CN111768231B - Product information recommendation method and device - Google Patents
Product information recommendation method and device Download PDFInfo
- Publication number
- CN111768231B CN111768231B CN202010587105.7A CN202010587105A CN111768231B CN 111768231 B CN111768231 B CN 111768231B CN 202010587105 A CN202010587105 A CN 202010587105A CN 111768231 B CN111768231 B CN 111768231B
- Authority
- CN
- China
- Prior art keywords
- target
- user
- product information
- vector
- information recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000013598 vector Substances 0.000 claims description 100
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013519 translation Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 230000005540 biological transmission Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 230000014616 translation Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 230000007704 transition Effects 0.000 description 5
- 239000000872 buffer Substances 0.000 description 4
- 230000002860 competitive effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Probability & Statistics with Applications (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a product information recommendation method and device, wherein the method comprises the following steps: constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users; determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph; and transmitting the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold. The method and the device can improve accuracy and individuation degree of product information recommendation, and are convenient for potential users to select financial products.
Description
Technical Field
The application relates to the technical field of knowledge maps, in particular to a product information recommendation method and device.
Background
The existing product information recommendation system generally adopts a collaborative filtering algorithm to realize the recommendation process, and the essence of the system is to search for similarity and focus on analyzing the interests and hobbies of users; through statistical analysis of the data, users with the same interest are found to serve as the same group, and the purchase probability of other users in the group on the same type of financial products is predicted and recommended by utilizing the purchase behaviors of one person.
However, the problem of sparsity is presented, and in a practical scene, the interaction information between a user and a financial product is often very sparse; applying such few observations to predict a large amount of unknown information can greatly increase the risk of overfitting with poor accuracy. Secondly, the cold start problem is that for newly added users, the newly added users have no corresponding interest history information, and for newly added financial products, the newly added financial products have no corresponding groups, so that modeling and recommendation are difficult to accurately perform. And thirdly, the individuation problem is solved, the contact between users in the group is not considered, the contact between the users and the financial products is not considered, and the individuation degree of the recommendation result is insufficient.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a product information recommending method and device, which can improve the accuracy and individuation degree of product information recommendation and facilitate the selection of potential users on financial products.
In order to solve the technical problems, the application provides the following technical scheme:
in a first aspect, the present application provides a product information recommendation method, including:
constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users;
Determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph;
and transmitting the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold.
Further, the relationship data between the two target entities includes: direct relationship data between users, direct relationship data between users and financial products, and potential relationship data between users and financial products.
Further, the determining the respective target purchase probability value of each user corresponding to the financial product based on the target product information recommendation knowledge graph includes: and generating respective corresponding vectors of the relation data by applying a preset knowledge representation model and the target product information recommendation knowledge graph, obtaining the weight of each relation data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relation data purchased by a user corresponding to the relation data.
Further, the edge between the two nodes represents relationship data between two target entities, including: the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities; correspondingly, the application of the preset knowledge representation model and the target product information recommendation knowledge graph generates respective corresponding vectors of the relational data, and obtains weights of the relational data according to a cosine similarity algorithm and the vectors, including: applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph to generate solid line vectors corresponding to the direct relation data, and obtaining weights of the direct relation data based on the solid line vectors and a cosine similarity algorithm to update the target product information recommendation knowledge graph; applying a preset second knowledge representation sub-model and an updated target product information recommendation knowledge graph to generate a dotted line vector corresponding to each potential relation data; and obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm.
In a second aspect, the present application provides a product information recommendation apparatus, including:
the construction module is used for constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relationship data between the target entities, wherein an edge between two nodes represents the relationship data between the two target entities, and the target entity comprises: financial products and users;
the purchase probability determining module is used for determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph;
and the pushing module is used for sending the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold value.
Further, the relationship data between the two target entities includes: direct relationship data between users, direct relationship data between users and financial products, and potential relationship data between users and financial products.
Further, the purchase probability determination module includes: the weight determining unit is used for applying a preset knowledge representation model and the target product information recommendation knowledge graph, generating respective corresponding vectors of the relational data, obtaining the weight of the relational data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relational data purchased by a user corresponding to the relational data.
Further, the edge between the two nodes represents relationship data between two target entities, including: the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities; correspondingly, the weight determining module comprises: the first weight determining unit is used for applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph to generate solid line vectors corresponding to the direct relation data, and obtaining the weight of the direct relation data based on the solid line vectors and a cosine similarity algorithm to update the target product information recommendation knowledge graph; the vector determining unit is used for applying a preset second knowledge representation sub-model and an updated target product information recommendation knowledge graph to generate a dotted vector corresponding to each potential relation data; and the second weight determining unit is used for obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the product information recommendation method when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon computer instructions that, when executed, implement the product information recommendation method.
According to the technical scheme, the application provides a product information recommending method and device. Wherein the method comprises the following steps: constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users; determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph; the shopping information of the financial product is sent to the target user of which the target purchase probability value exceeds a probability threshold value, so that the accuracy and individuation degree of product information recommendation can be improved, and the potential user can conveniently select the financial product; specifically, the accuracy and individuation degree of product information recommendation can be improved, user experience is improved, and meanwhile, the competitive capacity of financial products in the industry can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a product information recommendation method in an embodiment of the present application;
FIG. 2 is a flowchart of a product information recommendation method according to another embodiment of the present application;
fig. 3 is a flowchart illustrating steps 301 to 303 of a product information recommendation method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of the knowledge graph in the specific application example of the present application;
FIG. 5 is a vector representation of the knowledge-graph conversion in a specific application example of the present application;
FIG. 6 is a vector representation of a relationship graph between users in a specific application example of the present application;
FIG. 7 is a schematic diagram of a relationship between users in an example of an application of the present application;
FIG. 8 is a schematic diagram of an updated attribute in a specific application example of the present application;
FIG. 9 is a flowchart of a product information recommendation method in a specific application example of the present application;
fig. 10 is a schematic structural diagram of a product information recommendation device in an embodiment of the present application;
fig. 11 is a system configuration schematic block diagram of an electronic device 9600 according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions in the present specification, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
In order to improve accuracy and individuation degree of product information recommendation and facilitate selection of financial products by potential users, the embodiment of the application provides a product information recommendation device, which can be a server or user side equipment, wherein the user side equipment can comprise a smart phone, a tablet electronic device, a network set top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), vehicle-mounted equipment, intelligent wearable equipment and the like. Wherein, intelligent wearing equipment can include intelligent glasses, intelligent wrist-watch and intelligent bracelet etc..
In practical applications, the product information recommending part may be executed on the server side as described above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the ue and the limitation of the usage scenario of the user. The present application is not limited in this regard. If all operations are performed in the ue, the ue may further include a processor.
The user terminal device may have a communication module (i.e. a communication unit) and may be in communication connection with a remote server, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server of an intermediate platform, such as a server of a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.
Any suitable network protocol may be used for communication between the server and the client device, including those not yet developed at the filing date of this application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational State Transfer, representational state transfer protocol), etc. used above the above-described protocol.
The following examples are presented in detail.
In order to improve accuracy and individuation degree of product information recommendation and facilitate selection of financial products by potential users, the embodiment provides a product information recommendation method with an execution subject being a product information recommendation device, as shown in fig. 1, the method specifically includes the following contents:
step 101: constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users.
Step 102: and determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph.
Step 103: and transmitting the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold.
Specifically, the target entity comprises two types of financial products and users; the attribute data of the user comprises the consumption behavior, age layer, industry and the like of the user; the attribute data of the financial product includes: financial product risk types (including low, medium, and high risk types), issuer, and purchase amount, and the like. The relationship data between the two target entities includes: direct relationship data between users, direct relationship data between users and financial products, and potential relationship data between users and financial products; the direct relationship data between users is social relationship data between users, such as relative relationship data or friend relationship data; the direct relationship data between the user and the financial product may be direct purchase relationship data and browse but not purchase relationship data; the potential relationship data between the user and the financial product may be potential purchase relationship data; the direct relation data between the users and the financial products are represented by solid line edges between two nodes; the potential relationship data between the user and the financial product is represented by a dashed edge between two of the nodes.
As can be seen from the above description, the product information recommendation method provided in this embodiment constructs a target product information recommendation knowledge graph according to a large amount of observed data, such as relationship data between financial products and users, relationship data between users, and the like, so that accuracy of product information recommendation and individuation degree of recommendation results can be improved, and meanwhile, newly added users or financial products can be solved, and as no corresponding historical information exists, the problem of low recommendation accuracy can be facilitated, and selection of financial products by potential users can be facilitated.
In order to improve accuracy and efficiency of product information recommendation and improve the intelligentization degree of product information recommendation, referring to fig. 2, in one embodiment of the present application, step 102 includes:
step 201: and generating respective corresponding vectors of the relation data by applying a preset knowledge representation model and the target product information recommendation knowledge graph, obtaining the weight of each relation data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relation data purchased by a user corresponding to the relation data.
In order to further improve the reliability of the knowledge representation model and further improve the accuracy of determining the probability of purchasing the financial product by the user by applying the knowledge representation model, before the applying the preset knowledge representation model to generate the vectors corresponding to the respective relational data, the method may further include: acquiring a plurality of triples in a pre-stored knowledge base; the knowledge representation model, which may be a transient model, is trained using a plurality of the triplets and maximum spacing methods. The transition model may implement a distributed vector representation based on entities, as well as entity attributes and entity relationships, regarding the relationships in each triplet instance as translations from the originating entity to the target entity.
In order to further improve reliability of obtaining weights corresponding to the relationship data and further improve accuracy of determining a purchase probability of the potential user, in an embodiment of the present application, an edge between the two nodes represents the relationship data between the two target entities, including: the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities; correspondingly, referring to fig. 3, the step 201 includes:
Step 301: and generating a solid line vector corresponding to each direct relation data by applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph, and obtaining the weight of each direct relation data based on the solid line vector and a cosine similarity algorithm so as to update the target product information recommendation knowledge graph.
Step 302: and applying a preset second knowledge representation sub-model and the updated target product information recommendation knowledge graph to generate a dotted line vector corresponding to each potential relation data.
Step 303: and obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm.
It will be appreciated that the two entities to which the potential relationship data corresponds are financial products and users, respectively. The preset knowledge representation model may include: a first knowledge representation sub-model and a second knowledge representation sub-model; the preset first knowledge representation sub-model is a pre-trained transmission model, the preset second knowledge representation sub-model is also a pre-trained transmission model, training sets of the pre-trained transmission model and the pre-trained transmission model are different, and output of the trained transmission model is also different.
In order to further explain the present solution, the present application provides a specific application example of a product information recommendation method, as shown in fig. 9, where the method includes:
s1: constructing a knowledge graph; specifically, a knowledge graph of users and products is constructed. Referring to fig. 4, the entities in the knowledge graph include two types of users and products, and consumption behavior, age layers, industries and the like of the users are taken as attributes of the user entities. The relationship comprises: 1) Social relationships between users (relatives, friends, users of the same class, etc.), such as relationships between user A and user B, and relationships between user B and user C; 2) The relationship between the user and the product (direct purchase, browse not purchase, potential purchase probability, etc.), such as the relationship between the user B and the products a, B, C and D, respectively, may also correspond to credit card consumption record information. The solid line relationship is the relationship existing objectively between users or the relationship between users and the actual associated products (such as direct purchase and browsing are not purchased), the dotted line relationship represents the purchase behavior which does not occur yet, and the potential purchase probability can be determined by the specific application example. Suppose user B is the target user.
S2: modeling by trans E; as shown in fig. 5, the solid line relation among all entities in the knowledge graph is converted into a vector representation, wherein h represents the vector of the initial entity and the attribute thereof; t represents a vector of target entities and their attributes; r represents a vector of relationships between entities. Learning a transition model using knowledge-graph representation enables a distributed vector representation based on entities and their attributes and relationships, considering the relationships in each triplet instance as a translation from the originating entity to the target entity. By training the spectral representation learning transition model, h, r and t are continuously adjusted so that (h+r) is as equal as possible to t, i.e. h+r=t. In model training, a maximum interval method is adopted, an objective function L is minimized, and the expression of the objective function L is as follows:
wherein d (h+r, t) is a distance function; s is a triplet in a knowledge base, namely a training set; s' represents a negative sampling triplet, obtained by replacing h or t, which is artificially randomly generated. Gamma represents a spacing distance parameter with a value greater than 0, and is a super parameter. When [ x ] + represents a positive function, i.e., x >0, [ x ] +=x; when x is less than or equal to 0, [ x ] +=0. The gradient update only needs to calculate distances d (h+r, t) and d (h '+r, t'), h 'represents the vector of the initial entity and the attribute thereof in the last training model, t' represents the vector of the target entity and the attribute thereof in the last training model, and the gradient descent method is adopted for parameter adjustment.
S3: the weight of the solid line relation is calculated, namely, the weight between users and the relation between the users and the actual associated products (direct purchase, browse and not purchase, etc.) are calculated, and the weight corresponding to the direct purchase behavior is set as 1 by default.
The relationships between users are represented by vectors using trans. Suppose user B is the target user. As shown in fig. 6, the triplet user B-buddy-user a is represented by vector a. The set user B-principal-user B triplet is represented by vector B. The weight on the default user B-principal-user B edge is 1. And determining cosine similarity cos theta between the vector A and the vector B according to the vector A and the vector B, and comparing the similarity degree of the two vectors A and B by utilizing the cosine similarity of the included angles of the two vectors to obtain the weight omega 1 on the side of the user B, the friend and the user A. The expression for calculating cosine similarity is as follows:
where A and B represent norms of the vector A, B.
It can be seen from fig. 7 that the user a directly purchases the product B, and the edge weight ω2 is 1 at this time. From this the total weight on the side of user B-user a-product B can be calculated:
ω3=ω1×ω2
the weight ω3 calculated at this time is used in the subsequent transit modeling as one attribute of the entity of product B.
S4: modeling by trans E; and converting the dotted line relation among all the entities in the knowledge graph into vector representation. As shown in fig. 8, in step S3, the entity product B updates the weight ω3 as an attribute, and uses the transition modeling again, and at this time, the vector of the initial entity corresponds to the user B; the vector of the target entity corresponds to product B.
S5: and calculating the weight of the relation of the dotted line, namely calculating the weight of the relation between the target user B and the potential purchased product, and representing the relation between the user and the product by using a vector by using a transition. As shown in fig. 8, the triplet user B-potential purchase-product B is represented by vector C. The set user B-direct purchase-product a triplet is represented by vector D. Default user B-direct purchase-product a side weight is 1. And comparing the similarity degree of the two vectors C and D by using the cosine similarity degree of the included angle of the two vectors to obtain the weight omega 4 on the side of the user B-potential purchase-product C. This weight is the probability that target user B purchased product B.
The purchasing probability of the target user on each product is calculated, so that the user can intuitively see which products the target user is more interested in, and the success rate of recommendation is higher.
In order to improve accuracy and individuation degree of product information recommendation and facilitate selection of financial products by potential users, the application further provides an embodiment of a product information recommendation device for implementing all or part of contents in the product information recommendation method, referring to fig. 10, where the product information recommendation device specifically includes the following contents:
The construction module 10 is configured to construct a target product information recommendation knowledge graph using a target entity as a node according to attribute data of the target entity and relationship data between the target entities, where an edge between two nodes represents the relationship data between two target entities, and the target entity includes: financial products and users.
And the purchase probability determining module 20 is configured to determine respective target purchase probability values of the users corresponding to the financial products based on the target product information recommendation knowledge graph.
And the pushing module 30 is used for sending the shopping information of the financial product to the target user with the target purchase probability value exceeding a probability threshold.
Specifically, direct relationship data between users and financial products, and potential relationship data between users and financial products.
In one embodiment of the present application, the purchase probability determining module includes:
the weight determining unit is used for applying a preset knowledge representation model and the target product information recommendation knowledge graph, generating respective corresponding vectors of the relational data, obtaining the weight of the relational data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relational data purchased by a user corresponding to the relational data.
In one embodiment of the present application, the edge between the two nodes represents relationship data between two target entities, including: the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities; correspondingly, the weight determining module comprises:
the first weight determining unit is used for applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph to generate solid line vectors corresponding to the direct relation data, and obtaining the weight of the direct relation data based on the solid line vectors and a cosine similarity algorithm to update the target product information recommendation knowledge graph.
And the vector determining unit is used for applying a preset second knowledge representation sub-model and the updated target product information recommendation knowledge graph to generate a dotted vector corresponding to each potential relation data.
And the second weight determining unit is used for obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm.
The embodiment of the product information recommendation system provided in the present disclosure may be specifically used to execute the processing flow of the embodiment of the product information recommendation method, and the functions thereof are not described herein again, and may refer to the detailed description of the embodiment of the product information recommendation method.
As can be seen from the above description, the product information recommending method and device provided by the present application can improve accuracy and individuation degree of product information recommendation, and facilitate selection of financial products by potential users; specifically, the accuracy and individuation degree of product information recommendation can be improved, user experience is improved, and meanwhile, the competitive capacity of financial products in the industry can be improved.
In order to improve accuracy and individuation degree of product information recommendation and facilitate selection of financial products by potential users, in terms of hardware, the application provides an embodiment of an electronic device for implementing all or part of contents in a product information recommendation method, where the electronic device specifically includes the following contents:
a processor (processor), a memory (memory), a communication interface (Communications Interface), and a bus; the processor, the memory and the communication interface complete communication with each other through the bus; the communication interface is used for realizing information transmission between the product information recommending device and related equipment such as a user terminal; the electronic device may be a desktop computer, a tablet computer, a mobile terminal, etc., and the embodiment is not limited thereto. In this embodiment, the electronic device may be implemented with reference to the embodiment for implementing the product information recommendation method and the embodiment for implementing the product information recommendation device, and the content thereof is incorporated herein, and the repetition is omitted.
Fig. 11 is a schematic block diagram of a system configuration of an electronic device 9600 of an embodiment of the present application. As shown in fig. 11, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 11 is exemplary; other types of structures may also be used in addition to or in place of the structures to implement telecommunications functions or other functions.
In one or more embodiments of the present application, the product information recommendation function may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:
step 101: constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users.
Step 102: and determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph.
Step 103: and transmitting the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold.
From the above description, the electronic device provided by the embodiment of the application can improve accuracy and individuation degree of product information recommendation, and is convenient for potential users to select financial products.
In another embodiment, the product information recommending apparatus may be configured separately from the central processor 9100, for example, the product information recommending apparatus may be configured as a chip connected to the central processor 9100, and the product information recommending function is implemented by control of the central processor.
As shown in fig. 11, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 need not include all of the components shown in fig. 11; in addition, the electronic device 9600 may further include components not shown in fig. 11, and reference may be made to the related art.
As shown in fig. 11, the central processor 9100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives inputs and controls the operation of the various components of the electronic device 9600.
The memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.
The memory 9140 may also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. A communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, as in the case of conventional mobile communication terminals.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.
As can be seen from the above description, the electronic device provided by the embodiment of the present application can improve accuracy and individuation degree of product information recommendation, and is convenient for a potential user to select a financial product.
The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the product information recommendation method in the above embodiments, the computer-readable storage medium storing thereon a computer program which, when executed by a processor, implements all the steps in the product information recommendation method in the above embodiments, for example, the processor implements the following steps when executing the computer program:
step 101: constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users.
Step 102: and determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph.
Step 103: and transmitting the shopping information of the financial product to the target user of which the target purchase probability value exceeds a probability threshold.
As can be seen from the above description, the computer readable storage medium provided by the embodiments of the present application can improve accuracy and individuation degree of product information recommendation, and facilitate selection of financial products by potential users.
All embodiments of the method are described in a progressive manner, and identical and similar parts of all embodiments are mutually referred to, and each embodiment mainly describes differences from other embodiments. For relevance, see the description of the method embodiments.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principles and embodiments of the present application are described herein with reference to specific examples, the description of which is only for the purpose of aiding in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (4)
1. A product information recommendation method, comprising:
constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relation data between the target entities, wherein an edge between two nodes represents the relation data between the two target entities, and the target entity comprises: financial products and users; the relationship data between the two target entities includes: direct relationship data between users, direct relationship data between users and financial products, and potential relationship data between users and financial products, wherein the direct relationship data between users is social relationship data between users;
determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph;
transmitting shopping information of the financial product to a target user of which the target purchase probability value exceeds a probability threshold value;
the determining the respective target purchase probability value of each user corresponding to the financial product based on the target product information recommendation knowledge graph comprises the following steps:
the method comprises the steps of generating respective corresponding vectors of each piece of relation data by applying a preset knowledge representation model and a target product information recommendation knowledge graph, obtaining weight of each piece of relation data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relation data purchased by a user corresponding to the relation data;
The edge between the two nodes represents the relationship data between two target entities, comprising:
the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities;
correspondingly, the application of the preset knowledge representation model and the target product information recommendation knowledge graph generates respective corresponding vectors of the relational data, and obtains weights of the relational data according to a cosine similarity algorithm and the vectors, including:
applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph to generate solid line vectors corresponding to the direct relation data, and obtaining weights of the direct relation data based on the solid line vectors and a cosine similarity algorithm to update the target product information recommendation knowledge graph;
applying a preset second knowledge representation sub-model and an updated target product information recommendation knowledge graph to generate a dotted line vector corresponding to each potential relation data;
obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm;
The obtaining weights of the direct relation data based on the solid line vector and cosine similarity algorithm to update the target product information recommendation knowledge graph comprises the following steps:
and obtaining a weight omega 1 on the side of the user B-friend-user A by using cosine similarity of an included angle between the vector A and the vector B, wherein the target entity comprises: the method comprises the steps that direct relation data exist between a user A, a user B, a product A and a product B, direct relation data exist between the user A and the user B, potential relation data exist between the user B and the product B, direct relation data exist between the user B and the product A, a vector A is a vector representation of a user B-friend-user A triplet, and a vector B is a vector representation of a user B-principal-user B;
the total weight on the side of the user B-user A-product B is ω3=ω1×ω2, wherein ω2 is the weight on the side of the user A-product B, and ω3 is taken as an attribute of the product B to update the target product information recommendation knowledge graph;
the weight obtaining method based on the weight, the dotted line vector and the cosine similarity algorithm of the direct relation data, obtains the weight of each potential relation data, and comprises the following steps:
and obtaining weight omega 4 on the side of the user B-potential purchase-product B by using cosine similarity of an included angle between a vector C and a vector D, wherein the vector C is the vector representation of the user B-potential purchase-product B triplet in the updated target product information recommendation knowledge graph, and the vector D is the vector representation of the user B-direct purchase-product A triplet in the updated target product information recommendation knowledge graph.
2. A product information recommendation device, characterized by comprising:
the construction module is used for constructing a target product information recommendation knowledge graph taking a target entity as a node according to attribute data of the target entity and relationship data between the target entities, wherein an edge between two nodes represents the relationship data between the two target entities, and the target entity comprises: financial products and users; the relationship data between the two target entities includes: direct relationship data between users, direct relationship data between users and financial products, and potential relationship data between users and financial products, wherein the direct relationship data between users is social relationship data between users;
the purchase probability determining module is used for determining respective target purchase probability values of all users corresponding to the financial products based on the target product information recommendation knowledge graph;
the pushing module is used for sending the shopping information of the financial product to a target user of which the target purchase probability value exceeds a probability threshold value;
the purchase probability determination module includes:
the weight determining unit is used for applying a preset knowledge representation model and the target product information recommendation knowledge graph, generating respective corresponding vectors of the relational data, obtaining the weight of the relational data according to a cosine similarity algorithm and the vectors, and taking the weight as a target purchase probability value, wherein the knowledge representation model is a translation model trained in advance, and the target purchase probability value is a purchase probability value of a financial product corresponding to the relational data purchased by a user corresponding to the relational data;
The edge between the two nodes represents the relationship data between two target entities, comprising: the solid line edge between two said nodes represents the direct relationship data between two target entities, and the dashed line edge between two said nodes represents the potential relationship data between two target entities;
correspondingly, the weight determining module comprises:
the first weight determining unit is used for applying a preset first knowledge representation sub-model and the target product information recommendation knowledge graph to generate solid line vectors corresponding to the direct relation data, and obtaining the weight of the direct relation data based on the solid line vectors and a cosine similarity algorithm to update the target product information recommendation knowledge graph;
the vector determining unit is used for applying a preset second knowledge representation sub-model and an updated target product information recommendation knowledge graph to generate a dotted vector corresponding to each potential relation data;
the second weight determining unit is used for obtaining the weight of each potential relation data based on the weight of the direct relation data, the dotted line vector and the cosine similarity algorithm;
the obtaining weights of the direct relation data based on the solid line vector and cosine similarity algorithm to update the target product information recommendation knowledge graph comprises the following steps:
And obtaining a weight omega 1 on the side of the user B-friend-user A by using cosine similarity of an included angle between the vector A and the vector B, wherein the target entity comprises: the method comprises the steps that direct relation data exist between a user A, a user B, a product A and a product B, direct relation data exist between the user A and the user B, potential relation data exist between the user B and the product B, direct relation data exist between the user B and the product A, a vector A is a vector representation of a user B-friend-user A triplet, and a vector B is a vector representation of a user B-principal-user B;
the total weight on the side of the user B-user A-product B is ω3=ω1×ω2, wherein ω2 is the weight on the side of the user A-product B, and ω3 is taken as an attribute of the product B to update the target product information recommendation knowledge graph;
the weight obtaining method based on the weight, the dotted line vector and the cosine similarity algorithm of the direct relation data, obtains the weight of each potential relation data, and comprises the following steps:
and obtaining weight omega 4 on the side of the user B-potential purchase-product B by using cosine similarity of an included angle between a vector C and a vector D, wherein the vector C is the vector representation of the user B-potential purchase-product B triplet in the updated target product information recommendation knowledge graph, and the vector D is the vector representation of the user B-direct purchase-product A triplet in the updated target product information recommendation knowledge graph.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the product information recommendation method of claim 1 when the program is executed by the processor.
4. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the product information recommendation method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010587105.7A CN111768231B (en) | 2020-06-24 | 2020-06-24 | Product information recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010587105.7A CN111768231B (en) | 2020-06-24 | 2020-06-24 | Product information recommendation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111768231A CN111768231A (en) | 2020-10-13 |
CN111768231B true CN111768231B (en) | 2024-04-09 |
Family
ID=72722231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010587105.7A Active CN111768231B (en) | 2020-06-24 | 2020-06-24 | Product information recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111768231B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112364181B (en) * | 2020-11-27 | 2024-05-28 | 深圳市慧择时代科技有限公司 | Insurance product matching degree determining method and apparatus |
CN112598472B (en) * | 2020-12-25 | 2024-02-13 | 中国工商银行股份有限公司 | Product recommendation method, device, system, medium and program product |
CN112581281A (en) * | 2020-12-28 | 2021-03-30 | 中国建设银行股份有限公司 | Product recommendation method and device, storage medium and electronic equipment |
CN112767144A (en) * | 2021-03-18 | 2021-05-07 | 中国工商银行股份有限公司 | Bank financial marketing recommendation method and device |
CN113408627A (en) * | 2021-06-22 | 2021-09-17 | 中国工商银行股份有限公司 | Target object determination method and device and server |
CN113297338B (en) * | 2021-07-27 | 2022-03-29 | 平安科技(深圳)有限公司 | Method, device and equipment for generating product recommendation path and storage medium |
CN114022246B (en) * | 2021-11-05 | 2023-08-11 | 平安科技(深圳)有限公司 | Product information pushing method and device, terminal equipment and storage medium |
CN115239442B (en) * | 2022-09-22 | 2023-01-06 | 湖南快乐通宝小额贷款有限公司 | Method and system for popularizing internet financial products and storage medium |
CN116304303B (en) * | 2023-02-01 | 2023-09-08 | 北京三维天地科技股份有限公司 | Asset recommendation method and system based on knowledge graph |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241449A (en) * | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
CN109508419A (en) * | 2018-11-23 | 2019-03-22 | 成都品果科技有限公司 | A kind of recommended method and system of knowledge based study |
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 |
CN110335112A (en) * | 2019-06-18 | 2019-10-15 | 中国平安财产保险股份有限公司 | A kind of Products Show method, apparatus and computer storage medium |
CN110969350A (en) * | 2019-11-28 | 2020-04-07 | 中国银行股份有限公司 | Product information recommendation method and device, electronic equipment and storage medium |
CN111199459A (en) * | 2019-12-30 | 2020-05-26 | 深圳市盟天科技有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
-
2020
- 2020-06-24 CN CN202010587105.7A patent/CN111768231B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241449A (en) * | 2018-10-30 | 2019-01-18 | 国信优易数据有限公司 | A kind of item recommendation method and device |
CN109508419A (en) * | 2018-11-23 | 2019-03-22 | 成都品果科技有限公司 | A kind of recommended method and system of knowledge based study |
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 |
CN110335112A (en) * | 2019-06-18 | 2019-10-15 | 中国平安财产保险股份有限公司 | A kind of Products Show method, apparatus and computer storage medium |
CN110969350A (en) * | 2019-11-28 | 2020-04-07 | 中国银行股份有限公司 | Product information recommendation method and device, electronic equipment and storage medium |
CN111199459A (en) * | 2019-12-30 | 2020-05-26 | 深圳市盟天科技有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
CN111241300A (en) * | 2020-01-09 | 2020-06-05 | 中信银行股份有限公司 | Public opinion early warning and risk propagation analysis method, system, equipment and storage medium |
Non-Patent Citations (1)
Title |
---|
基于平移模型的知识图谱补全算法研究;蔡泽胤;《中国优秀硕士学位论文全文数据库 信息科技辑》(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111768231A (en) | 2020-10-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111768231B (en) | Product information recommendation method and device | |
CN110390108B (en) | Task type interaction method and system based on deep reinforcement learning | |
CN111861569B (en) | Product information recommendation method and device | |
US9491257B2 (en) | Facilitation of social interactions | |
CN103535056A (en) | Presenting messages associated with locations | |
CN112948695A (en) | User portrait based general financial fast loan product recommendation method and device | |
CN111159570A (en) | Information recommendation method and server | |
US11763204B2 (en) | Method and apparatus for training item coding model | |
US20180197109A1 (en) | Methods and Systems for Ranking Comments on a Post in an Online Service | |
KR20230152723A (en) | Compressing image-to-image models using average smoothing | |
CN111787042B (en) | Method and device for pushing information | |
JP2024508502A (en) | Methods and devices for pushing information | |
CN111480348B (en) | System and method for audio-based augmented reality | |
CN112418929A (en) | Data sharing method and device | |
CN112395490B (en) | Method and device for generating information | |
CN117033599A (en) | Digital content generation method and related equipment | |
CN111191143B (en) | Application recommendation method and device | |
CN115757933A (en) | Recommendation information generation method, device, equipment, medium and program product | |
CN116561735B (en) | Mutual trust authentication method and system based on multiple authentication sources and electronic equipment | |
CN117216538A (en) | Content release model training method, content release method, device and electronic equipment | |
CN118278536A (en) | Training method, device and system for user attention hotspot prediction model | |
CN117056810A (en) | Group classification method and device | |
CN114912585A (en) | Neural network generation method and device | |
US20200401667A1 (en) | Systems and methods for content provisioning | |
CN117493666A (en) | Article cold start recommendation method and article cold start recommendation model training method |
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 |