WO2019114333A1 - 一种广告投放方法及平台 - Google Patents

一种广告投放方法及平台 Download PDF

Info

Publication number
WO2019114333A1
WO2019114333A1 PCT/CN2018/104183 CN2018104183W WO2019114333A1 WO 2019114333 A1 WO2019114333 A1 WO 2019114333A1 CN 2018104183 W CN2018104183 W CN 2018104183W WO 2019114333 A1 WO2019114333 A1 WO 2019114333A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement
webpage
label
subject
participle
Prior art date
Application number
PCT/CN2018/104183
Other languages
English (en)
French (fr)
Inventor
吴伟勇
Original Assignee
优视科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 优视科技有限公司 filed Critical 优视科技有限公司
Publication of WO2019114333A1 publication Critical patent/WO2019114333A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • 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

Definitions

  • the present application relates to the field of Internet technologies, and in particular, to an advertisement delivery method and platform.
  • the mainstream advertising strategy is roughly the following:
  • Hard advertising That is, ignoring the relevance of webpage information and advertisements, and placing advertisements rigidly. For example, on a webpage that broadcasts earthquake news in Mexico, a game-like advertisement is placed.
  • Keyword matching association Based on the keyword matching algorithm of the webpage information and the advertisement, the appropriate advertisement is selected for implementation. For example, on a webpage that broadcasts earthquake news in Mexico, a Mexican travel advertisement with the keyword "Mexico" is placed.
  • This strategy mainly considers the relationship between the user's interest tendency and the advertisement, regardless of the factors of the webpage information, and the webpage more reflects the role of acting as an advertisement slot. For example, a user prefers to travel, and when he browses a web page that broadcasts earthquake news in Mexico (and browses other different types of web pages), it places travel-related advertisements.
  • the above three methods have deficiencies in the advertising effect (or conversion rate).
  • the core of a better ad serving strategy is the ability of its ads to match the audience (or part of it). This way, the ad conversion rate will remain at an effective level. For example, on a webpage that broadcasts earthquake news in Mexico, a book advertisement that inserts a seismic aid knowledge may have a better advertising conversion rate. Because among the users browsing the information, a certain percentage of the population may have a need to understand the self-rescue knowledge after the earthquake, thereby generating a subjective will to click on the advertisement.
  • the embodiments of the present application provide an advertisement delivery method and platform, a computing device, and a computer readable storage medium to solve the technical defects existing in the prior art.
  • the embodiment of the present application discloses an advertisement delivery method, which is applied to an advertisement delivery platform, and includes:
  • Parsing text information of the webpage and adding a main scene label to the webpage according to the parsing result;
  • the main scene label of the webpage is associated with the application scenario label of the advertisement, and the advertisement is delivered to the webpage. Show.
  • the method for advertising an advertisement further includes:
  • An application scenario tag of the advertisement of the database is predetermined.
  • an application scenario tag that predetermines an advertisement of the database includes:
  • the description information includes: a type of the advertisement and a use of the advertisement;
  • the advertisements are classified, and the set of scene keywords corresponding to each advertisement in each type of advertisements is respectively obtained, and the scene keywords whose occurrence times are greater than the threshold are used as the application scene labels of the advertisements.
  • the subject scene tag includes: a subject name and a subject behavior
  • Parsing the text information of the webpage, and adding a main scene label to the webpage according to the parsing result including:
  • Corresponding behavior descriptors are retrieved according to the predicate participle as the subject behavior; wherein the behavior descriptors are pre-stored in the server.
  • the method further includes: adding an auxiliary information tag to the webpage according to the result of the parsing; wherein the auxiliary information tag comprises: subject description information and/or a body description location.
  • the method for obtaining the auxiliary information label specifically includes:
  • the subject description information and/or the subject description location are selected in the subject participle, the attributive participle, and/or the object participle of the content of the text information.
  • the application scenario tag of the advertisement in the database is adapted to the body scene tag of the webpage, and specifically includes: determining an application scenario tag of the advertisement and the subject The name is adapted.
  • the method before the displaying the advertisement to the webpage for presentation, the method further includes: according to the subject description information, the subject description location, and/or the subject behavior, The application scenario tag is filtered by an advertisement that matches the body name of the webpage.
  • the method further includes: acquiring a user's interest-oriented click rate, and displaying the webpage according to the interest-pending click rate. Advertising is filtered.
  • the embodiment of the present application further discloses an advertisement delivery platform, including:
  • a text information acquisition module wherein the text information acquisition module acquires text information of a webpage
  • the main body scene label adding module parses text information of the webpage, and adding a main scene label to the webpage according to the parsing result;
  • a scene label association module after the scene label association module determines that the application scene label of the advertisement in the database is adapted to the main scene label of the webpage, and associates the main scene label of the webpage with the application scene label of the advertisement ;
  • An advertisement delivery module wherein the advertisement delivery module delivers the advertisement to the webpage for presentation.
  • the platform further includes:
  • An application scenario tag adding module predetermining an application scenario tag of the advertisement of the database.
  • the application scenario tag adding module predetermines an application scenario tag of the advertisement of the database, including:
  • the application scenario tag adding module performs analysis according to the description information of the advertisement, and extracts the scenario keywords corresponding to each advertisement respectively; wherein the description information includes: a type of the advertisement and a use of the advertisement;
  • the application scenario tag adding module classifies advertisements, respectively obtains a set of scene keywords corresponding to each advertisement in each type of advertisement, and uses a scene keyword whose number of occurrences is greater than a threshold as an application scenario label of the advertisement. .
  • the subject scene tag includes: a subject name and a subject behavior
  • the main body scene label adding module parses the text information of the webpage, and adds a main scene label to the webpage according to the parsing result, including:
  • Corresponding behavior descriptors are retrieved according to the predicate participle as the subject behavior; wherein the behavior descriptors are pre-stored in the server.
  • the platform further includes:
  • auxiliary information label adding module adds an auxiliary information label to the webpage according to the parsing result; wherein the auxiliary information label comprises: a body description information and/or a body description location.
  • the method for obtaining the auxiliary information label specifically includes:
  • the auxiliary information label adding module performs language analysis on the content of the text information
  • the auxiliary information label adding module selects the subject description information and/or the subject description location in the subject participle, the attributive participle, and/or the object participle of the content of the text information according to the result of the language analysis and the subject name.
  • the scenario tag association module determines that an application scenario tag of an advertisement in the database is adapted to a body scene tag of the webpage, and specifically includes: the scenario tag association module determines The application scenario tag of the advertisement is adapted to the subject name.
  • the method before the advertisement delivery module, the method further includes:
  • the first screening module performs an advertisement corresponding to the application name tag and the body name of the webpage according to the body description information, the subject description location, and/or the subject behavior filter.
  • the method further includes:
  • the second screening module acquires a user's interest-to-click rate, and filters the advertisement displayed on the webpage according to the interest-oriented click rate.
  • the embodiment of the present application further discloses a computing device, including a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the following steps when executing the program:
  • Parsing text information of the webpage and adding a main scene label to the webpage according to the parsing result;
  • the main scene label of the webpage is associated with the application scenario label of the advertisement, and the advertisement is delivered to the webpage. Show.
  • the embodiment of the present application further discloses a computer readable storage medium storing a computer program, wherein the program is executed by a processor to implement the steps of the advertisement delivery method as described above.
  • the advertisement delivery method and platform, the computing device and the computer readable storage medium provided by the application by extracting the main scene label of the webpage, adapting the application scene label of the advertisement to the main scene label of the webpage, and then placing the advertisement to the webpage, Thereby achieving effective delivery of the advertisement.
  • FIG. 1 is a schematic flow chart of an advertisement delivery method according to an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of an advertisement delivery method according to an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of an advertisement delivery method according to an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of an advertisement delivery method according to an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of an advertisement delivery platform according to an embodiment of the present application.
  • FIG. 6 is a schematic flowchart of an advertisement delivery platform according to an embodiment of the present application.
  • FIG. 7 is a structural block diagram of a computing device according to an embodiment of the present application.
  • the embodiment of the present application discloses an advertisement delivery method, which is applied to an advertisement delivery platform.
  • the method includes:
  • the ad serving platform can be a mobile browser or a website that provides web pages. Get the text information of the web page when loading the web page.
  • the text information of the webpage may be information or news information.
  • the main scene label includes: a subject name and a subject behavior.
  • the text information of the webpage is parsed, and the main scene label is added to the webpage according to the parsed result, including:
  • the role of the subject name is to implement the main scene label of the webpage in the subsequent step and the application scene label of the advertisement, and the role of the main body behavior is to filter the associated advertisement.
  • the main scene label For example, for a webpage of “Meeting Messages Held by the Nineteenth National Congress”, the main scene label is extracted, the main body name is “meeting”, and the main body behavior is “convening”; for a “Mexico 7.1 Earthquake” webpage, extract it.
  • the main scene label has the main body name “earthquake” and the main body behavior as “occurrence”; for a web page of “Olympic swimming event war situation broadcast”, the main scene label is extracted, the main body name is “swim”, and the main body behavior is “going”. ".
  • the main scene label of the webpage is associated with the application scenario label of the advertisement.
  • the application scene label of the advertisement is predetermined and stored in the database of the advertisement platform.
  • the application scenario tags of the advertisements of the predetermined database include:
  • the description information includes: a type of the advertisement and a use of the advertisement;
  • the advertisements are classified, and the set of scene keywords corresponding to each advertisement in each type of advertisements is respectively obtained, and the scene keywords whose occurrence times are greater than the threshold are used as the application scene labels of the advertisements.
  • the threshold can be artificially set. For example, for the scene keyword set of the same category of advertisements, according to the order of the number of occurrences of the keywords, the top five keywords are selected as the application scene labels of the advertisements. At this stage, certain standardization corrections can be made according to the labeling strategy made by the manual operation.
  • the application scene label for their advertisements can be "conference supplies”; for example, earthquake self-help kits, which can As a preparation item before people prevent earthquakes
  • the application scene label for the advertisement of “Seismic Self-help Package” may be “earthquake preparation supplies”; for example, sunscreen cream/hand cream, when people swim in the open air (especially at the seaside) You need to use sunscreen skin care products to avoid burning your skin.
  • the application label for the "Sunscreen Cream/Hand Cream” advertisement can be "Sunscreen Skin Care”.
  • a specific ad may have multiple app scene tags.
  • the possible application scene labels may be: conference consumables, gift items, health supplies, and/or value-preserving items.
  • the application scene label of the advertisement is matched with the subject name, and the main scene label of the webpage and the application scene label of the advertisement are matched. Association.
  • the association strategy in addition to the above label matching, also includes: manual label association and machine learning training association.
  • the advertisement is delivered to the webpage for presentation.
  • the advertisement delivery method provided by the application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • An embodiment of the present application also discloses an advertisement delivery method. Referring to FIG. 2, the method includes:
  • the ad serving platform can be a mobile browser or a website that provides web pages. Get the text information of the web page when loading the web page.
  • the text information of the webpage may be information or news information.
  • the main scene label includes: a subject name and a subject behavior.
  • the text information of the webpage is parsed, and the main scene label is added to the webpage according to the parsed result, including:
  • the role of the subject name is to implement the main scene label of the webpage in the subsequent step and the application scene label of the advertisement, and the role of the main body behavior is to filter the associated advertisement.
  • the main scene label For example, for a webpage of “Meeting Messages Held by the Nineteenth National Congress”, the main scene label is extracted, the main body name is “meeting”, and the main body behavior is “convening”; for a “Mexico 7.1 Earthquake” webpage, extract it.
  • the main scene label has the main body name “earthquake” and the main body behavior as “occurrence”; for a web page of “Olympic swimming event war situation broadcast”, the main scene label is extracted, the main body name is “swim”, and the main body behavior is “going”. ".
  • step 202 the method further includes:
  • the auxiliary information tag includes: a body description information and/or a body description location.
  • the aforementioned "Meeting Message of the Nineteenth Conference” extracts the subject name of the subject scene label as “meeting”, the subject behavior as “convening”, and extracts the subject description information of the auxiliary information label as "the 19th session”.
  • the People's Congress, the main body of the description is the "Great Hall of the People.”
  • the subject name of the subject scene label is extracted as “earthquake”
  • the subject behavior is “occurrence”
  • the subject description information of the auxiliary information label is extracted as "7.1 earthquake”
  • the subject The location is described as "Mexico”.
  • the main body name of the main scene label is “Swimming”
  • the main body behavior is “Progress”
  • the main body description information of the auxiliary information label is “Olympic” and “Project”.
  • the obtaining of the auxiliary information label may be performed by filtering the advertisement of the application scene label and the body name of the webpage in a subsequent step according to the subject description information and/or the subject description location.
  • the main scene label of the webpage is associated with the application scenario label of the advertisement.
  • the application scene label of the advertisement is predetermined and stored in the database of the advertisement platform.
  • the application scenario tags of the advertisements of the predetermined database include:
  • the description information includes: a type of the advertisement and a use of the advertisement;
  • the advertisements are classified, and the set of scene keywords corresponding to each advertisement in each type of advertisements is respectively obtained, and the scene keywords whose occurrence times are greater than the threshold are used as the application scene labels of the advertisements.
  • the threshold can be artificially set. For example, for the scene keyword set of the same category of advertisements, according to the order of the number of occurrences of the keywords, the top five keywords are selected as the application scene labels of the advertisements. At this stage, certain standardization corrections can be made according to the labeling strategy made by the manual operation.
  • the application scene label for their advertisements can be "conference supplies”; for example, earthquake self-help kits, which can As a preparation item before people prevent earthquakes
  • the application scene label for the advertisement of “Seismic Self-help Package” may be “earthquake preparation supplies”; for example, sunscreen cream/hand cream, when people swim in the open air (especially at the seaside) You need to use sunscreen skin care products to avoid burning your skin.
  • the application label for the "Sunscreen Cream/Hand Cream” advertisement can be "Sunscreen Skin Care”.
  • a specific ad may have multiple app scene tags.
  • the possible application scene labels may be: conference consumables, gift items, health supplies, and/or value-preserving items.
  • the application scene label of the advertisement is matched with the subject name, and the main scene label of the webpage and the application scene label of the advertisement are matched. Association.
  • the association strategy in addition to the above label matching, also includes: manual label association and machine learning training association.
  • Filter according to the subject description information, the subject description location, and/or the subject behavior, an advertisement that matches the application scene label and the body name of the webpage.
  • the advertisements that can be placed on the webpage include: conference venue (site rental), conference consumables (tea cup, tea and conference paper) ) and conference system (meeting secret ballot system, video conferencing application). Then, the advertisement is filtered. For example, if the subject behavior in the main scene label of the webpage is “holding”, the advertisement before the conference or after the conference is removed.
  • the advertisement is delivered to the webpage for presentation.
  • the advertisement delivery method provided by the embodiment of the present application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • the embodiment of the present application may further extract the auxiliary information label from the webpage to implement further screening of the advertisement.
  • the embodiment of the present application further discloses an advertisement delivery method. Referring to FIG. 3, the method includes:
  • the ad serving platform can be a mobile browser or a website that provides web pages. Get the text information of the web page when loading the web page.
  • the text information of the webpage may be information or news information.
  • the main scene label includes: a subject name and a subject behavior.
  • the text information of the webpage is parsed, and the main scene label is added to the webpage according to the parsed result, including:
  • the role of the subject name is to implement the main scene label of the webpage in the subsequent step and the application scene label of the advertisement, and the role of the main body behavior is to filter the associated advertisement.
  • the main scene label For example, for a webpage of “Meeting Messages Held by the Nineteenth National Congress”, the main scene label is extracted, the main body name is “meeting”, and the main body behavior is “convening”; for a “Mexico 7.1 Earthquake” webpage, extract it.
  • the main scene label has the main body name “earthquake” and the main body behavior as “occurrence”; for a web page of “Olympic swimming event war situation broadcast”, the main scene label is extracted, the main body name is “swim”, and the main body behavior is “going”. ".
  • the subject scene label of the webpage is associated with the application scenario label of the advertisement.
  • the application scene label of the advertisement is predetermined and stored in the database of the advertisement platform.
  • the application scenario tags of the advertisements of the predetermined database include:
  • the description information includes: a type of the advertisement and a use of the advertisement;
  • the advertisements are classified, and the set of scene keywords corresponding to each advertisement in each type of advertisements is respectively obtained, and the scene keywords whose occurrence times are greater than the threshold are used as the application scene labels of the advertisements.
  • the threshold can be artificially set. For example, for the scene keyword set of the same category of advertisements, according to the order of the number of occurrences of the keywords, the top five keywords are selected as the application scene labels of the advertisements. At this stage, certain standardization corrections can be made according to the labeling strategy made by the manual operation.
  • the application scene label for their advertisements can be "conference supplies”; for example, earthquake self-help kits, which can As a preparation item before people prevent earthquakes
  • the application scene label for the advertisement of “Seismic Self-help Package” may be “earthquake preparation supplies”; for example, sunscreen cream/hand cream, when people swim in the open air (especially at the seaside) You need to use sunscreen skin care products to avoid burning your skin.
  • the application label for the "Sunscreen Cream/Hand Cream” advertisement can be "Sunscreen Skin Care”.
  • a specific ad may have multiple app scene tags.
  • the possible application scene labels may be: conference consumables, gift items, health supplies, and/or value-preserving items.
  • the application scene label of the advertisement is matched with the subject name, and the main scene label of the webpage and the application scene label of the advertisement are matched. Association.
  • the association strategy in addition to the above label matching, also includes: manual label association and machine learning training association.
  • the advertisement is delivered to the webpage for presentation.
  • the advertisement delivery method provided by the embodiment of the present application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • the embodiment of the present application may further filter the advertisement according to the user's click rate of the advertisement.
  • the headline of the news is “The spirit of a city’s procuratorate to organize the study of the 19th National Congress”.
  • the textual information of the news is “Since the party’s 19th National Congress, a city’s people’s procuratorate has held a special meeting of the party group. Organize cadre conferences, special study sessions, organize police officers' discussions, collective learning, etc., continue to deeply convey and study and implement the spirit of the 19th Party Congress, and demand that the study and implementation of the spirit of the 19th National Congress be the primary political task of the current and future period. Guided by the spirit of the 19th National Congress and promoted the procuratorial work to a new level. Before the meeting, we won the 19th security and stabilized the battle.
  • a method in an embodiment of the present application includes:
  • the advertisement delivery platform obtains text information of the webpage.
  • the advertisement delivery platform parses the text information of the webpage, divides the title and content of the text information of the webpage, and classifies the divided word segments into a main word segmentation, a predicate participle, an object participle, an attributive participle, and an adverbial participle according to a grammatical structure.
  • the advertisement delivery platform counts the frequency of the occurrence of the subject participle, the attributive participle, and/or the object participle in the content of the text information in the title of the text information, and the subject participle in the title whose frequency is greater than the threshold. , the attributive participle and/or the object participle as the subject name.
  • the advertisement delivery platform retrieves the corresponding behavior description word according to the predicate participle as the subject behavior.
  • the advertisement delivery platform selects, according to the result of the language analysis and the subject name, the subject description information and/or the subject description location in the subject participle, the attributive participle, and/or the object participle of the content of the text information.
  • the advertisement delivery platform determines that the application scenario label of the advertisement in the database is adapted to the main scene label of the webpage, the main scene label of the webpage is associated with the application scenario label of the advertisement.
  • the advertisement delivery platform delivers the advertisement to the webpage for presentation.
  • the advertisement delivery method provided by the embodiment of the present application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • the embodiment of the present application discloses an advertisement delivery platform 50. Referring to FIG. 5, the method includes:
  • the text information obtaining module 501 acquires text information of the webpage.
  • the main scene label adding module 502 parses the text information of the web page, and adds a main scene label to the web page according to the parsing result.
  • the subject scene label includes: a subject name and a subject behavior
  • the main scene label adding module 502 parses the text information of the webpage, and adds a main scene label to the webpage according to the parsing result, including:
  • Corresponding behavior descriptors are retrieved according to the predicate participle as the subject behavior; wherein the behavior descriptors are pre-stored in the server.
  • the scene label association module 503 after the scene label association module 503 determines that the application scene label of the advertisement in the database is adapted to the main scene label of the webpage, the subject scene label of the webpage and the application scenario of the advertisement Tag association.
  • the scene label association module 503 determines that the application scene label of the advertisement in the database is adapted to the body scene label of the webpage, and specifically includes: the scene label association module 503 determines the application scene label of the advertisement and the subject The name is adapted.
  • the advertisement delivery module 504, the advertisement delivery module 504 delivers an advertisement to the webpage for presentation.
  • the advertisement delivery platform of the embodiment further includes: an application scenario label adding module, where the application scenario label adding module predetermines an application scenario label of the advertisement of the database.
  • the application scenario tag adding module predetermines the application scenario tag of the advertisement of the database, where the application scenario tag adding module performs analysis according to the description information of the advertisement, and extracts corresponding scenario keywords corresponding to each advertisement; wherein the description Information includes: the type of advertising and the purpose of the advertisement; and
  • the application scenario tag adding module classifies advertisements, respectively obtains a set of scene keywords corresponding to each advertisement in each type of advertisement, and uses a scene keyword whose number of occurrences is greater than a threshold as an application scenario label of the advertisement. .
  • the advertisement delivery platform provided by the application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • the embodiment of the present application discloses an advertisement delivery platform 60, as shown in FIG. 6, which includes:
  • the text information obtaining module 601 acquires text information of the webpage.
  • the main scene label adding module 602 parses the text information of the web page, and adds a main scene label to the web page according to the parsing result.
  • the subject scene label includes: a subject name and a subject behavior
  • the main scene label adding module 602 parses the text information of the webpage, and adds a main scene label to the webpage according to the parsing result, including:
  • Corresponding behavior descriptors are retrieved according to the predicate participle as the subject behavior; wherein the behavior descriptors are pre-stored in the server.
  • the auxiliary information label adding module 603 adds an auxiliary information label to the web page according to the parsed result; wherein the auxiliary information label includes: subject description information and/or a body description location.
  • the method for obtaining the auxiliary information label specifically includes:
  • the auxiliary information label adding module 603 performs language analysis on the content of the text information
  • the auxiliary information label adding module 603 selects the subject description information and/or the subject description location in the subject word segment, the attributive participle, and/or the object participle of the content of the text information according to the result of the language analysis and the subject name.
  • the scene label association module 604 after the scene label association module 604 determines that the application scene label of the advertisement in the database is adapted to the main scene label of the webpage, the subject scene label of the webpage and the application scenario of the advertisement Tag association.
  • the scene label association module 604 determines that the application scene label of the advertisement in the database is adapted to the body scene label of the webpage, and specifically includes: the scene label association module 604 determines the application scene label of the advertisement and the subject The name is adapted.
  • the first screening module 605 filters the advertisements of the application scene label and the body name of the webpage according to the body description information, the subject description location, and/or the subject behavior.
  • the advertisement delivery module 606 sends the advertisement to the webpage for presentation.
  • the second screening module 607 is configured to obtain a user's interest-to-click rate, and filter the advertisement displayed on the webpage according to the interest-based click rate.
  • the advertisement delivery platform of the embodiment further includes: an application scenario label adding module, where the application scenario label adding module predetermines an application scenario label of the advertisement of the database.
  • the application scenario tag adding module predetermines the application scenario tag of the advertisement of the database, where the application scenario tag adding module performs analysis according to the description information of the advertisement, and extracts corresponding scenario keywords corresponding to each advertisement; wherein the description
  • the information includes: the type of the advertisement and the purpose of the advertisement; and the application scene label adding module classifies the advertisement, respectively obtains a set of scene keywords corresponding to each advertisement in each type of advertisement, and the scenes whose occurrence times are greater than the threshold
  • the keyword is used as the application scenario tag for this type of advertisement.
  • the advertisement delivery platform provided by the application obtains the main scene label of the webpage, adapts the application scene label of the advertisement to the main scene label of the webpage, and then delivers the advertisement to the webpage, thereby realizing effective delivery of the advertisement.
  • An embodiment of the present application further provides a computing device 700.
  • a memory 710, a processor 720, and a computer program stored on the memory 710 and executable on the processor 720 are included.
  • computing device 700 can also include a network interface that enables computing device 100 to communicate via one or more networks.
  • networks include a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet.
  • the network interface may include one or more of any type of network interface (eg, a network interface card (NIC)), wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, global microwave interconnect access (Wi- MAX) interface, Ethernet interface, Universal Serial Bus (USB) interface, cellular network interface, Bluetooth interface, Near Field Communication (NFC) interface, and more.
  • the computing device can access the page through a network interface.
  • the other components of computing device 700 described above and not shown in FIG. 7 may also be connected to one another, such as by a bus. It should be understood that the structural block diagram of the computing device shown in FIG. 7 is for illustrative purposes only and is not intended to limit the scope of the application. Those skilled in the art can add or replace other components as needed.
  • Computing device 700 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (eg, tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (eg, smart phones) ), wearable computing devices (eg, smart watches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs.
  • Computing device 700 can also be a mobile or static server.
  • the processor 720 implements the following steps when executing the program:
  • Parsing text information of the webpage and adding a main scene label to the webpage according to the parsing result;
  • the main scene label of the webpage is associated with the application scenario label of the advertisement, and the advertisement is delivered to the webpage. Show.
  • An embodiment of the present application further provides a computer readable storage medium storing a computer program, the program being executed by a processor to implement the steps of the advertisement delivery method as described above.
  • the above is a schematic illustration of a computer readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the above-mentioned automatic test method, and the details of the technical solution of the storage medium are not described in detail, and can refer to the description of the technical solution of the above-mentioned automatic test method.
  • the computer instructions include computer program code, which may be in the form of source code, an object code, an executable, or some intermediate form.
  • the computer readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM). , random access memory (RAM, Random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in a jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, computer readable media Does not include electrical carrier signals and telecommunication signals.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本申请提供一种广告投放方法及平台，所述方法包括：获取网页的文本信息；解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。本申请提供的广告投放方法，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。

Description

一种广告投放方法及平台 技术领域
本申请涉及互联网技术领域，特别涉及一种广告投放方法及平台。
背景技术
随着移动互联网的蓬勃发展，使用移动终端浏览网页也成为绝大部分移动用户日常的习惯性行为。Web站点为了盈利增加收入，也开始在页面上见缝插针甚至不遗余力地发布广告。
主流的广告投放策略，大致上有以下几种：
1)硬性投放广告。也就是无视网页信息与广告的关联性，硬性地投放广告。比如在一个播报墨西哥地震新闻的网页上，投放游戏类的广告。
2)关键词匹配关联。基于网页信息与广告的关键词匹配算法，而选择合适的广告实施投放。比如在一个播报墨西哥地震新闻的网页上，投放带“墨西哥”关键词的墨西哥旅游广告。
3)基于用户关联。这种策略主要考虑用户的兴趣倾向与广告的关系，而不考虑网页信息的因素，网页更多地体现出充当广告位的作用。比如某个用户比较喜欢旅游，在他浏览播报墨西哥地震新闻的网页时(以及浏览其它不同类型的网页)，投放旅游相关的广告。
上述三种方法在广告投放效果(或转化率)上，均存在不足之处。较好的广告投放策略，核心在于其广告能够匹配到受众群体(或者其一部分)的需求。这样，广告转化率才会维持在一个有效的水平。比如在一个播报墨西哥地震新闻的网页上，插入一个地震救助知识的书籍广告，可能会有较好的广告转化率。 因为浏览该信息的用户中，可能有一定比例的人群具有了解地震后的自救知识的需求，从而会产生点击该广告的主观意愿。
综上所述，如何对广告进行有效地投放，是需要解决的技术问题。
发明内容
有鉴于此，本申请实施例提供了一种广告投放方法及平台、计算设备和计算机可读存储介质，以解决现有技术中存在的技术缺陷。
本申请实施例公开了一种广告投放方法，应用于广告投放平台，包括：
获取网页的文本信息；
解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。
在本申请的一个示意性的实施方案中，所述广告投放方法还包括：
预先确定所述数据库的广告的应用场景标签。
在本申请的一个示意性的实施方案中，预先确定所述数据库的广告的应用场景标签包括：
根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
在本申请的一个示意性的实施方案中，所述主体场景标签包括：主体名称和主体行为；
解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
在本申请的一个示意性的实施方案中，所述方法还包括：根据解析的结果为所述网页添加辅助信息标签；其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
在本申请的一个示意性的实施方案中，所述辅助信息标签的获取方法具体包括：
对所述文本信息的内容进行语言分析；
根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
在本申请的一个示意性的实施方案中，所述确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：确定所述广告的应用场景标签与所述主体名称相适配。
在本申请的一个示意性的实施方案中，在投放所述广告至所述网页进行展现前，还包括：根据所述主体描述信息、所述主体描述地点和/或所述主体行为， 对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
在本申请的一个示意性的实施方案中，在投放所述广告至所述网页进行展现后，还包括：获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示的所述广告进行筛选。
本申请实施例还公开了一种广告投放平台，包括：
文本信息获取模块，所述文本信息获取模块获取网页的文本信息；
主体场景标签添加模块，所述主体场景标签添加模块解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
场景标签关联模块，所述场景标签关联模块确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联；
广告投放模块，所述广告投放模块投放所述广告至所述网页进行展现。
在本申请的一个示意性的实施方案中，所述平台还包括：
应用场景标签添加模块，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签。
在本申请的一个示意性的实施方案中，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签包括：
所述应用场景标签添加模块根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
所述应用场景标签添加模块对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为 该类广告的应用场景标签。
在本申请的一个示意性的实施方案中，所述主体场景标签包括：主体名称和主体行为；
所述主体场景标签添加模块解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
在本申请的一个示意性的实施方案中，所述平台还包括：
辅助信息标签添加模块，所述辅助信息标签添加模块根据解析的结果为所述网页添加辅助信息标签；其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
在本申请的一个示意性的实施方案中，所述辅助信息标签的获取方法具体包括：
所述辅助信息标签添加模块对所述文本信息的内容进行语言分析；
所述辅助信息标签添加模块根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
在本申请的一个示意性的实施方案中，所述场景标签关联模块确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：所述场景标签关联模块确定所述广告的应用场景标签与所述主体名称相适配。
在本申请的一个示意性的实施方案中，在所述广告投放模块前，还包括：
第一筛选模块，所述第一筛选模块根据所述主体描述信息、所述主体描述地点和/或所述主体行为，对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
在本申请的一个示意性的实施方案中，在所述广告投放模块后，还包括：
第二筛选模块，所述第二筛选模块获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示的所述广告进行筛选。
本申请实施例还公开了一种计算设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现以下步骤：
获取网页的文本信息；
解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。
本申请实施例还公开了一种计算机可读存储介质，其存储有计算机程序，其特征在于，该程序被处理器执行时实现如上所述广告投放方法的步骤。
本申请提供的广告投放方法及平台、计算设备和计算机可读存储介质，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签 相适配，然后投放广告至网页，从而实现广告的有效投放。
附图说明
图1是本申请一实施例的广告投放方法的流程示意图；
图2是本申请一实施例的广告投放方法的流程示意图；
图3是本申请一实施例的广告投放方法的流程示意图；
图4是本申请一实施例的广告投放方法的流程示意图；
图5是本申请一实施例的广告投放平台的流程示意图；
图6是本申请一实施例的广告投放平台的流程示意图；
图7是本申请一实施例的计算设备的结构框图。
具体实施方式
下面结合附图对本申请的具体实施方式进行描述。
为了实现对广告进行有效地投放，本申请实施例公开了一种广告投放方法，应用于广告投放平台，参见图1，包括：
101、获取网页的文本信息。
广告投放平台可以为移动浏览器或提供网页的站点。在加载网页时，获得网页的文本信息。本实施例中，网页的文本信息可以为资讯类或新闻类信息。
102、解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签。
其中，主体场景标签包括：主体名称和主体行为。
更为详尽地，解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
1021、将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
1022、统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
1023、根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
主体名称的作用是在后续步骤中实现网页的主体场景标签与广告的应用场景标签关联，主体行为的作用是对关联后的广告进行筛选。
例如对于一个“十九大召开的会议消息”的网页，提取其主体场景标签，其主体名称为“会议”，主体行为为“召开”；对于一个“墨西哥7.1级大地震”的网页，提取其主体场景标签，其主体名称为“地震”，主体行为为“发生”；对于一个“奥运会游泳项目战况播报”的网页，提取其主体场景标签，其主体名称为“游泳”，主体行为为“进行”。
103、确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联。
应用时，广告的应用场景标签为预先确定，并存储于广告平台的数据库中。
在一个具体的实施方案中，预先确定数据库的广告的应用场景标签包括：
根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
其中，阈值可以人为设定。例如对于同一种类别的广告的场景关键词集合，按照关键词的出现次数高低排序，筛选出排名前五的关键词作为该类广告的应用场景标签。这个阶段，可以根据人工运营所作的标注策略而进行一定的标准化矫正。
例如对于茶叶、茶杯、会议用纸/用笔，因为它们都可以作为在会议中使用的用品，那么关于它们的广告的应用场景标签可以为“会议耗用品”；又例如地震自救包，其可以作为人们在预防地震发生前的准备物品，那么关于“地震自救包”的广告的应用场景标签可以为“地震准备用品”；又例如防晒面霜/手霜，人们在露天游泳时(尤其在海边)，需要使用防晒护肤品，避免灼伤皮肤，那么关于“防晒面霜/手霜”的广告的应用场景标签可以为“防晒护肤品”。
需要注意的是，一个具体广告可能具有多个应用场景标签。以茶叶为例，其可能具有的应用场景标签可以为：会议耗用品、送礼用品、养生用品和/或保值物品等。
在一个具体的实施方案中，在获取到广告的应用场景标签与网页的主体场景标签后，将广告的应用场景标签与主体名称相适配，并将网页的主体场景标签与广告的应用场景标签关联。
在关联的过程中，除去上述的标签匹配外，关联策略还包括：人工标注关联以及机器学习训练关联。
104、投放所述广告至所述网页进行展现。
本申请提供的广告投放方法，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
本申请一实施例还公开了一种广告投放方法，参见图2，包括：
201、获取网页的文本信息。
广告投放平台可以为移动浏览器或提供网页的站点。在加载网页时，获得网页的文本信息。本实施例中，网页的文本信息可以为资讯类或新闻类信息。
202、解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签。
其中，主体场景标签包括：主体名称和主体行为。
更为详尽地，解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
2021、将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
2022、统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
2023、根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
主体名称的作用是在后续步骤中实现网页的主体场景标签与广告的应用场景标签关联，主体行为的作用是对关联后的广告进行筛选。
例如对于一个“十九大召开的会议消息”的网页，提取其主体场景标签，其主体名称为“会议”，主体行为为“召开”；对于一个“墨西哥7.1级大地震”的网页，提取其主体场景标签，其主体名称为“地震”，主体行为为“发生”；对于一个“奥运会游泳项目战况播报”的网页，提取其主体场景标签，其主体 名称为“游泳”，主体行为为“进行”。
在步骤202后，还包括：
203、根据解析的结果为所述网页添加辅助信息标签。其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
其中，辅助信息标签的获取方法具体包括：
2031、对所述文本信息的内容进行语言分析。
2032、根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
例如前述的“十九大召开的会议消息”的网页，提取其主体场景标签的主体名称为“会议”，主体行为为“召开”，提取其辅助信息标签的主体描述信息为“第十九届人民代表大会”，主体描述地点为“人民大会堂”。
又如对于“墨西哥7.1级大地震”的网页，提取其主体场景标签的主体名称为“地震”，主体行为为“发生”，提取其辅助信息标签的主体描述信息为“7.1级地震”，主体描述地点为“墨西哥”。
对于一个“奥运会游泳项目战况播报”的网页，提取其主体场景标签的主体名称为“游泳”，主体行为为“进行”，提取其辅助信息标签的主体描述信息为“奥运会”和“项目”。
辅助信息标签的获得，可以根据所述主体描述信息和/或所述主体描述地点，在后续步骤中对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
204、确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联。
应用时，广告的应用场景标签为预先确定，并存储于广告平台的数据库中。
在一个具体的实施方案中，预先确定数据库的广告的应用场景标签包括：
根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
其中，阈值可以人为设定。例如对于同一种类别的广告的场景关键词集合，按照关键词的出现次数高低排序，筛选出排名前五的关键词作为该类广告的应用场景标签。这个阶段，可以根据人工运营所作的标注策略而进行一定的标准化矫正。
例如对于茶叶、茶杯、会议用纸/用笔，因为它们都可以作为在会议中使用的用品，那么关于它们的广告的应用场景标签可以为“会议耗用品”；又例如地震自救包，其可以作为人们在预防地震发生前的准备物品，那么关于“地震自救包”的广告的应用场景标签可以为“地震准备用品”；又例如防晒面霜/手霜，人们在露天游泳时(尤其在海边)，需要使用防晒护肤品，避免灼伤皮肤，那么关于“防晒面霜/手霜”的广告的应用场景标签可以为“防晒护肤品”。
需要注意的是，一个具体广告可能具有多个应用场景标签。以茶叶为例，其可能具有的应用场景标签可以为：会议耗用品、送礼用品、养生用品和/或保值物品等。
在一个具体的实施方案中，在获取到广告的应用场景标签与网页的主体场景标签后，将广告的应用场景标签与主体名称相适配，并将网页的主体场景标签与广告的应用场景标签关联。
在关联的过程中，除去上述的标签匹配外，关联策略还包括：人工标注关联以及机器学习训练关联。
205、根据所述主体描述信息、所述主体描述地点和/或所述主体行为，对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
例如对于前述“十九大召开的会议消息”的网页，在获取其主体场景标签时，针对该网页可投放的广告包括：会议场地(场地租赁)、会议耗用品(茶杯、茶叶和会议用纸)和会议系统(会议无记名投票系统、视频会议应用)。然后对广告进行筛选，例如参考该网页的主体场景标签中的主体行为为“召开”，那么将针对会议召开前或会议召开后的广告去除掉。
206、投放所述广告至所述网页进行展现。
本申请实施例提供的广告投放方法，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
并且，本申请实施例还可以对网页进行辅助信息标签的提取，以实现对广告的进一步筛选。
本申请实施例还公开了一种广告投放方法，参见图3，包括：
301、获取网页的文本信息。
广告投放平台可以为移动浏览器或提供网页的站点。在加载网页时，获得网页的文本信息。本实施例中，网页的文本信息可以为资讯类或新闻类信息。
302、解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签。
其中，主体场景标签包括：主体名称和主体行为。
更为详尽地，解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
3021、将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
3022、统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
3023、根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
主体名称的作用是在后续步骤中实现网页的主体场景标签与广告的应用场景标签关联，主体行为的作用是对关联后的广告进行筛选。
例如对于一个“十九大召开的会议消息”的网页，提取其主体场景标签，其主体名称为“会议”，主体行为为“召开”；对于一个“墨西哥7.1级大地震”的网页，提取其主体场景标签，其主体名称为“地震”，主体行为为“发生”；对于一个“奥运会游泳项目战况播报”的网页，提取其主体场景标签，其主体名称为“游泳”，主体行为为“进行”。
303、确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联。
应用时，广告的应用场景标签为预先确定，并存储于广告平台的数据库中。
在一个具体的实施方案中，预先确定数据库的广告的应用场景标签包括：
根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
其中，阈值可以人为设定。例如对于同一种类别的广告的场景关键词集合，按照关键词的出现次数高低排序，筛选出排名前五的关键词作为该类广告的应用场景标签。这个阶段，可以根据人工运营所作的标注策略而进行一定的标准化矫正。
例如对于茶叶、茶杯、会议用纸/用笔，因为它们都可以作为在会议中使用的用品，那么关于它们的广告的应用场景标签可以为“会议耗用品”；又例如地震自救包，其可以作为人们在预防地震发生前的准备物品，那么关于“地震自救包”的广告的应用场景标签可以为“地震准备用品”；又例如防晒面霜/手霜，人们在露天游泳时(尤其在海边)，需要使用防晒护肤品，避免灼伤皮肤，那么关于“防晒面霜/手霜”的广告的应用场景标签可以为“防晒护肤品”。
需要注意的是，一个具体广告可能具有多个应用场景标签。以茶叶为例，其可能具有的应用场景标签可以为：会议耗用品、送礼用品、养生用品和/或保值物品等。
在一个具体的实施方案中，在获取到广告的应用场景标签与网页的主体场景标签后，将广告的应用场景标签与主体名称相适配，并将网页的主体场景标签与广告的应用场景标签关联。
在关联的过程中，除去上述的标签匹配外，关联策略还包括：人工标注关联以及机器学习训练关联。
304、投放所述广告至所述网页进行展现。
305、获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示 的所述广告进行筛选。
本申请实施例提供的广告投放方法，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
并且，本申请实施例还可以根据用户对广告的点击率，对广告进一步筛选。
下述以一个新闻网页为例，新闻的标题为“某市检察院组织学习十九大精神”，新闻的文本信息为“自党的十九大召开以来，某市人民检察院通过召开党组专题会议、机关干部大会、专题学习会，组织干警座谈、集体学习等形式，继续深入传达和学习贯彻党的十九大精神，并要求将学习贯彻十九大精神作为当前和今后一个时期的首要政治任务，用十九大精神指导、推动各项检察工作再上新台阶。会前，打赢十九大安保维稳攻坚战。为确保十九大期间安保工作万无一失，该市检察院全体干警参加了十九大维稳安保誓师大会，全体干警向党和人民庄严宣誓，许下安保诺言，对党忠诚，担当尽责，服从命令，听从指挥……会后，学习贯彻落实十九大精神，通过多种形式学习十九大精神，要求把学习贯彻十九大精神与推进各项检察工作结合起来，充分发挥检察职能作用，全面履行检察机关提起公益诉讼职能，坚持从严治检，打造过硬队伍，为推进司法体制改革做出新的贡献”。
参见图4，本申请一实施例的方法包括：
401、广告投放平台获取网页的文本信息。
402、广告投放平台解析网页的文本信息，将网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词。
403、广告投放平台统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称。
404、广告投放平台根据谓语分词检索出对应的行为描述词，作为主体行为。
405、广告投放平台根据语言分析的结果以及主体名称，在文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
406、广告投放平台确定数据库中的广告的应用场景标签与网页的主体场景标签相适配后，将所述网页的主体场景标签与广告的应用场景标签关联。
407、广告投放平台投放广告至网页进行展现。
根据上述步骤401～407，将“会议”作为主体场景标签中的主体名称，将“召开”作为主体场景标签中的主体行为，将“十九大”作为辅助信息标签中的主体描述信息，将“某市检察院”作为辅助信息标签中的主体描述地点。根据主题场景标签和辅助信息标签，推送“会议耗用品”类、“会议场地租赁”类以及“会议系统”类的广告至网页进行展示。
本申请实施例提供的广告投放方法，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
本申请实施例公开了一种广告投放平台50，参见图5，包括：
文本信息获取模块501，所述文本信息获取模块501获取网页的文本信息。
主体场景标签添加模块502，所述主体场景标签添加模块502解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签。
可选地，主体场景标签包括：主体名称和主体行为；
所述主体场景标签添加模块502解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
场景标签关联模块503，所述场景标签关联模块503确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联。
可选地，场景标签关联模块503确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：场景标签关联模块503确定所述广告的应用场景标签与所述主体名称相适配。
广告投放模块504，所述广告投放模块504投放广告至所述网页进行展现。
可选地，本实施例的广告投放平台还包括：应用场景标签添加模块，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签。
可选地，应用场景标签添加模块预先确定数据库的广告的应用场景标签包括：应用场景标签添加模块根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途； 及
所述应用场景标签添加模块对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
本申请提供的广告投放平台，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
本申请实施例公开了一种广告投放平台60，如图6所示，包括：
文本信息获取模块601，所述文本信息获取模块601获取网页的文本信息。
主体场景标签添加模块602，所述主体场景标签添加模块602解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签。
可选地，主体场景标签包括：主体名称和主体行为；
所述主体场景标签添加模块602解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
辅助信息标签添加模块603，所述辅助信息标签添加模块603根据解析的结 果为所述网页添加辅助信息标签；其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
可选地，辅助信息标签的获取方法具体包括：
所述辅助信息标签添加模块603对所述文本信息的内容进行语言分析；
所述辅助信息标签添加模块603根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
场景标签关联模块604，所述场景标签关联模块604确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联。
可选地，场景标签关联模块604确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：场景标签关联模块604确定所述广告的应用场景标签与所述主体名称相适配。
第一筛选模块605，所述第一筛选模块605根据主体描述信息、主体描述地点和/或主体行为，对应用场景标签与网页的主体名称相适配的广告进行筛选。
广告投放模块606，所述广告投放模块606投放广告至所述网页进行展现。
第二筛选模块607，所述第二筛选模块607获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示的所述广告进行筛选。
可选地，本实施例的广告投放平台还包括：应用场景标签添加模块，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签。
可选地，应用场景标签添加模块预先确定数据库的广告的应用场景标签包括：应用场景标签添加模块根据广告的描述信息进行分析，分别提取每个广告 所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及应用场景标签添加模块对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
本申请提供的广告投放平台，通过提取网页的主体场景标签，并将广告的应用场景标签与网页的主体场景标签相适配，然后投放广告至网页，从而实现广告的有效投放。
本申请一实施例还提供一种计算设备700，参见图7，包括存储器710、处理器720及存储在存储器710上并可在处理器720上运行的计算机程序。
虽然图7中没有示出，但是应该知道，计算设备700还可以包括网络接口，网络接口使得计算设备100能够经由一个或多个网络通信。这些网络的示例包括局域网(LAN)、广域网(WAN)、个域网(PAN)或诸如因特网的通信网络的组合。网络接口可以包括有线或无线的任何类型的网络接口(例如，网络接口卡(NIC))中的一个或多个，诸如IEEE802.11无线局域网(WLAN)无线接口、全球微波互联接入(Wi-MAX)接口、以太网接口、通用串行总线(USB)接口、蜂窝网络接口、蓝牙接口、近场通信(NFC)接口，等等。计算设备可以通过网络接口访问页面。
在本申请的一个实施例中，计算设备700的上述以及图7中未示出的其他部件也可以彼此相连接，例如通过总线。应当理解，图7所示的计算设备结构框图仅仅是出于示例的目的，而不是对本申请范围的限制。本领域技术人员可以根据需要，增添或替换其他部件。
计算设备700可以是任何类型的静止或移动计算设备，包括移动计算机或移动计算设备(例如，平板计算机、个人数字助理、膝上型计算机、笔记本计 算机、上网本等)、移动电话(例如，智能手机)、可佩戴的计算设备(例如，智能手表、智能眼镜等)或其他类型的移动设备，或者诸如台式计算机或PC的静止计算设备。计算设备700还可以是移动式或静止式的服务器。
所述处理器720执行所述程序时实现以下步骤：
获取网页的文本信息；
解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。
本申请一实施例还提供一种计算机可读存储介质，其存储有计算机程序，该程序被处理器执行时实现如前所述广告投放方法的步骤。
上述为本实施例的一种计算机可读存储介质的示意性方案。需要说明的是，该存储介质的技术方案与上述的自动化测试方法的技术方案属于同一构思，存储介质的技术方案未详细描述的细节内容，均可以参见上述自动化测试方法的技术方案的描述。
所述计算机指令包括计算机程序代码，所述计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。所述计算机可读介质可以包括：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。需要说明的是，所述计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区， 根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。
需要说明的是，对于前述的各方法实施例，为了简便描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其它顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定都是本申请所必须的。
上面结合附图对本申请优选的具体实施方式和实施例作了详细说明，但是本申请并不限于上述实施方式和实施例，在本领域技术人员所具备的知识范围内，还可以在不脱离本申请构思的前提下做出各种变化。

Claims (20)

  1. 一种广告投放方法，其特征在于，应用于广告投放平台，包括：
    获取网页的文本信息；
    解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
    确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。
  2. 根据权利要求1所述的广告投放方法，其特征在于，还包括：
    预先确定所述数据库的广告的应用场景标签。
  3. 根据权利要求2所述的广告投放方法，其特征在于，预先确定所述数据库的广告的应用场景标签包括：
    根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
    对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
  4. 根据权利要求1所述的广告投放方法，其特征在于，所述主体场景标签包括：主体名称和主体行为；
    解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
    将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
    统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文 本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
    根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
  5. 根据权利要求4所述的广告投放方法，其特征在于，还包括：根据解析的结果为所述网页添加辅助信息标签；其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
  6. 根据权利要求5所述的广告投放方法，其特征在于，所述辅助信息标签的获取方法具体包括：
    对所述文本信息的内容进行语言分析；
    根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
  7. 根据权利要求5所述的广告投放方法，其特征在于，所述确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：确定所述广告的应用场景标签与所述主体名称相适配。
  8. 根据权利要求7所述的广告投放方法，其特征在于，在投放所述广告至所述网页进行展现前，还包括：根据所述主体描述信息、所述主体描述地点和/或所述主体行为，对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
  9. 根据权利要求1所述的广告投放方法，其特征在于，在投放所述广告至所述网页进行展现后，还包括：
    获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示的所 述广告进行筛选。
  10. 一种广告投放平台，其特征在于，包括：
    文本信息获取模块，所述文本信息获取模块获取网页的文本信息；
    主体场景标签添加模块，所述主体场景标签添加模块解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
    场景标签关联模块，所述场景标签关联模块确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联；
    广告投放模块，所述广告投放模块投放所述广告至所述网页进行展现。
  11. 根据权利要求10所述的广告投放平台，其特征在于，还包括：
    应用场景标签添加模块，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签。
  12. 根据权利要求11所述的广告投放平台，其特征在于，所述应用场景标签添加模块预先确定所述数据库的广告的应用场景标签包括：
    所述应用场景标签添加模块根据广告的描述信息进行分析，分别提取每个广告所对应的场景关键词；其中，所述描述信息包括：广告的类型以及广告的用途；及
    所述应用场景标签添加模块对广告进行分类，分别获取每一类广告中的每个广告所对应的场景关键词的集合，并将出现次数大于阈值的场景关键词作为该类广告的应用场景标签。
  13. 根据权利要求10所述的广告投放平台，其特征在于，所述主体场景标签包括：主体名称和主体行为；
    所述主体场景标签添加模块解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签，包括：
    将所述网页的文本信息的标题和内容进行划分，并将划分后的分词按照语法结构分类为主语分词、谓语分词、宾语分词、定语分词和状语分词；
    统计所述文本信息的标题中的主语分词、定语分词和/或宾语分词在所述文本信息的内容中出现的频率，并将出现频率大于阈值的所述标题中的主语分词、定语分词和/或宾语分词作为所述主体名称；
    根据所述谓语分词检索出对应的行为描述词，作为所述主体行为；其中，所述行为描述词为预先存储于服务器中。
  14. 根据权利要求13所述的广告投放平台，其特征在于，还包括：
    辅助信息标签添加模块，所述辅助信息标签添加模块根据解析的结果为所述网页添加辅助信息标签；其中，所述辅助信息标签包括：主体描述信息和/或主体描述地点。
  15. 根据权利要求14所述的广告投放平台，其特征在于，所述辅助信息标签的获取方法具体包括：
    所述辅助信息标签添加模块对所述文本信息的内容进行语言分析；
    所述辅助信息标签添加模块根据语言分析的结果以及所述主体名称，在所述文本信息的内容的主语分词、定语分词和/或宾语分词中选择得到主体描述信息和/或主体描述地点。
  16. 根据权利要求14所述的广告投放平台，其特征在于，
    所述场景标签关联模块确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配，具体包括：所述场景标签关联模块确定所述广告的应用 场景标签与所述主体名称相适配。
  17. 根据权利要求16所述的广告投放平台，其特征在于，在所述广告投放模块前，还包括：
    第一筛选模块，所述第一筛选模块根据所述主体描述信息、所述主体描述地点和/或所述主体行为，对所述应用场景标签与所述网页的主体名称相适配的广告进行筛选。
  18. 根据权利要求10所述的广告投放平台，其特征在于，在所述广告投放模块后，还包括：
    第二筛选模块，所述第二筛选模块获取用户的兴趣倾向点击率，并根据所述兴趣倾向点击率对网页显示的所述广告进行筛选。
  19. 一种计算设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现以下步骤：
    获取网页的文本信息；
    解析所述网页的文本信息，根据解析的结果为所述网页添加主体场景标签；
    确定数据库中的广告的应用场景标签与所述网页的主体场景标签相适配后，将所述网页的主体场景标签与所述广告的应用场景标签关联，并投放所述广告至所述网页进行展现。
  20. 一种计算机可读存储介质，其存储有计算机程序，其特征在于，该程序被处理器执行时实现权利要求1-9中任意一项所述方法的步骤。
PCT/CN2018/104183 2017-12-12 2018-09-05 一种广告投放方法及平台 WO2019114333A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711318573.9A CN109919641B (zh) 2017-12-12 2017-12-12 一种广告投放方法及平台
CN201711318573.9 2017-12-12

Publications (1)

Publication Number Publication Date
WO2019114333A1 true WO2019114333A1 (zh) 2019-06-20

Family

ID=66819914

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/104183 WO2019114333A1 (zh) 2017-12-12 2018-09-05 一种广告投放方法及平台

Country Status (2)

Country Link
CN (1) CN109919641B (zh)
WO (1) WO2019114333A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473008A (zh) * 2019-07-31 2019-11-19 腾讯科技（深圳）有限公司 一种数据处理方法、装置、设备及存储介质
CN111080359A (zh) * 2019-12-13 2020-04-28 北京搜狐新媒体信息技术有限公司 一种标签算法确定方法、装置、服务器及存储介质
CN111160953A (zh) * 2019-12-12 2020-05-15 浙江大华技术股份有限公司 一种应用内广告投放方法、装置以及存储介质
CN111415202A (zh) * 2020-03-23 2020-07-14 政采云有限公司 一种广告投放方法及相关装置
CN113342334A (zh) * 2021-04-23 2021-09-03 阿里巴巴（中国）有限公司 视觉设计投放方法及装置
CN113781114A (zh) * 2021-09-13 2021-12-10 北京声智科技有限公司 电梯广告投放方法、系统、装置和电子设备
CN115409553A (zh) * 2022-08-30 2022-11-29 南京智慧橙网络科技有限公司 一种基于大数据和位置信息的广告投放系统及其方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111767439B (zh) * 2020-06-28 2023-12-15 百度在线网络技术（北京）有限公司 基于页面分类标签的推荐方法、设备和介质
CN113032551B (zh) * 2021-05-24 2021-09-10 北京泽桥传媒科技股份有限公司 基于大数据及文章标题结合的投放进度计算方法及系统
CN114119070A (zh) * 2021-10-29 2022-03-01 深圳市豪斯莱科技有限公司 广告生成方法、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101183396A (zh) * 2007-12-27 2008-05-21 深圳市迅雷网络技术有限公司 一种广告显示方法、系统和装置
CN102789453A (zh) * 2011-05-16 2012-11-21 阿里巴巴集团控股有限公司 广告信息投放方法及装置
US20120303444A1 (en) * 2010-02-05 2012-11-29 Microsoft Corporation Semantic advertising selection from lateral concepts and topics
CN106204165A (zh) * 2016-08-11 2016-12-07 广州出益信息科技有限公司 一种广告投放方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101458690A (zh) * 2007-12-14 2009-06-17 北京龙拓互动广告有限公司 一种发布广告的方法和广告服务器
US20100100417A1 (en) * 2008-10-20 2010-04-22 Yahoo! Inc. Commercial incentive presentation system and method
CN102663046A (zh) * 2012-03-29 2012-09-12 中国科学院自动化研究所 一种面向微博短文本的情感分析方法
CN103853824B (zh) * 2014-03-03 2017-05-24 沈之锐 一种基于深度语义挖掘的内文广告发布方法与系统
CN105335398B (zh) * 2014-07-18 2020-08-25 华为技术有限公司 一种服务推荐方法及终端
CN106651444A (zh) * 2016-12-20 2017-05-10 深圳飓风传媒科技有限公司 通过将用户标签化进行广告投放的方法和系统
CN106843889A (zh) * 2017-01-25 2017-06-13 百度在线网络技术（北京）有限公司 一种场景定制的方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101183396A (zh) * 2007-12-27 2008-05-21 深圳市迅雷网络技术有限公司 一种广告显示方法、系统和装置
US20120303444A1 (en) * 2010-02-05 2012-11-29 Microsoft Corporation Semantic advertising selection from lateral concepts and topics
CN102789453A (zh) * 2011-05-16 2012-11-21 阿里巴巴集团控股有限公司 广告信息投放方法及装置
CN106204165A (zh) * 2016-08-11 2016-12-07 广州出益信息科技有限公司 一种广告投放方法及装置

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110473008A (zh) * 2019-07-31 2019-11-19 腾讯科技（深圳）有限公司 一种数据处理方法、装置、设备及存储介质
CN110473008B (zh) * 2019-07-31 2024-02-20 腾讯科技（深圳）有限公司 一种数据处理方法、装置、设备及存储介质
CN111160953A (zh) * 2019-12-12 2020-05-15 浙江大华技术股份有限公司 一种应用内广告投放方法、装置以及存储介质
CN111160953B (zh) * 2019-12-12 2023-11-03 浙江大华技术股份有限公司 一种应用内广告投放方法、装置以及存储介质
CN111080359A (zh) * 2019-12-13 2020-04-28 北京搜狐新媒体信息技术有限公司 一种标签算法确定方法、装置、服务器及存储介质
CN111415202A (zh) * 2020-03-23 2020-07-14 政采云有限公司 一种广告投放方法及相关装置
CN111415202B (zh) * 2020-03-23 2023-11-10 政采云有限公司 一种广告投放方法及相关装置
CN113342334A (zh) * 2021-04-23 2021-09-03 阿里巴巴（中国）有限公司 视觉设计投放方法及装置
CN113342334B (zh) * 2021-04-23 2023-09-15 淘宝（中国）软件有限公司 视觉设计投放方法及装置
CN113781114A (zh) * 2021-09-13 2021-12-10 北京声智科技有限公司 电梯广告投放方法、系统、装置和电子设备
CN115409553A (zh) * 2022-08-30 2022-11-29 南京智慧橙网络科技有限公司 一种基于大数据和位置信息的广告投放系统及其方法
CN115409553B (zh) * 2022-08-30 2024-05-10 南京智慧橙网络科技有限公司 一种基于大数据和位置信息的广告投放系统及其方法

Also Published As

Publication number Publication date
CN109919641A (zh) 2019-06-21
CN109919641B (zh) 2021-04-23

Similar Documents

Publication Publication Date Title
WO2019114333A1 (zh) 一种广告投放方法及平台
Newman Tracking the release of IPCC AR5 on Twitter: Users, comments, and sources following the release of the Working Group I Summary for Policymakers
Son et al. Content features of tweets for effective communication during disasters: A media synchronicity theory perspective
Ross The journalist, the housewife, the citizen and the press: Women and men as sources in local news narratives
Flew Entertainment media, cultural power, and post-globalization: The case of China’s international media expansion and the discourse of soft power
Johnson et al. Wag the blog: How reliance on traditional media and the Internet influence credibility perceptions of weblogs among blog users
Arlt et al. Climate change and media usage: Effects on problem awareness and behavioural intentions
Kim et al. Projected and perceived destination brand personalities: The case of South Korea
Gould et al. Should anti-tobacco media messages be culturally targeted for Indigenous populations? A systematic review and narrative synthesis
Conrad et al. Social media as an alternative to surveys of opinions about the economy
CN109145204A (zh) 画像标签生成和使用方法及系统
CN106227786A (zh) 用于推送信息的方法和装置
US10529031B2 (en) Method and systems of implementing a ranked health-content article feed
Denisova Viral journalism. Strategy, tactics and limitations of the fast spread of content on social media: Case study of the United Kingdom quality publications
US20180322103A1 (en) Extracting audiovisual features from digital components
Huang et al. Impact of the ‘Giving Cigarettes is Giving Harm’campaign on knowledge and attitudes of Chinese smokers
US10902197B1 (en) Vocabulary determination and vocabulary-based content recommendations
Schwemmer The limited influence of right-wing movements on social media user engagement
Clark et al. Capturing the attitudes of adolescent males’ towards computerised mental health help‐seeking
Driscoll et al. Searching and clustering methodologies: Connecting political communication content across platforms
Sabatovych Do social media create revolutions? Using Twitter sentiment analysis for predicting the Maidan Revolution in Ukraine
Du et al. When press freedom meets national interest: How terrorist attacks are framed in the news in China and the US
Pennock-Speck et al. Imperatives in voice-overs in British TV commercials:‘Get this, buy that, taste the other’
Lutkenhaus et al. Using markers for digital engagement and social change: Tracking meaningful narrative exchange in transmedia edutainment with text analytics techniques
Roche et al. Bright club: Establishing a science comedy variety night in Ireland

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18887269

Country of ref document: EP

Kind code of ref document: A1