WO2018006099A1 - Procédé, système et appareil de ciblage de segment - Google Patents

Procédé, système et appareil de ciblage de segment Download PDF

Info

Publication number
WO2018006099A1
WO2018006099A1 PCT/US2017/040620 US2017040620W WO2018006099A1 WO 2018006099 A1 WO2018006099 A1 WO 2018006099A1 US 2017040620 W US2017040620 W US 2017040620W WO 2018006099 A1 WO2018006099 A1 WO 2018006099A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
conversation
intent
preferences
profile
Prior art date
Application number
PCT/US2017/040620
Other languages
English (en)
Inventor
Jonathan MELLINGER
Marcus TEWKSBURY
Original Assignee
Mellinger Jonathan
Tewksbury Marcus
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 Mellinger Jonathan, Tewksbury Marcus filed Critical Mellinger Jonathan
Publication of WO2018006099A1 publication Critical patent/WO2018006099A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G06N5/013—Automatic theorem proving
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute

Definitions

  • the present disclosure generally relates to targeted content, and more
  • an ad or ads, pop-up ads, springing ads, and the like are frequently provided to internet users surfing on a Web browser, often in a targeted manner. These advertisements are typically targeted based on demographic data indicated by so -called “cookies", which cookies are indicative of prior internet usage by the user of the subject web browser.
  • cookies may indicate the age range, demographic status, geographic preferences, likes and dislikes, and so on of a user using the browser to surf the internet. As such, advertisers may target advertising to that particular user in that particular segment based on the user's tracked data.
  • cookie technology will be largely inapplicable to allow for accumulation of user preference data based on usage. Therefore, the need exists for a new intent development system that may be used with alternative user interface methodologies distinct from the web browser interfaces used previously, to allow for targeted user advertisements based on the developed intent.
  • the disclosure includes an apparatus, system and method for providing an end-to-end, multi-channel artificial intelligence (AI) engine capable of enabling website publishers to at least to identify, engage, and converse with users.
  • the apparatus, system and method may include recording each conversation between the user and the AI engine; extracting, via at least neuro-linguistic processing and machine learning, of user intent from the recorded conversation; assigning the user intent and a conversation identifier into a user profile having secondary- data associated therewith that is uniquely- associated with that user, wherein the assigning comprises generating a hashed alphanumeric key for each identified user, user intent, and conversation; creating a detailed profile in accordance with the user intent, conversation identifier, and the user profile indicative of at least preferences of the user; spawning at least one targeting model comprising a decision tree applied to the preferences of the user, wherein the decision tree applies criteria that results in at least one of a permanent assigning of the discerned preferences to the user profile, an action or inaction by the AT. engine in relation to the user, or a
  • the embodiments provide at least a new intent development system that may be used with alternative user interface methodologies distinct from the web browser interfaces used previously, to allow for targeted user advertisements based on the developed intent.
  • FIG. 1 is an exemplary illustration of aspects of the instant, invention
  • FIG. 2 is an exemplary illustration of aspects of the instant invention
  • FIG. 3 is an exemplary illustration of aspects of the instant, invention.
  • FIG. 4 is an exemplary illustration of aspects of the instant invention.
  • first, second, third, etc. may be used herein to describe various elements, functions, steps, components, regions, layers and/or sections, these elements, components, functions, steps, regions, layers and/or sections should not be limited by these terms. These terms may be only used to distinguish one element, component, function, step, region, layer or section from another element, component, region, layer or section. Thus, terms such as “first,” “second,” and other numerical terms, when used herein, do not imply a sequence or order unless clearly indicated by the context. Thus, a first element, component, region, layer or section discussed below could be termed a second element, component, region, layer or section without departing from the teachings of the exemplary embodiments.
  • a computer program product in accordance with one embodiment may comprise a tangible computer usable medium (e.g., standard RAM, an optical disc, a USB drive, or the like) having computer-readable program code embodied therein, wherein the computer-readable program code is adapted to be executed by a processor (working in connection with an operating system) to implement one or more functions and methods as described below, in this regard, the program code may be implemented in any desired language, and may be implemented as machine code, assembly code, byte code, inteipretable source code or the like (e.g., via C, C++, C#, Java, Actionscript, Objective-C, Javascript, CSS, XML, etc.), by way of non-limiting example.
  • a tangible computer usable medium e.g., standard RAM, an optical disc, a USB drive, or the like
  • the program code may be implemented in any desired language, and may be implemented as machine code, assembly code, byte code, inteipretable source code or the like (e.g., via C,
  • FIG. 1 depicts an exemplary computing system 1100 for use in association with the herein described systems and methods.
  • Computing system 1100 is capable of executing software, such as an operating system (OS) and/or one or more computing applications 1190, such as applications applying the algorithms discussed herein, and may execute such applications using data, such as may be gained via the I/O port.
  • OS operating system
  • computing applications 1190 such as applications applying the algorithms discussed herein, and may execute such applications using data, such as may be gained via the I/O port.
  • exemplary computing system 1100 is controlled primarily by computer readable instructions, such as instructions stored in a computer readable storage medium, such as hard disk drive (HDD) 1115, optical disk (not shown) such as a CD or DVD, solid state drive (not shown) such as a USB “thumb drive,” or the like.
  • a computer readable storage medium such as hard disk drive (HDD) 1115, optical disk (not shown) such as a CD or DVD, solid state drive (not shown) such as a USB “thumb drive,” or the like.
  • Such instructions may be executed within central processing unit (CPU) 1110 to cause computing system 1100 to perform the operations discussed throughout.
  • CPU 1110 is implemented in an integrated circuit called a processor.
  • exemplary computing system 1100 is shown to comprise a single CPU 1110, such description is merely illustrative, as computing system 1100 may comprise a plurality of CPUs 1110. Additionally, computing system 1100 may exploit the resources of remote CPUs (not shown), for example, through communications network 1170 or some other data communications means.
  • CPU 1110 fetches, decodes, and executes instructions from a computer readable storage medium, such as HDD 1115.
  • Such instructions may be included in software such as an operating system (OS), executable programs such as the applications discussed above, and the like.
  • Information, such as computer instructions and other computer readable data is transferred between components of computing system 1100 via the system's main data- transfer path.
  • the main data-transfer path may use a system bus architecture 1105, although other computer architectures (not shown) can be used, such as architectures using serializers and deserializers and crossbar switches to communicate data between devices over serial communication paths.
  • System bus 1105 may include data lines for sending data, address lines for sending addresses, and control lines for sending interrupts and for operating the system bus.
  • Some busses provide bus arbitration that regulates access to the bus by extension cards, controllers, and CPU 1110.
  • Memory devices coupled to system bus 1105 may include random access memory (RAM) 1125 and/or read only memory (ROM) 1130. Such memories include circuitry that allows information to be stored and retrieved. ROMs 1130 generally contain stored data that cannot be modified. Data stored in RAM 1125 can be read or changed by CPU 1110 or other hardware devices. Access to RAM 1125 and/or ROM 1130 may be controlled by memory controller 1120. Memory controller 1120 may provide an address translation function that translates virtual addresses into physical addresses as instructions are executed. Memory controller 1120 may also provide a memory protection function that isolates processes within the system and isolates system processes from user processes.
  • RAM random access memory
  • ROM read only memory
  • Such memories include circuitry that allows information to be stored and retrieved. ROMs 1130 generally contain stored data that cannot be modified. Data stored in RAM 1125 can be read or changed by CPU 1110 or other hardware devices. Access to RAM 1125 and/or ROM 1130 may be controlled by memory controller 1120. Memory controller 1120 may provide an address translation function that translates virtual addresses into physical addresses
  • computing system 1100 may contain peripheral communications bus 135, which is responsible for communicating instructions from CPU 1110 to, and/or receiving data from, peripherals, such as peripherals 1140, 1145, and 1150, which may include printers, keyboards, and/or the sensors discussed herein throughout.
  • peripherals such as peripherals 1140, 1145, and 1150, which may include printers, keyboards, and/or the sensors discussed herein throughout.
  • Peripheral bus is the Peripheral
  • PCI Component Interconnect
  • Display 1160 which is controlled by display controller 1155, may be used to display visual output and/or presentation generated by or at the request of computing system 1100, responsive to operation of the aforementioned computing program. Such visual output may include text, graphics, animated graphics, and/or video, for example.
  • Display 1160 may be implemented with a CRT-based video display, an LCD or LED-based display, a gas plasma-based flat-panel display, a touch-panel display, or the like.
  • Display controller 1155 includes electronic components required to generate a video signal that is sent to display 1160.
  • computing system 1100 may contain network adapter 1165 which may be used to couple computing system 1100 to external communication network 1170, which may include or provide access to the Internet, an intranet, an extranet, or the like.
  • Communications network 1170 may provide user access for computing system 1100 with means of communicating and transferring software and information electronically.
  • communications network 1170 may provide for distributed processing, which involves several computers and the sharing of workloads or cooperative efforts in performing a task. It is appreciated that the network connections shown are exemplary and other means of establishing communications links between computing system 1100 and remote users may be used.
  • Network adaptor 1165 may communicate to and from network 1170 using any available wired or wireless technologies. Such technologies may include, by way of non-limiting example, cellular, Wi-Fi, Bluetooth, infrared, or the like. It is appreciated that exemplary computing system 1100 is merely illustrative of a computing environment in which the herein described systems and methods may operate, and does not limit the implementation of the herein described systems and methods in computing environments having differing components and configurations. That is to say, the inventive concepts described herein may be implemented in various computing environments using various components and configurations,
  • cookies which are typically Java script components, are used to track a user's usage of the internet, such as may occur over network adaptor 1165 of computing system 1100 as discussed above. This data is then discerned in real time in order to assess likely desires or preferences of the user so that advertising can be targeted specifically to that user, it goes without saying that advertising experiences a heightened impact when targeted to a user most likely to respond to that advertisement.
  • the present invention may use voice or text query input to alternative user interfaces to assess a user's intent, thereby generating "cookie- esque" data that may be compared, such as in a flat data file format, to available cookie pool data, such as in order to allow advertisements to be pulled from the typical cookie pool data in a manner that will optimally target the pulled content to the user of the alternative user interface.
  • the user may ask an artificial intelligence assistant for a hotel room reservation, and, based on the user's prior inquiries, the geography in which the hotel room is requested, the user' s age and the ages of other known users in the requesting household, the user's prior purchase requests through the Al, and whether the speaking voice is male or female, an advertisement for a hotel room may be targeted directly to a user via the alternative user interface.
  • the present invention provides new systems and methods for receiving and aggregating user query and input data to alternative user interfaces to enable the production of targeted advertisements to the user through classic or alternative user interface means.
  • the database taxonomy may indicate that, based on other prior queries and/or a user profile, the requesting user is a male, aged 18-35, who likes to eat fruit and play golf, who asks frequent questions about the hours of local gyms, and is in a high income bracket.
  • an advertiser may compare this information to desired information for advertisement targets.
  • each of the foregoing advertisers may have indicated the desire to advertise to a segment of a "cookie" pool that matches the user segment indicated for this exemplary user interacting with any Ui, or interacting specifically with an alternative user interface.
  • the disclosed embodiments tor intent development may be employed in conjunction with actual cookie data gained through web browsing
  • the disclosed intent development data, or "cookie-esque" data discussed herein constitutes a separate data generation mechanism from the cookie data known in the present art.
  • the present system and method generates spoken or typed intent data in accordance with session mining during a use session of an alternative user interface, as that phrase is defined herein.
  • the captured intent data provided by the instant systems and methods may be matched to existing cookie pool data, and consequently the "front end" provided by the instant invention may be employed with an existing, cookie-based advertisement "back end" to allow for the provision of targeted advertisements through the disclosed alternative user interfaces, in light of the foregoing, the data necessary to employ and make use of the instant invention, and the generation of such data, is less intensive than the generation of data necessary to employ historical cookies to target advertisements. That is, based on the voice and text recognition already inherent in the APIs of most of the aforementioned alternative user interfaces, the data sought to do the disclosed intent capture is already generated by these alternative user interface vehicles. Therefore, this existing data may be mined for the taxonomy items of interest to allow for the development of user intent, and, as discussed above, once this taxonomy is created it may simply be interfaced to existing back end cookie pool data.
  • the instant intent capture data may be akin to historical cookie data
  • privacy and security in relation to cookies may also be employed with the instant invention. That is, users of alternative user interfaces may be enabled to opt out of intent capture data, may be forewarned that intent capture data is being captured, or the intent capture features may be "closed" into the API of the de vice providing the alternative user interface, whereby the fullness of the user's intent capture data will not be available to any third party.
  • Figure 2 illustrates a system 200 in which the disclosed systems and methods are applicable.
  • a user session may occur through an alternative user interface 202, such as a chat box/bot (as shown), and the API 204 of the alternative user interface device 202 may include a natural language parsing engine 206 whereby the natural language query 208 into the alternative UI 202 is parsed.
  • the user session may include a user profile 210, and/or the user profiles of other possible users of the device, wherein the user profiles 210 may include additional information regarding or indicative of the user's intent, such as entered user profile information 210, web browser cookie data for that use previously associated with the user' s profile, or the like.
  • the natural language data 206 of the user' s query may be structured to allow for a database comparison to assess the user' s intent.
  • an intent development engine 220 may employ various methodologies to use the user's query to capture the user's intent.
  • the user's intent data and the user's profile data may be combined to formulate a taxonomy of the user's targeting profile 230, which may be compared, as shown, against the desired audience segment 240 for an advertisement.
  • this audience segment 240 may be an indicated preference by an advertiser unique to the currently disclosed alternative user interface environment, or may be a historic cookie pool segment choice by the advertiser.
  • the targeted advertisement may be produced 250.
  • the targeted advertisement may be produced via the alternative user interface as defined herein and/or via one or more other interfaces known to be associated with that user.
  • Figure 3 is a flow diagram illustrating a method according to the
  • the method provides an end-to-end, multi-channel (web, mobile, SMS) deployment of artificial intelligence, such as "chatbots", to enable website publishers (such as brands and enterprises) to identify, engage, and converse with (such as for marketing purposes) customers.
  • artificial intelligence such as "chatbots”
  • a record of each conversation between a user and an AI is recorded.
  • This provides a detailed record of the conversation between the AI and user; the use of neuro-linguistic processing and machine learning allows for extraction, by the disclosed engine and system, of sentiment and user intent from these conversations at step 304; and a unique identifier for that user and that conversation with the AI is assigned at step 306.
  • a hashed alphanumeric key for each identity/identifier is generated at step 310.
  • additional personally identifiable information may be appended to the Identity, such as in a database, such as a relational database, at step 320.
  • Other datasets may also be appended to this Identity and PII, such as geolocation and time of day, to create a detailed profile at step 322 that indicates, with particularity, WHO said WHAT, WHERE they were, and WHEN they said it, which, when taken in conjunction with other information (such as user profile), is indicative of like/dislikes/intent. Accordingly, this information forms an emotional Intelligence profile.
  • a decision tree may be spawned from steps 320 and 322 to allow for application of any of various selected targeting or intent assessment models, which may be executed, input and/or called at step 330.
  • Such models may, improve aspects of customer engagement based on the customer's desired outcome or key performance indicators (KPIs), by way of non-limiting example.
  • the Intents of a specific Identity may be assessed, such as by performing an internal auction or decisioning process (as dictated by the particular model or model of models).
  • the outcome of the modelling may determine the next action of the AI at step 334.
  • the AI may do nothing and the user may continue communicating with the chatbot, or the AI may return a pre-defined application (App) that is to be provided under certain criteria.
  • apps may consist of audio or video content, marketing- specific content, surveys, or other information that may be delivered directly into the chat stream of the user and the AI.
  • each of the foregoing interactions may form a recorded data "event", created and maintained in the disclosed data environment.
  • each Intent may be scored for relevancy to developing the ongoing customer profile at step 350.
  • some interactions between a user and the AI may be meaningless, unrelated to the specific customer, or just noise, but some interactions may be provide strong signals of intent and sentiment.
  • Those interactions that are highly indicative of intent/wants/needs/likes/dislikes may be appended to the Identity, and may be share with enterprise customers as valuable business intelligence insights.
  • the decision tree process may include multiple prongs, such as is illustrated in the logical block diagram of Figure 4.
  • the logic may include decisions as to intent discovery 402, action mapping 404, automation 406, and dialog 408 with the user and the AI engine.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

La présente invention comprend un appareil, un système et un procédé qui permettent de fournir un moteur d'intelligence artificielle à canaux multiples de bout en bout (IA) susceptible d'autoriser des éditeurs de sites Web au moins à identifier des utilisateurs, à collaborer et à converser avec eux. L'appareil, le système et le procédé peuvent consister : à enregistrer chaque conversation entre l'utilisateur et le moteur IA ; à extraire, par l'intermédiaire d'au moins un traitement neurolinguistique et d'un apprentissage machine, l'intention de l'utilisateur de la conversation enregistrée : l'attribution de l'intention de l'utilisateur et d'un identifiant de conversation dans un profil d'utilisateur possédant des données secondaires associées avec ce dernier, qui sont associées de manière unique à cet utilisateur, l'attribution consistant : à générer une clé alphanumérique hachée pour chaque utilisateur identifié, l'intention de l'utilisateur et la conversation ; à créer un profil détaillé en fonction de l'intention de l'utilisateur, de l'identifiant de conversation et du profil d'utilisateur indiquant au moins les préférences de l'utilisateur, au moins un modèle de ciblage comprenant un arbre de décision appliqué aux préférences de l'utilisateur, l'arbre de décision appliquant des critères qui se traduisent par au moins l'une d'une attribution permanente des préférences déterminées au profil d'utilisateur, une action ou une inaction effectuée par le moteur IA par rapport à l'utilisateur, ou une suppression des préférences déterminées comme non pertinentes.
PCT/US2017/040620 2016-07-01 2017-07-03 Procédé, système et appareil de ciblage de segment WO2018006099A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201662357749P 2016-07-01 2016-07-01
US62/357,749 2016-07-01

Publications (1)

Publication Number Publication Date
WO2018006099A1 true WO2018006099A1 (fr) 2018-01-04

Family

ID=60787510

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2017/040620 WO2018006099A1 (fr) 2016-07-01 2017-07-03 Procédé, système et appareil de ciblage de segment

Country Status (1)

Country Link
WO (1) WO2018006099A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030014489A1 (en) * 1999-05-27 2003-01-16 Inala Suman Kumar Method and apparatus for a site-sensitive interactive chat network
US20100058183A1 (en) * 2008-09-02 2010-03-04 International Business Machines Corporation Method, system, and program product for allocating virtual universe customer service
US20120166180A1 (en) * 2009-03-23 2012-06-28 Lawrence Au Compassion, Variety and Cohesion For Methods Of Text Analytics, Writing, Search, User Interfaces
US20120221502A1 (en) * 2010-01-25 2012-08-30 Andrew Peter Nelson Jerram Apparatuses, methods and systems for a digital conversation management platform
US20140013249A1 (en) * 2012-07-06 2014-01-09 Shahram Moeinifar Conversation management systems and methods

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030014489A1 (en) * 1999-05-27 2003-01-16 Inala Suman Kumar Method and apparatus for a site-sensitive interactive chat network
US20100058183A1 (en) * 2008-09-02 2010-03-04 International Business Machines Corporation Method, system, and program product for allocating virtual universe customer service
US20120166180A1 (en) * 2009-03-23 2012-06-28 Lawrence Au Compassion, Variety and Cohesion For Methods Of Text Analytics, Writing, Search, User Interfaces
US20120221502A1 (en) * 2010-01-25 2012-08-30 Andrew Peter Nelson Jerram Apparatuses, methods and systems for a digital conversation management platform
US20140013249A1 (en) * 2012-07-06 2014-01-09 Shahram Moeinifar Conversation management systems and methods

Similar Documents

Publication Publication Date Title
US20230274205A1 (en) Multi computational agent performance of tasks
US10854188B2 (en) Synthesized voice selection for computational agents
US10853747B2 (en) Selection of computational agent for task performance
US20200082432A1 (en) Automated creative extension selection for content performance optimization
AU2014399168B2 (en) Automated click type selection for content performance optimization
US9569536B2 (en) Identifying similar applications
US9690847B2 (en) Selecting content using query-independent scores of query segments
US20200342496A1 (en) Providing a modified content item to a user
WO2013138742A1 (fr) Systèmes et procédés relatifs à des techniques de distribution de services contextualisés sur des dispositifs mobiles
US20140172562A1 (en) Query-refinement advertisements based on query-completion suggestions
US11049304B2 (en) Mitigation of bias in digital reality sessions
US11720920B1 (en) Combining content with a search result
US9656166B1 (en) Using game data for providing content items
US11663535B2 (en) Multi computational agent performance of tasks
WO2018006099A1 (fr) Procédé, système et appareil de ciblage de segment
US10803486B1 (en) Item recommendations based on media content
US20170372377A1 (en) Providing image-like versions of text advertisements
US20230409352A1 (en) Systems and Methods for Dynamically Generating Context Aware Active Icons on a Mobile Device
US11347763B2 (en) Providing a notification in place of content item

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17821448

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17821448

Country of ref document: EP

Kind code of ref document: A1