CN111859147A - Object recommendation method, object recommendation device and electronic equipment - Google Patents
Object recommendation method, object recommendation device and electronic equipment Download PDFInfo
- Publication number
- CN111859147A CN111859147A CN202010756547.XA CN202010756547A CN111859147A CN 111859147 A CN111859147 A CN 111859147A CN 202010756547 A CN202010756547 A CN 202010756547A CN 111859147 A CN111859147 A CN 111859147A
- Authority
- CN
- China
- Prior art keywords
- node
- user
- association
- nodes
- layer
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides an object recommendation method, an object recommendation device and an electronic device, which can be used in the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring a user identifier; matching the user identification in a knowledge graph to obtain an associated layer node and an associated object node of a user node corresponding to the user identification, wherein the knowledge graph comprises an association relation among the user node, the layer node and the object node, and each layer node comprises at least one object node; processing the associated layer nodes, the associated object nodes and the user nodes by using an object recommendation model, and determining a first association degree between each associated layer node and each user node and a second association degree between each associated object node and each user node; and performing recommendation sequencing on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree so as to recommend the association layer and the respective association objects of the association layer for the user identification.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to an object recommendation method, an object recommendation apparatus, an electronic device, and a computer-readable storage medium.
Background
With the rapid development of electronic technology, the amount of information, services and products provided to users by programs (such as applications and software) is also showing an explosive growth trend. In order to more intuitively display data such as information, services, and products to a user, in the related art, the information, services, and products may be classified and displayed in a form of a floor.
In implementing the disclosed concept, the inventors found that there are at least the following problems in the related art: the floors sorted by manual rules do not take the use habits and preferences of users into consideration, so that the sorting is not in accordance with personal preferences, and the user experience is poor. Meanwhile, if the contents displayed in the floors are sorted by the rule, the displayed contents lack personalization. In addition, if a model is allocated to each floor for recommendation prediction, model training cost is too high, and when multiple models predict the contents of the floors at the same time, the calculation amount is large, time consumption is long, and online recommendation requirements cannot be met.
Disclosure of Invention
In view of the above, the present disclosure provides an object recommendation method, an object recommendation apparatus, and an electronic device that combine a knowledge graph to solve the problem that content recommendation for multiple online floors cannot be satisfied.
One aspect of the present disclosure provides an object recommendation method performed by an electronic device. The method comprises the following steps: acquiring a user identifier; matching the user identification in a knowledge graph to obtain an associated layer node and an associated object node of a user node corresponding to the user identification, wherein the knowledge graph comprises an association relation among the user node, the layer node and the object node, and each layer node comprises at least one object node; processing the associated layer nodes, the associated object nodes and the user nodes by using an object recommendation model, and determining a first association degree between each associated layer node and each user node and a second association degree between each associated object node and each user node; and performing recommendation sequencing on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree so as to recommend the association layer and the respective association objects of the association layer for the user identification.
According to an embodiment of the present disclosure, constructing a knowledge-graph includes: determining a user node, a user attribute node, a function node, a layer node, a product node and a product attribute node; determining a first connection relation between a user node and a user attribute node, a function node, a layer node or a product node respectively, determining a second connection relation between a plurality of function nodes, determining a third connection relation between the layer node and the function node and the product node respectively, and determining a fourth connection relation between the product node and the product attribute node; and constructing a directed graph based on the user nodes, the user attribute nodes, the function nodes, the layer nodes, the product attribute nodes, the first connection relations, the second connection relations, the third connection relations and the fourth connection relations to generate the knowledge graph.
According to an embodiment of the present disclosure, an object recommendation model is trained by: acquiring training data, wherein the training data comprises first sub-training data, second sub-training data and third sub-training data, the first sub-training data is user historical operation data before a designated time, the second sub-training data is atlas data determined by extending a knowledge atlas by using user information in the first sub-training data, and the third sub-training data is user historical operation data after the designated time; and inputting the first sub-training data and/or the second sub-training data into the object recommendation model, and adjusting model parameters of the object recommendation model so that the output of the object recommendation model approaches to the third sub-training data.
Another aspect of the present disclosure provides an object recommendation apparatus performed by an electronic device. The device includes: the system comprises an identification acquisition module, an association layer determination module, an association degree determination module and a recommendation sorting module. The identification acquisition module is used for acquiring a user identification; the association layer determining module is used for matching the user identification in the knowledge graph to obtain an association layer node and an association object node of the user node corresponding to the user identification, the knowledge graph comprises an association relation among the user node, the layer node and the object node, and each layer node comprises at least one object node; the association degree determining module is used for processing the association layer nodes, the association object nodes and the user nodes by using the object recommendation model, and determining a first association degree between each association layer node and each user node and a second association degree between each association object node and each user node; and the recommendation sequencing module is used for performing recommendation sequencing on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree so as to recommend the association layer for the user identification and the respective association objects of the association layer.
Another aspect of the present disclosure provides an electronic device including: one or more processors; a memory for storing one or more instructions, wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement an object recommendation method as performed by the electronic device above.
Another aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the object recommendation method performed by an electronic device as above.
Another aspect of the present disclosure provides a computer program comprising computer executable instructions for implementing the object recommendation method performed by an electronic device as described above when executed.
