CN113343024B - Object recommendation method and device, electronic equipment and storage medium - Google Patents

Object recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113343024B
CN113343024B CN202110889451.5A CN202110889451A CN113343024B CN 113343024 B CN113343024 B CN 113343024B CN 202110889451 A CN202110889451 A CN 202110889451A CN 113343024 B CN113343024 B CN 113343024B
Authority
CN
China
Prior art keywords
recommendation
information
recommended
parameter information
objects
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
Application number
CN202110889451.5A
Other languages
Chinese (zh)
Other versions
CN113343024A (en
Inventor
刘聪
沈璠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Dajia Internet Information Technology Co Ltd
Original Assignee
Beijing Dajia Internet Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Dajia Internet Information Technology Co Ltd filed Critical Beijing Dajia Internet Information Technology Co Ltd
Priority to CN202110889451.5A priority Critical patent/CN113343024B/en
Publication of CN113343024A publication Critical patent/CN113343024A/en
Application granted granted Critical
Publication of CN113343024B publication Critical patent/CN113343024B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/732—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/735—Filtering based on additional data, e.g. user or group profiles
    • 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
    • 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
    • G06Q30/0277—Online advertisement

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computational Linguistics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The disclosure relates to an object recommendation method, an object recommendation device, an electronic device and a storage medium. The method comprises the following steps: acquiring first recommendation parameter information corresponding to a plurality of objects to be recommended and a plurality of objects to be recommended respectively; the first recommendation parameter information corresponding to the object to be recommended is obtained based on historical feedback behavior information of the object to be recommended, at least one piece of content associated information in historical feedback content and importance degree information of the at least one piece of content associated information in the historical feedback content; determining recommendation index information of a plurality of objects to be recommended according to the first recommendation parameter information; and recommending the plurality of objects to be recommended based on the recommendation index information. According to the technical scheme provided by the disclosure, the recommended processing pressure can be reduced, and the object recommendation precision and efficiency can be improved.

Description

Object recommendation method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of internet application technologies, and in particular, to an object recommendation method and apparatus, an electronic device, and a storage medium.
Background
With the development of internet applications, more and more platforms are performing object recommendation, such as advertisement recommendation, work recommendation and the like on short video platforms. In the related art, the recommendation publicity-based content should be consistent with the actual content of the object, and the publicity content needs to be verified, but on one hand, the recommended object is large in magnitude, and on the other hand, some recommended objects need to participate deeply to confirm whether the recommended objects are consistent, so that the server processing pressure is large, and the recommendation efficiency is low.
Disclosure of Invention
The present disclosure provides an object recommendation method, an object recommendation device, an electronic device, and a storage medium, so as to at least solve the problem of how to improve the efficiency of object recommendation in the related art. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided an object recommendation method, including:
the method comprises the steps of obtaining a plurality of objects to be recommended and first recommendation parameter information corresponding to the plurality of objects to be recommended respectively; the first recommendation parameter information corresponding to the object to be recommended is obtained based on historical feedback behavior information of the object to be recommended, at least one piece of content related information in historical feedback content and importance degree information of the at least one piece of content related information in the historical feedback content;
determining recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information;
and recommending the plurality of objects to be recommended based on the recommendation index information.
In a possible implementation manner, the at least one piece of content related information is at least one piece of content participle; before the step of obtaining a plurality of objects to be recommended and first recommendation parameter information corresponding to each of the plurality of objects to be recommended, the method further includes:
acquiring the historical feedback content and the historical feedback behavior information of the object to be recommended;
extracting the at least one content participle from the historical feedback content;
determining importance degree information of the content participles in the historical feedback content;
and determining first recommendation parameter information corresponding to the plurality of objects to be recommended respectively based on the at least one content participle, the importance degree information of the at least one content participle in the historical feedback content and the historical feedback behavior information.
In a possible implementation manner, the step of determining, based on the at least one content participle, the importance information of the at least one content participle in the historical feedback content, and the historical feedback behavior information, first recommendation parameter information corresponding to each of the plurality of objects to be recommended includes:
and inputting the at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, and performing recommendation parameter prediction processing to obtain first recommendation parameter information corresponding to the plurality of objects to be recommended respectively.
In one possible implementation, the method further includes:
acquiring second recommendation parameter information corresponding to the plurality of objects to be recommended respectively, wherein the second recommendation parameter information represents preset recommendation priority information of the plurality of objects to be recommended;
the step of determining recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information comprises:
and determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information.
In a possible implementation manner, the step of determining the recommendation indicator information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information includes:
determining weight information corresponding to the first recommendation parameter information based on the second recommendation parameter information;
and determining the recommendation index information of the plurality of objects to be recommended according to the second recommendation parameter information, the first recommendation parameter information and the corresponding weight information.
In a possible implementation manner, the determining, according to the first recommendation parameter information and the second recommendation parameter information, the recommendation indicator information of the multiple objects to be recommended includes:
acquiring a recommended parameter threshold;
acquiring a first target object of which the first recommendation parameter information is lower than the recommendation parameter threshold and a second target object of which the first recommendation parameter information is higher than or equal to the recommendation parameter threshold from the plurality of objects to be recommended;
determining first recommendation index information of the first target object according to the second recommendation parameter information;
determining second recommendation index information of the second target object according to the first recommendation parameter information and the second recommendation parameter information;
and determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation index information and the second recommendation index information.
According to a second aspect of the embodiments of the present disclosure, there is provided an object recommendation apparatus including:
the recommendation system comprises a first recommendation parameter information acquisition module, a recommendation processing module and a recommendation processing module, wherein the first recommendation parameter information acquisition module is configured to acquire a plurality of objects to be recommended and first recommendation parameter information corresponding to the objects to be recommended; the first recommendation parameter information corresponding to the object to be recommended is obtained based on historical feedback behavior information of the object to be recommended, at least one piece of content related information in historical feedback content and importance degree information of the at least one piece of content related information in the historical feedback content;
a recommendation index information determination module configured to perform determination of recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information;
and the recommending module is configured to execute recommending processing on the plurality of objects to be recommended based on the recommending index information.
In a possible implementation manner, the at least one piece of content related information is at least one piece of content participle; the device further comprises:
a history feedback obtaining module configured to perform obtaining the history feedback content and the history feedback behavior information of the object to be recommended;
a word segmentation module configured to perform extraction of the at least one content word from the historical feedback content;
an importance information determination module configured to perform determining importance information of the content participles in the history feedback content;
the recommendation parameter information presetting module is configured to determine first recommendation parameter information corresponding to each of the plurality of objects to be recommended based on the at least one content participle, the importance degree information of the at least one content participle in the historical feedback content and the historical feedback behavior information.
In a possible implementation manner, the recommendation parameter information presetting module includes:
and the recommendation parameter information presetting unit is configured to input the at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, perform recommendation parameter prediction processing, and obtain first recommendation parameter information corresponding to each of the plurality of objects to be recommended.
In one possible implementation, the apparatus further includes:
the second recommendation parameter information acquisition module is configured to execute acquisition of second recommendation parameter information corresponding to each of the multiple objects to be recommended, and the second recommendation parameter information represents preset recommendation priority information of the multiple objects to be recommended;
the recommendation indicator information determination module includes:
a recommendation index information determination unit configured to perform determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information.
In one possible implementation manner, the recommendation indicator information determining unit includes:
a weight information determination subunit configured to perform determination of weight information corresponding to the first recommendation parameter information based on the second recommendation parameter information;
a recommendation index information determination subunit configured to perform determining the recommendation index information of the plurality of objects to be recommended according to the second recommendation parameter information, the first recommendation parameter information, and the corresponding weight information.
In one possible implementation manner, the recommendation indicator information determining unit includes:
a recommended parameter threshold acquisition subunit configured to perform acquisition of a recommended parameter threshold;
an object dividing subunit configured to perform, from the plurality of objects to be recommended, acquiring a first target object of which the first recommendation parameter information is lower than the recommendation parameter threshold and a second target object of which the first recommendation parameter information is higher than or equal to the recommendation parameter threshold;
a first recommendation index information determination subunit configured to perform determining first recommendation index information of the first target object according to the second recommendation parameter information;
a second recommendation indicator information determination subunit configured to perform determining second recommendation indicator information of the second target object according to the first recommendation parameter information and the second recommendation parameter information;
a recommendation indicator information determination subunit configured to further perform determining the recommendation indicator information of the plurality of objects to be recommended according to the first recommendation indicator information and the second recommendation indicator information.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of any of the first aspects above.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of the first aspect of the embodiments of the present disclosure.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer instructions which, when executed by a processor, cause a computer to perform the method of any one of the first aspects of the embodiments of the present disclosure.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
the recommendation index information is determined through the first recommendation parameter information corresponding to the multiple objects to be recommended, the multiple objects to be recommended are recommended based on the recommendation index information, the first recommendation parameter information corresponding to the multiple objects to be recommended is obtained based on the historical feedback behavior information of the multiple objects to be recommended, at least one content relevant information in the historical feedback content and the importance degree information of the at least one content relevant information in the historical feedback content, the accuracy of the first recommendation parameter information can be improved, the content of the objects to be recommended can be known quickly through the historical feedback information, and therefore processing pressure can be reduced, and efficiency is improved; in addition, differential recommendation processing can be performed on a plurality of objects to be recommended based on recommendation index information, and flexibility and recommendation effect of object recommendation are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a schematic diagram illustrating an application environment in accordance with an exemplary embodiment.
Fig. 2 is a flowchart illustrating a first recommendation parameter information determination method according to an exemplary embodiment.
FIG. 3 is a flow diagram illustrating a method of object recommendation, according to an example embodiment.
FIG. 4 is a flow diagram illustrating a method of object recommendation, according to an example embodiment.
Fig. 5 is a flowchart illustrating a method for determining recommendation index information of a plurality of objects to be recommended according to first recommendation parameter information and second recommendation parameter information according to an exemplary embodiment.
Fig. 6 is a flowchart illustrating a method for determining recommendation index information of a plurality of objects to be recommended according to first recommendation parameter information and second recommendation parameter information according to an exemplary embodiment.
FIG. 7 is a block diagram illustrating an object recommendation device according to an example embodiment.
FIG. 8 is a block diagram illustrating an electronic device for object recommendation, according to an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
In recent years, with research and development of artificial intelligence technology, the artificial intelligence technology is widely applied in a plurality of fields, and the scheme provided by the embodiment of the application relates to technologies such as machine learning/deep learning, and is specifically described by the following embodiments:
referring to fig. 1, fig. 1 is a schematic diagram illustrating an application environment according to an exemplary embodiment, which may include a server 01 and a terminal 02, as shown in fig. 1.
In an alternative embodiment, server 01 may be used for the object recommendation process. Specifically, the server 01 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like.
In an alternative embodiment, the terminal 02 may be used to present the recommended objects. Specifically, the terminal 02 may include, but is not limited to, a smart phone, a desktop computer, a tablet computer, a notebook computer, a smart speaker, a digital assistant, an Augmented Reality (AR)/Virtual Reality (VR) device, a smart wearable device, and other types of electronic devices. Optionally, the operating system running on the electronic device may include, but is not limited to, an android system, an IOS system, linux, windows, and the like.
In addition, it should be noted that fig. 1 illustrates only one application environment of the image processing method provided by the present disclosure.
In the embodiment of the present specification, the server 01 and the terminal 02 may be directly or indirectly connected by a wired or wireless communication method, and the present application is not limited herein.
It should be noted that the following figures show a possible sequence of steps, and in fact do not limit the order that must be followed. Some steps may be performed in parallel without being dependent on each other. User information (including but not limited to user device information, user personal information, user behavior information, etc.) and data (including but not limited to data for presentation, training, etc.) to which the present disclosure relates are both information and data that are authorized by the user or sufficiently authorized by various parties.
Fig. 2 is a flowchart illustrating a first recommendation parameter information determination method according to an exemplary embodiment. As shown in fig. 2, the following steps may be included.
In step S201, the history feedback content and history feedback behavior information of the object to be recommended are acquired.
In this embodiment of the specification, the object to be recommended may be an object used for recommendation or delivery in a platform, and may be any one of a plurality of objects to be recommended. The object may be an advertisement, multimedia, and the like, and the multimedia may include a short video, a long video, a text, and the like, which is not limited in this disclosure. The platform can be an e-commerce platform, a multimedia resource platform, and the like. The historical feedback content may refer to feedback content of the object to be recommended by the user in the platform, and may include, for example, historical comment information; in the case that the object to be recommended is in a video form, the history feedback content may further include history bullet screen information and the like. The historical comment information may refer to information that a user comments on an object to be recommended in the platform, and the historical comment information may be text comment information. The historical bullet screen information may refer to information popped up in an interface for playing an object to be recommended in the platform. The historical feedback behavior information of the object to be recommended may refer to feedback operation information of the object to be recommended by the user in the platform, for example, feedback operation information such as approval and dislike, such as time information and frequency information corresponding to the feedback operation.
In practical application, in order to reduce the processing pressure of the platform and improve the recommendation efficiency and recommendation effect, the first recommendation parameter information of the object in the platform may be predetermined, so that the object is recommended when the object is recommended by using the predetermined first recommendation parameter information. Based on the method, the historical feedback content and the historical feedback behavior information of each object to be recommended can be obtained, and therefore the first recommendation parameter information corresponding to each object to be recommended can be obtained based on the historical feedback content and the historical feedback behavior information. Optionally, first recommendation parameter information corresponding to each of the plurality of objects to be recommended may be stored so as to be used when the object is recommended.
In step S203, at least one content participle is extracted from the history feedback content.
In this embodiment of the present specification, word segmentation processing may be performed on the history feedback content, so that at least one content word segmentation may be extracted from the history feedback content, and the word segmentation processing manner is not limited in this disclosure.
In step S205, importance degree information of the content participle in the history feedback content is determined.
In this embodiment of the present specification, in order to ensure an effective degree of influence of any content participle on the first recommendation parameter information, the content participle may be processed, for example, importance degree information of any content participle in the historical comment information may be determined. In one example, the importance information of any content participle in the historical feedback content may be determined based on TFIDF (term frequency-inverse text frequency index), for example, the importance information of any content participle in the historical feedback content may be determined using the following formula (1):
Figure 960278DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 338432DEST_PATH_IMAGE002
the importance degree information of the ith content participle in the history feedback content of the jth object to be recommended in the history feedback content can be obtained;
Figure 160894DEST_PATH_IMAGE003
the number of the ith content participles in the history feedback content of the jth object to be recommended can be set;
Figure 427928DEST_PATH_IMAGE004
the number of all content participles in the history feedback content of the jth object to be recommended can be set; w may be the total number of the historical feedback contents of a plurality of objects to be recommended;
Figure 689145DEST_PATH_IMAGE005
the number of the historical feedback contents of the ith content participle in the historical feedback contents of the plurality of objects to be recommended can be set; i and j may be integers greater than 0.
In step S207, based on the at least one content participle, the importance information of the at least one content participle in the history feedback content, and the history feedback behavior information, first recommendation parameter information corresponding to each of the plurality of objects to be recommended is determined.
In practical applications, at least one content participle, importance information of at least one content participle in history feedback content, and history feedback behavior information may be statistically processed, for example, a target content participle in which importance program information is higher than an importance threshold in at least one content participle may be statistically processed, and a type of the target content participle, such as positive feedback participle or negative feedback participle, may be determined; and the times of positive feedback behaviors and the times of negative feedback behaviors in historical feedback behavior information can be counted. Further, the corresponding first recommendation parameter information may be determined based on the number of positive feedback participles, the number of negative feedback participles, the number of positive feedback behaviors, and the number of negative feedback behaviors. In one example, the number of positive feedback participles, the number of negative feedback participles, the number of positive feedback behaviors, and the correspondence between the number of negative feedback behaviors and the first recommendation parameter information may be set in advance, so that the corresponding first recommendation parameter information may be determined based on the correspondence. The first recommendation parameter information may represent a content consistency degree of the object to be recommended, for example, when the first recommendation parameter information is a numerical value, the first recommendation parameter information and the content consistency degree may be a negative correlation relationship.
The first recommendation parameter information is determined through the content participles, the importance degree information of the content participles in the historical feedback content and the historical feedback behavior information, so that the first recommendation parameter information can represent the recommendation priority of the object to be recommended more accurately, and the object recommendation effect can be improved.
In a possible implementation manner, the S207 may include:
and inputting at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, and performing recommendation parameter prediction processing to obtain first recommendation parameter information corresponding to each of a plurality of objects to be recommended.
The recommended parameter prediction model can be obtained by training a preset machine learning model based on a training sample set, the training sample set can comprise a plurality of sample data and corresponding recommended parameter labels, one sample data can be sample history feedback information of one sample object, the recommended parameter label can be a numerical value, the numerical value can be in a preset numerical value range, and the preset numerical value range is not limited by the disclosure.
In one example, the sample historical feedback information may include a plurality of sample content participles, importance information of the plurality of sample content participles in the sample historical feedback content, and sample historical feedback behavior information. Here, the obtaining manner of the multiple sample content participles, the importance degree information of the multiple sample content participles in the sample history feedback content, and the sample history feedback behavior information may refer to the above steps S201 to S205, which are not described herein again.
In one example, considering that the historical feedback information of the sample is a sparse feature, the preset machine learning model can be selected as an FM (factorization machine) model, the FM model is a machine learning model based on matrix decomposition, the learning capability of the machine learning model is good for sparse data, and the prediction accuracy of the recommended parameter prediction model can be improved. Here is merely an example, and the present disclosure does not limit the preset machine learning model.
In practical applications, the recommendation parameter tag may be manually labeled, for example, a recommendation parameter determination criterion may be preset, such as that the description information of the object is inconsistent with the content of the object. For example, the description information of a game advertisement is a phishing game, and the user may find the game is a role playing game after downloading, so that the description information of the game advertisement may be considered inconsistent with the content of the game, and the recommended parameter tag of the game advertisement may be marked with a higher value.
Optionally, the training of the recommended parameter prediction model may be performed periodically, for example, the training may be performed every day, so that the recommended parameter prediction model may be updated periodically to adapt to prediction of an object that is continuously updated in the platform, and accuracy of the recommended parameter prediction model is ensured.
Further, a test sample set may be obtained, which may include a plurality of verification sample data and corresponding recommended parameter tags. The trained recommended parameter prediction model can be tested based on the test sample set to obtain a test result, and if the test result meets a preset condition, the recommended parameter prediction model can be determined to pass the test; if the test result does not meet the preset condition, the recommended parameter prediction model can be continuously trained until the test result meets the preset condition. The preset condition may be that the prediction accuracy reaches an accuracy threshold, or that the model evaluation index auc (area under the curve) is greater than the index threshold, which is not limited in this disclosure.
The first recommendation parameter information corresponding to the plurality of objects to be recommended is determined through the recommendation parameter prediction model, so that the accuracy of the first recommendation parameter information is guaranteed, the prediction efficiency is improved, and the recommendation demand of the objects to be recommended, which is rapidly increased in a platform, can be effectively met.
FIG. 3 is a flow diagram illustrating a method of object recommendation, according to an example embodiment. As shown in fig. 3, the object recommendation method may include:
in step S301, first recommendation parameter information corresponding to a plurality of objects to be recommended and a plurality of objects to be recommended is obtained; the first recommendation parameter information corresponding to any object to be recommended is obtained based on historical feedback behavior information of any object to be recommended, at least one piece of content related information in historical feedback content and importance degree information of the at least one piece of content related information in the historical feedback content. Here, the historical feedback behavior information, the at least one content related information in the historical feedback content, and the importance degree information of the at least one content related information in the historical feedback content may be used as the historical feedback information.
In this embodiment of the present specification, the first recommendation parameter information corresponding to each of the multiple objects to be recommended may be obtained in advance through the steps S201 to S207. For example, after each time the recommended parameter prediction model is periodically updated, the recommended parameter prediction processing may be performed on all objects in the platform based on the current recommended parameter prediction model to obtain first recommended parameter information of all the objects, and the first recommended parameter information may be stored. Therefore, when the object is recommended, the first recommendation parameter information corresponding to each of the plurality of objects to be recommended can be acquired from the stored first recommendation parameter information.
In step S303, recommendation index information of a plurality of objects to be recommended is determined according to the first recommendation parameter information.
In this embodiment, the recommendation index information may refer to recommendation priority information of an object. In an example, the plurality of objects to be recommended may be ranked according to the first recommendation parameter information, and a ranking result of the plurality of objects to be recommended is obtained as recommendation index information.
It should be noted that, when the first recommendation parameter information is negatively correlated with the content consistency degree of the object to be recommended, that is, the higher the first recommendation parameter information is, the lower the content consistency degree representing the corresponding object to be recommended is. The plurality of objects to be recommended may be ranked according to the order of the first recommendation parameter information from low to high, and a ranking result of the plurality of objects to be recommended is obtained as recommendation index information. The higher the ranking corresponding to the recommendation index information is, the higher the recommendation priority of the object to be recommended can be represented, that is, the object is recommended preferentially.
In step S305, a recommendation process is performed on a plurality of objects to be recommended based on the recommendation index information.
In one example, a plurality of objects to be recommended may be recommended in the order of the recommendation index information to ensure that objects to be recommended with a high degree of content consistency may be recommended preferentially.
In another example, a plurality of objects to be recommended may be divided into high-consistency objects and low-consistency objects based on recommendation index information, and a presentation time length of the high-consistency objects may be set to be longer than a presentation time length of the low-consistency objects. When recommending, a plurality of objects to be recommended can be presented based on the presentation duration. The object to be recommended with recommendation index information smaller than the recommendation index threshold can be used as a high consistency object, and the object to be recommended with recommendation index information not smaller than the recommendation index threshold can be used as a low consistency object.
The recommendation index information is determined through the first recommendation parameter information corresponding to the multiple objects to be recommended, the multiple objects to be recommended are recommended based on the recommendation index information, the first recommendation parameter information corresponding to the multiple objects to be recommended is obtained based on the historical feedback behavior information of the multiple objects to be recommended, at least one content relevant information in the historical feedback content and the importance degree information of the at least one content relevant information in the historical feedback content, the accuracy of the first recommendation parameter information can be improved, the content of the objects to be recommended can be known quickly through the historical feedback information, and therefore processing pressure can be reduced, and efficiency is improved; in addition, differential recommendation processing can be performed on a plurality of objects to be recommended based on recommendation index information, and flexibility and recommendation effect of object recommendation are improved.
FIG. 4 is a flow diagram illustrating a method of object recommendation, according to an example embodiment. As shown in fig. 4, the object recommendation method may further include:
in step 401, second recommendation parameter information corresponding to each of a plurality of objects to be recommended is obtained, where the second recommendation parameter information may represent preset recommendation priority information of the plurality of objects to be recommended;
accordingly, step S303 may include:
in step 403, recommendation index information of a plurality of objects to be recommended is determined according to the first recommendation parameter information and the second recommendation parameter information.
In practical application, the object may be preset with second recommendation parameter information, and the higher the second recommendation parameter information is, the higher the priority of the object to be recommended is, that is, the second recommendation parameter information may form a positive correlation with the priority of the object to be recommended. As an example, for the advertisement, the corresponding second recommendation parameter information may be preset based on the advertisement delivery parameter, and the preset manner is not limited by the present disclosure.
In this embodiment of the present specification, the recommendation index information may be determined by combining preset second recommendation parameter information and first recommendation parameter information based on historical feedback. For example, a difference between the second recommendation parameter information and the second recommendation parameter information may be used as the recommendation index information.
By combining the preset second recommendation parameter information and the first recommendation parameter information based on the historical feedback, the preset recommendation priority of the object to be recommended and the dynamic recommendation priority determined based on the historical feedback can be balanced, so that the recommendation index information of the object to be recommended is dynamic, and the recommendation effectiveness and the recommendation conversion rate can be improved.
Fig. 5 is a flowchart illustrating a method for determining recommendation index information of a plurality of objects to be recommended according to first recommendation parameter information and second recommendation parameter information according to an exemplary embodiment. As shown in fig. 5, in a possible implementation manner, the step S403 may include:
in step S501, based on the second recommendation parameter information, determining weight information corresponding to the first recommendation parameter information;
in step S503, recommendation index information of a plurality of objects to be recommended is determined according to the second recommendation parameter information, the first recommendation parameter information, and the corresponding weight information.
In practical application, the magnitude of the second recommended parameter information may be different from the magnitude of the first recommended parameter information, and in order to reflect the role of the first recommended parameter information on the recommendation index information, the weight information corresponding to the first recommended parameter information may be determined based on the second recommended parameter information. For example, the magnitude of the second recommended parameter information is higher, and the magnitude of the first recommended parameter information is lower, so that the weight information may be determined to be a higher value, so that the product of the first recommended parameter information and the weight information may be in the same magnitude as the second recommended parameter information. Therefore, the influence degree of the first recommendation parameter information on the recommendation index information can be more effectively embodied.
In this embodiment of the present specification, recommendation index information of a plurality of objects to be recommended may be determined according to the second recommendation parameter information, the first recommendation parameter information, and the corresponding weight information. For example, the recommendation index information P may be determined according to the following formula (2):
Figure 358023DEST_PATH_IMAGE006
wherein ecpm may be second recommended parameter information; weight may be weight information; the prediction may be the first recommended parameter information.
The weight information corresponding to the first recommendation parameter is dynamically determined based on the second recommendation parameter information, and the recommendation index information of the plurality of objects to be recommended is determined according to the second recommendation parameter information, the first recommendation parameter information and the corresponding weight information, so that the recommendation index information can be more accurate and effective.
Fig. 6 is a flowchart illustrating a method for determining recommendation index information of a plurality of objects to be recommended according to first recommendation parameter information and second recommendation parameter information according to an exemplary embodiment. As shown in fig. 6, in a possible implementation manner, the step S403 may include:
in step S601, a recommended parameter threshold is acquired;
in step S603, a first target object whose first recommendation parameter information is lower than a recommendation parameter threshold and a second target object whose first recommendation parameter information is higher than or equal to the recommendation parameter threshold are obtained from the plurality of objects to be recommended;
in step S605, determining first recommendation index information of the first target object according to the second recommendation parameter information;
in step S607, determining second recommendation index information of the second target object according to the first recommendation parameter information and the second recommendation parameter information;
in step S609, recommendation index information of a plurality of objects to be recommended is determined according to the first recommendation index information and the second recommendation index information.
In practical application, a recommendation parameter threshold can be set to divide a plurality of objects to be recommended so as to realize differential recommendation of the objects to be recommended based on the first recommendation parameter information. In one example, when the first recommendation parameter information is in a negative correlation with the recommendation priority, the first target object (the object to be recommended with high recommendation priority/the object to be recommended with high quality) whose first recommendation parameter information is lower than the recommendation parameter threshold may be kept as the preset second recommendation parameter information, that is, the second recommendation parameter information of the first target object may be determined as the first recommendation index information of the first target object;
further, the second recommendation parameter information of the second target object (the object to be recommended with low recommendation priority/the object to be recommended with low quality) whose first recommendation parameter information is higher than or equal to the recommendation parameter threshold may be adjusted, for example, the second recommendation index information of the second target object may be determined according to the first recommendation parameter information and the second recommendation parameter information, and in one example, a difference value between the second recommendation parameter information and the first recommendation parameter information may be used as the second recommendation index information. And then, according to the first recommendation index information and the second recommendation index information, the recommendation index information of the plurality of objects to be recommended can be determined. For example, the plurality of objects to be recommended may be sorted according to the first recommendation index information and the second recommendation index information to obtain a sorting result, so that the sorting result may be used as the recommendation index information of the plurality of objects to be recommended.
By setting the recommendation parameter threshold, only the second recommendation parameter information of the second target object with low recommendation priority is adjusted, and the recommendation index information of a plurality of objects to be recommended can be processed in a differentiated mode based on the first recommendation parameter information, so that the flexibility and the recommendation effectiveness of object recommendation are improved.
FIG. 7 is a block diagram illustrating an object recommendation device according to an example embodiment. Referring to fig. 7, the apparatus may include:
a first recommendation parameter information obtaining module 701 configured to perform obtaining of first recommendation parameter information corresponding to each of a plurality of objects to be recommended and a plurality of objects to be recommended; the first recommendation parameter information corresponding to any object to be recommended is obtained based on historical feedback behavior information of any object to be recommended, at least one piece of content related information in historical feedback content and importance degree information of the at least one piece of content related information in the historical feedback content;
a recommendation index information determining module 703 configured to perform determining recommendation index information of a plurality of objects to be recommended according to the first recommendation parameter information;
and the recommending module 705 is configured to perform recommending processing on a plurality of objects to be recommended based on the recommendation index information.
The recommendation index information is determined through the first recommendation parameter information corresponding to the multiple objects to be recommended, the multiple objects to be recommended are recommended based on the recommendation index information, the first recommendation parameter information corresponding to the multiple objects to be recommended is obtained based on the historical feedback behavior information of the multiple objects to be recommended, at least one content relevant information in the historical feedback content and the importance degree information of the at least one content relevant information in the historical feedback content, the accuracy of the first recommendation parameter information can be improved, the content of the objects to be recommended can be known quickly through the historical feedback information, and therefore processing pressure can be reduced, and efficiency is improved; in addition, differential recommendation processing can be performed on a plurality of objects to be recommended based on recommendation index information, and flexibility and recommendation effect of object recommendation are improved.
In one possible implementation manner, the at least one piece of content related information is at least one piece of content participle; the apparatus may further include:
the history feedback acquisition module is configured to execute acquisition of history feedback content and history feedback behavior information of the object to be recommended;
a word segmentation module configured to perform extraction of at least one content word from the historical feedback content;
the importance degree information determining module is configured to execute the determination of the importance degree information of the content participles in the historical feedback content;
the recommendation parameter information presetting module is configured to determine first recommendation parameter information corresponding to each of the plurality of objects to be recommended based on at least one content word, the importance degree information of the at least one content word in historical feedback content and the historical feedback behavior information.
In one possible implementation manner, the recommendation parameter information presetting module may include:
and the recommendation parameter information presetting unit is configured to input at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, perform recommendation parameter prediction processing and obtain first recommendation parameter information corresponding to each of the plurality of objects to be recommended.
In one possible implementation, the apparatus may further include:
the second recommendation parameter information acquisition module is configured to execute acquisition of second recommendation parameter information corresponding to each of the plurality of objects to be recommended, and the second recommendation parameter information represents preset recommendation priority information of the plurality of objects to be recommended;
the recommendation indicator information determining module 703 may include:
and the recommendation index information determining unit is configured to determine recommendation index information of a plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information.
In one possible implementation manner, the recommendation indicator information determining unit may include:
a weight information determination subunit configured to perform determination of weight information corresponding to the first recommendation parameter information based on the second recommendation parameter information;
and the recommendation index information determining subunit is configured to determine recommendation index information of the plurality of objects to be recommended according to the second recommendation parameter information, the first recommendation parameter information and the corresponding weight information.
In one possible implementation manner, the recommendation indicator information determining unit may include:
a recommended parameter threshold acquisition subunit configured to perform acquisition of a recommended parameter threshold;
the object dividing subunit is configured to acquire a first target object of which the first recommendation parameter information is lower than a recommendation parameter threshold and a second target object of which the first recommendation parameter information is higher than or equal to the recommendation parameter threshold from the plurality of objects to be recommended;
a first recommendation index information determination subunit configured to perform determining first recommendation index information of the first target object according to the second recommendation parameter information;
a second recommendation index information determination subunit configured to perform determining second recommendation index information of a second target object according to the first recommendation parameter information and the second recommendation parameter information;
and the recommendation index information determining subunit is configured to further execute the determination of the recommendation index information of the plurality of objects to be recommended according to the first recommendation index information and the second recommendation index information.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 8 is a block diagram illustrating an electronic device for object recommendation, which may be a server, according to an exemplary embodiment, and an internal structure thereof may be as shown in fig. 8. The electronic device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method of object recommendation.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and does not constitute a limitation on the electronic devices to which the disclosed aspects apply, as a particular electronic device may include more or less components than those shown, or combine certain components, or have a different arrangement of components.
In an exemplary embodiment, there is also provided an electronic device including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the object recommendation method as in the embodiments of the present disclosure.
In an exemplary embodiment, there is also provided a computer-readable storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform an object recommendation method in an embodiment of the present disclosure. The computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the object recommendation method in the embodiments of the present disclosure.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims (12)

1. An object recommendation method, comprising:
the method comprises the steps of obtaining a plurality of objects to be recommended and first recommendation parameter information corresponding to the plurality of objects to be recommended respectively; the first recommendation parameter information represents the consistency degree of the description information of the object to be recommended and the content of the object to be recommended; the consistency degree of the first recommendation parameter information and the content is in a negative correlation relationship;
determining recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information;
recommending the plurality of objects to be recommended based on the recommendation index information;
wherein the first recommended parameter information is determined in advance by the following steps:
acquiring historical feedback content and historical feedback behavior information of the object to be recommended;
extracting at least one content word from the historical feedback content;
determining importance degree information of the content participles in the historical feedback content;
and determining first recommendation parameter information corresponding to the plurality of objects to be recommended respectively based on the at least one content participle, the importance degree information of the at least one content participle in the historical feedback content and the historical feedback behavior information.
2. The object recommendation method according to claim 1, wherein the step of determining the first recommendation parameter information corresponding to each of the plurality of objects to be recommended based on the at least one content participle, the importance degree information of the at least one content participle in the historical feedback content, and the historical feedback behavior information comprises:
and inputting the at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, and performing recommendation parameter prediction processing to obtain first recommendation parameter information corresponding to the plurality of objects to be recommended respectively.
3. The object recommendation method of claim 1, further comprising:
acquiring second recommendation parameter information corresponding to the plurality of objects to be recommended respectively, wherein the second recommendation parameter information represents preset recommendation priority information of the plurality of objects to be recommended;
the step of determining recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information comprises:
and determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information.
4. The object recommendation method according to claim 3, wherein the determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information comprises:
determining weight information corresponding to the first recommendation parameter information based on the second recommendation parameter information;
and determining the recommendation index information of the plurality of objects to be recommended according to the second recommendation parameter information, the first recommendation parameter information and the corresponding weight information.
5. The object recommendation method according to claim 3, wherein the determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information comprises:
acquiring a recommended parameter threshold;
acquiring a first target object of which the first recommendation parameter information is lower than the recommendation parameter threshold and a second target object of which the first recommendation parameter information is higher than or equal to the recommendation parameter threshold from the plurality of objects to be recommended;
determining first recommendation index information of the first target object according to the second recommendation parameter information;
determining second recommendation index information of the second target object according to the first recommendation parameter information and the second recommendation parameter information;
and determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation index information and the second recommendation index information.
6. An object recommendation apparatus, comprising:
the recommendation system comprises a first recommendation parameter information acquisition module, a recommendation processing module and a recommendation processing module, wherein the first recommendation parameter information acquisition module is configured to acquire a plurality of objects to be recommended and first recommendation parameter information corresponding to the objects to be recommended; the first recommendation parameter information represents the consistency degree of the description information of the object to be recommended and the content of the object to be recommended; the consistency degree of the first recommendation parameter information and the content is in a negative correlation relationship;
a recommendation index information determination module configured to perform determination of recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information;
the recommending module is configured to execute recommending processing on the plurality of objects to be recommended based on the recommending index information;
wherein the apparatus further comprises the following means for predetermining the first recommended parameter information:
the history feedback acquisition module is configured to execute acquisition of history feedback content and history feedback behavior information of the object to be recommended;
a word segmentation module configured to perform extraction of at least one content word from the historical feedback content;
an importance information determination module configured to perform determining importance information of the content participles in the history feedback content;
the recommendation parameter information presetting module is configured to determine first recommendation parameter information corresponding to each of the plurality of objects to be recommended based on the at least one content participle, the importance degree information of the at least one content participle in the historical feedback content and the historical feedback behavior information.
7. The object recommendation device of claim 6, wherein the recommendation parameter information presetting module comprises:
and the recommendation parameter information presetting unit is configured to input the at least one content word, the importance degree information of the at least one content word in the historical feedback content and the historical feedback behavior information into a recommendation parameter prediction model, perform recommendation parameter prediction processing, and obtain first recommendation parameter information corresponding to each of the plurality of objects to be recommended.
8. The object recommendation device of claim 6, further comprising:
the second recommendation parameter information acquisition module is configured to execute acquisition of second recommendation parameter information corresponding to each of the multiple objects to be recommended, and the second recommendation parameter information represents preset recommendation priority information of the multiple objects to be recommended;
the recommendation indicator information determination module includes:
a recommendation index information determination unit configured to perform determining the recommendation index information of the plurality of objects to be recommended according to the first recommendation parameter information and the second recommendation parameter information.
9. The object recommendation device according to claim 8, wherein the recommendation index information determination unit includes:
a weight information determination subunit configured to perform determination of weight information corresponding to the first recommendation parameter information based on the second recommendation parameter information;
a recommendation index information determination subunit configured to perform determining the recommendation index information of the plurality of objects to be recommended according to the second recommendation parameter information, the first recommendation parameter information, and the corresponding weight information.
10. The object recommendation device according to claim 8, wherein the recommendation index information determination unit includes:
a recommended parameter threshold acquisition subunit configured to perform acquisition of a recommended parameter threshold;
an object dividing subunit configured to perform, from the plurality of objects to be recommended, acquiring a first target object of which the first recommendation parameter information is lower than the recommendation parameter threshold and a second target object of which the first recommendation parameter information is higher than or equal to the recommendation parameter threshold;
a first recommendation index information determination subunit configured to perform determining first recommendation index information of the first target object according to the second recommendation parameter information;
a second recommendation indicator information determination subunit configured to perform determining second recommendation indicator information of the second target object according to the first recommendation parameter information and the second recommendation parameter information;
a recommendation indicator information determination subunit configured to further perform determining the recommendation indicator information of the plurality of objects to be recommended according to the first recommendation indicator information and the second recommendation indicator information.
11. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the object recommendation method of any of claims 1 to 5.
12. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the object recommendation method of any of claims 1-5.
CN202110889451.5A 2021-08-04 2021-08-04 Object recommendation method and device, electronic equipment and storage medium Active CN113343024B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110889451.5A CN113343024B (en) 2021-08-04 2021-08-04 Object recommendation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110889451.5A CN113343024B (en) 2021-08-04 2021-08-04 Object recommendation method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113343024A CN113343024A (en) 2021-09-03
CN113343024B true CN113343024B (en) 2021-12-07

Family

ID=77480585

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110889451.5A Active CN113343024B (en) 2021-08-04 2021-08-04 Object recommendation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113343024B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113868522A (en) * 2021-09-26 2021-12-31 北京达佳互联信息技术有限公司 Object recommendation method and device, electronic equipment and storage medium
CN114254193B (en) * 2021-12-20 2022-11-22 北京达佳互联信息技术有限公司 Content recommendation method and device, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106250550A (en) * 2016-08-12 2016-12-21 智者四海（北京）技术有限公司 A kind of method and apparatus of real time correlation news content recommendation
CN109145221A (en) * 2018-09-10 2019-01-04 北京点网聚科技有限公司 Content recommendation method and device, electronic equipment, readable storage medium storing program for executing
CN109388760A (en) * 2017-08-03 2019-02-26 腾讯科技（北京）有限公司 Recommend label acquisition method, media content recommendations method, apparatus and storage medium
CN111209476A (en) * 2019-12-31 2020-05-29 广州市百果园信息技术有限公司 Recommendation method, model generation method, device, medium and equipment

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050043969A (en) * 2002-09-16 2005-05-11 코닌클리케 필립스 일렉트로닉스 엔.브이. System and method for adapting an interest profile on a media system
CN104050163B (en) * 2013-03-11 2017-08-25 广州帷策智能科技有限公司 Content recommendation system
CN107818166A (en) * 2017-11-07 2018-03-20 暴风集团股份有限公司 A kind of information recommends method, apparatus, server and system
CN109615487A (en) * 2019-01-04 2019-04-12 平安科技（深圳）有限公司 Products Show method, apparatus, equipment and storage medium based on user behavior
CN110781391B (en) * 2019-10-22 2023-12-12 深圳市雅阅科技有限公司 Information recommendation method, device, equipment and storage medium
CN111475729B (en) * 2020-04-07 2023-07-25 腾讯科技（深圳）有限公司 Search content recommendation method and device
CN112269943B (en) * 2020-12-03 2021-04-02 北京达佳互联信息技术有限公司 Information recommendation system and method
CN112541787B (en) * 2020-12-09 2023-12-19 北京奇艺世纪科技有限公司 Advertisement recommendation method, advertisement recommendation system, storage medium and electronic equipment
CN112765452B (en) * 2020-12-31 2024-02-27 北京百度网讯科技有限公司 Search recommendation method and device and electronic equipment
CN112733024A (en) * 2021-01-05 2021-04-30 北京三快在线科技有限公司 Information recommendation method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106250550A (en) * 2016-08-12 2016-12-21 智者四海（北京）技术有限公司 A kind of method and apparatus of real time correlation news content recommendation
CN109388760A (en) * 2017-08-03 2019-02-26 腾讯科技（北京）有限公司 Recommend label acquisition method, media content recommendations method, apparatus and storage medium
CN109145221A (en) * 2018-09-10 2019-01-04 北京点网聚科技有限公司 Content recommendation method and device, electronic equipment, readable storage medium storing program for executing
CN111209476A (en) * 2019-12-31 2020-05-29 广州市百果园信息技术有限公司 Recommendation method, model generation method, device, medium and equipment

Also Published As

Publication number Publication date
CN113343024A (en) 2021-09-03

Similar Documents

Publication Publication Date Title
US11348249B2 (en) Training method for image semantic segmentation model and server
CN112330685B (en) Image segmentation model training method, image segmentation device and electronic equipment
CN109800307B (en) Product evaluation analysis method and device, computer equipment and storage medium
CN113343024B (en) Object recommendation method and device, electronic equipment and storage medium
CN112395500A (en) Content data recommendation method and device, computer equipment and storage medium
CN113204660B (en) Multimedia data processing method, tag identification device and electronic equipment
CN111178983B (en) User gender prediction method, device, equipment and storage medium
CN113641835B (en) Multimedia resource recommendation method and device, electronic equipment and medium
CN114461871B (en) Recommendation model training method, object recommendation device and storage medium
CN114399396A (en) Insurance product recommendation method and device, computer equipment and storage medium
CN113918738B (en) Multimedia resource recommendation method and device, electronic equipment and storage medium
CN114201626B (en) Multimedia recommendation method and device, electronic equipment and storage medium
CN114626524A (en) Target service network determining method, service processing method and device
CN108550019B (en) Resume screening method and device
CN114461869A (en) Service characteristic data processing method and device, electronic equipment and storage medium
CN113704509A (en) Multimedia recommendation method and device, electronic equipment and storage medium
CN112948526A (en) User portrait generation method and device, electronic equipment and storage medium
CN114491093B (en) Multimedia resource recommendation and object representation network generation method and device
CN113610215B (en) Task processing network generation method, task processing device and electronic equipment
CN113935554B (en) Model training method in delivery system, resource delivery method and device
CN115222112A (en) Behavior prediction method, behavior prediction model generation method and electronic equipment
CN114385918A (en) Message pushing method and device, computer equipment and storage medium
CN114021739B (en) Business processing method, business processing model training device and electronic equipment
CN110929163A (en) Course recommendation method and device, computer equipment and storage medium
CN114048392B (en) Multimedia resource pushing method and device, electronic equipment and storage medium

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