CN116738057A - Information recommendation method, device, computer equipment and storage medium - Google Patents
Information recommendation method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116738057A CN116738057A CN202310768925.XA CN202310768925A CN116738057A CN 116738057 A CN116738057 A CN 116738057A CN 202310768925 A CN202310768925 A CN 202310768925A CN 116738057 A CN116738057 A CN 116738057A
- Authority
- CN
- China
- Prior art keywords
- information
- recommended
- user
- term
- sequence
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003068 static effect Effects 0.000 claims abstract description 51
- 230000000007 visual effect Effects 0.000 claims abstract description 23
- 230000006399 behavior Effects 0.000 claims description 46
- 230000007774 longterm Effects 0.000 claims description 42
- 238000001914 filtration Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the field of artificial intelligence and intelligent medical treatment, and provides an information recommendation method, an information recommendation device, information recommendation equipment and a computer storage medium, wherein the method comprises the following steps: based on a preset multi-mode model, acquiring static characteristics of information to be recommended, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended; determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended; clustering the information to be recommended according to the static information and the dynamic information, and determining the information type of the information to be recommended; and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information. The information recommendation method provided by the application can be applied to a medical platform, combines diversified information characteristics as the basis of information recommendation, and improves the accuracy of information recommendation.
Description
Technical Field
The present application relates to the field of artificial intelligence and intelligent medical science, and in particular, to an information recommendation method, an information recommendation device, a computer device, and a storage medium.
Background
With the rise of intelligent recommendation algorithms, applications of the intelligent recommendation algorithms in the content platform are becoming more and more common, and content which may be of interest to a user can be recommended according to content browsed by the user through the intelligent recommendation algorithm. The content platform can be, for example, a medical platform, and the user searches for medical information to be known, and the platform recommends other content to the user according to the correlation between the content browsed by the user and the other content. However, the existing intelligent recommendation algorithm is often recommended according to labels of contents, some labels are even added by users, the basis for determining recommended contents is often single, on the basis of the fact, user intention is difficult to accurately identify, and the accuracy of the recommended contents is low.
Disclosure of Invention
The application mainly aims to provide an information recommendation method, device, equipment and computer storage medium, aiming at improving the accuracy of information recommendation.
In a first aspect, the present application provides an information recommendation method, including the steps of:
based on a preset multi-mode model, acquiring static characteristics of information to be recommended, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended;
determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended;
clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended;
and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
In a second aspect, the present application also provides an information recommendation apparatus, including:
the static information acquisition module is used for acquiring static characteristics of information to be recommended based on a preset multi-mode model, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended;
the dynamic information acquisition module is used for determining the dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended;
the information clustering module is used for carrying out clustering processing on the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended;
and the information recommending module is used for determining target recommending information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements an information recommendation method as described above.
In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements an information recommendation method as described above.
The application provides an information recommending method, an information recommending device, information recommending equipment and a computer storage medium, wherein static characteristics of information to be recommended are obtained based on a preset multi-mode model, and the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended; determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended; clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended; and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information. As diversified information features are combined to serve as information recommendation bases, target recommendation information recommended to the user is more in line with actual intention of the user, and accuracy of information recommendation is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of an information recommendation method according to an embodiment of the present application;
FIG. 2 is a view of a usage scenario of an information recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic block diagram of an information recommendation device according to an embodiment of the present application;
fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.
The embodiment of the application provides an information recommendation method, an information recommendation device, computer equipment and a computer readable storage medium.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a flowchart of an information recommendation method according to an embodiment of the application. The information recommendation method can be used in a terminal or a server to realize information recommendation to a user browsing content information in a content platform. The terminal can be electronic equipment such as a mobile phone, a tablet personal computer, a notebook computer, a desktop computer, a personal digital assistant, wearable equipment and the like; the server may be an independent server, a server cluster, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), basic cloud computing services such as big data and artificial intelligence platforms, and the like.
The information recommending method provided by the embodiment of the application can be applied to a medical platform, and content related to the information browsed by the user is recommended to the user according to the medical information browsed by the user.
Referring to fig. 2, fig. 2 is a usage scenario diagram according to an embodiment of the present application. As shown in fig. 2, the static characteristics of the information to be recommended are determined according to the visual characteristics and the text characteristics, and the dynamic characteristics of the information to be recommended are determined according to the user sequence of the user performing the operation on the information to be recommended; after the dynamic characteristics and the static characteristics of the information to be recommended are determined, the information type of the information to be recommended is determined according to the dynamic information and the static information.
As shown in fig. 1, the information recommendation method includes steps S101 to S104.
Step S101, based on a preset multi-mode model, acquiring static characteristics of information to be recommended, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended.
For example, the information to be recommended in the content platform may include various forms of information, such as image information and voice information; of course, the present application is not limited thereto, and may include voice information, video information, and the like, and is not limited thereto.
The multi-modal model can process information in various different forms, integrate characteristics of the information in various different forms, and obtain static characteristics capable of summarizing overall characteristics of information to be recommended.
The static feature may be obtained based on the visual feature of the image information in the information to be recommended and the text feature of the text information, which is not limited to this, and may also include the voice feature of the voice information in the information to be recommended.
In some embodiments, the acquiring static features of the information to be recommended based on the preset multimodal model, where the static features include a visual feature and a text feature of the information to be recommended, includes: and fusing the visual features and the text features of the information to be recommended based on a preset self-attention model to obtain the static features.
By way of example, the multimodal model may be a visual feature and text feature capable self-attention model (Vision-and-Language Transformer, viLT).
By way of example, by inputting visual and textual features of the information to be recommended into the ViLT, static features can be derived that can be used to describe the information to be recommended. The static feature may be embodied by a vector, which is not limited thereto.
In some embodiments, the method further comprises: acquiring image information in the information to be recommended, and splitting the image information into a plurality of sub-image information; inputting the sub-image information into a preset image feature extraction network to obtain sub-image features corresponding to the sub-image information; and determining the image characteristics of the image information according to the sub-image characteristics to obtain the visual characteristics of the information to be recommended.
The calculation amount required for extracting the features of the image information in the information to be recommended is large, the features of the image information can be obtained by dividing the image information into sub-image (patch) information and extracting the features of the sub-image (patch), and the features of the sub-image (patch) information are combined according to the features of each patch to obtain the image features of the image information, which are used as the visual features of the information to be recommended.
The image characteristics of the image information may be determined by transformation, and are not limited thereto. The sub-image features and the image features may be represented by vectors, which are not limited thereto.
In some embodiments, the method further comprises: acquiring text information in the information to be recommended, and performing word segmentation on the text information to obtain entity text corresponding to the text information; and determining the text characteristics of the entity text based on a preset bidirectional coding model to obtain the text characteristics of the information to be recommended.
By way of example, word segmentation is performed on text information in information to be recommended to obtain entity texts with practical meanings in the text information, nonsensical texts such as auxiliary words and word gases in the text information are filtered, and accuracy of text features is improved.
The feature extraction is performed on the entity text based on a bi-directional coding model (Bidirectional Encoder Representation from Transformers, BERT) to obtain text features of the entity text corresponding to the information to be recommended. The text feature may be embodied by a vector, which is not limited thereto, and is not limited thereto.
Step S102, determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended.
The behavior sequence of the information to be recommended may be, for example, a user sequence [ user ] for performing a browsing operation on the information to be recommended 1 ,user 2 ……user n ]。
Illustratively, since the dynamic characteristics may change over time, the dynamic characteristics may be updated based on a preset period. For example, the preset period may be 7 days, and the dynamic characteristics of the information to be recommended are redetermined every 7 days.
In some embodiments, the determining the dynamic characteristics of the information to be recommended according to the behavior sequence for the information to be recommended includes: classifying the behavior information according to the recording time of the behavior information in the behavior sequence to obtain a long-term behavior sequence and a short-term behavior sequence; establishing a double-tower model based on the long-term behavior sequence and the short-term behavior sequence, wherein the double-tower model is used for determining long-term dynamic characteristics and short-term dynamic characteristics of the information to be recommended; and if the similarity of the long-term dynamic characteristics and the short-term dynamic characteristics is larger than a preset threshold, determining the dynamic characteristics of the recommended information according to the long-term dynamic characteristics and the short-term dynamic characteristics.
By way of example, since a large number of behavior sequences may exist for each piece of information to be recommended, and the double-tower model has the characteristic of high processing speed, the dynamic characteristics of the information to be recommended are determined through the double-tower model, so that the processing efficiency of processing the behavior sequences is improved, and the processing time is reduced.
For example, since the long-term dynamic feature and the short-term dynamic feature are specific to the same information to be recommended, the similarity of the long-term dynamic feature and the short-term dynamic feature is high, and therefore, the dynamic feature of the recommended information is determined according to the long-term dynamic feature and the short-term dynamic feature when the similarity of the long-term dynamic feature and the short-term dynamic feature is greater than a preset threshold.
The similarity may be determined from the similarity between the long-term dynamic characteristics and the short-term dynamic characteristics, for example, but is not limited thereto.
In some embodiments, the sequence of actions includes: a user sequence for executing browsing operation on the information to be recommended; classifying the behavior information according to the recording time of the behavior information in the behavior sequence to obtain a long-term behavior sequence and a short-term behavior sequence, wherein the method comprises the following steps: and classifying the user information according to the recording time of the user information in the user sequence to obtain a long-term user sequence and a short-term user sequence.
For example, users who browse the same information to be recommended generally have a certain common feature, and thus, the characteristics of the information to be recommended may be determined by the user who clicks on the information to be recommended and performs the browsing operation.
For example, the user sequences may be divided into short-term user sequences and long-term user sequences. The short-term user sequence may be, for example, a user sequence composed of users browsing the information to be recommended within 7 days; the long-term user sequence may be a user sequence consisting of users browsing the information to be recommended within 7 to 30 days.
In some embodiments, the classifying the user information according to the recording time of the user information in the user sequence, to obtain a long-term user sequence and a short-term user sequence, includes at least one of the following: filtering the user information in the long-term user sequence based on the browsing duration of the browsing operation of the user corresponding to the user information on the information to be recommended; filtering the user information in the long-term user sequence based on the preference intensity of the user corresponding to the user information on the information to be recommended, wherein the preference intensity is determined according to whether the user executes preset operation on the information to be recommended; and filtering the user information in the long-term user sequence based on the user attribute corresponding to the user information in the user sequence.
For example, since the long-term user sequence is a user sequence that performs browsing operation on information to be recommended for a long period of time, the data size may be large, so that the user information in the long-term user sequence may be filtered, the data size of the long-term user sequence is reduced, and the acquisition efficiency of dynamic features is improved.
For example, the user information in the long-term user sequence may be filtered by a browsing duration of a browsing operation performed on the information to be recommended by the user corresponding to the user information. It can be appreciated that some users may browse the information to be recommended due to the operation of clicking by mistake, and the users who click by mistake have low reference to the features of the information to be recommended; because the user who clicks by mistake usually exits the page in a short time, the browsing of the information to be recommended is stopped, and therefore the user who clicks by mistake can be filtered according to the browsing time. Specifically, if the browsing duration of the user corresponding to the user information is smaller than a preset duration, the user information is filtered.
For example, the preference strength of the user to the information to be recommended may be determined according to an operation performed by the user to the information to be recommended, where the preset operation performed by the user to the information to be recommended may include: purchase operations, join shopping cart operations, etc. It can be understood that if the user performs the purchase operation or the shopping cart joining operation with respect to the information to be recommended, the user has a stronger preference strength for the information to be recommended, and the browsing operation performed with respect to the information to be recommended by the user also has a better referential property. Specifically, if the user corresponding to the user information does not execute the preset operation on the information to be recommended, filtering the user information.
For example, users performing browsing operations on the same information to be recommended typically have similar user attributes, where the user attributes include: user age, user region, etc. Thus, user information may be filtered based on user attributes. Specifically, determining the sparsity of the user information in the user sequence according to the user information, and filtering the user information if the sparsity of the user information is greater than a preset sparsity.
And step 103, clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended.
The clustering processing is performed on the information to be recommended according to the static characteristics and the dynamic characteristics based on a K-means clustering algorithm.
By clustering the information to be recommended according to the static characteristics and the dynamic characteristics, the information to be recommended with similar characteristics is determined to be of the same information type, so that content information recommended to a user can be determined according to the information type later.
Step S104, determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
The content information is information currently browsed by a user, information to be recommended which belongs to the same information type as the content information is determined to be target recommendation information based on the information type of the content information, and the target recommendation information is displayed to the user in a page of the content information.
For example, if the number of information to be recommended in the information type is large, the target recommendation information may be determined according to the similarity between the information to be recommended in the information type and the content information. Specifically, according to the similarity between the information to be recommended in the information type and the content information, determining the recommendation sequence of the information to be recommended, and determining the information to be recommended, of which the recommendation sequence is within a preset number, as target recommendation information.
For example, if the preset number is 5, that is, the number of target recommended information to be displayed in the page of the content information is 5, the information to be recommended, which has a similarity rank with the content information of top 5, is determined as the target recommended information. The preset number can be determined according to actual requirements, and is not limited herein.
For example, if the number of information to be recommended in the information type is small, for example, if the number of information to be recommended in the information type is smaller than the preset number, the information to be recommended belonging to other information types may be determined as the target recommendation information. Specifically, the other information type may be an information type having the greatest similarity to the information type corresponding to the content information.
The similarity may be determined according to a predetermined distance, but is not limited thereto.
According to the information recommendation method provided by the embodiment, the static characteristics of the information to be recommended are obtained based on the preset multi-mode model, and the static characteristics are determined according to the visual characteristics and the text characteristics of the information to be recommended; determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended; clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended; and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information. As diversified information features are combined to serve as information recommendation bases, target recommendation information recommended to the user is more in line with actual intention of the user, and accuracy of information recommendation is improved.
Referring to fig. 3, fig. 3 is a schematic diagram of an information recommendation device according to an embodiment of the present application, where the information recommendation device may be configured in a server or a terminal, for executing the foregoing information recommendation method.
As shown in fig. 3, the information recommendation device includes: a static information acquisition module 110, a dynamic information acquisition module 120, an information clustering module 130, and an information recommendation module 140.
The static information acquisition module 110 is configured to acquire static features of information to be recommended based on a preset multi-modal model, where the static features include visual features and text features of the information to be recommended;
the dynamic information acquisition module 120 is configured to determine dynamic characteristics of the information to be recommended according to a behavior sequence for the information to be recommended;
the information clustering module 130 is configured to perform clustering processing on the information to be recommended according to the static feature and the dynamic feature, and determine an information type of the information to be recommended;
the information recommending module 140 is configured to determine, according to a browsing operation for content information, target recommendation information corresponding to the content information from the information to be recommended based on an information type corresponding to the content information.
Illustratively, the dynamic information acquisition module 120 further includes an information classification sub-module, a dual tower model sub-module, and a dynamic feature determination sub-module.
The classification sub-module is used for classifying the behavior information according to the recording time of the behavior information in the behavior sequence to obtain a long-term behavior sequence and a short-term behavior sequence;
the double-tower model submodule is used for establishing a double-tower model based on the long-term behavior sequence and the short-term behavior sequence, and the double-tower model is used for determining long-term dynamic characteristics and short-term dynamic characteristics of the information to be recommended;
and the dynamic characteristic determining submodule is used for determining the dynamic characteristic of the recommended information according to the long-term dynamic characteristic and the short-term dynamic characteristic if the similarity of the long-term dynamic characteristic and the short-term dynamic characteristic is larger than a preset threshold value.
Illustratively, the classification submodule includes a user-sequence classification submodule.
And the user sequence classification sub-module is used for classifying the user information according to the recording time of the user information in the user sequence to obtain a long-term user sequence and a short-term user sequence.
Illustratively, the user sequence classification submodule includes at least one of a browse duration filtering submodule, a preference strength filtering submodule and an information attribute filtering submodule.
The browse time length filtering sub-module is used for filtering the user information in the long-term user sequence based on browse time length of the browse operation of the user corresponding to the user information on the information to be recommended;
the preference intensity filtering sub-module is used for filtering the user information in the long-term user sequence based on the preference intensity of the user information corresponding to the user information on the information to be recommended, wherein the preference intensity is determined according to whether the user executes preset operation on the information to be recommended or not;
and the information attribute filtering sub-module is used for filtering the user information in the long-term user sequence based on the user attribute corresponding to the user information in the user sequence.
Illustratively, the static information acquisition module 110 includes a feature fusion sub-module.
And the feature fusion sub-module is used for fusing the visual features and the text features of the information to be recommended based on a preset self-attention model to obtain the static features.
The information recommending device further comprises an image splitting module, an image feature extracting module and an image feature determining module.
The image splitting module is used for acquiring image information in the information to be recommended and splitting the image information into a plurality of sub-image information;
the image feature extraction module is used for inputting the sub-image information into a preset image feature extraction network to obtain sub-image features corresponding to the sub-image information;
and the image characteristic determining module is used for determining the image characteristics of the image information according to the sub-image characteristics to obtain the visual characteristics of the information to be recommended.
The information recommending device further comprises a text word segmentation module and a text feature determining module.
The text word segmentation module is used for acquiring text information in the information to be recommended, and performing word segmentation on the text information to obtain entity text corresponding to the text information;
and the text feature determining module is used for determining the text features of the entity text based on a preset bidirectional coding model to obtain the text features of the information to be recommended.
It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and each module, unit may refer to corresponding processes in the foregoing method embodiments, which are not repeated herein.
The methods and apparatus of the present application are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The above-described methods, apparatus may be implemented, for example, in the form of a computer program that is executable on a computer device as shown in fig. 4.
Referring to fig. 4, fig. 4 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device may be a server or a terminal.
As shown in fig. 4, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a storage medium and an internal memory.
The storage medium may store an operating system and a computer program. The computer program comprises program instructions that, when executed, cause a processor to perform any of a number of information recommendation methods.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program in a storage medium that, when executed by a processor, causes the processor to perform any of a number of information recommendation methods.
The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by persons skilled in the art that the architecture shown in fig. 4 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein in one embodiment the processor is configured to run a computer program stored in the memory to implement the steps of:
based on a preset multi-mode model, acquiring static characteristics of information to be recommended, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended;
determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended;
clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended;
and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
It should be noted that, for convenience and brevity of description, a specific working process of the above description information recommendation may refer to a corresponding process in the foregoing information recommendation control method embodiment, which is not described herein again.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, the computer program including program instructions, which when executed implement methods that can be referred to in various embodiments of the information recommendation method of the present application.
The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, which are provided on the computer device.
It is to be understood that the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. An information recommendation method, the method comprising:
based on a preset multi-mode model, acquiring static characteristics of information to be recommended, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended;
determining dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended;
clustering the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended;
and determining target recommendation information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
2. The information recommendation method according to claim 1, wherein the determining the dynamic characteristics of the information to be recommended according to the behavior sequence for the information to be recommended includes:
classifying the behavior information according to the recording time of the behavior information in the behavior sequence to obtain a long-term behavior sequence and a short-term behavior sequence;
establishing a double-tower model based on the long-term behavior sequence and the short-term behavior sequence, wherein the double-tower model is used for determining long-term dynamic characteristics and short-term dynamic characteristics of the information to be recommended;
and if the similarity of the long-term dynamic characteristics and the short-term dynamic characteristics is larger than a preset threshold, determining the dynamic characteristics of the recommended information according to the long-term dynamic characteristics and the short-term dynamic characteristics.
3. The information recommendation method according to claim 2, wherein the behavior sequence includes: a user sequence for executing browsing operation on the information to be recommended; classifying the behavior information according to the recording time of the behavior information in the behavior sequence to obtain a long-term behavior sequence and a short-term behavior sequence, wherein the method comprises the following steps:
and classifying the user information according to the recording time of the user information in the user sequence to obtain a long-term user sequence and a short-term user sequence.
4. The information recommendation method according to claim 3, wherein the classifying the user information according to the recording time of the user information in the user sequence to obtain a long-term user sequence and a short-term user sequence includes at least one of:
filtering the user information in the long-term user sequence based on the browsing duration of the browsing operation of the user corresponding to the user information on the information to be recommended;
filtering the user information in the long-term user sequence based on the preference intensity of the user corresponding to the user information on the information to be recommended, wherein the preference intensity is determined according to whether the user executes preset operation on the information to be recommended;
and filtering the user information in the long-term user sequence based on the user attribute corresponding to the user information in the user sequence.
5. The information recommendation method according to claim 1, wherein the acquiring static features of the information to be recommended based on the preset multimodal model, wherein the static features include determining according to visual features and text features of the information to be recommended, includes:
and fusing the visual features and the text features of the information to be recommended based on a preset self-attention model to obtain the static features.
6. The information recommendation method according to any one of claims 1 to 5, further comprising:
acquiring image information in the information to be recommended, and splitting the image information into a plurality of sub-image information;
inputting the sub-image information into a preset image feature extraction network to obtain sub-image features corresponding to the sub-image information;
and determining the image characteristics of the image information according to the sub-image characteristics to obtain the visual characteristics of the information to be recommended.
7. The information recommendation method according to any one of claims 1 to 5, further comprising:
acquiring text information in the information to be recommended, and performing word segmentation on the text information to obtain entity text corresponding to the text information;
and determining the text characteristics of the entity text based on a preset bidirectional coding model to obtain the text characteristics of the information to be recommended.
8. An information recommendation device, characterized in that the information recommendation device comprises:
the static information acquisition module is used for acquiring static characteristics of information to be recommended based on a preset multi-mode model, wherein the static characteristics are determined according to visual characteristics and text characteristics of the information to be recommended;
the dynamic information acquisition module is used for determining the dynamic characteristics of the information to be recommended according to the behavior sequence aiming at the information to be recommended;
the information clustering module is used for carrying out clustering processing on the information to be recommended according to the static characteristics and the dynamic characteristics, and determining the information type of the information to be recommended;
and the information recommending module is used for determining target recommending information corresponding to the content information from the information to be recommended based on the information type corresponding to the content information according to the browsing operation of the content information.
9. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of the information recommendation method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the information recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768925.XA CN116738057A (en) | 2023-06-27 | 2023-06-27 | Information recommendation method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310768925.XA CN116738057A (en) | 2023-06-27 | 2023-06-27 | Information recommendation method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116738057A true CN116738057A (en) | 2023-09-12 |
Family
ID=87911356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310768925.XA Pending CN116738057A (en) | 2023-06-27 | 2023-06-27 | Information recommendation method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116738057A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611245A (en) * | 2023-12-14 | 2024-02-27 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
-
2023
- 2023-06-27 CN CN202310768925.XA patent/CN116738057A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611245A (en) * | 2023-12-14 | 2024-02-27 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
| CN117611245B (en) * | 2023-12-14 | 2024-05-31 | 浙江博观瑞思科技有限公司 | Data analysis management system and method for planning E-business operation activities |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111797210A (en) | Information recommendation method, device and equipment based on user portrait and storage medium | |
| CN113159010B (en) | Video classification method, device, equipment and storage medium | |
| US11599727B2 (en) | Intelligent text cleaning method and apparatus, and computer-readable storage medium | |
| CN107832338B (en) | Method and system for recognizing core product words | |
| CN112818111B (en) | Document recommendation method, device, electronic equipment and medium | |
| CN113806588B (en) | Method and device for searching video | |
| CN112765478B (en) | Method, apparatus, device, medium and program product for recommending content | |
| CN111125491A (en) | Commodity information searching method and device, storage medium and electronic device | |
| CN116738057A (en) | Information recommendation method, device, computer equipment and storage medium | |
| CN113407851A (en) | Method, device, equipment and medium for determining recommendation information based on double-tower model | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN110297953A (en) | Product information recommended method, device, computer equipment and storage medium | |
| CN109829033B (en) | Data display method and terminal equipment | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| US10963690B2 (en) | Method for identifying main picture in web page | |
| CN113435523A (en) | Method and device for predicting content click rate, electronic equipment and storage medium | |
| CN116597443A (en) | Material tag processing method and device, electronic equipment and medium | |
| CN114036397B (en) | Data recommendation method, device, electronic equipment and medium | |
| CN114139052B (en) | Ranking model training method for intelligent recommendation, intelligent recommendation method and device | |
| CN111782850A (en) | Object searching method and device based on hand drawing | |
| CN114445833B (en) | Text recognition method, device, electronic equipment and storage medium | |
| CN115576789A (en) | Method and system for identifying lost user | |
| CN114154052A (en) | Information recommendation method and device, computer equipment and storage medium | |
| US20230325391A1 (en) | Method and system of retrieving assets from personalized asset libraries | |
| CN116911304B (en) | Text recommendation method and device |
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 |