According to the embodiment of the disclosure, the association relationship between the user and the floor nodes (floors) is mined based on the knowledge graph, and the association relationship between the user and the object nodes (such as functions and products) in the floors is mined, so that the floors are intelligently sorted according to the use habits, preferences and the like of the user, and partial objects in the floors are recommended, so that the user can easily find the floors concerned by the user, commonly used floors, the objects concerned by the user and the like, the heterogeneous network recommendation is realized, the recommendation calculation cost is reduced, the user operation cost is reduced, and the user experience is improved.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:
fig. 1 schematically illustrates an application scenario of an object recommendation method, an object recommendation apparatus and an electronic device according to an embodiment of the present disclosure;
fig. 2 schematically shows a system architecture suitable for an object recommendation method, an object recommendation apparatus and an electronic device according to an embodiment of the present disclosure;
FIG. 3 schematically shows a flow chart of an object recommendation method performed by an electronic device according to an embodiment of the present disclosure;
FIG. 4 schematically shows a schematic diagram of a layer node according to an embodiment of the disclosure;
FIG. 5 schematically illustrates a flow diagram of a method of constructing a knowledge graph according to an embodiment of the present disclosure;
FIG. 6 schematically shows a schematic diagram of a knowledge-graph according to an embodiment of the present disclosure;
FIG. 7 schematically illustrates a schematic diagram of a knowledge-graph according to another embodiment of the present disclosure;
figure 8 schematically shows a schematic diagram of atlas data according to an embodiment of the disclosure;
FIG. 9 schematically shows a schematic diagram of a recommendation ranking according to an embodiment of the present disclosure;
fig. 10 is a block diagram schematically illustrating a structure of an object recommending apparatus executed by an electronic device according to an embodiment of the present disclosure; and
fig. 11 schematically shows a block diagram of an electronic device adapted to perform an object recommendation method performed by the electronic device according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features.
With the rapid development of internet financial business, data of information, services and products provided by internet financial application also show an explosive growth trend, so that the related data are visually shown to users, the convenience of user operation is improved, and if the needed functions, products and the like can be found more quickly, classified display can be carried out in a floor form.
For example, when recommending products, all products may be sorted, if sorting is performed according to the hot sales of a plurality of products, then the user is recommended the products sorted in the top, and then the sorting result is divided into a plurality of rows according to the number of products that can be displayed in a row. However, the sorting method does not consider the requirements of the user for classified display, such as the mixing of various categories of products, functions and the like, which is inconvenient for the user to quickly find the required object and poor in user experience.
For example, when product recommendation is performed, the floors may be sorted based on rules, such as the category of the hot-sold product is set at the uppermost floor, and then a recommendation model is assigned to each floor to determine the sorting of the products of the floor. However, the user's preferences and habits are different, which results in poor experience when the ranking does not conform to the personal preferences. In addition, this results in excessive computation, consumes excessive computing resources, and may not meet the online recommendation. The floor refers to a display area of certain type of data and belongs to one row in the list, the related content of the type can be displayed in the floor, and the layout modes of different types of floors can be customized.
The embodiment of the disclosure provides an object recommendation method, an object recommendation device and electronic equipment. The method includes an association layer determination process and a ranking process. In the process of determining the association layer, firstly, user identification is obtained, then, the user identification is matched in a knowledge graph, association layer nodes and association object nodes of user nodes corresponding to the user identification are obtained, the knowledge graph comprises association relations among the user nodes, the layer nodes and the object nodes, and each layer node comprises at least one object node. After the association layer determining process is completed, a sorting process is started, firstly, association layer nodes, association object nodes and user nodes are processed by an object recommendation model, a first association degree between each association layer node and each user node and a second association degree between each association object node and each user node are determined, then, recommendation sorting is carried out on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree, and association objects of the association layers and the association layers aiming at the user identification are recommended. The knowledge graph comprises the associated layers and the object information, so that the sequencing of the associated layers and the sequencing of objects in the associated layers can be obtained simultaneously through the object recommendation model, the consumed computing resources are less, and the online recommendation requirement can be met.
Fig. 1 schematically illustrates an object recommendation method, an object recommendation apparatus, and an application scenario of an electronic device according to an embodiment of the present disclosure. It should be noted that the object recommendation method, the object recommendation device and the electronic device in the embodiments of the present disclosure may be used in the technical field of artificial intelligence, and may also be used in various fields other than the technical field of artificial intelligence, such as the technical field of big data. The application fields of the object recommendation method, the object recommendation device and the electronic equipment in the embodiments of the disclosure are not limited.
As shown in fig. 1, an Application (APP) in a mobile phone is taken as an example for explanation, and in the application, different types of functions, products, and the like can be respectively displayed on a plurality of floors. The first level of fig. 1 shows financial products, such as life payment, financial products, etc. that the user can find in the first level. The second layer displays products that the user can purchase online, such as various electronic products (it should be noted that products that can be purchased online can be subdivided, such as consumer electronic products, computer office products, camera products, earphone products, clothing products, luggage products, travel products, etc.). The third layer displays information, such as the current affairs, finance and economics, colorful fashion, etc. In the related art, floors are usually fixed, and if consumer electronics are the hottest ones at present, the first floor seen by all users is consumer electronics. However, each user has different requirements, some users may be more concerned about financial products, some users may be more concerned about information, and some users may be more concerned about travel products, so that the floor fixing manner may not facilitate diversified requirements of the users. The object recommendation method, the object recommendation device and the electronic equipment provided by the embodiment of the disclosure can realize the floor recommendation of thousands of people, and the contents in the floors are also sorted according to the use habits, hobbies and the like of the user, so that the user can quickly find out required products, functions and the like with low cost (such as time cost and the like), and the user experience is improved.
Fig. 2 schematically shows a system architecture suitable for an object recommendation method, an object recommendation apparatus, and an electronic device according to an embodiment of the present disclosure. It should be noted that fig. 2 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.
