further configured to input text information of the target business object into the object class identification model to obtain a text vector of the target business object output by a preset layer in the hidden layer.
In embodiments, the hidden layer includes a full-connection layer, and the obtaining module 1202 is further configured to input text information of the target business object into the object class identification model, so as to obtain a text vector of the target business object output by a last full-connection layer in the hidden layer.
In embodiments, the determining module 1204 is further configured to obtain a similarity between the text vector of the target business object and the text vectors of the other business objects, and determine the business object to be recommended in the other business objects according to the similarity.
In embodiments, the determining module 1204 is further configured to obtain a vector distance between the text vector of the target business object and the text vectors of the other business objects, and characterize a similarity between the text vector of the target business object and the text vectors of the other business objects by using the vector distance.
In embodiments, the determining module 1204 is further configured to sort the other business objects by using the similarity, and determine the business object to be recommended according to a sorting result.
In embodiments, the determining module 1204 is further configured to select, according to the sorting result, a preset number of the other service objects according to the order from the largest similarity to the smallest similarity, and use the selected other service objects as the service objects to be recommended.
In embodiments, as shown in fig. 13, the apparatus 1200 for recommending a business object further includes a training module 1206, where the obtaining module 1202 is further configured to obtain text information of a sample business object and a category to which the sample business object belongs, and the training module 1206 is configured to train the object category identification model in a back propagation manner according to the text information of the sample business object and the category to which the sample business object belongs.
Fig. 14 shows an internal structure diagram of a computer device in embodiments, where the computer device may specifically be the terminal in fig. 1, as shown in fig. 14, the computer device includes a processor, a memory and a network interface connected by a system bus, where the memory includes a nonvolatile storage medium and an internal memory, the nonvolatile storage medium of the computer device stores an operating system and may also store a computer program, and when the computer program is executed by the processor, the computer program may cause the processor to implement a method for recommending a business object.
Those skilled in the art will appreciate that the architecture shown in fig. 14 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In embodiments, the recommendation apparatus for a business object provided by the present application can be implemented in the form of computer programs that can be run on a computer device as shown in fig. 14, the memory of the computer device can store various program modules constituting the recommendation apparatus for a business object, such as an acquisition module 1202 and a determination module 1204 shown in fig. 12, the computer programs constituted by the various program modules enable a processor to execute the steps in the recommendation method for a business object of the various embodiments of the present application described in the present specification.
In embodiments, computer devices are provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method for recommending business objects described above.
In embodiments, storage media are provided, which store computer programs that, when executed by a processor, cause the processor to perform the steps of the method for recommending a business object described above.
Those of ordinary skill in the art will appreciate that all or a portion of the processes in the methods of the above embodiments may be implemented by a computer program that may be stored in a non-volatile computer-readable storage medium that, when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, non-volatile memory may include read-only memory (ROM), programmable ROM (prom), electrically programmable ROM (eprom), electrically erasable programmable ROM (eeprom), or flash memory, volatile memory may include Random Access Memory (RAM) or external cache memory, RAM is available in a variety of forms, such as static RAM (sram), dynamic RAM (dram), synchronous dram (sdram), double data rate sdram (ddrsdram), sdram (sdram), synchronous sdram (sdram), and dynamic RAM (rdram), and direct RAM (rdram) bus (rddram).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (13)
1, recommendation method of business objects, characterized in that, the method includes:
acquiring a text vector of a triggered target service object;
acquiring text vectors of other business objects except the target business object, wherein the text vectors of the business objects are determined according to an object class identification model obtained by training, and the business objects comprise the target business object and the other business objects;
and determining a service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects, and outputting the service object to be recommended.
2. The method according to claim 1, wherein the obtaining the text vector of the target business object corresponding to the user operation behavior comprises:
acquiring a matching relation between a pre-stored business object and a text vector, wherein the matching relation is established according to the business object and the text vector of the business object determined by the object type identification model;
and searching the text vector of the target business object corresponding to the user operation behavior according to the matching relation.
3. The method according to claim 1, wherein the obtaining the text vector of the target business object corresponding to the user operation behavior comprises:
acquiring text information of a target service object corresponding to the user operation behavior;
and inputting the text information of the target business object into the object type identification model to obtain a text vector of the target business object.
4. The method of claim 3, wherein the object class recognition model comprises a hidden layer;
the step of inputting the text information of the target business object into the object type identification model to obtain the text vector of the target business object includes:
and inputting the text information of the target business object into the object type identification model to obtain a text vector of the target business object output by a preset layer in the hidden layer.
5. The method of claim 4, wherein the hidden layer comprises a fully connected layer;
the inputting the text information of the target business object into the object type recognition model to obtain the text vector of the target business object output by a preset layer in the hidden layer includes:
and inputting the text information of the target service object into the object class identification model to obtain a text vector of the target service object output by the last full-connection layer in the hidden layer.
6. The method according to claim 1, wherein the determining the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects comprises:
acquiring the similarity between the text vector of the target business object and the text vectors of the other business objects;
and determining the business object to be recommended in the other business objects according to the similarity.
7. The method according to claim 6, wherein the obtaining the similarity between the text vector of the target business object and the text vectors of the other business objects comprises:
and acquiring the vector distance between the text vector of the target business object and the text vectors of other business objects, and representing the similarity between the text vector of the target business object and the text vectors of other business objects by using the vector distance.
8. The method according to claim 6, wherein the determining the business object to be recommended among the other business objects according to the similarity comprises:
sorting the other business objects by utilizing the similarity;
and determining the service object to be recommended according to the sequencing result.
9. The method according to claim 8, wherein the determining the service object to be recommended according to the sorting result comprises:
and selecting a preset number of other service objects according to the sequencing result and the sequence of the similarity from big to small, and taking the selected other service objects as the service objects to be recommended.
10. The method of claim 1, wherein the training of the object class recognition model comprises:
acquiring text information of a sample business object and a category to which the sample business object belongs;
and training the object class identification model in a back propagation mode according to the text information of the sample business object and the class to which the sample business object belongs.
Apparatus for recommending service objects of the 11 th kinds, said apparatus comprising:
the acquisition module is used for acquiring the text vector of the triggered target business object;
the acquiring module is further configured to acquire text vectors of other business objects except the target business object, where the text vectors of the business objects are determined according to an object class identification model obtained through training, and the business objects include the target business object and the other business objects;
and the determining module is used for determining the service object to be recommended according to the text vector of the target service object and the text vectors of the other service objects and outputting the service object to be recommended.
12, computer device comprising a memory and a processor, the memory having stored thereon a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1-10.
Storage medium having stored thereon computer-executable instructions which, when executed by a processor, cause the processor to perform the steps of the method of any of claims 1 to 10, .
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910973183.8A CN110737834B (en) | 2019-10-14 | 2019-10-14 | Recommendation method and device for business objects, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910973183.8A CN110737834B (en) | 2019-10-14 | 2019-10-14 | Recommendation method and device for business objects, storage medium and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110737834A true CN110737834A (en) | 2020-01-31 |
| CN110737834B CN110737834B (en) | 2024-04-02 |
Family
ID=69268851
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910973183.8A Active CN110737834B (en) | 2019-10-14 | 2019-10-14 | Recommendation method and device for business objects, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110737834B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113343711A (en) * | 2021-06-29 | 2021-09-03 | 南方电网数字电网研究院有限公司 | Work order generation method, device, equipment and storage medium |
| CN113850384A (en) * | 2021-09-30 | 2021-12-28 | 维沃移动通信有限公司 | Model training method and device |
| US11460851B2 (en) | 2019-05-24 | 2022-10-04 | Ford Global Technologies, Llc | Eccentricity image fusion |
| US11521494B2 (en) | 2019-06-11 | 2022-12-06 | Ford Global Technologies, Llc | Vehicle eccentricity mapping |
| WO2023035940A1 (en) * | 2021-09-10 | 2023-03-16 | 上海明品医学数据科技有限公司 | Target object recommendation method and system |
| US11662741B2 (en) | 2019-06-28 | 2023-05-30 | Ford Global Technologies, Llc | Vehicle visual odometry |
| US11783707B2 (en) | 2018-10-09 | 2023-10-10 | Ford Global Technologies, Llc | Vehicle path planning |
| US12046047B2 (en) | 2021-12-07 | 2024-07-23 | Ford Global Technologies, Llc | Object detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296195A (en) * | 2015-05-29 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and device |
| WO2018099275A1 (en) * | 2016-11-29 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Method, apparatus, and system for generating business object attribute identifier |
| WO2019105432A1 (en) * | 2017-11-29 | 2019-06-06 | 腾讯科技（深圳）有限公司 | Text recommendation method and apparatus, and electronic device |
| CN110020112A (en) * | 2017-09-25 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Object Push method and its system |
| CN110209922A (en) * | 2018-06-12 | 2019-09-06 | 中国科学院自动化研究所 | Object recommendation method, apparatus, storage medium and computer equipment |
| CN110309427A (en) * | 2018-05-31 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of object recommendation method, apparatus and storage medium |
-
2019
- 2019-10-14 CN CN201910973183.8A patent/CN110737834B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296195A (en) * | 2015-05-29 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and device |
| WO2018099275A1 (en) * | 2016-11-29 | 2018-06-07 | 阿里巴巴集团控股有限公司 | Method, apparatus, and system for generating business object attribute identifier |
| CN110020112A (en) * | 2017-09-25 | 2019-07-16 | 北京京东尚科信息技术有限公司 | Object Push method and its system |
| WO2019105432A1 (en) * | 2017-11-29 | 2019-06-06 | 腾讯科技（深圳）有限公司 | Text recommendation method and apparatus, and electronic device |
| CN110309427A (en) * | 2018-05-31 | 2019-10-08 | 腾讯科技（深圳）有限公司 | A kind of object recommendation method, apparatus and storage medium |
| CN110209922A (en) * | 2018-06-12 | 2019-09-06 | 中国科学院自动化研究所 | Object recommendation method, apparatus, storage medium and computer equipment |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11783707B2 (en) | 2018-10-09 | 2023-10-10 | Ford Global Technologies, Llc | Vehicle path planning |
| US11460851B2 (en) | 2019-05-24 | 2022-10-04 | Ford Global Technologies, Llc | Eccentricity image fusion |
| US11521494B2 (en) | 2019-06-11 | 2022-12-06 | Ford Global Technologies, Llc | Vehicle eccentricity mapping |
| US11662741B2 (en) | 2019-06-28 | 2023-05-30 | Ford Global Technologies, Llc | Vehicle visual odometry |
| CN113343711A (en) * | 2021-06-29 | 2021-09-03 | 南方电网数字电网研究院有限公司 | Work order generation method, device, equipment and storage medium |
| CN113343711B (en) * | 2021-06-29 | 2024-05-10 | 南方电网数字电网研究院有限公司 | Work order generation method, device, equipment and storage medium |
| WO2023035940A1 (en) * | 2021-09-10 | 2023-03-16 | 上海明品医学数据科技有限公司 | Target object recommendation method and system |
| CN113850384A (en) * | 2021-09-30 | 2021-12-28 | 维沃移动通信有限公司 | Model training method and device |
| US12046047B2 (en) | 2021-12-07 | 2024-07-23 | Ford Global Technologies, Llc | Object detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110737834B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110737834A (en) | Business object recommendation method and device, storage medium and computer equipment | |
| CN108959603B (en) | Personalized recommendation system and method based on deep neural network | |
| CN105426528B (en) | A kind of retrieval ordering method and system of commodity data | |
| CN110458627B (en) | Commodity sequence personalized recommendation method for dynamic preference of user | |
| CN109829775B (en) | Article recommendation method, device and equipment and readable storage medium | |
| CN103714130B (en) | Video recommendation system and method | |
| CN107357793B (en) | Information recommendation method and device | |
| CN105740268B (en) | A kind of information-pushing method and device | |
| CN109492180A (en) | Resource recommendation method, device, computer equipment and computer readable storage medium | |
| Ullah et al. | Image-based service recommendation system: A JPEG-coefficient RFs approach | |
| CN110175895B (en) | Article recommendation method and device | |
| CN106777051A (en) | A kind of many feedback collaborative filtering recommending methods based on user's group | |
| CN106250545A (en) | A kind of multimedia recommendation method and system searching for content based on user | |
| CN113722583A (en) | Recommendation method, recommendation model training method and related products | |
| Bansal et al. | User tweets based genre prediction and movie recommendation using LSI and SVD | |
| CN107133854A (en) | Information recommendation method and device | |
| CN113268667B (en) | Chinese comment emotion guidance-based sequence recommendation method and system | |
| CN115712780A (en) | Information pushing method and device based on cloud computing and big data | |
| Addagarla et al. | e-SimNet: A visual similar product recommender system for E-commerce | |
| CN110083766B (en) | Query recommendation method and device based on meta-path guiding embedding | |
| CN114706987A (en) | Text category prediction method, device, equipment, storage medium and program product | |
| Won et al. | A hybrid collaborative filtering model using customer search keyword data for product recommendation | |
| CN113704617A (en) | Article recommendation method, system, electronic device and storage medium | |
| Zhao et al. | Personalized recommendation by exploring social users’ behaviors | |
| CN110851694A (en) | Personalized recommendation system based on user memory network and tree structure depth model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40021459 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |