CN113449201A - Cross-session recommendation method, system, storage medium and electronic device - Google Patents
Cross-session recommendation method, system, storage medium and electronic device Download PDFInfo
- Publication number
- CN113449201A CN113449201A CN202110691296.6A CN202110691296A CN113449201A CN 113449201 A CN113449201 A CN 113449201A CN 202110691296 A CN202110691296 A CN 202110691296A CN 113449201 A CN113449201 A CN 113449201A
- Authority
- CN
- China
- Prior art keywords
- session
- conversation
- sequence
- knowledge
- cross
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Abstract
The application discloses a cross-session recommendation method, a system, a storage medium and an electronic device, wherein the cross-session recommendation method comprises the following steps: a session sequence construction step: preprocessing an original conversation text to obtain a conversation sequence; a session graph construction step: constructing a conversation graph based on the conversation sequence; a session sequence encoding step: encoding a session structure of the session graph to obtain a session vector; a knowledge acquisition step: outputting the conversation text knowledge through a knowledge acquisition model according to the conversation vector; a prediction step: and acquiring a recommendation result related to the user interest through a multilayer perceptron according to the conversation text knowledge. The invention considers the local conversation text knowledge and the global conversation text knowledge, so that the content recommendation material is richer.
Description
Technical Field
The invention belongs to the field of cross-session recommendation, and particularly relates to a cross-session recommendation method, a cross-session recommendation system, a storage medium and electronic equipment.
Background
In the recommendation system, basic recommendation basis is provided for user portrait data and article portrait data, besides, data such as historical behavior data of a user and click records of articles play an extremely important role, and more sufficient basis is provided for personalized recommendation. With the technology of the recommendation system becoming mature, data such as behavior data of users and click records of articles become bottlenecks in determining recommendation effects. In other words, the recommendation algorithm has richer data and can exert better recommendation effect. Therefore, how to obtain and construct richer behavior feature data is very important to be represented.
Detailed description of the prior art:
in the existing recommendation scenario, two main categories of recommendation routes can be mainly classified:
(1) user-based recommendations:
the user-based recommendation route mainly utilizes user-side data including user portrait, historical behavior data and the like, and then utilizes technologies such as collaborative filtering and matrix decomposition to obtain content interested by a user, or utilizes a mainstream wide-deep neural network based on deep learning to recommend the content.
(2) Item-based recommendations:
similar to the user-based recommendation, the item-based recommendation route also utilizes content portrait, history browsing, clicking and other data on the item side, and the subsequent flow is the same as the user-based recommendation route to complete the recommendation of the content.
Disclosure of Invention
The embodiment of the application provides a cross-session recommendation method, a cross-session recommendation system, a storage medium and electronic equipment, which are used for at least solving the problem that user behavior data and item click record data are insufficient in the existing cross-session recommendation method.
The invention provides a cross-session recommendation method, which comprises the following steps:
a session sequence construction step: preprocessing an original conversation text to obtain a conversation sequence;
a session graph construction step: constructing a conversation graph based on the conversation sequence;
a session sequence encoding step: encoding a session structure of the session graph to obtain a session vector;
a knowledge acquisition step: outputting the conversation text knowledge through a knowledge acquisition model according to the conversation vector;
a prediction step: and acquiring a recommendation result related to the user interest through a multilayer perceptron according to the conversation text knowledge.
The cross-session recommendation method described above, wherein the session sequence encoding step includes: and inputting the session structure into a neural network of a graph, and encoding the session structure to obtain the session vector containing global information.
The cross-session recommendation method described above, wherein the knowledge acquisition step includes: and modeling the conversation sequence by utilizing a time sequence convolution neural network to obtain the knowledge acquisition model, and acquiring the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence through the knowledge acquisition model according to the conversation vector.
The cross-session recommendation method described above, wherein the predicting step includes:
a prediction result obtaining step: predicting the content interested by the user through a multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to obtain a plurality of prediction results;
and a prediction result output step: and outputting the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
The invention also provides a cross-session recommendation system, which comprises the following components:
the conversation sequence building module is used for preprocessing an original conversation text to obtain a conversation sequence;
a session graph construction module that constructs a session graph based on the session sequence;
the session sequence coding module codes a session structure of the session graph to obtain a session vector;
the knowledge acquisition module outputs the conversation text knowledge through a knowledge acquisition model according to the conversation vector;
and the prediction module acquires a recommendation result related to the user interest through a multilayer perceptron according to the session text knowledge.
In the above cross-session recommendation system, the session sequence encoding module inputs the session structure into a neural network, encodes the session structure, and obtains the session vector including global information.
In the cross-session recommendation system, the knowledge acquisition module utilizes a time-series convolutional neural network to model the session sequence to obtain the knowledge acquisition model, and obtains the text knowledge of the current session sequence and the global text knowledge before the session sequence through the knowledge acquisition model according to the session vector.
The above cross-session recommendation system, wherein the prediction module comprises:
the prediction result acquisition unit is used for predicting the content interested by the user through a multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to obtain a plurality of prediction results;
and the prediction result output unit outputs the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor implements any one of the cross-session recommendation methods when executing the computer program.
The present invention also provides a storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the cross-session recommendation methods described herein.
The invention has the beneficial effects that:
the invention belongs to the field of recommendation algorithms in recommendation technologies. Based on the session text, the invention provides a cross-session recommendation method, and meanwhile, the problem of recommending cold start can be relieved; local conversation text knowledge and global conversation text knowledge are considered at the same time, so that content recommendation materials are richer; the user session behavior is expressed by using the structure of the graph, so that on one hand, the relationship flow among the users can be well expressed, on the other hand, the potential relationship possibly existing among all the users can be found from the whole graph, and a data support basis is provided for the subsequent user behavior relationship mining.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application.
In the drawings:
FIG. 1 is a technical route flow diagram of a cross-session recommendation method of the present invention;
FIG. 2 is a flow chart of a cross-session recommendation method of the present invention;
FIG. 3 is a flow chart illustrating substeps of step S5 according to the present invention;
FIG. 4 is a schematic structural diagram of the cross-session recommendation system of the present invention;
fig. 5 is a frame diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The present invention is described in detail with reference to the embodiments shown in the drawings, but it should be understood that these embodiments are not intended to limit the present invention, and those skilled in the art should understand that functional, methodological, or structural equivalents or substitutions made by these embodiments are within the scope of the present invention.
Before describing in detail the various embodiments of the present invention, the core inventive concepts of the present invention are summarized and described in detail by the following several embodiments.
The first embodiment is as follows:
the invention provides a cross-session recommendation method, the main technical route of the invention is shown in figure 1, and the method comprises the following specific steps:
referring to fig. 2, fig. 2 is a flowchart of a cross-session recommendation method. As shown in fig. 2, the cross-session recommendation method of the present invention includes:
session sequence construction step S1: and preprocessing the original conversation text to obtain a conversation sequence.
Specifically, the original conversation text is preprocessed, and the main purpose of this step is to construct the existing conversation text into a series of conversation sequences, as shown in table 1, we obtain the conversation texts of 3 users, and then we can obtain the conversation sequence representation as shown in the last column of table 1 according to the sequence of the conversation.
Session map building step S2: a conversation graph is constructed based on the conversation sequence.
Specifically, a session graph is constructed based on the session sequence, and the original session sequence is shown in the form of the graph, so that the advantage that the context information of the current session can be obtained, and the session information except the current session can also be obtained to supplement the current session. In addition, the number of interactions between sessions is adopted as a weight coefficient for the weight between the nodes in the graph, i.e., the weight ratio is larger as the frequency of session interaction is higher.
Session sequence encoding step S3: and coding the session structure of the session graph to obtain a session vector.
Specifically, the obtained session graph structure is input into a graph neural network, and the session structure is further encoded to obtain a session sequence vectorization representation containing global information.
Knowledge acquisition step S4: and outputting the conversation text knowledge through a knowledge acquisition model according to the conversation vector.
Specifically, the obtained session graph structure is input into a graph neural network, and the session structure is further encoded to obtain a session sequence vectorization representation containing global information.
Prediction step S5: and acquiring a recommendation result related to the user interest through a multilayer perceptron according to the conversation text knowledge.
Referring to fig. 3, fig. 3 is a flowchart of the prediction step S5. As shown in fig. 3, the predicting step S5 includes:
prediction result acquisition step S51: predicting the content interested by the user through a multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to obtain a plurality of prediction results;
prediction result output step S52: and outputting the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
Specifically, the invention finally completes the content prediction of interest of the user through a multi-layer perceptron (MLP), and outputs the content according to the sequence from high to low of the score, thus obtaining the recommendation result.
The cross-session recommendation method provided by the invention starts from user behaviors, simultaneously considers local characteristic information of the user and simultaneously considers all characteristic information, and the technical key points of the invention can be summarized as the following points:
1. based on local information and by utilizing the advantages of a graph structure, global characteristic information is expanded, on one hand, richer materials are provided, and on the other hand, the problem of cold start in a recommendation system can be indirectly relieved.
2. The method and the device can recommend the content which is interesting to the user, and can also mine and recommend the content which is potentially interesting to the user.
Example two:
referring to fig. 4, fig. 4 is a schematic structural diagram of a cross-session recommendation system according to the present invention. Fig. 4 shows a cross-session recommendation system of the present invention, which includes:
the conversation sequence building module is used for preprocessing an original conversation text to obtain a conversation sequence;
a session graph construction module that constructs a session graph based on the session sequence;
the session sequence coding module codes a session structure of the session graph to obtain a session vector;
the knowledge acquisition module outputs the conversation text knowledge through a knowledge acquisition model according to the conversation vector;
and the prediction module acquires a recommendation result related to the user interest through a multilayer perceptron according to the session text knowledge.
In the above cross-session recommendation system, the session sequence encoding module inputs the session structure into a neural network, encodes the session structure, and obtains the session vector including global information.
In the cross-session recommendation system, the knowledge acquisition module utilizes a time-series convolutional neural network to model the session sequence to obtain the knowledge acquisition model, and obtains the text knowledge of the current session sequence and the global text knowledge before the session sequence through the knowledge acquisition model according to the session vector.
The above cross-session recommendation system, wherein the prediction module comprises:
and the prediction result acquisition unit is used for predicting the content interested by the user through the multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to acquire a plurality of prediction results.
And the prediction result output unit outputs the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
Example three:
referring to fig. 5, this embodiment discloses a specific implementation of an electronic device. The electronic device may include a processor 81 and a memory 82 storing computer program instructions.
Specifically, the processor 81 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 82 may be used to store or cache various data files for processing and/or communication use, as well as possible computer program instructions executed by the processor 81.
The processor 81 implements any of the cross-session recommendation methods in the above embodiments by reading and executing computer program instructions stored in the memory 82.
In some of these embodiments, the electronic device may also include a communication interface 83 and a bus 80. As shown in fig. 5, the processor 81, the memory 82, and the communication interface 83 are connected via the bus 80 to complete communication therebetween.
The communication interface 83 is used for implementing communication between modules, devices, units and/or equipment in the embodiment of the present application. The communication port 83 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.
The bus 80 includes hardware, software, or both to couple the components of the electronic device to one another. Bus 80 includes, but is not limited to, at least one of the following: data Bus (Data Bus), Address Bus (Address Bus), Control Bus (Control Bus), Expansion Bus (Expansion Bus), and Local Bus (Local Bus). By way of example, and not limitation, Bus 80 may include an Accelerated Graphics Port (AGP) or other Graphics Bus, an Enhanced Industry Standard Architecture (EISA) Bus, a Front-Side Bus (Front Side Bus), an FSB (FSB), a Hyper Transport (HT) Interconnect, an ISA (ISA) Bus, an Infini Band Interconnect, a Low Pin Count (LPC) Bus, a memory Bus, a microchannel Architecture (MCA) Bus, a PCI (Peripheral Component Interconnect) Bus, a PCI-Express (PCI-X) Bus, a Serial Advanced Technology Attachment (SATA) Bus, a Video Electronics Bus (audio Electronics Association), abbreviated VLB) bus or other suitable bus or a combination of two or more of these. Bus 80 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.
The electronic device may implement the methods described in conjunction with fig. 2-3 based on cross-session recommendations.
In addition, in combination with the cross-session recommendation method in the foregoing embodiments, embodiments of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the cross-session recommendation methods in the embodiments described above.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
In summary, the beneficial effects of the invention are that the scheme is based on the session text, the invention provides a cross-session recommendation method, and meanwhile, the problem of recommending cold start can be alleviated; local conversation text knowledge and global conversation text knowledge are considered at the same time, so that content recommendation materials are richer; the user session behavior is expressed by using the structure of the graph, so that on one hand, the relationship flow among the users can be well expressed, on the other hand, the potential relationship possibly existing among all the users can be found from the whole graph, and a data support basis is provided for the subsequent user behavior relationship mining.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A cross-session recommendation method, comprising:
a session sequence construction step: preprocessing an original conversation text to obtain a conversation sequence;
a session graph construction step: constructing a conversation graph based on the conversation sequence;
a session sequence encoding step: encoding a session structure of the session graph to obtain a session vector;
a knowledge acquisition step: outputting the conversation text knowledge through a knowledge acquisition model according to the conversation vector;
a prediction step: and acquiring a recommendation result related to the user interest through a multilayer perceptron according to the conversation text knowledge.
2. The cross-session recommendation method of claim 1, wherein the session sequence encoding step comprises: and inputting the session structure into a neural network of a graph, and encoding the session structure to obtain the session vector containing global information.
3. The cross-session recommendation method of claim 1, wherein the knowledge acquisition step comprises: and modeling the conversation sequence by utilizing a time sequence convolution neural network to obtain the knowledge acquisition model, and acquiring the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence through the knowledge acquisition model according to the conversation vector.
4. The cross-session recommendation method of claim 3, wherein the predicting step comprises:
a prediction result obtaining step: predicting the content interested by the user through a multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to obtain a plurality of prediction results;
and a prediction result output step: and outputting the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
5. A cross-session recommendation system, comprising:
the conversation sequence building module is used for preprocessing an original conversation text to obtain a conversation sequence;
a session graph construction module that constructs a session graph based on the session sequence;
the session sequence coding module codes a session structure of the session graph to obtain a session vector;
the knowledge acquisition module outputs the conversation text knowledge through a knowledge acquisition model according to the conversation vector;
and the prediction module acquires a recommendation result related to the user interest through a multilayer perceptron according to the session text knowledge.
6. The cross-session recommendation system of claim 5, wherein the session sequence encoding module inputs the session structure into a graph neural network, encodes the session structure, and obtains the session vector containing global information.
7. The cross-session recommendation system of claim 5, wherein the knowledge acquisition module utilizes a time-series convolutional neural network to model the session sequence to obtain the knowledge acquisition model, and obtains the text knowledge of the current session sequence and the global text knowledge before the session sequence through the knowledge acquisition model according to the session vector.
8. The cross-session recommendation system of claim 7, wherein the prediction module comprises:
the prediction result acquisition unit is used for predicting the content interested by the user through a multilayer perceptron according to the text knowledge of the current conversation sequence and the global text knowledge before the conversation sequence to obtain a plurality of prediction results;
and the prediction result output unit outputs the plurality of prediction results according to the sequence of a preset rule to obtain the recommendation result.
9. 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 cross-session recommendation method of any one of claims 1-4 when executing the computer program.
10. A storage medium on which a computer program is stored, which program, when executed by a processor, implements a cross-session recommendation method as claimed in any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110691296.6A CN113449201A (en) | 2021-06-22 | 2021-06-22 | Cross-session recommendation method, system, storage medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110691296.6A CN113449201A (en) | 2021-06-22 | 2021-06-22 | Cross-session recommendation method, system, storage medium and electronic device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113449201A true CN113449201A (en) | 2021-09-28 |
Family
ID=77812111
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110691296.6A Pending CN113449201A (en) | 2021-06-22 | 2021-06-22 | Cross-session recommendation method, system, storage medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113449201A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109816101A (en) * | 2019-01-31 | 2019-05-28 | 中科人工智能创新技术研究院(青岛)有限公司 | A kind of session sequence of recommendation method and system based on figure convolutional neural networks |
CN111859160A (en) * | 2020-08-07 | 2020-10-30 | 成都理工大学 | Method and system for recommending session sequence based on graph neural network |
CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
CN112115352A (en) * | 2020-08-28 | 2020-12-22 | 齐鲁工业大学 | Session recommendation method and system based on user interests |
-
2021
- 2021-06-22 CN CN202110691296.6A patent/CN113449201A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109816101A (en) * | 2019-01-31 | 2019-05-28 | 中科人工智能创新技术研究院(青岛)有限公司 | A kind of session sequence of recommendation method and system based on figure convolutional neural networks |
CN111859160A (en) * | 2020-08-07 | 2020-10-30 | 成都理工大学 | Method and system for recommending session sequence based on graph neural network |
CN111949885A (en) * | 2020-08-27 | 2020-11-17 | 桂林电子科技大学 | Personalized recommendation method for scenic spots |
CN112115352A (en) * | 2020-08-28 | 2020-12-22 | 齐鲁工业大学 | Session recommendation method and system based on user interests |
Non-Patent Citations (1)
Title |
---|
RUI YE, QING ZHANG, HENGLIANG LUO: "Cross-Session Aware Temporal Convolutional Network for Session-based Recommendation", 《2020 INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW)》, pages 221 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111680219B (en) | Content recommendation method, device, equipment and readable storage medium | |
CN110309427B (en) | Object recommendation method and device and storage medium | |
US9864803B2 (en) | Method and system for multimodal clue based personalized app function recommendation | |
US11423234B2 (en) | Content generation using target content derived modeling and unsupervised language modeling | |
US9436768B2 (en) | System and method for pushing and distributing promotion content | |
CN110569496A (en) | Entity linking method, device and storage medium | |
CN113010778A (en) | Knowledge graph recommendation method and system based on user historical interest | |
CN110968564B (en) | Data processing method and training method of data state prediction model | |
CN108319628B (en) | User interest determination method and device | |
CN106803092B (en) | Method and device for determining standard problem data | |
CN114840869A (en) | Data sensitivity identification method and device based on sensitivity identification model | |
US11233761B1 (en) | Determining topic cohesion between posted and linked content | |
CN112328909A (en) | Information recommendation method and device, computer equipment and medium | |
US9454568B2 (en) | Method, apparatus and computer storage medium for acquiring hot content | |
CN113590948B (en) | Information recommendation method, device, equipment and computer storage medium | |
CN113743277A (en) | Method, system, equipment and storage medium for short video frequency classification | |
CN111324725B (en) | Topic acquisition method, terminal and computer readable storage medium | |
CN113535912A (en) | Text association method based on graph convolution network and attention mechanism and related equipment | |
CN113449201A (en) | Cross-session recommendation method, system, storage medium and electronic device | |
WO2022246162A1 (en) | Content generation using target content derived modeling and unsupervised language modeling | |
CN115186085A (en) | Reply content processing method and interaction method of media content interaction content | |
CN114328910A (en) | Text clustering method and related device | |
CN110837596B (en) | Intelligent recommendation method and device, computer equipment and storage medium | |
CN113919905A (en) | Risk user identification method, system, equipment and storage medium | |
CN112035622A (en) | Integrated platform and method for natural language processing |
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 |