As shown in fig. 2, a system architecture 200 according to an embodiment of the present disclosure may include terminal devices 201, 202, 203, a network 204, a server 205. The terminal devices 201, 202, 203, the server 205 may be connected via a network 204, and the network 204 may comprise various connection types, such as wired, wireless communication links, or fiber optic cables, etc.
The terminal devices 201, 202, 203 may be of a type having a display screen and/or may be installed with various programs, such as client applications, software, etc., including but not limited to smart phones, tablets, laptop portable computers, mainframe and desktop computers, etc. The terminal devices 201, 202 and 203 can provide various functional portals to users through client applications to meet various requirements of the users.
According to an embodiment of the present disclosure, the terminal devices 201, 202, 203 may further have a processing function to process a floor, a function, a product, and the like to be recommended to the user according to the user information. And preferentially displaying the interaction components corresponding to the recommended floors, functions and products in a display interface of the client application. Referring to fig. 1, a plurality of floors may be included, such as a first floor, a second floor, and the like, wherein the first floor may include living payment, financial products, and the like, and the second floor may include electronic products, such as a mobile phone, a camera, and the like.
The network 204 is used to provide a medium for communication links between terminal devices and servers. The network may include various connection types, such as wired and/or wireless communication links, and so forth.
The server 205 may be a server that provides various services. For example, the server 205 may interact with the terminal devices 201, 202, 203 through the network 204, for example, to acquire the user information acquired by the terminal devices 201, 202, 203. The server 205 may also be configured to obtain a function to be recommended to the user according to user information processing, and send the function to be recommended to the user to the terminal devices 201, 202, and 203, so that the terminal devices 201, 202, and 203 preferentially expose a function entry corresponding to the function to be recommended to the user in a running client application.
It should be noted that the object recommendation method executed by the electronic device according to the embodiment of the present disclosure may be executed by the terminal devices 201, 202, and 203 or the server 205. Accordingly, the object recommendation device executed by the electronic device provided by the embodiment of the present disclosure may be disposed in the terminal device 201, 202, 203 or the server 205.
It should be understood that the types and numbers of terminal devices 201, 202, 203, network 204 and server 205 in fig. 2 are merely illustrative.
Fig. 3 schematically shows a flowchart of an object recommendation method performed by an electronic device according to an embodiment of the present disclosure.
As shown in fig. 3, the method for detecting a heap memory attack performed by a server may include operations S301 to S307.
In operation S301, a user identity is acquired. The user identification may be used to uniquely identify a user or user node, such as in a knowledge graph.
In operation S303, the user identifier is matched in the knowledge graph, so as to obtain an associated layer node and an associated object node of the user node corresponding to the user identifier.
In this embodiment, the knowledge graph includes an association relationship between each of the user nodes, the layer nodes, and the object nodes, and each layer node includes at least one object node.
In particular, the knowledge-graph may include user nodes, layer nodes identified for a user, and at least one of function nodes and product nodes, user attribute nodes, and product attribute nodes identified for a plurality of functions. The system comprises a user node, a function node, a layer node and a product node, wherein incidence relations exist between the user node and the function node, between the layer node and the product node, a hierarchical relation exists between a plurality of function nodes, an incidence relation exists between the user node and the user attribute node, and an incidence relation exists between the product node and the product attribute node. The knowledge graph can be constructed based on historical operation data of the user, functions provided by programs, products sold and the like, and the characteristic data of the user and the historical operation data of the user and various related relations are shown in the form of the knowledge graph. Accordingly, an object required by the user can be predicted based on the knowledge graph.
For example, after the user node corresponding to the user identifier in the knowledge graph is determined, the corresponding user node may be diffused according to the association relationship with other nodes. And then, diffusing according to the user characteristic information to obtain functions which are possibly interested by the user, and obtaining the associated layer nodes according to the diffused result. Compared with the recommendation algorithm in the related art, the method can solve the problem of cold start of the user in the related art.
In operation S305, the association layer nodes, the association object nodes, and the user nodes are processed using the object recommendation model, and a first degree of association between each association layer node and the user node and a second degree of association between the association object node and the user node are determined.
In one embodiment, the association between each user and the associated level node, object node, etc. may be determined through an artificial intelligence model, so as to determine the floor and product desired by the user based on the association.
For example, the artificial intelligence model may employ a neural network, which may be of a heterogeneous network type, to enhance the adaptability of the model and the expressive power of the features. For example, vectorization is performed on the user node, the associated layer node, and object nodes included in the user node, so as to obtain a feature vector, then the feature vector is input into a trained heterogeneous network model, and the association degree of a plurality of floors, products, and functions with respect to the current user node is obtained after processing by the heterogeneous network model (if the score is higher, the association degree is higher). Wherein the higher the relevance, the higher the user interest level is characterized.
In one embodiment, the object recommendation model is trained as follows. Firstly, training data is obtained, wherein the training data comprises first sub-training data, second sub-training data and third sub-training data, the first sub-training data is user historical operation data before a specified time, the second sub-training data is atlas data determined by extending a knowledge atlas by using user information in the first sub-training data, and the third sub-training data is user historical operation data after the specified time. Then, the first sub-training data and/or the second sub-training data are input into the object recommendation model, and model parameters of the object recommendation model are adjusted so that an output of the object recommendation model approaches the third sub-training data.
For example, first, the construction of the training data. For each user, nodes related to the user are found on the knowledge graph. If the association relationship includes: user node-attribute node, user node-function node, user node-layer node, user node-product node. Starting at these nodes, there is a constant outward diffusion of the edges in the knowledge-graph for a specified number of times, e.g., 2 times.
