CN113724022B - Keyword determination method and device, computer equipment and medium - Google Patents
Keyword determination method and device, computer equipment and medium Download PDFInfo
- Publication number
- CN113724022B CN113724022B CN202111295116.9A CN202111295116A CN113724022B CN 113724022 B CN113724022 B CN 113724022B CN 202111295116 A CN202111295116 A CN 202111295116A CN 113724022 B CN113724022 B CN 113724022B
- Authority
- CN
- China
- Prior art keywords
- keyword
- resource
- determining
- target
- keywords
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/258—Heading extraction; Automatic titling; Numbering
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a keyword determination method, a keyword determination device, computer equipment and a medium, and belongs to the technical field of internet. In the embodiment of the disclosure, when determining the keyword of the target service, not only the content resource under the target service is considered, but also the keyword of the target object associated with the content resource is considered, because the target object is a user who satisfies the first correlation condition with the target service, the keyword of the target service is determined based on the correlation between the keyword of the target object and the target service, the keyword with high correlation with the target service can be determined, the accuracy of determining the keyword is improved, and then the delivery object of the content resource under the target service is determined based on the determined keyword, so that the delivery accuracy is improved.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to a keyword determination method, apparatus, computer device, and medium.
Background
With the rapid development of internet technology and the gradual expansion of network user scale, various industries can adopt a mode of putting resources (such as advertisements) related to self business to carry out propaganda of self business.
Generally, when a business party releases a resource, keywords included in the content of the resource are extracted according to the content of the released resource, or keywords included in the resource title are extracted according to the resource title of the released resource, a keyword library of the business party is generated, and various keyword tags are added to a user according to the interactive behavior of the user based on the resource. Further, when the business party puts resources again, keywords are selected from the keyword library, and the resources are put to the users carrying the keywords, so that the effect of directional putting is achieved.
However, in the above technology, the keywords of the service corresponding to the resource are determined based on the content and title of the resource, and it is difficult to determine the keywords with high correlation with the service, thereby reducing the accuracy of delivery.
Disclosure of Invention
The disclosure provides a keyword determination method, a keyword determination device, computer equipment and a medium, which improve the accuracy of determining keywords and further improve the accuracy of putting. The technical scheme of the present disclosure includes the following.
According to a first aspect of the embodiments of the present disclosure, there is provided a keyword determination method, including:
acquiring resource information of at least one content resource under a target service and keywords of at least one target object associated with the at least one content resource, wherein the target object and the target service meet a first relevancy condition;
determining at least one corresponding relevancy of the keyword based on the resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the relevancy represents the relevancy between the keyword and the target service;
and determining the keywords with the correlation degree meeting the second correlation degree condition as the keywords of the target service, wherein the keywords are used for determining the delivery object of the content resource under the target service.
In the embodiment of the disclosure, when determining the keyword of the target service, not only the content resource under the target service is considered, but also the keyword of the target object associated with the content resource is considered, because the target object is a user who satisfies the first correlation condition with the target service, the keyword of the target service is determined based on the correlation between the keyword of the target object and the target service, the keyword with high correlation with the target service can be determined, the accuracy of determining the keyword is improved, and then the delivery object of the content resource under the target service is determined based on the determined keyword, so that the delivery accuracy is improved.
In some embodiments, the obtaining of the resource information of the at least one content resource under the target service includes:
acquiring resource introduction information of at least one content resource under the target service, wherein the resource introduction information is used for introducing the target service;
resource information of the at least one content resource is determined based on the resource introduction information of the at least one content resource.
In the embodiment of the disclosure, the resource introduction information of the content resource is utilized, the resource information of the content resource can be determined quickly, the efficiency of determining the resource information is improved, and the efficiency of determining the keyword is further improved.
In some embodiments, determining the resource information of the at least one content resource based on the resource introduction information of the at least one content resource comprises:
for any content resource, carrying out word segmentation on the resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
resource information of the content resource is determined based on the word vector of the at least one keyword.
In the embodiment of the disclosure, the resource information of the content resource is calculated by using the word vector of the keyword included in the resource introduction information, so that the efficiency of determining the resource information is improved, and the subsequent similarity calculation is performed based on the vector by determining the vector for representing the content resource.
In some embodiments, the obtaining of the keyword of the at least one target object associated with the at least one content resource comprises:
selecting at least one target object with conversion time meeting target conditions from the target objects associated with the at least one content resource, wherein the conversion time represents the time for the target object to execute target operation on the content resource;
and acquiring the keywords of at least one target object in the target time period.
In the embodiment of the disclosure, by selecting the target object whose conversion time meets the target condition, the conversion object with better time dimension can be selected and obtained, and accordingly, the obtained keyword is also the keyword of the better conversion user, and the accuracy of determining the keyword can be improved.
In some embodiments, determining the relevance of at least one of the keywords based on the resource information of the at least one content resource and the associated keywords of the at least one target object comprises:
respectively determining similarity between the resource information of the at least one content resource and the associated keywords of the at least one target object, wherein the similarity represents the similarity between the keywords and the content resource;
and determining the corresponding relevance of at least one keyword based on the corresponding similarity of at least one keyword.
In the embodiment of the disclosure, the degree of correlation between each keyword and the target service is determined by using the degree of similarity between each keyword and the corresponding content resource, so that the degree of correlation corresponding to each keyword can be quickly determined, the efficiency of determining the degree of correlation is improved, and the efficiency of determining the keywords is further improved.
In some embodiments, determining the relevance corresponding to at least one of the keywords based on the similarity corresponding to at least one of the keywords comprises:
for any keyword, determining the sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
In the embodiment of the disclosure, in the dimension of the keyword, the average value of the similarity corresponding to each keyword is adopted to represent the correlation between the keyword and the target service, so that the correlation corresponding to each keyword can be quickly determined, the efficiency of determining the correlation is improved, and the efficiency of determining the keyword is further improved.
In some embodiments, the keywords whose relevancy satisfies the second relevancy condition are determined as the keywords of the target service, and the keywords include any one of the following items:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
In the embodiment of the disclosure, by selecting the part of the keywords with the highest relevance rank, or selecting the part of the keywords with the relevance greater than a certain threshold, the keywords with the higher relevance can be selected, the keywords with the high relevance to the target service can be determined, the accuracy of determining the keywords is improved, and the putting accuracy is further improved.
According to a second aspect of the embodiments of the present disclosure, there is provided a keyword determination apparatus, including:
the acquisition unit is configured to execute acquisition of resource information of at least one content resource under a target service and a keyword of at least one target object associated with the at least one content resource, wherein a first correlation condition is satisfied between the target object and the target service;
a relevancy determining unit configured to perform determining at least one relevancy corresponding to the keyword based on the resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the relevancy represents a relevancy between the keyword and the target service;
and the keyword determining unit is configured to determine a keyword, of which the relevance meets a second relevance condition, as the keyword of the target service, wherein the keyword is used for determining an object to be delivered of the content resource under the target service.
In some embodiments, the obtaining unit includes:
an introduction information obtaining subunit, configured to perform obtaining resource introduction information of at least one content resource under the target service, where the resource introduction information is used for introducing the target service;
a resource information obtaining subunit configured to perform determining resource information of the at least one content resource based on the resource introduction information of the at least one content resource.
In some embodiments, the resource information obtaining subunit is configured to perform:
for any content resource, carrying out word segmentation on the resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
resource information of the content resource is determined based on the word vector of the at least one keyword.
In some embodiments, the obtaining unit includes:
the target object acquisition subunit is configured to execute the step of selecting at least one target object with conversion time meeting a target condition from the target objects associated with the at least one content resource, wherein the conversion time represents the time for the target object to execute the target operation on the content resource;
a keyword acquisition subunit configured to perform acquiring a keyword of the at least one target object.
In some embodiments, the correlation determination unit includes:
a similarity determination subunit configured to perform determining a similarity between the resource information of the at least one content resource and the associated keyword of the at least one target object, respectively, the similarity representing a degree of similarity between the keyword and the content resource;
and the relevancy determining subunit is configured to determine the relevancy corresponding to at least one keyword based on the similarity corresponding to the at least one keyword.
In some embodiments, the relevance determining subunit is configured to perform:
for any keyword, determining the sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
In some embodiments, the keyword determination unit is configured to perform any one of:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
According to a third aspect of embodiments of the present disclosure, there is provided a computer apparatus comprising:
one or more processors;
a memory for storing the processor executable program code;
wherein the processor is configured to execute the program code to implement the keyword determination method described above.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium including: the program code in the computer readable storage medium, when executed by a processor of a computer device, enables the computer device to perform the keyword determination method described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the keyword determination method described above.
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 diagram illustrating an implementation environment for a keyword determination method in accordance with an illustrative embodiment;
FIG. 2 is a flow diagram illustrating a keyword determination method in accordance with an exemplary embodiment;
FIG. 3 is a flow diagram illustrating a keyword determination method in accordance with an exemplary embodiment;
FIG. 4 is a block diagram illustrating a keyword determination apparatus in accordance with an exemplary embodiment;
FIG. 5 is a block diagram illustrating a server in accordance with 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.
The data or information to which the present disclosure relates may be data or information that is authorized by a user or sufficiently authorized by various parties.
First, description is made for an application scenario related to an embodiment of the present disclosure: the keyword determination method related to the embodiment of the disclosure can be applied to a resource launching scene under a target service, for example, an advertisement launching scene under the target service. In the embodiment of the present disclosure, the keyword refers to a vocabulary related to the target service.
In the related art, when a business party puts resources, keywords included in the content of the resources are extracted according to the content of the put resources, or keywords included in the resource titles are extracted according to the resource titles of the put resources, a keyword library of the business party is generated, and then various keyword labels are added to users according to the interactive behaviors of the users based on the resources. Further, when the business party puts resources to the user again, keywords are selected from the keyword library, and the resources are put to the user carrying the keywords, so that putting is realized. However, the related technology is difficult to determine the keywords with high business relevance, and the delivery accuracy is reduced.
Based on this, the embodiment of the present disclosure provides a keyword determination method, which includes obtaining resource information of at least one content resource under a target service and a keyword of at least one target object associated with the at least one content resource, determining a degree of correlation corresponding to at least one keyword based on the resource information of the at least one content resource and the keyword of the associated at least one target object, and determining a keyword whose degree of correlation satisfies a second degree of correlation condition as the keyword of the target service. Therefore, the accuracy of determining the keywords is improved, and the putting accuracy is further improved.
Fig. 1 is a schematic diagram of an implementation environment of a keyword determination method provided in an embodiment of the present disclosure, referring to fig. 1, where the implementation environment includes: a server 101.
The server 101 may be an independent physical server, a server cluster or a distributed file 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 web 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.
Optionally, the number of the servers 101 may be more or less, and the embodiment of the present disclosure does not limit this. Of course, the server 101 may also include other functional servers in order to provide more comprehensive and diversified services.
In this embodiment of the present disclosure, the server 101 is configured to obtain resource information of at least one content resource under a target service and a keyword of at least one target object associated with the at least one content resource, determine, based on the resource information of the at least one content resource and the keyword of the associated at least one target object, a degree of correlation corresponding to the at least one keyword, and determine, as the keyword of the target service, the keyword whose degree of correlation satisfies a second degree of correlation condition.
In some embodiments, the keyword determination method provided by the embodiment of the present disclosure is periodically executed by the server 101, for example, the server 101 executes the process executed by the keyword determination method once every target time period (e.g., 1 hour).
In other embodiments, the keyword determination method provided by the embodiment of the present disclosure is triggered by the terminal 102 when the keyword of the target service needs to be determined, for example, the terminal 102 sends a keyword determination request to the server 101 in response to a triggering operation of (a manager of) a service party on the keyword determination, so as to request the server 101 to determine the keyword of the target service.
In some embodiments, the server 101 and the terminal 102 may be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiments of the present disclosure.
The terminal 102 may be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop portable computer, and the like, and the terminal 102 has a communication function and can access a wired network or a wireless network. The terminal 102 may be generally referred to as one of a plurality of terminals, and the embodiment is merely illustrated by the terminal 102. Those skilled in the art will appreciate that the number of terminals described above may be greater or fewer.
Fig. 2 is a flow chart illustrating a keyword determination method, as performed by a server, as shown in fig. 2, according to an exemplary embodiment, including the following steps.
In step 201, a server obtains resource information of at least one content resource under a target service and a keyword of at least one target object associated with the at least one content resource, where a first relevancy condition is satisfied between the target object and the target service.
In step 202, the server determines at least one degree of relevance corresponding to the keyword based on the resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the degree of relevance represents the degree of relevance between the keyword and the target service.
In step 203, the server determines the keyword whose relevancy satisfies the second relevancy condition as the keyword of the target service, where the keyword is used to determine the delivery object of the content resource under the target service.
According to the technical scheme provided by the embodiment of the disclosure, when determining the keyword of the target service, not only the content resource under the target service is considered, but also the keyword of the target object associated with the content resource is considered, because the target object is a user meeting a first correlation condition with the target service, the keyword of the target service is determined based on the correlation between the keyword of the target object and the target service, the keyword with high correlation with the target service can be determined, the accuracy of determining the keyword is improved, and then the delivery object of the content resource under the target service is determined based on the determined keyword, and the delivery accuracy is improved.
In some embodiments, the obtaining of the resource information of the at least one content resource under the target service includes:
acquiring resource introduction information of at least one content resource under the target service, wherein the resource introduction information is used for introducing the target service;
resource information of the at least one content resource is determined based on the resource introduction information of the at least one content resource.
In some embodiments, determining the resource information of the at least one content resource based on the resource introduction information of the at least one content resource comprises:
for any content resource, carrying out word segmentation on the resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
resource information of the content resource is determined based on the word vector of the at least one keyword.
In some embodiments, the obtaining of the keyword of the at least one target object associated with the at least one content resource comprises:
selecting at least one target object with conversion time meeting target conditions from the target objects associated with the at least one content resource, wherein the conversion time represents the time for the target object to execute target operation on the content resource;
and acquiring the keywords of the at least one target object.
In some embodiments, determining the relevance of at least one of the keywords based on the resource information of the at least one content resource and the associated keywords of the at least one target object comprises:
respectively determining similarity between the resource information of the at least one content resource and the associated keywords of the at least one target object, wherein the similarity represents the similarity between the keywords and the content resource;
and determining the corresponding relevance of at least one keyword based on the corresponding similarity of at least one keyword.
In some embodiments, determining the relevance corresponding to at least one of the keywords based on the similarity corresponding to at least one of the keywords comprises:
for any keyword, determining the sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
In some embodiments, the keywords whose relevancy satisfies the second relevancy condition are determined as the keywords of the target service, and the keywords include any one of the following items:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
Fig. 2 is a basic flow chart of the present disclosure, and the scheme provided by the present disclosure is further described below based on a specific implementation, and fig. 3 is a flow chart of a keyword determination method according to an exemplary embodiment, and referring to fig. 3, the method includes the following steps.
In step 301, the server obtains resource information of at least one content resource under the target service.
In some embodiments, the target business is a target industry. For example, the target industry may be a secondary industry, which refers to a specific industry under the primary industry, e.g., the primary industry may be agriculture, industry, service industry, and correspondingly, the secondary industry may be steel industry, clothing industry, food industry, etc. In other embodiments, the target business is a specific business within the industry. For example, taking the industry as the clothing industry as an example, the target business can be a women's clothing business, a men's clothing business, a children's clothing business and the like.
In the embodiment of the present disclosure, the content resource under the target service refers to a multimedia resource containing the relevant content of the target service. Understandably, the content resource is also a multimedia resource for advertising the target service. For example, the content assets under the targeted service may be advertising videos, promotional videos, etc. of the targeted service. In some embodiments, the content resource is represented with a resource identification. For example, the resource Identification may be a resource name, a resource number, a resource ID (Identification), and the like.
In the embodiment of the present disclosure, the resource information refers to a feature vector of the content resource.
In some embodiments, the process of the server obtaining resource information of the content resource includes: the server acquires resource introduction information of at least one content resource under the target service, and determines resource information of the at least one content resource based on the resource introduction information of the at least one content resource. Therefore, the resource information of the content resources can be quickly determined by using the resource introduction information of the content resources, the efficiency of determining the resource information is improved, and the efficiency of determining the keywords is further improved.
Wherein the resource introduction information is used for introducing the target service. In some embodiments, the resource introduction information is a resource title, such as a video title, of the content resource; alternatively, the resource introduction information is a resource description of the content resource, such as a video description. Before implementing the present solution, when a service party (e.g., an advertiser) puts a content resource in a target service, a resource title or a resource description of the content resource is filled in a putting plan (e.g., an advertisement plan) of the content resource. It should be understood that the content contained in the resource title or resource description of the content resource is the content that is strongly related to the target service.
In some embodiments, the process of determining, by the server, the resource information of the content resource based on the resource introduction information includes: for any content resource, the server cuts words of the resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information, and determines the resource information of the content resource based on the word vector of the at least one keyword. In an alternative embodiment, the server determines the resource information of the content resource based on the word vector of the at least one keyword by: the server obtains an average value of the word vectors of the at least one keyword, and determines the obtained average value as the resource information of the content resource. In this way, the resource information of the content resource is calculated by using the word vector of the keyword included in the resource introduction information, so that the efficiency of determining the resource information is improved, and the subsequent similarity calculation is performed based on the resource information by determining the vector for representing the content resource.
In the embodiment of the present disclosure, the keyword refers to a vocabulary related to the target service. For example, in the case of a target business for women's clothing, the keyword may be a dress, a high-heeled shoe, a coat, or the like. The word vector of the keyword refers to a feature vector of the keyword.
In an alternative embodiment, the process of the server obtaining the word vector of the keyword is as follows: for any keyword, the server determines a word vector corresponding to the keyword based on the keyword in a first corresponding relationship, wherein the first corresponding relationship comprises a plurality of vocabularies and word vectors corresponding to the vocabularies. In another alternative embodiment, the process of the server obtaining the word vector of the keyword is as follows: for any keyword, the server inputs the keyword into a word vector extraction model, and performs feature extraction based on the keyword through the word vector extraction model to obtain a word vector of the keyword.
In some embodiments, the Word vector extraction model is a Word2vec model. Wherein the Word2vec model is a correlation model for generating Word vectors. In some embodiments, before implementing the present solution, the server generates Word vectors corresponding to a plurality of words based on the words included in the corpus using a Word2vec model, and generates the first corresponding relationship based on the plurality of words and the Word vectors corresponding to the plurality of words. In an alternative embodiment, the server selects a vocabulary related to the target service from a plurality of vocabularies included in the corpus, generates a Word vector corresponding to the vocabulary related to the target service by using a Word2vec model, and generates the first corresponding relationship based on the vocabulary related to the target service and the Word vector corresponding to the vocabulary related to the target service.
In step 302, the server obtains a keyword of at least one target object associated with the at least one content resource, where a first relevancy condition is satisfied between the target object and the target service.
The target object refers to a target user, and particularly refers to a conversion user of the content resource. The conversion user refers to a user who performs a target operation on a content resource under a target service, and it should be understood that the conversion user is a user who is interested in the target service, and for the target service, the conversion user is a high-value user with a high conversion rate. In the embodiment of the disclosure, the condition that the target object and the target service meet the first relevancy condition indicates that the target object and the target service have a strong relevancy relationship. It should be understood that, when advertising or publicizing the target service, the core goal is to expect to bring the conversion users, and the conversion users are users having strong correlation with the target service. In some embodiments, the target object is represented using object identification. For example, the object identification may be a user name, a user account, a user ID, and the like.
The following description will be made based on the content resources of the advertisement type as an example: taking a conventional advertisement as an example, the conventional advertisement is converted based on the click operation of a user, correspondingly, the target operation is the click operation on the advertisement, and the conversion user is a user who performs the click operation on the conventional advertisement; taking application program advertisement as an example, the application program advertisement realizes conversion based on the downloading of the application program by the user, correspondingly, the target operation is the downloading operation of the application program, and the conversion user is the user who downloads the corresponding application program based on the application program advertisement; taking a consultation advertisement as an example, the consultation advertisement is converted based on the online consultation of the user, correspondingly, the target operation is online consultation operation, and the conversion user is a user initiating online consultation based on the consultation advertisement; taking an information collection advertisement as an example, the information collection advertisement is converted based on the filling operation of the user in the information form, correspondingly, the target operation is the filling operation in the information form, and the conversion user is the user who writes information in the information form of the information collection advertisement; taking a product advertisement as an example, the product advertisement realizes conversion based on the purchase operation of the user on the product, accordingly, the target operation is the purchase operation on the product, and the conversion user is the user who purchases the corresponding product based on the product advertisement.
In some embodiments, for any content resource, the server determines, based on the resource identifier of the content resource, at least one object identifier corresponding to the resource identifier in a second corresponding relationship, determines an object identifier of a target object in the at least one object identifier, and obtains a keyword of the target object, where the second corresponding relationship includes a plurality of resource identifiers and object identifiers corresponding to the plurality of resource identifiers. In an alternative embodiment, the process of the server obtaining the keyword of the target object is as follows: after determining the target object, the server obtains the key word of the target object from the user portrait of the target object. The user representation is a tool for abstracting concrete information such as attributes and behaviors of a user into user tags and describing the user by using the user tags.
In some embodiments, the server selects at least one target object whose conversion time satisfies a target condition from the target objects associated with the at least one content resource, where the conversion time represents a time for the target object to perform a target operation on the content resource, and obtains a keyword of the at least one target object. In some embodiments, the conversion time meets the target condition that the conversion time is within a target time period closest to the current time, where the target time period is a predetermined time period, such as within 90 days. Therefore, by selecting the target object in the target time period with the conversion time closest to the current time, the latest conversion object in the time dimension can be selected and obtained, and accordingly, the obtained keywords are also the keywords of the latest conversion user, and the accuracy of determining the keywords can be improved.
In step 303, the server determines similarity between the resource information of the at least one content resource and the associated keyword of the at least one target object, respectively, the similarity indicating a degree of similarity between the keyword and the content resource.
In some embodiments, the similarity is expressed by cosine similarity between vectors, and the corresponding process is as follows: for any keyword of the target object, the server acquires a word vector of the keyword of the target object, calculates cosine similarity between the word vector of the keyword and resource information based on the word vector of the keyword and the resource information of the content resource corresponding to the target object, and determines the cosine similarity obtained by calculation as the similarity between the keyword and the corresponding content resource.
The process of obtaining the word vector of the keyword of the target object by the server refers to the process of obtaining the word vector of the keyword in the resource introduction information in step 301, which is not described again.
The above-described embodiment is a process of determining the similarity between the keyword and the content resource by calculating the cosine similarity between vectors. In other embodiments, the server determines the similarity between the keyword and the content resource based on other similarity calculation methods. For example, the similarity between the keyword and the content resource is determined by calculating the distance between the vectors. The distance may be any one of an euclidean distance, a manhattan distance, a chebyshev distance, a chi-square distance, and a hamming distance, and the selection of which distance is used for calculating the similarity is not limited in the embodiment of the present disclosure. It should be understood that the smaller the distance, the greater the similarity, and the larger the distance, the lesser the similarity. Alternatively, the server can also determine the similarity between the keyword and the content resource by calculating a correlation coefficient between the vectors. Wherein the correlation coefficient may be any one of a pearson correlation coefficient and a Jaccard correlation coefficient.
In a specific example, taking advertisement 1 as an example, the target objects associated with advertisement 1 may include user 1 and user 2, the keyword of user 1 may be a, and the keyword of user 2 may be B; taking advertisement 2 as an example, the target objects associated with advertisement 2 may include user 3 and user 4, the keywords of user 3 may be a, and the keywords of user 4 may be a and C. Then, the process of calculating the similarity corresponding to the keyword a of the user 1 is as follows: calculating the similarity between the vector of the keyword A and the vector of the advertisement 1; the process of calculating the similarity corresponding to the keyword B of the user 2 is as follows: calculating the similarity between the vector of the keyword B and the vector of the advertisement 2; the process of calculating the similarity corresponding to the keyword a of the user 3 is as follows: calculating the similarity between the vector of the keyword A and the vector of the advertisement 2; the process of calculating the similarity corresponding to the keyword a of the user 4 is as follows: calculating the similarity between the vector of the keyword A and the vector of the advertisement 2; the process of calculating the similarity corresponding to the keyword C of the user 4 is as follows: the similarity between the vector of keyword C and the vector of advertisement 2 is calculated.
In an alternative embodiment, after determining the similarity between each keyword and the corresponding content resource, the server ranks the keywords according to an arrangement order of the similarity from high to low, selects the keyword corresponding to the similarity in the front of the arrangement order, and performs step 304 based on the selected keyword. Therefore, the calculation amount of the server is effectively reduced, and the processing speed of the server is further improved.
In step 304, the server determines a degree of relevance corresponding to at least one of the keywords based on the degree of similarity corresponding to the at least one of the keywords, where the degree of relevance represents a degree of relevance between the keyword and the target service.
In the embodiment of the disclosure, the degree of correlation between the keyword and the target service is expressed by adopting the degree of correlation, and it should be understood that the greater the degree of correlation, the greater the degree of correlation between the keyword and the target service is expressed; the smaller the degree of correlation, the smaller the degree of correlation between the keyword and the target service.
In some embodiments, for any keyword, the server determines a sum of at least one similarity corresponding to the keyword, and determines a relevance corresponding to the keyword based on the sum of the at least one similarity and the number of the at least one similarity. In an optional embodiment, after determining the sum of at least one similarity corresponding to the keyword, the server calculates an average of the at least one similarity based on the sum of the at least one similarity and the number of the at least one similarity, and determines the calculated average as the correlation corresponding to the keyword. Therefore, in the dimension of the keyword, the average value of the similarity corresponding to each keyword is adopted to represent the correlation between the keyword and the target service, the correlation corresponding to each keyword can be quickly determined, the efficiency of determining the correlation is improved, and the efficiency of determining the keyword is further improved.
In a specific example, based on the example in step 303, it is assumed that the similarity corresponding to the keyword a of the user 1 is 80, the similarity corresponding to the keyword B of the user 2 is 70, the similarity corresponding to the keyword a of the user 3 is 90, the similarity corresponding to the keyword a of the user 4 is 90, and the similarity corresponding to the keyword C of the user 4 is 60, and it can be found that, according to the dimensions of the keywords, the keywords a respectively correspond to 3 similarities, which are 80, 90, and 90 respectively. Then, the process of calculating the relevance corresponding to each keyword based on step 304 is: for keyword a, the degree of correlation corresponding to keyword a is (80 +90+ 90)/3 ≈ 86.7.
In the embodiment, the degree of correlation between each keyword and the target service is determined by using the degree of similarity between each keyword and the corresponding content resource, so that the degree of correlation corresponding to each keyword can be quickly determined, the efficiency of determining the degree of correlation is improved, and the efficiency of determining the keywords is further improved.
In step 305, the server determines a keyword, of which the relevance satisfies the second relevance condition, as the keyword of the target service, where the keyword is used to determine an object to be delivered by the content resource under the target service.
In some embodiments, the server sorts the keywords according to an arrangement order of the relevance degrees from high to low, and determines the keywords corresponding to the relevance degrees of the arrangement order located at the front target digit as the keywords of the target service. Wherein, the target digit is a preset digit, such as 10 digits. For example, the keyword corresponding to the correlation degree with the ranking order located in the top 10 digits is selected as the keyword of the target service.
In other embodiments, the server sorts the keywords according to the ranking order of the relevancy from high to low, and determines the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service. Wherein the target threshold is a predetermined threshold, such as 90. For example, a keyword corresponding to a relevance of 90 is selected as the keyword of the target service.
In the embodiment, the keywords with higher relevance can be selected by selecting part of the keywords with the highest relevance ranking or selecting part of the keywords with the relevance higher than a certain threshold, so that the keywords with high relevance to the target service can be determined, the accuracy of determining the keywords is improved, and the delivery accuracy is further improved.
Through the steps 301 to 305, a keyword mining method for a target service is realized, and a keyword with high relevance to the target service, that is, a high-value keyword, can be determined. On one hand, the embodiment of the disclosure calculates the relevance between each keyword and the target service, and then selects the keyword with higher relevance, so that the selected keyword is closely related to the target service; on the other hand, the keywords of the target object (that is, the conversion user) in the target service are adopted in the embodiment of the disclosure, and since the conversion rate of the target service by the part of users is high, the keywords are selected from the keywords of the part of users, so that the high-value keywords can be further determined. Furthermore, when the business party utilizes the keyword determined by the embodiment of the disclosure to perform subsequent resource delivery, the user determined based on the keyword is a user with a relatively high conversion rate, so that the difficulty of selecting the keyword by the business party is reduced, the orientation of the business party is more accurate, and the delivery effect of the resource is improved.
In some embodiments, a terminal operated by a service party can display keywords of a target service determined in the embodiments of the present disclosure, when the service party determines an object to be delivered of a content resource, the service party can perform a selection operation on a plurality of keywords displayed on the terminal, the terminal obtains a selected keyword in response to the selection operation of the service party on the plurality of keywords, and sends a delivery request for the content resource to a server based on the selected keyword, where the delivery request carries the selected keyword. The server responds to the received release request of the content resource, determines the user carrying the keyword based on the keyword carried by the release request, namely determines the release object of the content resource, and further sends the content resource to the terminal corresponding to the determined user. Therefore, the releasing method based on the keywords is realized, and the releasing accuracy is effectively improved because the adopted keywords are the keywords with high correlation degree with the target service.
According to the technical scheme provided by the embodiment of the disclosure, when determining the keyword of the target service, not only the content resource under the target service is considered, but also the keyword of the target object associated with the content resource is considered, because the target object is a user meeting a first correlation condition with the target service, the keyword of the target service is determined based on the correlation between the keyword of the target object and the target service, the keyword with high correlation with the target service can be determined, the accuracy of determining the keyword is improved, and then the delivery object of the content resource under the target service is determined based on the determined keyword, and the delivery accuracy is improved.
Fig. 4 is a block diagram illustrating a keyword determination apparatus according to an example embodiment. Referring to fig. 4, the apparatus includes an acquisition unit 401, a correlation determination unit 402, and a keyword determination unit 403:
an obtaining unit 401 configured to perform obtaining resource information of at least one content resource under a target service and a keyword of at least one target object associated with the at least one content resource, where a first correlation condition is satisfied between the target object and the target service;
a relevance determining unit 402 configured to perform determining a relevance corresponding to at least one keyword based on the resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the relevance represents a degree of relevance between the keyword and the target service;
a keyword determining unit 403, configured to perform a keyword that satisfies the relevance with a second relevance condition, and determine the keyword as a keyword of the target service, where the keyword is used to determine an object to be delivered for the content resource under the target service.
According to the technical scheme provided by the embodiment of the disclosure, when determining the keyword of the target service, not only the content resource under the target service is considered, but also the keyword of the target object associated with the content resource is considered, because the target object is a user meeting a first correlation condition with the target service, the keyword of the target service is determined based on the correlation between the keyword of the target object and the target service, the keyword with high correlation with the target service can be determined, the accuracy of determining the keyword is improved, and then the delivery object of the content resource under the target service is determined based on the determined keyword, and the delivery accuracy is improved.
In some embodiments, the obtaining unit 401 includes:
an introduction information obtaining subunit, configured to perform obtaining resource introduction information of at least one content resource under the target service, where the resource introduction information is used for introducing the target service;
a resource information obtaining subunit configured to perform determining resource information of the at least one content resource based on the resource introduction information of the at least one content resource.
In some embodiments, the resource information obtaining subunit is configured to perform:
for any content resource, carrying out word segmentation on the resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
resource information of the content resource is determined based on the word vector of the at least one keyword.
In some embodiments, the obtaining unit 401 includes:
the target object acquisition subunit is configured to execute the step of selecting at least one target object with conversion time meeting a target condition from the target objects associated with the at least one content resource, wherein the conversion time represents the time for the target object to execute the target operation on the content resource;
a keyword acquisition subunit configured to perform acquiring a keyword of the at least one target object.
In some embodiments, the correlation determination unit 402 includes:
a similarity determination subunit configured to perform determining a similarity between the resource information of the at least one content resource and the associated keyword of the at least one target object, respectively, the similarity representing a degree of similarity between the keyword and the content resource;
and the relevancy determining subunit is configured to determine the relevancy corresponding to at least one keyword based on the similarity corresponding to the at least one keyword.
In some embodiments, the relevance determining subunit is configured to perform:
for any keyword, determining the sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
In some embodiments, the keyword determination unit 403 is configured to perform any one of the following:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
It should be noted that: the keyword determining apparatus provided in the foregoing embodiment is only illustrated by dividing the functional modules when determining the keyword, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the keyword determination apparatus and the keyword determination method provided in the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments in detail and are not described herein again.
The computer device mentioned in the embodiment of the present disclosure may be provided as a server. Fig. 5 is a block diagram of a server according to an exemplary embodiment, where the server 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 501 and one or more memories 502, where at least one program code is stored in the one or more memories 502, and the at least one program code is loaded and executed by the one or more processors 501 to implement the processes executed by the server in the keyword determination method provided by the above-mentioned method embodiments. Of course, the server 500 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 500 may also include other components for implementing the functions of the device, which is not described herein again.
In an exemplary embodiment, a computer readable storage medium comprising program code, such as a memory 502 comprising program code, executable by a processor 501 of the server 500 to perform the keyword determination method described above is also provided. Alternatively, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact-Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is also provided, comprising a computer program which, when executed by a processor, implements the keyword determination method described above.
In some embodiments, a computer program according to embodiments of the present disclosure may be deployed to be executed on one computer device or on multiple computer devices located at one site, or on multiple computer devices distributed at multiple sites and interconnected by a communication network, and the multiple computer devices distributed at the multiple sites and interconnected by the communication network may constitute a block chain system.
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 disclosure 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 (14)
1. A method for determining keywords, the method comprising:
acquiring resource information of at least one content resource under a target service;
selecting at least one target object with conversion time meeting target conditions from the target objects associated with the at least one content resource, and acquiring keywords of the at least one target object, wherein the conversion time represents the time for the target object to execute target operation on the content resource, and a first correlation condition is met between the target object and the target service;
determining a degree of correlation corresponding to at least one keyword based on the resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the degree of correlation represents the degree of correlation between the keyword and the target service;
and determining the keywords with the correlation degrees meeting a second correlation degree condition as the keywords of the target service, wherein the keywords are used for determining the delivery object of the content resources under the target service.
2. The method according to claim 1, wherein the obtaining of the resource information of the at least one content resource under the target service comprises:
acquiring resource introduction information of at least one content resource under the target service, wherein the resource introduction information is used for introducing the target service;
determining resource information of the at least one content resource based on the resource introduction information of the at least one content resource.
3. The method according to claim 2, wherein the determining the resource information of the at least one content resource based on the resource introduction information of the at least one content resource comprises:
for any content resource, carrying out word segmentation on resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
determining resource information of the content resource based on the word vector of the at least one keyword.
4. The method according to claim 1, wherein determining the relevance of at least one keyword corresponding to the resource information of the at least one content resource and the associated keyword of the at least one target object comprises:
respectively determining similarity between the resource information of the at least one content resource and the associated keywords of the at least one target object, wherein the similarity represents the similarity between the keywords and the content resource;
and determining the corresponding relevance of at least one keyword based on the corresponding similarity of at least one keyword.
5. The method according to claim 4, wherein determining the relevance corresponding to at least one of the keywords based on the similarity corresponding to at least one of the keywords comprises:
for any keyword, determining a sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
6. The method according to claim 1, wherein the determining the keyword whose relevancy satisfies a second relevancy condition as the keyword of the target service includes any one of:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
7. An apparatus for determining keywords, the apparatus comprising:
an acquisition unit configured to perform acquisition of resource information of at least one content resource under a target service;
the obtaining unit is further configured to select at least one target object with conversion time meeting a target condition from the target objects associated with the at least one content resource, and obtain a keyword of the at least one target object, where the conversion time represents time for the target object to perform a target operation on the content resource, and a first correlation condition is met between the target object and the target service;
a relevancy determining unit configured to perform determining relevancy corresponding to at least one keyword based on resource information of the at least one content resource and the associated keyword of the at least one target object, wherein the relevancy represents relevancy between the keyword and the target business;
and the keyword determining unit is configured to execute a keyword for determining the relevancy meets a second relevancy condition as the keyword of the target service, wherein the keyword is used for determining an object for delivering the content resource under the target service.
8. The keyword determination apparatus according to claim 7, wherein the acquisition unit includes:
an introduction information obtaining subunit, configured to perform obtaining resource introduction information of at least one content resource under the target service, where the resource introduction information is used for introducing the target service;
a resource information obtaining subunit configured to perform determining resource information of the at least one content resource based on the resource introduction information of the at least one content resource.
9. The keyword determination apparatus according to claim 8, wherein the resource information acquisition subunit is configured to perform:
for any content resource, carrying out word segmentation on resource introduction information of the content resource to obtain at least one keyword included in the resource introduction information;
determining resource information of the content resource based on the word vector of the at least one keyword.
10. The keyword determination apparatus according to claim 7, wherein the correlation determination unit includes:
a similarity determination subunit configured to perform determination of a similarity between the resource information of the at least one content resource and the associated keyword of the at least one target object, respectively, the similarity representing a degree of similarity between the keyword and the content resource;
and the relevancy determining subunit is configured to determine the relevancy corresponding to at least one keyword based on the similarity corresponding to the at least one keyword.
11. The keyword determination apparatus according to claim 10, wherein the relevancy determination subunit is configured to perform:
for any keyword, determining a sum of at least one similarity corresponding to the keyword;
and determining the corresponding relevancy of the keyword based on the sum of the at least one similarity and the number of the at least one similarity.
12. The keyword determination apparatus according to claim 7, wherein the keyword determination unit is configured to perform any one of:
sequencing according to the sequence of the relevance from high to low, and determining the keywords corresponding to the relevance of the sequence in the front target digit as the keywords of the target service;
and sequencing according to the sequence of the relevancy from high to low, and determining the keywords corresponding to the relevancy with the relevancy reaching the target threshold as the keywords of the target service.
13. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory for storing the processor executable program code;
wherein the processor is configured to execute the program code to implement the keyword determination method of any of claims 1 to 6.
14. A computer-readable storage medium, characterized in that, when program code in the computer-readable storage medium is executed by a processor of a computer device, the computer device is enabled to execute the keyword determination method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295116.9A CN113724022B (en) | 2021-11-03 | 2021-11-03 | Keyword determination method and device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111295116.9A CN113724022B (en) | 2021-11-03 | 2021-11-03 | Keyword determination method and device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724022A CN113724022A (en) | 2021-11-30 |
| CN113724022B true CN113724022B (en) | 2022-03-25 |
Family
ID=78686584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111295116.9A Active CN113724022B (en) | 2021-11-03 | 2021-11-03 | Keyword determination method and device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724022B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485525A (en) * | 2015-08-31 | 2017-03-08 | 百度在线网络技术（北京）有限公司 | Information processing method and device |
| CN106204156A (en) * | 2016-07-20 | 2016-12-07 | 天涯社区网络科技股份有限公司 | A kind of advertisement placement method for network forum and device |
| CN108984554B (en) * | 2017-06-01 | 2021-06-29 | 北京京东尚科信息技术有限公司 | Method and device for determining keywords |
| CN111368038B (en) * | 2020-03-09 | 2023-04-11 | 广州市百果园信息技术有限公司 | Keyword extraction method and device, computer equipment and storage medium |
| CN112446214B (en) * | 2020-12-09 | 2024-02-02 | 北京有竹居网络技术有限公司 | Advertisement keyword generation method, device, equipment and storage medium |
| CN113570413B (en) * | 2021-07-28 | 2023-12-05 | 杭州王道控股有限公司 | Advertisement keyword generation method and device, storage medium and electronic equipment |
-
2021
- 2021-11-03 CN CN202111295116.9A patent/CN113724022B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724022A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220405607A1 (en) | Method for obtaining user portrait and related apparatus | |
| CN107426328B (en) | Information pushing method and device | |
| CN110147882B (en) | Neural network model training method, crowd diffusion method, device and equipment | |
| CN111242748B (en) | Method, apparatus, and storage medium for recommending items to a user | |
| CN111144952A (en) | Advertisement recommendation method, device, server and storage medium based on user interests | |
| CN112818224B (en) | Information recommendation method and device, electronic equipment and readable storage medium | |
| CN112000871A (en) | Method, device and equipment for determining search result list and storage medium | |
| CN112581162A (en) | Information content display method, device, storage medium and terminal | |
| CN108076387A (en) | Business object method for pushing and device, electronic equipment | |
| CN115907868A (en) | Advertisement delivery analysis method and device | |
| CN113379449A (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
| CN114245165B (en) | Live broadcast recommendation method and device, electronic equipment and storage medium | |
| CN113570416B (en) | Method and device for determining delivered content, electronic equipment and storage medium | |
| CN113225580B (en) | Live broadcast data processing method and device, electronic equipment and medium | |
| CN111597469B (en) | Display position determining method and device, electronic equipment and storage medium | |
| CN110020108B (en) | Network resource recommendation method, device, computer equipment and storage medium | |
| CN109299378B (en) | Search result display method and device, terminal and storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| CN113724022B (en) | Keyword determination method and device, computer equipment and medium | |
| CN112115354A (en) | Information processing method, information processing apparatus, server, and storage medium | |
| CN112288461A (en) | Advertisement information pushing method, device, medium and electronic equipment | |
| CN113901244A (en) | Label construction method and device for multimedia resource, electronic equipment and storage medium | |
| CN114491093A (en) | Multimedia resource recommendation and object representation network generation method and device | |
| CN112200614A (en) | Advertisement text implanting and displaying method and corresponding device, equipment and medium | |
| CN111898033A (en) | Content pushing method and device and electronic equipment |
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 |