CN106982256B - Information pushing method, device, equipment and storage medium - Google Patents
Information pushing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN106982256B CN106982256B CN201710211369.0A CN201710211369A CN106982256B CN 106982256 B CN106982256 B CN 106982256B CN 201710211369 A CN201710211369 A CN 201710211369A CN 106982256 B CN106982256 B CN 106982256B
- Authority
- CN
- China
- Prior art keywords
- determining
- real
- hot
- information
- content
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an information pushing method, an information pushing device, information pushing equipment and a storage medium. The method comprises the following steps: determining a first feature tag of the real-time hot content; determining a second characteristic label of the information pushing party; determining target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic tag and the second characteristic tag; and determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, the mapping relation between the pre-constructed hot content and the user portrait and the mapping relation between the pre-constructed hot content and the media site portrait. The target delivery crowd and the target delivery media site matched with the information delivery party are determined based on the target real-time hot content, so that the information popularization rate and the low return rate of the information delivery party investment are improved, the operation of the information delivery party is simplified, and the user experience is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of internet, in particular to an information pushing method, an information pushing device, information pushing equipment and a storage medium.
Background
With the rapid development of the mobile internet technology, the exponential dramatic increase of the number of mobile netizens in China reaches 8.6 hundred million, the information propagation speed is greatly improved along with the expansion of mobile social contact on the basis of the huge base number, and real-time events of group-based social close-up, praise, comment and propagation of the netizens form network hotspots, span all limits of age, region, hierarchy and the like, are rapidly propagated on the network, and even influence the thought, behavior and life of the netizens.
The hot data contains huge commercial value, and has extremely important practical significance for real-time mining, research and utilization of hot topics, public opinion monitoring, business decision support and the like. How to better use hot spot data presents opportunities and challenges to internet enterprises for business services. The rapid development of big data and artificial intelligence technology brings better possibility for value mining of real-time data in the aspect of information push service. Meanwhile, with the sharp increase of data volume and the refinement of industry distribution, the information delivery strategy has also been upgraded from blind push coverage to personalized recommendation by using a big data mining algorithm. Especially in search engine and electronic business marketing application, information push serves a large number of information push parties, internet information is pushed to specific crowds in a proper mode, and cost calculation is carried out according to a certain business mode. This makes information push a direction of application that is pleasant to the hand.
However, the existing information pushing method has the disadvantages that only retrieval and browsing behaviors (such as web pages or commodities) of users are extracted for similarity association, the association degree is relatively single, deep consumption requirements of the users cannot be mined, after an information pushing party purchases a certain keyword at a certain price, the final information popularization efficiency cannot be matched with the keyword bid, and the investment return rate of the information pushing party is low. On the other hand, in the traffic peak period of an internet hotspot outbreak, an information pushing party meeting the requirements of consumers, especially an information pushing party of a medium-sized and small-sized enterprise is often suffering from the problem that the information pushing party cannot timely capture proper information release opportunity, release media and release crowds.
Disclosure of Invention
The embodiment of the invention provides an information pushing method, an information pushing device, information pushing equipment and a storage medium, which can improve the information popularization rate and the return on investment of an information pushing party.
In a first aspect, an embodiment of the present invention provides an information pushing method, including:
determining a first feature tag of the real-time hot content;
determining a second characteristic label of the information pushing party;
determining target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic tag and the second characteristic tag;
and determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, the mapping relation between the pre-constructed hot content and the user portrait and the mapping relation between the pre-constructed hot content and the media site portrait.
In a second aspect, an embodiment of the present invention further provides an information pushing apparatus, including:
the first tag determining module is used for determining a first characteristic tag of the real-time hot content;
the second label determining module is used for determining a second characteristic label of the information pushing party;
the target real-time hotspot module is used for determining target real-time hotspot content matched with the information pushing party according to the matching relation between the first characteristic tag and the second characteristic tag;
and the target delivery information module is used for determining target delivery crowds and target delivery media sites matched with the information pushing party according to the target real-time hot content matched with the information pushing party, the mapping relation between the pre-constructed hot content and the user portrait and the mapping relation between the pre-constructed hot content and the media site portrait.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the information push method according to the embodiment of the present invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the information pushing method according to the embodiment of the present invention.
According to the technical scheme provided by the embodiment of the invention, the target real-time hot content matched with the information pushing party is determined according to the matching relationship between the first characteristic tag of the real-time hot content and the second characteristic tag of the information pushing party, and the target delivery crowd and the target delivery media site matched with the information pushing party are determined according to the target real-time hot content matched with the information pushing party, the mapping relationship between the pre-constructed hot content and the user portrait and the mapping relationship between the pre-constructed hot content and the media site portrait, namely the target delivery crowd and the target delivery media site matched with the information pushing party are determined based on the target real-time hot content, so that the information popularization rate and the low return rate of investment of the information pushing party are improved, the operation of the information pushing party is simplified, and the user experience is improved.
Drawings
Fig. 1 is a flowchart of an information pushing method according to a first embodiment of the present invention;
fig. 2 is a flowchart of an information pushing method in the second embodiment of the present invention;
fig. 3 is a flowchart of an information pushing method in a third embodiment of the present invention;
fig. 4 is a flowchart of an information pushing method in the fourth embodiment of the present invention;
fig. 5 is a structural diagram of an information pushing apparatus in a fifth embodiment of the present invention;
fig. 6 is a block diagram of an apparatus in the sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an information pushing method according to an embodiment of the present invention, where the present embodiment is applicable to various information pushing situations, and the method may be executed by an information pushing apparatus provided in an embodiment of the present invention, where the information pushing apparatus may be implemented in a software and/or hardware manner, and the information pushing apparatus may be integrated in any device that provides an information pushing function, for example, a computer, or a mobile terminal (e.g., a mobile phone, a tablet computer, etc.). As shown in fig. 1, the method may specifically include:
s110, determining a first characteristic label of the real-time hot content.
The real-time hot content is news and information which are concerned or welcomed by the masses in the current period, and can comprise hot social, life, domestic or international related content discussed by online friends in time. The first feature tag is a tool for marking the classification or characteristics of the real-time hot content, so that a user can conveniently find and locate the content. The determination of the real-time hot content can be combined with all available data sources to screen out the hot content with higher user attention. The first feature tag of the real-time hot content may include at least one of a specific name tag such as a region name, a person name or a brand name of the real-time hot content, and an industry tag. Specifically, the first feature tag for determining the real-time hot content may be determined by screening a noun, a character with regional information, or a brand with a product symbolic representation, or may be determined by determining an industry tag according to the semantics of the real-time hot content. It should be noted that, the manner of determining the first feature tag of the real-time hot content is not limited.
And S120, determining a second characteristic label of the information pushing party.
Wherein, the information pushing party refers to a user who utilizes the media site to promote a certain product. The second characteristic label is used for marking the characteristics of the information pushing party, and can be one or more of industry information, main operation region, operation product, credit and the like. Specifically, the second feature tag for determining the information pushing party can be obtained through objective data of historical pushing information of the information pushing party, or obtained from attribute information filled by the information pushing party when the application software or the network platform registers an account.
S130, determining the target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic label and the second characteristic label.
The first feature tag is used for marking real-time hot content, and the second feature tag is used for marking information delivery side, so that correlation matching can be carried out on the first feature tag and the second feature tag, the real-time hot content with high matching degree is determined as target real-time hot content of the information delivery side, and then the target real-time hot content can be used as the real-time hot content which recommends attention or promotion information delivery to the information delivery side.
S140, determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, a mapping relation between the pre-constructed hot content and the user portrait and a mapping relation between the pre-constructed hot content and the media site portrait.
Before the information push party is successfully matched with the target real-time hot content, the application software or the network platform is pre-established with the mapping relation between the hot content and the user portrait and the mapping relation between the hot content and the media site portrait. The hot content not only comprises real-time hot content, but also comprises historical hot content; a user representation refers to an attribute feature tag of a consumer group. A media site representation refers to an attribute feature tag of a media site. For example, the construction of the mapping relationship between the hot content and the user representation may include: determining basic information and a behavior tag of a user according to historical retrieval behaviors of the user and historical click behaviors of the user, and taking the basic information and the behavior tag as user images; and determining a mapping relation between the hot content and the user portrait according to a matching relation between the first feature tag of the hot content and the user portrait.
The user portrait can comprise basic information and behavior tags of the user, the basic information comprises age, sex, industry, life stage, long-term interest, attention categories and the like of the user, and the behavior tags comprise behaviors with higher occurrence frequency in historical retrieval behaviors and historical click behaviors of the user. The feature tag related to the user can be analyzed through the historical retrieval behavior of the user and the historical click behavior of the user, and the user portrait can be obtained. And then, determining a mapping relation between the hot content and the user portrait according to the matching relation between the first characteristic label of the hot content and the basic information and the behavior label of the user. For example, if user a frequently clicks on information about car X, then car X may be taken as one of user portraits of user a, and hot content that also has a car X tag may be mapped to user a.
For example, the construction of the mapping relationship between the hotspot content and the media site representation may include: and determining a mapping relation between the hot content and the portrait of the media site according to a matching relation between the first characteristic tag of the hot content and the portrait of the media site, wherein the portrait of the media site comprises an industry type to which the media site belongs.
Wherein, the media site portrayal can comprise the industry type of the media site. For example, the industry types include an automobile type, a mother-and-baby type, a cosmetics type, a shopping type, a travel type, and the like. And marking the media sites according to the industry types and classifying to obtain the industry labels of the media sites. Specifically, similar to the construction of the mapping relationship between the hot content and the user portrait, the mapping relationship between the hot content and the media site portrait can be determined according to the matching relationship between the first characteristic tag of the hot content and the industry tag of the media site, so that the target media site to be delivered, which is matched with the information provider, can be determined according to the mapping relationship. For example, the hot content with the car X tag described above can be matched to a media site that marks the type of car industry.
According to the embodiment, the target real-time hot content matched with the information pushing party is determined according to the matching relation between the first characteristic tag of the real-time hot content and the second characteristic tag of the information pushing party, and the target delivery crowd and the target delivery media site matched with the information pushing party are determined based on the target real-time hot content, so that the information popularization rate and the low return rate of the investment of the information pushing party are improved, the operation of the information pushing party is simplified, the user experience is improved, and the integration correlation connection of the hot content, the delivery crowd, the delivery media site and the information pushing party is realized.
Example two
Fig. 2 is a flowchart of an information pushing method according to a second embodiment of the present invention, which is optimized based on the second embodiment of the present invention, and provides an optimized processing method for determining a first feature tag of real-time hot content. Referring to fig. 2, the method provided in this embodiment may specifically include:
and S210, mining the real-time hot spot content from a real-time data source.
The real-time data source refers to a database in the network platform, such as a social network site, various types of websites, a search statistic database, and the like, which can provide real-time hot content. The mining of the real-time hot content can be to count the unit time forwarding amount, the unit time clicking amount, the unit time reading amount and the unit time praise amount of the real-time data source, and then to take one or more contents with the top ranking as the real-time hot content.
S220, filtering out non-promotion hot content contained in the real-time hot content.
In a period of time, because the real-time hot content concerned by the user is not always suitable for information promotion, hot content which is not suitable for promotion and is contained in the real-time hot content can be filtered by a certain method. For example, a non-promotion package library may be pre-constructed, wherein the non-promotion package library contains a large number of words or sentences unsuitable for promotion. And filtering real-time hot content which is not suitable for Internet promotion according to the non-promotion word packet library.
For example, the non-promotion word package library includes a word of "earthquake", and in a certain time period, the real-time hotspot content is "the Chinese donates materials such as tents to earthquake-stricken areas of a certain country", so that the "earthquake" can be filtered according to the non-promotion word package library.
S230, determining at least one hot keyword contained in the real-time hot content.
For example, N L P (Nature L and natural language) word cutting equipment can be used for cutting words of the real-time hot content, removing numbers, adverbs, quantifiers, pronouns, partial adjectives and the like, and the rest nouns, verbs and the like are used as the hot keywords.
S240, according to manual industry label processing operation, adjusting the mapping relation between industry items and keywords contained in the industry word packet data.
The industry package data refers to a database containing industry items and keywords, and the mapping relation between the industry items and the keywords is recorded. Industry entry, i.e., name of industry type; the keywords include not only real-time hotspot keywords but also non-real-time hotspot keywords, and one industry entry may correspond to at least one keyword. Specifically, the manual industry label processing operation refers to correcting and adding the mapping relation between the industry items and the keywords contained in the industry vocabulary packet data in a manual auxiliary mode so as to update the industry vocabulary packet data in real time.
Alternatively, the manual industry tag processing operation may add new keywords or industry items to the industry package data. For example, a certain automobile brand company has recently introduced a new vehicle, and thus the new vehicle model is not available in the industry package data. Thus, the new vehicle model number may be added to the industry package data and correspond to the "auto" industry entry through a manual industry tag handling operation.
Optionally, the manual industry tag processing operation may also correct matching incorrect industry entries and keywords. For example, many emerging words originate from the network, and thus many new old word ideas appear. For example, the network word "blue thin mushroom" may have an industry entry corresponding to the original industry packet data as "vegetable", and therefore, the industry entry of the "blue thin mushroom" needs to be modified manually into "mood".
S250, determining the industry label of the hot keyword according to the mapping relation between the industry items and the keyword contained in the industry word packet data.
Specifically, after determining the hot keywords in the real-time hot content, the hot keywords can be brought into the existing industry package data to find the industry entries matched with the hot keywords, and the industry entries are used as industry tags to mark the hot keywords. It should be noted that the industry label of the hot keyword may be one or more, for example, the industry label of the teacup may be tableware, or may be curio, and the like.
S260, determining at least one industry label of the real-time hot content according to the industry label of at least one hot keyword contained in the real-time hot content.
Because the hot keywords are representative contents in the real-time hot contents, the industry tags of the hot keywords can be determined as the industry tags of the real-time hot contents. In addition, since the real-time hot content may include a plurality of hot keywords, and each hot keyword may have a plurality of industry tags, one or more industry tags may be provided for the real-time hot content.
For example, the real-time hot content "jiastin biber's cup is auctioned", and the word segmentation is performed by N L P to obtain three hot keywords "jiastin biber", "cup" and "auction".
Illustratively, the determining at least one industry label of the real-time hot content according to the industry label of the at least one hot keyword included in the real-time hot content includes: determining part-of-speech weight and/or semantic weight of at least one hotspot keyword contained in the real-time hotspot content; and determining at least one industry label of the real-time hot content according to the part-of-speech weight and/or the semantic weight of the at least one hot keyword.
The parts-of-speech weight means that different parts-of-speech have different weights, for example, the part-of-speech weight of a noun is greater than the part-of-speech weight of a verb, the part-of-speech weight of a verb is greater than the part-of-speech weight of an adjective, and the like. Specifically, the real-time hot content can obtain a plurality of hot keywords after word segmentation, and the hot keywords have different part-of-speech weights due to different parts-of-speech. Preferably, the part-of-speech weight of a noun may be defined as a highest value, and then the industry tag corresponding to the noun with the highest part-of-speech weight may be used as the industry tag of the real-time hot content. When the real-time hot content contains hot keywords of a plurality of noun parts of speech, the industry tags corresponding to the hot keywords of the plurality of noun parts of speech can be used as the industry tags of the real-time hot content.
Or, the semantic weight of each hot keyword can be determined, and the industry label corresponding to one or more hot keywords with higher semantic weight is screened out to be used as the industry label of the real-time hot content. Optionally, the semantic weight may be determined according to the information promotion rate in the historical promotion data. For example, the real-time hot content "jiastin biber cup is auctioned", and according to historical promotion data, the promotion rate of the word "cup" is the highest, and the corresponding semantic weight is the highest, so that the "tableware" corresponding to the "cup" can be used as the industry label of the real-time hot content.
It should be noted that the industry label of the hot content may also be determined according to the part-of-speech weight and the semantic weight of the hot keyword. For example, the industry tag corresponding to the keyword with the highest semantic weight may be selected from the hot keywords of the part of speech of the noun as the industry tag of the real-time hot content.
And S270, determining a second characteristic label of the information pushing party.
S280, determining the target real-time hot content of the information push matching provider according to the matching relation between the first characteristic label and the second characteristic label.
S290, determining a target delivery crowd and a target delivery media site matched with the information push provider according to the target real-time hot content matched with the information push provider, a pre-constructed mapping relation between the real-time hot content and the user portrait and a pre-constructed mapping relation between the real-time hot content and the media site portrait.
It should be noted that, in the present embodiment, an example is formed by S210 to S290 to execute an information pushing method, but the present embodiment is only an example, and in other embodiments of the present invention, S230 and S250 to S290 may be formed as an example to execute an information pushing method, or S210 to S230 and S250 to S290 may be formed as an example to execute an information pushing method, or S230 to S290 may be formed as an example to execute an information pushing method.
In the embodiment, the industry tag of the hot keyword is used as the industry tag of the real-time hot content, the determination of the industry tag of the real-time hot content is specifically explained, and the accuracy of the determination of the industry tag of the real-time hot content can be improved through manual industry tag processing operation.
EXAMPLE III
Fig. 3 is a flowchart of an information pushing method according to a third embodiment of the present invention, where on the basis of the foregoing embodiment, after determining target real-time hot content of an information pushing party according to a matching relationship between the first feature tag and the second feature tag, the present embodiment further includes: acquiring a hotspot tag which the information pushing party pays attention to subscription; adding the hot content belonging to the hot tag into the target real-time hot content matched with the information pushing party; or, further comprising: acquiring an expected delivery user selected by the information delivery party; and obtaining hot content concerned by the expected releasing user according to the attribute characteristics and the retrieval behavior of the expected releasing user, and adding the hot content to the target real-time hot content matched with the information pushing party.
Referring to fig. 3, the method provided in this embodiment may include:
s310, determining a first characteristic label of the real-time hot content.
And S320, determining a second characteristic label of the information pushing party.
S330, determining the target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic label and the second characteristic label.
And S340, acquiring the hotspot tag which the information push party pays attention to subscription.
Wherein, the hot spot label can be an industry label of any industry. Specifically, when an information push party registers an account on application software or a network platform, the information push party can actively subscribe a hotspot tag which is desired to be concerned besides inputting attribute information. For example, an information push party is a certain automobile brand company, and there is a development direction in which insurance business is expected to be developed in the future, so that the information push party can actively pay attention to non-automobile hotspot tags such as the insurance industry and the like in addition to the hotspot tags related to the automobile industry.
And S350, adding the hot content belonging to the hot tag into the target real-time hot content matched with the information pushing party.
When it is detected that the account information of an information pushing party is related to subscription hot spot labels, hot content corresponding to the hot spot labels can be added to target real-time hot content matched with the information pushing party. That is to say, the target real-time hot content can be obtained not only from real-time data sources such as networks, social platforms and searches, but also from hot content corresponding to a hot tag which is actively subscribed by an information push party.
And S360, obtaining the expected delivery user selected by the information delivery party.
The expected delivery users refer to users who are selected by the information pushing party to be delivered in the future according to company requirements and business expansion. The prospective delivery user may be a user of a particular age group, a user of a particular profession, or a user of a particular region, etc. For example, a web site is in a transition period, and a future service object is locked as a middle school student, so that the prospective delivery user can be designated as a middle school student in the age range of 10-14 years. Similar to obtaining the hotspot tag which the information push party pays attention to subscribe, the expected delivery user can be obtained from the account information of the information push party.
And S370, obtaining the hot content concerned by the expected releasing user according to the attribute characteristics and the retrieval behavior of the expected releasing user, and adding the hot content to the target real-time hot content matched with the information pushing party.
Wherein, the attribute characteristics of the expected delivery user can be one or more of gender, age, industry, life stage, long-term interest and attention categories. The retrieval behavior can be historical retrieval information of a prospective delivery user or a historical behavior of clicking push information, and the like. By analyzing the attribute characteristics and retrieval behaviors of the expected delivery users, the hot content concerned by the expected delivery users can be obtained, and the hot content can be added into the target real-time hot content corresponding to the information push party. That is to say, the hot content selected by the information push party and expected to be focused by the delivery user can also be one of the sources of the target real-time hot content.
And S380, determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, the mapping relationship between the pre-constructed hot content and the user portrait and the mapping relationship between the pre-constructed hot content and the media site portrait.
It should be noted that, in the present embodiment, an example is formed by S310 to S380 to execute an information push method, but the present embodiment is only an example, and in other embodiments of the present invention, S310 to S350 and S380 may also be formed as an example to execute an information push method, or S310 to S330 and S360 to S380 may also be formed as an example to execute an information push method.
According to the embodiment, by acquiring the hotspot content which is concerned by the information pushing party and subscribed and corresponds to the hotspot tag or acquiring the hotspot content which is selected by the information pushing party and is expected to be concerned by a user, more materials are added to the target real-time hotspot content, the hotspot content which is concerned by the information pushing party is prevented from being omitted, and more choices are provided for the information pushing party.
Example four
Fig. 4 is a flowchart of an information pushing method according to a fourth embodiment of the present invention, where on the basis of the foregoing embodiment, after determining target real-time hot content matched by an information pusher, the embodiment further includes: determining target hotspot keywords contained in target real-time hotspot content matched with the information push party; determining the conversion rate of the target hotspot keywords; and determining the bid of the target hot keyword according to the cost value and the conversion rate of the target hot keyword.
Referring to fig. 4, the method provided in this embodiment may include:
s410, determining a first characteristic label of the real-time hot content.
And S420, determining a second characteristic label of the information pushing party.
S430, determining the target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic label and the second characteristic label.
S440, determining target hotspot keywords contained in the target real-time hotspot content matched with the information push party.
S450, determining the conversion rate of the target hotspot keywords.
The conversion rate of the target hotspot keyword can be the quotient of the number of clicks of the push information and the number of displays of the push information for the user. For example, if a certain information provider purchases the keyword M at a certain price, and if 50 users search for the keyword M and 40 users see the push information of the information provider within a certain period of time, if 20 users click on the push information, the conversion rate calculation formula is 20/40 ═ 0.5.
Exemplary, optionally, the determining the conversion rate of the target hotspot keyword includes: determining historical push information containing the target hotspot keywords; and determining the conversion rate of the target hotspot keywords according to the user retrieval behavior and the user click behavior corresponding to the historical push information.
The historical attention of the target hotspot keyword can be analyzed by determining the historical push information of the target hotspot keyword. The history push information comprises all information pushed by the information push party and other information push parties. And counting all user retrieval behaviors and all user click behaviors related to historical push information. Conversion rate of the target hotspot keywords and attention degree of the target hotspot keywords can be calculated and predicted through retrieval behavior and clicking behavior of the user on the historical push information, and the conversion rate of the target hotspot keywords with high attention degree is high.
S460, determining the bid of the target hot spot keyword according to the cost value and the conversion rate of the target hot spot keyword.
The cost value of the target hot keyword is a preliminary evaluation of the target hot keyword, and may be related to part of speech. For example, the cost value of the target hotspot keyword of the part of speech of the noun may be set higher, or the cost value of the target hotspot keyword of the part of speech of the verb may be set higher, or the like. The bid price of the target hotspot keyword can be calculated by combining the cost value and the conversion rate of the target hotspot keyword.
And S470, determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, a mapping relation between the pre-constructed hot content and the user portrait and a mapping relation between the pre-constructed hot content and the media site portrait.
According to the method and the device, the bid price of the target hot spot keyword is determined by calculating the cost value and the conversion rate of the target hot spot keyword, a more complete delivery scheme is provided for the information delivery party, the information delivery party can know the delivery value of the target hot spot keyword more comprehensively, and the delivery success rate is improved.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an information pushing apparatus according to a fifth embodiment of the present invention, where the present embodiment is applicable to various information pushing situations, the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be integrated in any device providing an information pushing function, for example, a computer, or a mobile terminal (e.g., a mobile phone, a tablet computer, etc.). As shown in fig. 5, the information pushing apparatus may specifically include: a first tag determination module 51, a second tag determination module 52, a target real-time hotspot module 53 and a target delivery information module 54.
A first tag determining module 51, configured to determine a first feature tag of the real-time hot content;
a second tag determining module 52, configured to determine a second feature tag of the information provider;
the target real-time hotspot module 53 is configured to determine, according to a matching relationship between the first feature tag and the second feature tag, target real-time hotspot content matched by the information presenter;
and a target delivery information module 54, configured to determine a target delivery crowd and a target delivery media site matched with the information presenter according to the target real-time hot content matched with the information presenter, a mapping relationship between the pre-constructed hot content and the user portrait, and a mapping relationship between the pre-constructed hot content and the media site portrait.
On the basis of the above embodiment, the first tag determination module 51 includes:
a hot keyword determining unit 61, configured to determine at least one hot keyword included in the real-time hot content;
a keyword industry label unit 62, configured to determine an industry label of the hot keyword according to a mapping relationship between industry items and keywords included in the industry package data;
a hot spot industry label unit 63, configured to determine at least one industry label of the real-time hot spot content according to an industry label of at least one hot spot keyword included in the real-time hot spot content.
On the basis of the above embodiment, the hot spot industry tag unit 63 is specifically configured to: determining part-of-speech weight and/or semantic weight of at least one hotspot keyword contained in the real-time hotspot content; and determining at least one industry label of the real-time hot content according to the part-of-speech weight and/or the semantic weight of the at least one hot keyword.
The first tag determination module 51 may also include a manual processing unit 64.
A manual processing unit 64, before the keyword industry labeling unit 62, configured to adjust a mapping relationship between the industry items and the keywords included in the industry package data according to a manual industry label processing operation.
The first tag determination module 51 may further comprise a filtering unit 65.
The filtering unit 65 is configured to, before the hot keyword determining unit 61, mine the real-time hot content from a real-time data source; and filtering the non-promotion hot content contained in the real-time hot content.
The information pushing apparatus may further include a first hot content adding module 66,
a first hot content adding module 66, configured to, after the target real-time hot module 53, obtain a hot tag that the information provider pays attention to subscription; and adding the hot content belonging to the hot tag into the target real-time hot content matched with the information pushing party.
The information pushing apparatus may further include a second hot content adding module 67,
a second hot content adding module 67, after the target real-time hot module 53, configured to obtain an expected delivery user selected by the information provider; and obtaining hot content concerned by the expected releasing user according to the attribute characteristics and the retrieval behavior of the expected releasing user, and adding the hot content to the target real-time hot content matched with the information pushing party.
The information pushing apparatus may further include a first mapping relationship creating module 68,
the first mapping relationship creation module 68 is configured to: determining basic information and a behavior tag of a user according to historical retrieval behaviors of the user and historical click behaviors of the user, and taking the basic information and the behavior tag as user images; and determining a mapping relation between the hot content and the user portrait according to a matching relation between the first feature tag of the hot content and the user portrait.
On the basis of the foregoing embodiment, the first mapping relationship creating module 68 is further configured to: and determining a mapping relation between the hot content and the portrait of the media site according to a matching relation between the first characteristic tag of the hot content and the portrait of the media site, wherein the portrait of the media site comprises an industry type to which the media site belongs.
The information pushing apparatus may further include a bid determination module 69,
a bid determination module 69, after the target real-time hot spot module 53, configured to determine a target hot spot keyword included in the target real-time hot spot content matched by the information provider; determining the conversion rate of the target hotspot keywords; and determining the bid of the target hot keyword according to the cost value and the conversion rate of the target hot keyword.
On the basis of the above embodiment, the bid determination module 69 is further configured to: determining historical push information containing the target hotspot keywords; and determining the conversion rate of the target hotspot keywords according to the user retrieval behavior and the user click behavior corresponding to the historical push information.
The information pushing apparatus of this embodiment is configured to execute the information pushing method of the foregoing embodiments, and the technical principle and the generated technical effect are similar, which are not described herein again.
EXAMPLE six
Fig. 6 is a schematic structural diagram of an apparatus according to a sixth embodiment of the present invention. Fig. 6 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 6 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present invention.
As shown in FIG. 6, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 6, and commonly referred to as a "hard drive"). Although not shown in FIG. 6, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement the information pushing method provided by the embodiment of the present invention.
EXAMPLE seven
The seventh embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the information pushing method provided in all the embodiments of the present invention in this application.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including AN object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (24)
1. An information pushing method, comprising:
determining a first feature tag of the real-time hot content, wherein the first feature tag is used for marking the classification or the characteristic of the real-time hot content;
determining a second characteristic label of an information pushing party, wherein the information pushing party refers to a user who utilizes a media site to publicize a certain type of product, and the second characteristic label is used for marking the characteristic of the information pushing party;
determining target real-time hot content matched with the information pushing party according to the matching relation between the first characteristic tag and the second characteristic tag;
and determining a target delivery crowd and a target delivery media site matched with the information pusher according to the target real-time hot content matched with the information pusher, the mapping relation between the pre-constructed hot content and the user portrait and the mapping relation between the pre-constructed hot content and the media site portrait.
2. The method of claim 1, wherein determining the first feature tag of the live hotspot content comprises:
determining at least one hotspot keyword contained in the real-time hotspot content;
determining an industry label of the hot keyword according to a mapping relation between industry items and keywords contained in industry word packet data;
and determining at least one industry label of the real-time hot content according to the industry label of at least one hot keyword contained in the real-time hot content.
3. The method according to claim 2, wherein the determining at least one industry label of the real-time hot content according to the industry label of the at least one hot keyword included in the real-time hot content comprises:
determining part-of-speech weight and/or semantic weight of at least one hotspot keyword contained in the real-time hotspot content;
and determining at least one industry label of the real-time hot content according to the part-of-speech weight and/or the semantic weight of the at least one hot keyword.
4. The method according to claim 2, wherein before determining the industry label of the hot keyword according to the mapping relationship between the industry items and the keywords contained in the industry package data, the method further comprises:
and adjusting the mapping relation between the industry items and the keywords contained in the industry word packet data according to manual industry label processing operation.
5. The method of claim 2, wherein before determining at least one hotspot keyword contained in the live hotspot content, the method further comprises:
mining the real-time hot content from a real-time data source;
and filtering the non-promotion hot content contained in the real-time hot content.
6. The method according to any one of claims 1 to 4, wherein after determining the target real-time hot content of the information push according to the matching relationship between the first feature tag and the second feature tag, the method further comprises:
acquiring a hotspot tag which the information pushing party pays attention to subscription;
and adding the hot content belonging to the hot tag into the target real-time hot content matched with the information pushing party.
7. The method according to any one of claims 1 to 4, after determining the target real-time hot content matched by the information push party according to the matching relationship between the first feature tag and the second feature tag, further comprising:
acquiring an expected delivery user selected by the information delivery party;
and obtaining hot content concerned by the expected releasing user according to the attribute characteristics and the retrieval behavior of the expected releasing user, and adding the hot content to the target real-time hot content matched with the information pushing party.
8. The method of claim 1, wherein constructing the mapping between the hotspot content and the user representation comprises:
determining basic information and a behavior tag of a user according to historical retrieval behaviors of the user and historical click behaviors of the user, and taking the basic information and the behavior tag as user images;
and determining a mapping relation between the hot content and the user portrait according to a matching relation between the first feature tag of the hot content and the user portrait.
9. The method of claim 1, wherein constructing the mapping between the hotspot content and the media site representation comprises:
and determining a mapping relation between the hot content and the portrait of the media site according to a matching relation between the first characteristic tag of the hot content and the portrait of the media site, wherein the portrait of the media site comprises an industry type to which the media site belongs.
10. The method of claim 1, wherein after determining the target real-time hot content matched with the information pusher, the method further comprises:
determining target hotspot keywords contained in target real-time hotspot content matched with the information push party;
determining the conversion rate of the target hotspot keywords;
and determining the bid of the target hot keyword according to the cost value and the conversion rate of the target hot keyword.
11. The method of claim 10, wherein the determining the conversion rate of the target hotspot keyword comprises:
determining historical push information containing the target hotspot keywords;
and determining the conversion rate of the target hotspot keywords according to the user retrieval behavior and the user click behavior corresponding to the historical push information.
12. An information pushing apparatus, comprising:
the first tag determining module is used for determining a first feature tag of the real-time hot content, and the first feature tag is used for marking the classification or the characteristic of the real-time hot content;
the second label determining module is used for determining a second characteristic label of an information pushing party, wherein the information pushing party refers to a user who utilizes the media site to publicize a certain type of product, and the second characteristic label is used for marking the characteristic of the information pushing party;
the target real-time hotspot module is used for determining target real-time hotspot content matched with the information pushing party according to the matching relation between the first characteristic tag and the second characteristic tag;
and the target delivery information module is used for determining target delivery crowds and target delivery media sites matched with the information pushing party according to the target real-time hot content matched with the information pushing party, the mapping relation between the pre-constructed hot content and the user portrait and the mapping relation between the pre-constructed hot content and the media site portrait.
13. The apparatus of claim 12, wherein the first tag determination module comprises:
the hot keyword determining unit is used for determining at least one hot keyword contained in the real-time hot content;
the keyword industry label unit is used for determining the industry label of the hot keyword according to the mapping relation between the industry items and the keyword contained in the industry word packet data;
and the hot spot industry label unit is used for determining at least one industry label of the real-time hot spot content according to the industry label of at least one hot spot keyword contained in the real-time hot spot content.
14. The apparatus of claim 13, wherein the hotspot industry tag unit is specifically configured to:
determining part-of-speech weight and/or semantic weight of at least one hotspot keyword contained in the real-time hotspot content;
and determining at least one industry label of the real-time hot content according to the part-of-speech weight and/or the semantic weight of the at least one hot keyword.
15. The apparatus of claim 13, further comprising:
and the manual processing unit is used for adjusting the mapping relation between the industry items and the keywords contained in the industry package data according to the manual industry label processing operation before the keyword industry label unit.
16. The apparatus of claim 13, further comprising:
the filtering unit is used for mining the real-time hot content from a real-time data source before the hot keyword determining unit; and filtering the non-promotion hot content contained in the real-time hot content.
17. The apparatus of any one of claims 12-15, further comprising:
the first hot content adding module is arranged behind the target real-time hot module and used for acquiring a hot tag which the information pushing party pays attention to and subscribes; and adding the hot content belonging to the hot tag into the target real-time hot content matched with the information pushing party.
18. The apparatus of any one of claims 12-15, further comprising:
the second hot content adding module is arranged behind the target real-time hot module and used for acquiring an expected delivery user selected by the information pushing party; and obtaining hot content concerned by the expected releasing user according to the attribute characteristics and the retrieval behavior of the expected releasing user, and adding the hot content to the target real-time hot content matched with the information pushing party.
19. The apparatus of claim 12, further comprising: a first mapping relationship creation module to:
determining basic information and a behavior tag of a user according to historical retrieval behaviors of the user and historical click behaviors of the user, and taking the basic information and the behavior tag as user images;
and determining a mapping relation between the hot content and the user portrait according to a matching relation between the first feature tag of the hot content and the user portrait.
20. The apparatus of claim 19, wherein the first mapping creation module is further configured to:
and determining a mapping relation between the hot content and the portrait of the media site according to a matching relation between the first characteristic tag of the hot content and the portrait of the media site, wherein the portrait of the media site comprises an industry type to which the media site belongs.
21. The apparatus of claim 12, further comprising:
the bid determination module is arranged behind the target real-time hotspot module and used for determining target hotspot keywords contained in target real-time hotspot content matched with the information pushing party; determining the conversion rate of the target hotspot keywords; and determining the bid of the target hot keyword according to the cost value and the conversion rate of the target hot keyword.
22. The apparatus of claim 21, wherein the bid determination module is further specifically configured to:
determining historical push information containing the target hotspot keywords;
and determining the conversion rate of the target hotspot keywords according to the user retrieval behavior and the user click behavior corresponding to the historical push information.
23. An information push apparatus, characterized in that the apparatus comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the information push method of any one of claims 1-11.
24. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the information push method according to any one of claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211369.0A CN106982256B (en) | 2017-03-31 | 2017-03-31 | Information pushing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710211369.0A CN106982256B (en) | 2017-03-31 | 2017-03-31 | Information pushing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106982256A CN106982256A (en) | 2017-07-25 |
| CN106982256B true CN106982256B (en) | 2020-07-28 |
Family
ID=59343783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710211369.0A Active CN106982256B (en) | 2017-03-31 | 2017-03-31 | Information pushing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106982256B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107426328B (en) * | 2017-08-08 | 2022-07-15 | 百度在线网络技术（北京）有限公司 | Information pushing method and device |
| CN107562884A (en) * | 2017-09-04 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | A kind of information flow shows method, apparatus, server and storage medium |
| CN107580073A (en) * | 2017-10-19 | 2018-01-12 | 世纪龙信息网络有限责任公司 | Realize the method and device of targeted customer's message push |
| CN109862057A (en) * | 2017-11-30 | 2019-06-07 | 北京嘀嘀无限科技发展有限公司 | Run method for pushing, device, server and computer readable storage medium |
| CN108521439B (en) * | 2018-03-08 | 2022-01-21 | 北京三快在线科技有限公司 | Message pushing method and device |
| CN108537578A (en) * | 2018-03-26 | 2018-09-14 | 杭州米趣网络科技有限公司 | Advertisement sending method based on big data and device |
| CN110196940B (en) * | 2018-05-30 | 2022-11-04 | 腾讯科技（深圳）有限公司 | Method, apparatus, display engine and medium for displaying hotspot network content to user |
| CN109033266B (en) * | 2018-07-09 | 2021-08-20 | 北京三快在线科技有限公司 | Information delivery method and device, electronic equipment and computer readable medium |
| CN109241408A (en) * | 2018-08-14 | 2019-01-18 | 深圳开黑科技有限公司 | User's portrait processing method, equipment and the system for playing platform are accompanied based on game |
| CN109284500A (en) * | 2018-08-20 | 2019-01-29 | 张连祥 | Information transmission system and method based on merchants inviting work process and reading preference |
| CN109447700A (en) * | 2018-10-23 | 2019-03-08 | 广州致轩服饰有限公司 | A kind of commodity feedback method and device based on storage user |
| CN109447748A (en) * | 2018-10-23 | 2019-03-08 | 广州致轩服饰有限公司 | A kind of commodity feedback method and device based on increment user |
| CN109636441B (en) * | 2018-11-06 | 2023-12-19 | 三六零科技集团有限公司 | Advertisement putting method and device |
| CN111814033A (en) * | 2019-04-12 | 2020-10-23 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for determining delivered medium information |
| CN110166811B (en) * | 2019-05-15 | 2021-08-10 | 口碑(上海)信息技术有限公司 | Bullet screen information processing method, device and equipment |
| WO2020252742A1 (en) * | 2019-06-20 | 2020-12-24 | 深圳市云中飞网络科技有限公司 | Resource pushing method and related product |
| CN110782123A (en) * | 2019-09-18 | 2020-02-11 | 中国平安财产保险股份有限公司 | Matching method and device of decision scheme, computer equipment and storage medium |
| CN111684815B (en) * | 2019-11-15 | 2021-06-25 | 深圳海付移通科技有限公司 | Message pushing method and device based on video data and computer storage medium |
| CN111539757B (en) * | 2019-12-30 | 2023-07-28 | 支付宝实验室(新加坡)有限公司 | Information delivery method, device, server and storage medium |
| CN112116391A (en) * | 2020-09-18 | 2020-12-22 | 北京达佳互联信息技术有限公司 | Multimedia resource delivery method and device, computer equipment and storage medium |
| CN112328937B (en) * | 2020-11-04 | 2024-01-30 | 支付宝(杭州)信息技术有限公司 | Information delivery method and device |
| CN113660515A (en) * | 2021-09-09 | 2021-11-16 | 深圳市易平方网络科技有限公司 | Hot spot data processing method, device, terminal and medium based on smart television |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636373A (en) * | 2013-11-11 | 2015-05-20 | 腾讯科技（深圳）有限公司 | Information push method and device |
| CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
| CN105915438A (en) * | 2016-04-15 | 2016-08-31 | 北京奇虎科技有限公司 | Message pushing method, apparatus, and system |
| CN106339507A (en) * | 2016-10-31 | 2017-01-18 | 腾讯科技（深圳）有限公司 | Method and device for pushing streaming media message |
| CN106484858A (en) * | 2016-10-09 | 2017-03-08 | 腾讯科技（北京）有限公司 | Hot Contents method for pushing and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9742855B2 (en) * | 2014-09-04 | 2017-08-22 | Mellanox Technologies, Ltd. | Hybrid tag matching |
| CN104298728B (en) * | 2014-09-28 | 2018-11-27 | 北京奇艺世纪科技有限公司 | A kind of method and system by internet distributing video advertisement |
-
2017
- 2017-03-31 CN CN201710211369.0A patent/CN106982256B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636373A (en) * | 2013-11-11 | 2015-05-20 | 腾讯科技（深圳）有限公司 | Information push method and device |
| CN104850662A (en) * | 2015-06-08 | 2015-08-19 | 浙江每日互动网络科技有限公司 | User portrait based mobile terminal intelligent message pushing method, server and system |
| CN105915438A (en) * | 2016-04-15 | 2016-08-31 | 北京奇虎科技有限公司 | Message pushing method, apparatus, and system |
| CN106484858A (en) * | 2016-10-09 | 2017-03-08 | 腾讯科技（北京）有限公司 | Hot Contents method for pushing and device |
| CN106339507A (en) * | 2016-10-31 | 2017-01-18 | 腾讯科技（深圳）有限公司 | Method and device for pushing streaming media message |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106982256A (en) | 2017-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106982256B (en) | Information pushing method, device, equipment and storage medium | |
| US20220114199A1 (en) | System and method for information recommendation | |
| US20150213361A1 (en) | Predicting interesting things and concepts in content | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| US11263248B2 (en) | Presenting content in accordance with a placement designation | |
| US9189470B2 (en) | Generation of explanatory summaries | |
| US10055755B2 (en) | Targeting content based on receipt of partial terms | |
| US11468481B2 (en) | Structured informational link annotations | |
| WO2008144444A1 (en) | Ranking online advertisements using product and seller reputation | |
| CN102598039A (en) | Multimode online advertisements and online advertisement exchanges | |
| US10002187B2 (en) | Method and system for performing topic creation for social data | |
| CN101833560A (en) | Manufacturer public praise automatic sequencing system based on internet | |
| CN110674620A (en) | Target file generation method, device, medium and electronic equipment | |
| CN112733042A (en) | Recommendation information generation method, related device and computer program product | |
| Ahmadi et al. | The bright side of consumers’ opinions of improving reverse logistics decisions: a social media analytic framework | |
| US11275777B2 (en) | Methods and systems for generating timelines for entities | |
| KR20220034134A (en) | Analysis of intellectual property data about products and services | |
| CN111310065A (en) | Social contact recommendation method and device, server and storage medium | |
| CN110717788A (en) | Target user screening method and device | |
| CN111400464B (en) | Text generation method, device, server and storage medium | |
| US11615245B2 (en) | Article topic alignment | |
| US10061751B1 (en) | Promoting content | |
| CN111222918B (en) | Keyword mining method and device, electronic equipment and storage medium | |
| CN112182414A (en) | Article recommendation method and device and electronic equipment | |
| Jiang et al. | Conducting product comparative analysis to outperform competitor’s product using Teardown JST Model |
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 |