Training data is then determined, which may include: and (3) user access volume (pv) data, and screening user click events of clicking a function menu in a floor by a user, clicking the floor by the user and clicking products in the floor by the user through the pv data. And (3) acquiring a historical record of products purchased by the user through the purchase record table (wherein the weight of the purchase data of the user can be higher than that of the pv data, such as doubling the purchase data of the user, and the like). The user clicks the floor, clicks the product, clicks the function menu, and purchases the product as the forward training sample, and the floor, the product and the function menu which are not clicked by the user are used to generate the negative sample for the purchased product (the screening rule of the negative sample is to sample according to the popular degree of the floor, the product and the function menu, and the user has no operation object, so that the probability of sampling can be improved, namely the weight of the sampling is increased).
Next, deep learning training is performed. The deep learning model adopts knowledge graph-based ripple network (rippelet), training data is used for training the model, a prediction function is fitted to predict the probability that a user may click floors, function menus and products, and parameters are adjusted in the training process, so that the model is optimal. It should be noted that a similar model may be used instead of the ripple net model.
For example, first user historical data before the first moment and data obtained by diffusion in the knowledge graph based on the first user historical data are input, the model output result is compared with the real user historical data at the first moment, and a loss value of the current model is calculated by adopting a loss function. And then adjusting the parameters in the current model according to the loss value. And finally, taking the model parameters with the accuracy rate not less than the preset accuracy rate as the model parameters of the object recommendation model through adjusting the parameters for multiple times. The loss function may be, for example, a cross entropy function, a sigmoid function, or the like, and the predetermined accuracy may be, for example, any value in a range of 70% to 95%. It is to be understood that the type of the loss function and the range of the predetermined accuracy are only examples to facilitate understanding of the present disclosure, and the present disclosure is not limited thereto.
After the object recommendation model is trained, prediction can be performed using the object recommendation model. For example, user nodes are obtained from a graph database through user identification (id) and continuously spread outwards from the user nodes for 2 times along the edges in the graph, the obtained data is input to a trained model, and the model calculates the prediction score and the user vector of the user for each floor.
In operation S307, the association layer nodes and the respective association object nodes are recommended and ranked based on the first association degree and the second association degree to recommend the association layer for the user identifier and the respective association object of the association layer.
In this embodiment, performing recommendation ranking on the association level nodes and the respective association object nodes based on the first association degree and the second association degree may include the following operations.
Firstly, performing first recommendation sequencing on the associated layer nodes based on the first relevance degree so as to take the associated layer nodes with the first designated number and the top sequencing as the layer nodes to be recommended.
Then, for each of the layer nodes to be recommended, second recommendation sorting is performed on the object nodes included in the layer node to be recommended based on the second relevance, so that the object nodes with the second specified number sorted in the top are used as the object nodes to be recommended of the layer node to be recommended. For example, a floor for which a score for a user node is higher than a predetermined score, and functions and products in the floor may be determined as functions to be recommended to a user corresponding to the user node. Alternatively, it may be that the floor with the highest score, Top 3(Top 3) for the user node is determined, and the functions and products in the floor are the associated floor and its object to be recommended to the user.
For example, the floors recommended to the user are ranked, such as according to floor node scores. Products recommended in the floor are sorted according to the user vector and the distance between various products in the product vector library, so that the recommendation of the floor sequence and the products in the floor is realized through one-time calculation of the model. Wherein the distance may be a euclidean distance, a cosine distance, etc.
In one embodiment, taking the function nodes included in one floor as an example for illustration, the functions may be sorted from large to small according to scores (which may be determined based on vector similarity) of the functions for the user nodes. Firstly, the functions are sorted according to the scores of the user nodes, so that the scores of the sorted functions for the user nodes are sequentially reduced. Then, a predetermined number of functions having the highest scores for the user node among the plurality of functions obtained by the ranking are determined as functions to be recommended to the user node. The predetermined number may be set, for example, according to a display mode of a program installed in the electronic device. For example, if the program display mode sets that 6 functions can be displayed at a time, the predetermined number is 6, and the functions listed in Top 6 are taken as the functions to be recommended.
According to the object recommendation method, the associated layer nodes and the user nodes obtained by combining the knowledge graph are processed through the neural network, scores of a plurality of associated layer nodes, products and functions for the user can be obtained, and the problem of cold start of the user in the related technology can be solved. Meanwhile, a model is not required to be distributed to each floor to give the sequence of each object in the floor, and the sequence of the floor and the sequence of each object in the floor can be obtained through an object recommendation model, so that the consumption of computing resources is reduced, and the response speed is improved.
In one embodiment, the object node includes: at least one of a function node or a product node, a hierarchy existing between at least two of the function nodes, the product node having an associated product attribute node. The user nodes have associated user attribute nodes.
Accordingly, the input of the object recommendation model includes the association level node and the user node, and at least one of: function nodes, product attribute nodes and user attribute nodes.
For example, the user attribute information of the user attribute node includes, but is not limited to: age, gender, academic history, occupation, and/or asset condition, etc. The user of the user node may be any one of users who use a predetermined program in the electronic device.
Fig. 4 schematically shows a schematic diagram of a layer node according to an embodiment of the disclosure.
As shown in fig. 4, the layer node named as the first layer is a layer node for a function, and the layer node includes a plurality of functions 1 to 7. Where function 1 is a parent of function 2 and function 3, function 2 is a parent of function 4, and function 6 is a parent of function 7. Therefore, a hierarchy exists between some of the functional nodes.
In one embodiment, the knowledge-graph may be constructed as follows.
FIG. 5 schematically shows a flow diagram of a method of constructing a knowledge-graph according to an embodiment of the present disclosure.
As shown in fig. 5, constructing the knowledge-graph may include operations S501 to S505.
In operation S501, a user node, a user attribute node, a function node, a layer node, a product node, and a product attribute node are determined.
In operation S503, a first connection relationship between the user node and the user attribute node, the function node, the layer node, or the product node, respectively, is determined, a second connection relationship between at least two function nodes is determined, a third connection relationship between the layer node and the function node and the product node, respectively, is determined, and a fourth connection relationship between the product node and the product attribute node is determined.
FIG. 6 schematically shows a schematic diagram of a knowledge-graph according to an embodiment of the disclosure.
As shown in FIG. 6, the knowledge graph includes a plurality of user nodes (…, m-1, m +1, …), a plurality of user attributes 1, 3, a plurality of layer nodes (…, n-1, n +1, …), a plurality of function nodes 1-5, etc., a plurality of product nodes 1, 2, 3, etc., and a plurality of product attribute nodes 1, etc. The first connection relationship is a connection relationship between the user node and the remaining nodes. The second connection relationship is a connection relationship between the functional nodes. The third connection relationship is a connection relationship between the layer node and the function node or the product node. The fourth connection relationship is a connection relationship between the product node and the product attribute node. Wherein m and n are positive integers greater than zero.
When the number of users using the program is large, and the number of functions or products provided by the program is large, the memory space occupied by the knowledge graph is too large. In order to solve the problem, the user node related information may be stored in a database, and when it is needed to be used, the user node related information, the corresponding layer node and its object node are associated by an association relationship.
Specifically, the knowledge graph comprises a user database and an object graph, and data of the user nodes, the user attribute nodes and the first connection relations are stored in the user database.
FIG. 7 schematically shows a schematic diagram of a knowledge-graph according to another embodiment of the present disclosure.
As shown in fig. 7, the knowledge-graph actually includes two parts: an object graph and a user database. The user database comprises user nodes, user attribute node related information and a first association relation. The first association relationship may be stored in a data structure manner, for example, in fig. 7, an association relationship exists between the user m-1 and the layer node of the nth layer, the function 3, the layer node of the N +1 th layer, and the user attribute node of the user attribute 1.
Figure 8 schematically shows a schematic diagram of atlas data according to an embodiment of the disclosure.
As shown in fig. 8, when object recommendation is required for, for example, user m-1, data related to user m-1 may be extracted from the user database, and then the extracted data is associated with layer nodes, function nodes, and product nodes in the object graph, so as to obtain a complete knowledge graph for user m-1. This can effectively save memory space. And then, based on the incidence relation, the data of the object recommendation model to be input can be obtained by outwards diffusing for 2 times in the knowledge graph with the user m-1 as a starting point.
In operation S505, a directed graph is constructed based on the user node, the user attribute node, the function node, the layer node, the product attribute node, the first connection relationship, the second connection relationship, the third connection relationship, and the fourth connection relationship to generate a knowledge graph.
In one embodiment, the layer nodes are formed as follows.
First, a first inclusion relationship and a second inclusion relationship are determined, the first inclusion relationship being a relationship between a layer node and a function node possessed by the layer node, and the second inclusion relationship being a relationship between the layer node and a product node exhibited by the layer node.
Then, a layer node is generated based on the function node and the first inclusion relation or based on the product node and the second inclusion relation.
For example, first, user attributes are extracted, the user and various attribute points are placed in a graph, and edges (user nodes-attribute nodes) are constructed according to the relationship of the user and the attributes.
Then, the function nodes are extracted, and edges (function nodes-function nodes) are constructed according to the parent-child relationship among the function nodes.
Next, a floor node is generated, an inclusion relationship is generated from the floor node and a function node included in the floor, and an edge (floor node-function node) is established.
Then, the products to be displayed and the product attributes in the floor are put into the map, and edges (product-attributes) are constructed according to the relationship between the products and the attributes.
Then, according to the inclusion relation between the floor and the product before the floor shows the product, the floor and the product edge (floor-product) are established.
Then, based on the history of the user's click on the function, the edges of the user and the function node (user-function) are constructed.
Next, based on the history of the user clicking on the floor, the edges of the user and the floor nodes (user-floor) are constructed.
The user-product edge is then constructed from the record of the user's clicks and purchases of the product (user-product).
Then, a directed graph is constructed as a knowledge graph according to the above rules.
The knowledge graph constructed by the method can embody the user attribute, the floor, the action of clicking the floor by the user, the relation between the display product in the floor and the floor, the attribute of the display product in the floor, the historical action of clicking or purchasing the product in the floor by the user and the like, namely the knowledge graph comprises a relation network among a plurality of nodes, so that the floor, the object and the like can be conveniently recommended to the user through model analysis and calculation based on the knowledge graph.
In one embodiment, after constructing the knowledge-graph, the method may further comprise the following operations. And inputting each node of the knowledge graph into the object recommendation model to determine a node vector of each node, wherein the first relevance and the second relevance are determined based on the similarity between the node vectors.
This facilitates the formation of product libraries, function libraries, etc. For example, after model training is completed, product nodes, function nodes, and layer nodes in the knowledge graph generate corresponding vectors through the trained model, and the dimensionality of the generated vectors can be adjusted during model training according to the number of products. And storing the generated vectors into a database to serve as a product vector library, and sorting according to the distance between the user vector and the product vector when product recommendation in the floor is performed.
In one embodiment, matching the user identifier in the knowledge-graph to obtain the association level node and the association object node of the user node corresponding to the user identifier may include the following operations. And extending the user nodes corresponding to the user identifications in the knowledge graph based on the association relation until reaching the specified extension depth to obtain the association layer nodes and the association object nodes of the user nodes corresponding to the user identifications.
For example, a first flooding is performed starting from a user node, and the first flooding may include: and determining the nodes pointed by the edges with the user nodes as the starting points according to the edges connected with the user nodes to obtain second nodes, and taking all the second nodes as the result of the first diffusion. In order to make the recommended floors, products and functions more comprehensive, the second node can be used as a starting point to perform second diffusion to obtain a third node. At least one diffusion node is obtained by using the second node and the third node … … obtained through diffusion as diffusion nodes. According to an embodiment of the present disclosure, the diffusion may include, for example, two, three, or more times in order to take into account the diversity and accuracy of the recommendation. It is to be understood that the above described number of diffusions is by way of example only to facilitate understanding of the present disclosure, and the present disclosure is not limited thereto. The diffusion times can be determined according to actual requirements.
The following is an exemplary description of how the node vector and the object recommendation model are input.
The description will be given by taking the user attribute node as an example to represent the user age. The age information can be converted into a feature vector by adopting an One-Hot mode. For example, the ages can be sequentially classified into categories corresponding to a plurality of age groups, such as (10, 20], (20, 30], (30, 40], (40, 50], (50, 60], (60, 70], (70, 80], (80, 90], (90, 100 ]), and (greater than 100). if the age of the user is 35 years, the user attribute node belongs to the section (30, 40), and accordingly, the node can be vectorized into 0,0,1,0,0,0,0,0,0, 0.
The vectors of all nodes needing to be input into the object recommendation model can be obtained through the method, then the vectors are spliced into a feature matrix, and the feature matrix is used as the input of the object recommendation model.
It should be noted that, considering that the feature information of the user and the directional relations of the nodes for multiple functions in the knowledge graph are relatively determined, in order to solve the problem that the recommendation is inaccurate due to drift of the user interest or short-term characteristics, recent history operations of the user may be further included as an input of the object recommendation model. For example, the last 1 day, the last 3 days, or the last 1 month, etc. In addition, when the historical operation data of the user is recorded in each node, if the product node records the number of times that the user recently clicked the product node, and the like, the recent record can be selected from each record. Therefore, the feature matrix can better represent the requirements of the user node at the current stage, and the score obtained according to the feature matrix is more consistent with the requirements of the user node at the current stage. Thereby, the recommendation result can meet the timeliness.
FIG. 9 schematically shows a schematic diagram of a recommendation ranking according to an embodiment of the disclosure.
As shown in fig. 9, the floors recommended by the object recommendation method include: floor 1, floor 2, floor 3, etc., wherein the degree of association of floor 1 with the user is greater than the degree of association of floor 2 with the user, and the degree of association of floor 2 with the user is greater than the degree of association of floor 3 with the user. The degree of association of object 1 with the user is greater than the degree of association of object 2 with the user. Two functions of life payment and financial products are recommended in the floor 1, wherein the degree of association between the life payment and the user is greater than the degree of association between the financial products and the user. Two products, namely a mobile phone and a camera, are recommended in the floor 2, wherein the association degree of the mobile phone and the user is greater than that of the camera and the user. Two information of the current financial affairs and colorful fashionable dresses are recommended in the floor 3, wherein the association degree of the current financial affairs and the users is larger than that of the colorful fashionable dresses and the users.
According to the embodiment of the disclosure, since not only sample data for a used function but also sample data for other functions that are not used are acquired, training of the neural network model according to a plurality of acquired sample data can improve scores of other functions for the user in an output result of the neural network model. Therefore, the diversity of the finally obtained recommendation results can be improved, and the method can be applied to scenes such as cold start.
Fig. 10 schematically shows a block diagram of an object recommendation apparatus executed by an electronic device according to an embodiment of the present disclosure.
As shown in fig. 10, an object recommendation apparatus 1000 executed by an electronic device according to an embodiment of the present disclosure. The object recommending apparatus 1000 may include an identification obtaining module 1010, an association layer determining module 1020, an association degree determining module 1030, and a recommendation ranking module 1040.
The identity obtaining module 1010 is configured to obtain a user identity.
The association layer determining module 1020 is configured to match the user identifier in a knowledge graph to obtain an association layer node and an association object node of the user node corresponding to the user identifier, where the knowledge graph includes an association relationship between each user node, each layer node, and each object node, and each layer node includes at least one object node.
The association degree determining module 1030 is configured to process the association layer nodes, the association object nodes and the user nodes by using an object recommendation model, and determine a first association degree between each association layer node and the user node and a second association degree between each association layer node and the user node.
The recommendation sorting module 1040 is configured to perform recommendation sorting on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree, so as to recommend the association layer for the user identifier and the respective association objects of the association layer.
It should be noted that, the operations that can be performed by the identifier obtaining module 1010, the association layer determining module 1020, the association degree determining module 1030, and the recommendation sorting module 1040 may be the same as those of the related parts of the foregoing method, and are not described herein again.
The object recommendation device disclosed by the embodiment of the disclosure applies the graph database and the deep neural network, the relationship between the user and the floor is mined, and the relationship between the user and the product is mined, so that the floors are intelligently sorted according to the use habits and preferences of the user, the products in the floor are recommended, the user can easily find the concerned and common floors and the concerned products, the heterogeneous network recommendation is realized, the calculation cost is reduced, the operation cost is reduced, and the user experience is improved.
Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.
For example, any plurality of the identifier obtaining module 1010, the association layer determining module 1020, the association degree determining module 1030 and the recommendation ranking module 1040 may be combined and implemented in one module/unit/sub-unit, or any one of the modules/units/sub-units may be split into a plurality of modules/units/sub-units. Alternatively, at least part of the functionality of one or more of these modules/units/sub-units may be combined with at least part of the functionality of other modules/units/sub-units and implemented in one module/unit/sub-unit. According to an embodiment of the present disclosure, at least one of the identifier obtaining module 1010, the association layer determining module 1020, the association degree determining module 1030, and the recommendation ranking module 1040 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or implemented by a suitable combination of any several of them. Alternatively, at least one of the identity acquisition module 1010, the association level determination module 1020, the association degree determination module 1030, and the recommendation ranking module 1040 may be implemented at least in part as a computer program module that, when executed, may perform a corresponding function.
Fig. 11 schematically shows a block diagram of an electronic device adapted to perform an object recommendation method according to an embodiment of the present disclosure. The electronic device shown in fig. 11 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 11, an electronic device 1100 according to an embodiment of the present disclosure includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)1102 or a program loaded from a storage section 1108 into a Random Access Memory (RAM) 1103. The processor 1101 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 1101 may also include on-board memory for caching purposes. The processor 1101 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to the embodiments of the present disclosure.
In the RAM1103, various programs and data necessary for the operation of the electronic device 1100 are stored. The processor 1101, the ROM 1102, and the RAM1103 are connected to each other by a bus 1104. The processor 1101 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1102 and/or the RAM 1103. It is to be noted that the programs may also be stored in one or more memories other than the ROM 1102 and the RAM 1103. The processor 1101 may also perform various operations of the method flows according to the embodiments of the present disclosure by executing programs stored in the one or more memories.
According to an embodiment of the present disclosure, a method flow according to an embodiment of the present disclosure may be implemented as a computer program. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 1109 and/or installed from the removable medium 1111. The computer program, when executed by the processor 1101, performs the above-described functions defined in the electronic device of the embodiments of the present disclosure. According to embodiments of the present disclosure, the electronic devices, apparatuses, devices, modules, units, and the like described above may be realized by computer program modules.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 1102 and/or the RAM1103 and/or one or more memories other than the ROM 1102 and the RAM1103 described above.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (12)
1. An object recommendation method performed by an electronic device, comprising:
acquiring a user identifier;
matching the user identification in a knowledge graph to obtain an associated layer node and an associated object node of a user node corresponding to the user identification, wherein the knowledge graph comprises an association relation among the user node, the layer node and the object node, and each layer node comprises at least one object node;
processing the association layer nodes, the association object nodes and the user nodes by using an object recommendation model, and determining a first association degree between each association layer node and the user node and a second association degree between the association object nodes and the user nodes; and
and performing recommendation sequencing on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree so as to recommend the association layer and the respective association object of the association layer for the user identification.
2. The method of claim 1, wherein:
the object node includes: at least one of a function node or a product node, a hierarchy existing between at least two of the function nodes, the product node having an associated product attribute node;
the user node has an associated user attribute node; and
the input of the object recommendation model comprises the association layer node and the user node, and at least one of the following: function nodes, product attribute nodes and user attribute nodes.
3. The method of claim 2, further comprising: constructing the knowledge graph;
the constructing the knowledge-graph comprises:
determining a user node, a user attribute node, a function node, a layer node, a product node and a product attribute node;
determining a first connection relationship between the user node and the user attribute node, the function node, the layer node or the product node, respectively, determining a second connection relationship between at least two of the function nodes, determining a third connection relationship between the layer node and the function node and the product node, respectively, and determining a fourth connection relationship between the product node and the product attribute node; and
constructing a directed graph based on the user node, the user attribute node, the function node, the layer node, the product attribute node, the first connection relationship, the second connection relationship, the third connection relationship, and the fourth connection relationship to generate the knowledge graph.
4. The method of claim 3, wherein the knowledge-graph comprises a user database and an object graph, the data of the user nodes, the user attribute nodes, and the first connection relationships being stored in the user database.
5. The method of claim 3, further comprising: after the construction of the knowledge-graph,
inputting each node of the knowledge-graph into the object recommendation model to determine a node vector of each node, wherein the first relevance and the second relevance are determined based on similarity between the node vectors.
6. The method of claim 3, wherein the layer node is formed by:
determining a first inclusion relationship and a second inclusion relationship, wherein the first inclusion relationship is the relationship between the layer node and a function node of the layer node, and the second inclusion relationship is the relationship between the layer node and a product node displayed by the layer node; and
generating the layer node based on the function node and the first inclusion relation or based on the product node and the second inclusion relation.
7. The method of claim 1, wherein the matching the user identifier in a knowledge graph to obtain an association level node and an association object node of a user node corresponding to the user identifier comprises:
and extending the user node corresponding to the user identifier in the knowledge graph based on the association relation until reaching a specified extension depth to obtain an association layer node and an association object node of the user node corresponding to the user identifier.
8. The method of claim 1, wherein the object recommendation model is trained by:
acquiring training data, wherein the training data comprises first sub-training data, second sub-training data and third sub-training data, the first sub-training data is user historical operation data before a specified time, the second sub-training data is atlas data determined by extending the knowledge atlas by using user information in the first sub-training data, and the third sub-training data is user historical operation data after the specified time; and
inputting the first sub-training data and/or the second sub-training data into the object recommendation model, and adjusting model parameters of the object recommendation model such that an output of the object recommendation model approaches the third sub-training data.
9. The method of claim 1, wherein the recommending ordering of the association level nodes and respective associated object nodes based on the first and second degrees of association comprises:
performing first recommendation sequencing on the associated layer nodes based on the first association degree so as to take the associated layer nodes with a first designated number in the top sequence as the layer nodes to be recommended; and
and for each layer node to be recommended, performing second recommendation sequencing on the object nodes included in the layer node to be recommended based on the second relevance, so that the object nodes with the second specified number sequenced in the front are used as the object nodes to be recommended of the layer node to be recommended.
10. An object recommendation apparatus executed by an electronic device, comprising:
the identification acquisition module is used for acquiring a user identification;
the association layer determining module is used for matching the user identification in a knowledge graph to obtain an association layer node and an association object node of a user node corresponding to the user identification, wherein the knowledge graph comprises an association relation between every two user nodes, layer nodes and object nodes, and each layer node comprises at least one object node;
the association degree determining module is used for processing the association layer nodes, the association object nodes and the user nodes by utilizing an object recommendation model, and determining a first association degree between each association layer node and the user node and a second association degree between the association object nodes and the user nodes; and
and the recommendation sequencing module is used for performing recommendation sequencing on the association layer nodes and the respective association object nodes based on the first association degree and the second association degree so as to recommend the association objects of the association layer and the association layer aiming at the user identifier.
11. An electronic device, comprising:
one or more processors; and
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-9.
12. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010756547.XA CN111859147B (en) | 2020-07-31 | 2020-07-31 | Object recommendation method, object recommendation device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010756547.XA CN111859147B (en) | 2020-07-31 | 2020-07-31 | Object recommendation method, object recommendation device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111859147A true CN111859147A (en) | 2020-10-30 |
| CN111859147B CN111859147B (en) | 2023-08-22 |
Family
ID=72952557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010756547.XA Active CN111859147B (en) | 2020-07-31 | 2020-07-31 | Object recommendation method, object recommendation device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111859147B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732883A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Fuzzy matching method and device based on knowledge graph and computer equipment |
| CN116342267A (en) * | 2022-12-29 | 2023-06-27 | 中央国债登记结算有限责任公司深圳分公司 | Method and device for analyzing similarity of underwriter behaviors, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699751A (en) * | 2014-12-30 | 2015-06-10 | 北京奇虎科技有限公司 | Search recommending method and device based on search terms |
| CN110321482A (en) * | 2019-06-11 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of recommended method of information, device and equipment |
| CN110688476A (en) * | 2019-09-23 | 2020-01-14 | 腾讯科技（北京）有限公司 | Text recommendation method and device based on artificial intelligence |
| CN111177582A (en) * | 2019-12-30 | 2020-05-19 | 深圳市盟天科技有限公司 | Method and device for determining friend user, electronic equipment and storage medium |
-
2020
- 2020-07-31 CN CN202010756547.XA patent/CN111859147B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104699751A (en) * | 2014-12-30 | 2015-06-10 | 北京奇虎科技有限公司 | Search recommending method and device based on search terms |
| WO2016107326A1 (en) * | 2014-12-30 | 2016-07-07 | 北京奇虎科技有限公司 | Search recommending method and device based on search terms |
| CN110321482A (en) * | 2019-06-11 | 2019-10-11 | 阿里巴巴集团控股有限公司 | A kind of recommended method of information, device and equipment |
| CN110688476A (en) * | 2019-09-23 | 2020-01-14 | 腾讯科技（北京）有限公司 | Text recommendation method and device based on artificial intelligence |
| CN111177582A (en) * | 2019-12-30 | 2020-05-19 | 深圳市盟天科技有限公司 | Method and device for determining friend user, electronic equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112732883A (en) * | 2020-12-31 | 2021-04-30 | 平安科技（深圳）有限公司 | Fuzzy matching method and device based on knowledge graph and computer equipment |
| WO2022142027A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Knowledge graph-based fuzzy matching method and apparatus, computer device, and storage medium |
| CN116342267A (en) * | 2022-12-29 | 2023-06-27 | 中央国债登记结算有限责任公司深圳分公司 | Method and device for analyzing similarity of underwriter behaviors, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111859147B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11216509B2 (en) | Dynamic faceting for personalized search and discovery | |
| KR20180121466A (en) | Personalized product recommendation using deep learning | |
| US11138681B2 (en) | Inference model for traveler classification | |
| US20140025688A1 (en) | Determining, distinguishing and visualizing users' engagement with resources on a social network | |
| Alexandrova | Connecting economic models to the real world: Game theory and the FCC spectrum auctions | |
| US11334750B2 (en) | Using attributes for predicting imagery performance | |
| CN111061979B (en) | User tag pushing method and device, electronic equipment and medium | |
| CN115917535A (en) | Recommendation model training method, recommendation device and computer readable medium | |
| CN110377829B (en) | Function recommendation method and device applied to electronic equipment | |
| CN111767466A (en) | Recommendation information recommendation method and device based on artificial intelligence and electronic equipment | |
| CN109359247A (en) | Content delivery method and storage medium, computer equipment | |
| US20190287143A1 (en) | Retrieving reviews based on user profile information | |
| CN111143684A (en) | Artificial intelligence-based generalized model training method and device | |
| CN111859147B (en) | Object recommendation method, object recommendation device and electronic equipment | |
| CN111931055A (en) | Object recommendation method, object recommendation device and electronic equipment | |
| CN112598472A (en) | Product recommendation method, device, system, medium and program product | |
| CN112650942A (en) | Product recommendation method, device, computer system and computer-readable storage medium | |
| CN113392200A (en) | Recommendation method and device based on user learning behaviors | |
| CN117057855A (en) | Data processing method and related device | |
| CN117251619A (en) | Data processing method and related device | |
| CN116204709A (en) | Data processing method and related device | |
| CN112182386B (en) | Target recommendation method and device based on knowledge graph | |
| CN113901313A (en) | Game recommendation method and device, readable medium and electronic equipment | |
| US11036812B2 (en) | Guided search results | |
| KR20210084641A (en) | Method and apparatus for transmitting information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |