WO2013173792A1 - Systèmes de commerce sans clic - Google Patents

Systèmes de commerce sans clic Download PDF

Info

Publication number
WO2013173792A1
WO2013173792A1 PCT/US2013/041705 US2013041705W WO2013173792A1 WO 2013173792 A1 WO2013173792 A1 WO 2013173792A1 US 2013041705 W US2013041705 W US 2013041705W WO 2013173792 A1 WO2013173792 A1 WO 2013173792A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
product
intent
implementations
server system
Prior art date
Application number
PCT/US2013/041705
Other languages
English (en)
Inventor
Nathan Stoll
Andrew ELLERHORST
Original Assignee
Luvocracy Inc.
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
Priority claimed from US13/769,181 external-priority patent/US20130317941A1/en
Priority claimed from US13/896,292 external-priority patent/US10740779B2/en
Application filed by Luvocracy Inc. filed Critical Luvocracy Inc.
Publication of WO2013173792A1 publication Critical patent/WO2013173792A1/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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0609—Buyer or seller confidence or verification
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Definitions

  • the disclosed implementations relate to the field of online commerce generally and in particular to providing convenient commerce interactions for users.
  • a method for enabling a user to pre-establish intent is disclosed. Allowing a user of a system to pre-establish intent results in a significantly improved user experience, as a user can establish products/services the user wants and a commerce system will automatically purchase the product or service when it becomes available. Once established, the user's purchasing intent can be used to purchase a single item, several products within a category, or even all products recommended by specific user or made by a particular company. Furthermore, purchasing intent data stored for a user can be integrated into the user's profile to help a commerce system to improve the level of customization and enhance the user experience.
  • a commerce system stores user data. Each user can indicate products or service that he or she would like to purchase.
  • the system stores the pre- established intent, along with any other associated attributes, such as price or size.
  • the system can then search an established database of products or product recommendations, as well as new products as they are added to determine if any match the specifications of pre- established intent. Once a matching product is found, it can be purchased on behalf of the users and delivered without the need for user input.
  • a user is able to set a preference once, and receive the product they are looking for without having to constantly monitor several different vendors. For example, if a user wants to purchase a specific graphics processing unit (GPU) at a particular price, they can establish that purchasing intent with the system. Once a matching product is found, the product is automatically purchased, without the need for the user to constantly monitor multiple vendors to see if a good sale has occurred.
  • GPU graphics processing unit
  • a user can establish intent to purchase a particular product on a periodic basis. For example, a user may elect to purchase one bottle of wine per week.
  • the system records the pre-established intent and finds, purchased, and delivers a matching product as established without further user intervention.
  • the user can, of course, alter the pre-established intent at any time.
  • the commerce system allows a user to make a purchase, without ever having to "click" or interact with a web site.
  • the commerce system determines commercial intent for a user. This commercial intent can be based on previous interactions with the commerce system. In some implementations, the commercial intent is determined based on information posted publicly by the user on a social networking site. The commerce system then determines one or more products that meet the determined
  • the commerce system then sends a
  • the commerce system may send a text message to a user recommending a product.
  • the user can then respond to the recommendation through the same communication through which the recommendation was received. For example, if the recommendation was received through a text message, the user can send instructions to purchase the product through a text message. In this way, user's can make purchasing decisions without having to log onto a computer.
  • a method for enabling clickless purchasing is disclosed.
  • the method is performed on a server system having one or more processors and memory storing one or more programs for execution by the one or more processors.
  • the server system detects commercial intent from a user of the computer system.
  • the server system determines a product relevant to the detected commercial intent of a user.
  • the server system sends a recommendation message to the user, wherein the recommendation message includes an option to purchase the product.
  • the server system receives a response message from the user, the message including authorization from the user to purchase the recommended product.
  • the server system purchases the recommended product on behalf of the user and delivers the purchased product to the user.
  • a server system for enabling clickless purchasing has one or more processors, and memory storing one or more programs to be executed by the one or more processors.
  • the one or more programs include instructions for detecting commercial intent from a user of the computer system. In response to detecting commercial intent, the one or more programs include instructions for determining a product relevant to a user.
  • the one or more programs include instructions for sending a recommendation message to the user, wherein the recommendation message includes an option to purchase the product.
  • the one or more programs include instructions for receiving a response message from the user, the message including authorization from the user to purchase the recommended product.
  • the one or more programs include instructions for purchasing the recommended product on behalf of the user and delivering the purchased product to the user.
  • a non-transitory computer readable storage medium storing one or more programs configured for execution by a server system.
  • the one or more programs also include instructions for detecting commercial intent from a user of the computer system.
  • the one or more programs include instructions for determining a product relevant to a user.
  • the one or more programs include instructions for sending a recommendation message to the user, wherein the recommendation message includes an option to purchase the product.
  • the one or more programs include instructions for receiving a response message from the user, the message including authorization from the user to purchase the recommended product.
  • the one or more programs include instructions for purchasing the recommended product on behalf of the user and delivering the purchased product to the user.
  • the method is performed on a server system having one or more processors and memory storing one or more programs for execution by the one or more processors.
  • the server system receives a recommendation for a product or service from a first user.
  • the server system determines whether a second user has pre-indicated intent to purchase a product or service in a category of product or service that includes the recommended product or service.
  • the server system then, in accordance with a determination that a second user has pre-indicated intent to purchase a product or service that matches the category of product or service of the recommended product or service, purchases the recommended product on behalf of the user without further input from the user.
  • the server system has one or more processors, and memory storing one or more programs to be executed by the one or more processors.
  • the one or more programs include instructions for receiving a recommendation for a product or service from a first user.
  • the one or more programs include instructions for determining whether a second user has pre-indicated intent to purchase a product or service in a category of product or service that includes the recommended product or service.
  • the one or more programs include instructions for, in accordance with a determination that a second user has pre-indicated intent to purchase a product or service that matches the category of product or service of the recommended product or service, purchasing the recommended product on behalf of the user without further input from the user.
  • a non-transitory computer readable storage medium storing one or more programs configured for execution by a client system.
  • the one or more programs include instructions for receiving a recommendation for a product or service from a first user.
  • the one or more programs include instructions for determining whether a second user has pre-indicated intent to purchase a product or service in a category of product or service that includes the recommended product or service.
  • the one or more programs include instructions for, in accordance with a determination that a second user has pre-indicated intent to purchase a product or service that matches the category of product or service of the recommended product or service, purchasing the recommended product on behalf of the user without further input from the user.
  • the method is performed on a server system having one or more processors and memory storing one or more programs for execution by the one or more processors.
  • the server system receives an indication of intent from a user to purchase a good or service within a specific category.
  • the server system based on the received indication of intent, identifies recommendations from other users of the server system for goods or services which fall within the category indicated by the users.
  • the server system then, based on the recommendations, selecting a specific product or service and purchasing the selected product or service on the user's behalf.
  • a server system for using recommendations to fulfill purchasing intent of a user has one or more processors, and memory storing one or more programs to be executed by the one or more processors.
  • the one or more programs include instructions for receiving an indication of intent from a user to purchase a good or service within a specific category.
  • the one or more programs include instructions for, based on the received indication of intent, identifying recommendations from other users of the server system for goods or services which fall within the category indicated by the users.
  • the one or more programs include instructions for based on the recommendations, selecting a specific product or service and purchasing the selected product or service on the user's behalf.
  • a non-transitory computer readable storage medium storing one or more programs configured for execution by a server system.
  • the one or more programs also include instructions for receiving an indication of intent from a user to purchase a good or service within a specific category.
  • the one or more programs include instructions for, based on the received indication of intent, identifying recommendations from other users of the server system for goods or services which fall within the category indicated by the users.
  • the one or more programs further include instructions for, based on the recommendations, selecting a specific product or service and purchasing the selected product or service on the user's behalf.
  • Figure 1 is a block diagram illustrating a client-server environment in accordance with some implementations.
  • Figure 2 is a block diagram illustrating a client system in accordance with some implementations.
  • Figure 3 is a block diagram illustrating a server system in accordance with some implementations.
  • Figure 4 depicts a block diagram of an exemplary data structure for a user profile database for storing information related to users of the server system.
  • Figure 5 is a flow diagram illustrating the process for clickless purchasing in accordance with some implementations.
  • Figure 6 is a flow diagram illustrating the process for using recommendations to fulfill pre-established intent in accordance with some implementations.
  • Figure 7 is a flow diagram illustrating the process for responding to commercial intent from a user in accordance with some implementations.
  • a server system operates a commerce system for allowing users to easily and quickly find and purchase goods and services that meet their specific needs and desires.
  • the commerce system is available online via a web site.
  • the commerce system operated by the server system leverages user relationships to improve user experience and personalize
  • the online commerce system improves the user purchasing experience by expanding the methods available to the users of the online commerce system to make purchasing decisions.
  • users of the online commerce system visit a web site operated by the online commerce system as an e-commerce portal. Users log onto the system, select products for purchase, and pay for their purchases via a web form.
  • the online commerce system allows registered users to make purchasing decisions without having to visit the web site associated with the online commerce system at the time of purchase.
  • click free or zero click
  • the terms zero click, clickless, click- less, and click free are used within the specification to indicate that the user is not required to click for the system to purchase a product or service on behalf of the user. These terms (zero click, clickless, and click free) are used interchangeably.
  • This application will refer to determining commercial intent and establishing purchasing intent. It should be noted that commercial intent differs from purchasing intent. Commercial intent is determined by the server system based on based on existing information the server system has gathered about the user but not based on a user's explicitly indicated intent to purchase an item. Once the user has explicitly indicated intent to purchase an item, the user has established purchasing intent. Thus, purchasing intent is intent to purchase a product or service that has been explicitly communicated from a user to the server system, either for immediate purchase request or for storage as pre-established purchasing intent.
  • the server system stores interest information for users registered with the online commerce system.
  • the interest information is stored in a user interest profile.
  • the interest information includes information detailing products and services that the user has indicated a current interest in purchasing, as well as previous purchases, recommendations, and information describing the trust relationships that the user has with other users of the server system.
  • the server system sends a recommendation message to a user that includes a recommendation to purchase a specific product.
  • This message can be sent through the online commerce website, over email, by text message (SMS), by voice mail, through a social networking service (such as Facebook or Twitter), or any other communication method.
  • SMS text message
  • social networking service such as Facebook or Twitter
  • the server system sends a text message including a recommendation to user A for a pair of men's athletic shoes.
  • the message includes all necessary information about the product to allow the user to make an informed decision, including but not limited to price, product specifications (size, color), brand, delivery options, payment options, or any other information stored in the product database.
  • the message includes only basic information about the product such as price and product specifications, and provides a link or other directions that allow the user to access more detailed information.
  • the request includes the user's request for a specific recommender or recommending group. For example, the user submits a request for a recommendation for shoes, but specifically includes instructions that the recommendation be made by a specific friend (Megan). The system then requests that Megan make a shoe recommendation.
  • the requested recommender is mandatory (i.e. the user will only accept recommendations for that user or group of users). In other implementations, the requested recommender is preferred by not mandatory.
  • recommendations made by a user of the server system have a corresponding strength. For example, a user submitting a recommendation chooses a value from 1 to 5, 5 being the strongest possible recommendation and 1 being the weakest possible recommendation. Strong recommendations (those with a high recommendation value) are more likely to be transmitted to a user than weaker
  • the user requests recommendations from the server system.
  • the requests can be sent to the server system by any communication method.
  • a user can send an email to the server system requesting recommendations for men's shoes.
  • the request sent by the user includes additional information, such as budget information, product specification, delivery options, and payment directions.
  • the request sent to the server system includes natural language.
  • a message sent to the server system could include the request "I'd like to buy some black formal men's shoes for less than $200.”
  • the server system parses the natural language to determine the user request.
  • the user responds to the recommendation message received from the server system through a response message.
  • the user responds message is sent using the same communication method that was used to send the recommendation message. For example, if the recommendation message from the server system was sent as a text message, the user may respond with a text message. In other implementations, the user responds to a recommendation message using a different communication method than was used to send the recommendation message. For example, if the recommendation message is delivered to the user via a voice message, the user may chose to respond via a text message, especially if he or she is in a place where speaking on the phone would be undesirable. In another example, the recommendation message is delivered as a text message, but the user logs onto the commerce website and responds using the sites internal message system. This may allow the user to see more details before deciding how to respond.
  • the recommendation message includes a unique recommendation code that allows the user to respond to the specific recommendation message through any medium simply by including the correct recommendation code.
  • a recommendation voicemail includes a unique recommendation code. If the user wants to respond to that recommendation message via text, he or she can include the unique recommendation code in the text message to specify the recommendation to which the user is responding. This will prevent errors caused by incorrectly identifying the recommendation message to which the user is responding.
  • the server system stores contact information for each user registered with the server system. In some implementations, the contact information is stored in a user profile associated with the user.
  • Contact information for a respective user includes a list of approved methods for communicating with that respective user based on information submitted by the user and well as the address, number, or ID needed to contact the user through that method.
  • the contact information for User A includes an email address, a phone number, an instant messaging service ID number, and physical address, and a commerce web site identification number.
  • a user contacts the server system though a communication method or account that the user has not previously submitted to the server system.
  • the server system stores contact information for the user that the user has not explicitly submitted, but will only use this information to associate incoming messages with the appropriate user, unless the user explicitly authorizes the server system to communicate through the new communication method or account.
  • the server system determines the best mode of communication from the stored contact information and stored user preferences. For example, the user might indicate that text messaging is the best mode of communication for reaching the user on weekends. Thus, the server system selects a text message to deliver the recommendation message on a Saturday.
  • the server system can check to determine if the user is currently logged onto one of the social media accounts of the user and then can use a communication method associated with that social media account to transmit a message to the user.
  • the server system then sends the recommendation message over the determined mode of communication.
  • the recommendation message sent by the server system includes a notification that the recommendation will expire after a certain amount of time. For example, the
  • recommendation may include a sale price for a product that will no longer be available after a certain time or that the product will be sold out and the server system will only reserve a product for a limited amount of time.
  • the server system determines that the user did not want the recommended item.
  • a user's profile is updated to include information on the products or services that the user either did not respond to or responded with a decision not to purchase.
  • the server system receives a response to a recommendation message.
  • the server system first identifies the user from whom the response is received by the source of the message (email address, phone number, etc), a unique user identification code included in the response, or the unique recommendation code included in the response.
  • the server system analyzes the received response to determine if the user desires to purchase the recommended product or service.
  • the user indicates that the server system should purchase the recommended product by including a simple predetermined text or oral directive such as "Buy,” “Yes,” or “Purchase.”
  • the server system specifically designates the specific written or oral phrases that it accepts as indicating a desire to purchase.
  • the approval options are specifically designated in the recommendation message.
  • the user is able to customize his or her own approval messages.
  • the received response includes a secret personal identification number (PIN) to ensure that the response actually comes from the registered user to whom the recommendation message was sent.
  • the response message must also include the unique recommendation code to ensure that the server system identifies the correct recommendation message to which the response message corresponds.
  • the response message also identifies the method of payment the user wishes to use.
  • a user's profile includes information detailing the user's default method of payment (e.g. a credit card on file) that is to be used when no payment method is explicitly listed.
  • the server system collects payment information from the user prior to sending any recommendations to the user and then uses the received payment information in all transactions until notified to do otherwise by the user.
  • the server system purchases the recommended product on behalf of the user.
  • users can respond to a recommendation message by whatever communication method is currently convenient without having to follow the purchase procedure typical of modern commerce websites. For example, during a holiday shopping season, a retailer temporarily marks down a popular product in limited quantity. These products often sell out quickly, and thus become unavailable to users who do not constantly monitor the retailer's sales.
  • the server system can quickly send a recommendation message to the user via any communication method that the user has registered with the server system (text, e-mail, twitter messages, telephone calls) and the user can conveniently respond in time to claim the desired product at the reduced sales price from wherever they are.
  • the server system receives an indication of intent to purchase a particular good or service from a user of the server system.
  • the server system stores that indication of intent.
  • the indication of intent specifies a particular product.
  • the indication of intent only specifies a class or category of product or service.
  • the indication of intent specifies a maximum budget for the purchase.
  • a user profile includes a total budget for all purchases made but particular indications of intent do not have specific budgets.
  • the server system itself stores a particular amount of currency from which purchases may be made.
  • the user and the indication of intent do not have a maximum budget.
  • the indication of intent is a message from the user to the server system describing a product the user wishes to purchase.
  • the server system may receive a text message from a user indicating the user wants to buy a copy of "Breaking Bad Season 1.”
  • the sent indication uses natural language. For example, an indication of intent may read "Looking to buy season 1 of Breaking Bad.” The server system parses the natural language request and responds accordingly.
  • the server system does not receive a direct request from a user, but infers commercial intent from information available to the server system.
  • the server system can infer commercial intent from publicly available social media data. For example, if the user has associated their twitter account with their user profile, the server system can monitor twitter messages by the user. If a message reads "Oh no! just broke my headphones. I loved those things ⁇ .” The server system infers that the user is now looking to purchase new headphones. The server system can then request recommendations in the "headphones" category to be sent to the user.
  • commercial intent is inferred from a user's search and browsing history.
  • the server system when the server system detects commercial intent in natural language, the server system must process the text of the commercial intent to determine a matching product or category of product.
  • the server system can use any appropriate matching algorithm to find an appropriate match.
  • the server system employs a matching system with fixed hierarchical product category taxonomy and then tries to match the text (e.g., natural language text) with one of the predefined categories.
  • the server system uses a more flexible system. Rather than defining strict predefined categories, the server system defines rules or algorithms for determining doing this will all look like statistical estimates of similarity (e.g., a very simple example is calculating the Levenstein distance between two strings). It should be noted that even though two types of algorithms have been listed, any suitable algorithm will work.
  • the server system includes a hierarchical product category taxonomy that includes all possible product categories and stores their relationship to each other. For example, music is a broad category and country music and rap music are narrower sub categories within the hierarchical taxonomy. In other implementations, the system does not include a hierarchical product category taxonomy.
  • the server system when the server system detects commercial intent or receives purchasing intent, the server system matches the commercial intent or the purchasing intent to one or more products stored in a product database. This matching can be
  • the server system uses intent includes a category of product.
  • the category is explicitly included by the user when they send the purchasing intent. For example, the user can explicitly request a book in the category "Thrillers.”
  • the user submits a request that includes natural language rather than explicitly indicating a particular product category.
  • the server system parses the natural language request to determine one or more product categories that are associated with the request. For example, a user request for "noise-canceling headphones" can be parsed and several categories, such as "Electronics,” “Music,” or “Office/Productivity" are associated with the natural language request.
  • the server system chooses one as the most preventatives category. In other implementations, the server system uses each category separately and then compares the results to find products exist in the potential match list of all of the categories. In yet other implementations, the server system uses all the categories at once to find the product that best matches all the associated categories. In some implementations, once the server system has determined one or more categories associated with a purchasing or commercial intent, the server system uses the one or more product categories to identify relevant products.
  • the category can be of any level within the hierarchical category taxonomy. In some
  • the detected or received intent specifies a very broad category of product (e.g., men's shoes). In other implementations, the detected or received intent specifies a narrow category of product (e.g. men's running shoe size 12 with a built in pedometer).
  • the server system includes a hierarchical category taxonomy that includes all possible product categories and stories them to each other. In some
  • the received or detected intent specifies a particular product, but allows the server system to choose the specific product options.
  • the intent specifies an iPod but not the model, capacity, or price.
  • the server system then chooses the best product based on the stored user information.
  • the server system uses a flexible statistical matching algorithm. In this case there are no predetermined categories. Instead, each new request is converted into a new bucket, and a statistical measure of its distance from other buckets is determined user statistical estimates of similarity / distance using n-dimensional math within infinite or pseudo-infinite semantic spaces. Once the distances are calculated, the server system selects one or more close products or categories.
  • the received indication of intent to purchase includes a list of product characteristics. For example, if the server system receives an indication of intent to purchase a woman's evening dress, the indication of intent may specify size, color, or any other characteristic of the product.
  • the server system determines whether any products or recommendations for products currently stored by the server system match or satisfy the specific purchasing intent indicated by the user. In accordance with a determination that a product or recommendation for a product matches or satisfies the received indication of purchasing intent, the server system purchases the product on behalf of the user. In some implementations, the server system purchases the product without any additional user intervention. For example, if the server system receives an indication from a user that the user intends to purchase a pair of running shoes for between $85 and $150 in men's size 12 in red, the server system determines whether any product or recommendation stored at the server system matches those specifications. If a pair of red running shoes in size 12 in men's sizes for between $85 and $150 is found, the server system then purchases the shoes for the user.
  • the user can specify that the server system does not need to locate an exact match.
  • the user can specify which aspects of the product are required and which are only preferred.
  • the user can specify specific alternatives. For example, a user requests a pair of shoes and specifies a price range, a size, and a color. The user indicates that the indicated price range and the size of the shoes are required to match exactly, but that the color is only preferred and thus an exact match for color is not necessary.
  • the user lists black, dark grey, and dark brown. The server system then only needs to find shoes that match one of the listed colors.
  • the server system itself is able to determine suitable alternative products. In some implementations, if the server system cannot find a matching product, it will find the best possible match (i.e. the most number of attributes matching the desired product) and send a recommendation to the user. The user can then decide whether the recommended product is acceptable and respond accordingly.
  • the server system can solicit new recommendations from users.
  • the server system selects one or more users in a first tier of potential recommenders.
  • the first tier of users is selected based on social connections and recorded trust levels with the requesting user. In this way, the most trust recommenders are the first users to have the opportunity to submit a recommendation.
  • the server system also factors in the success of previous
  • the server system would then select User C in the first tier rather than User B.
  • the server system sends a request for recommendations to each user in the first tier of users. In some implementations, the server system waits a predefined amount of time and, if no
  • the server system sends
  • the server system when the server system determines that no currently stored product or user-generated recommendation meets the requirements of the received indication of purchasing intent, the server system stores the indication of purchasing intent in a database for future use.
  • a received indication of purchasing intent includes a deadline or period of time after which the purchasing intent is no longer valid.
  • the server system retains the indication of purchasing intent for future use, but marks it as currently inactive, so that no purchases will be made on the basis of the saved purchasing intent.
  • the server system removes the indication of purchasing intent from the server system.
  • the server system when the server system receives a recommendation from a user of the server system, the server system determines whether the recommendation matches any active, stored indication of purchasing intent that has not been fulfilled. In some implementations, the server system determines that the received recommendation does not match any active, stored indication of purchasing intent. In this case the server system stores the recommendation in a database for use in fulfilling future received indications of purchasing intent.
  • the server system determines that the received recommendation matches a stored indication of purchasing intent, and in response, the server system determines whether to purchase the recommended product or service on behalf of the user who has submitted the indication of purchasing intent. In some implementations, the server system determines whether to purchase the recommended product based on social relationships between the recommending user and the user who submitted the indication of purchasing intent. For example, in some cases the server system only purchases
  • the server system only purchases products on behalf of a first user when the recommending second user is in the first user's social circle.
  • the server system maintains information describing trust relationships between users and only purchases products on behalf of a first user when the server system has trust information indicating a trust relationship between the first user and the recommending second user.
  • the server system only purchases a product or service if the trust level between the first user and the recommending second user is above a predetermined level. For example, the server system determines that an mp3 player recommended by user Bob matches user Alice's stored indication of purchasing intent. The server system then determines that Alice's user profile includes trust information for Bob. The server system then determines whether the stored value representing Alice's trust for Bob exceeds a predetermined level of trust. If so, the server system purchases the recommended mp3 player on Alice's behalf.
  • users of the server system designate customized purchase conditions under which the server system should automatically purchase a recommended product that matches a pre-established intent to purchase.
  • customized purchase conditions are customized for each stored pre- established intent record received by the server system.
  • the customized purchase conditions apply to all stored pre-established intent to purchase record.
  • Customizable factors include the level of trust between the two parties, the number of connections between the recommender and the purchaser on a graph of the social network associated with the site, whether the current price/product is time limited, among other factors.
  • a user can pre-establish intent to purchase all the recommendations from a particular user. In other implementations, a user can pre-establish intent to purchase all products in a specific product type that are recommended by a specific group of people.
  • a user can establish a recurring request, such that the server system automatically sends a recommendation for a particular product or service on a recurring schedule, without further action with the user.
  • the user is able to receive new recommendations in a particular category without having to submit a new request each time.
  • a user can request to get a new recommendation for a suspense novel each month.
  • a user can similarly request that a particular product or category of product be purchased automatically on a recurring schedule. For example, a user can arrange to have fresh fruit purchased and delivered once a week.
  • the server system is unable to find a product within a user's budget that matches a stored pre-established intent to purchase a product. In this case, if a matching product is available, but at a price above the user's budgeted price, the server system can then transmit an offer to purchase the product at a price within the user's budget to the appropriate vendor. The vendor can then accept or refuse the offered price. If the vender accepts, the server system can then purchase the product at the offered price.
  • FIG. 1 is a block diagram illustrating a client-server environment 100 in accordance with some implementations.
  • the client-server environment 100 includes one or more client systems 102-1 and 102-2, a server system 120, and one or more vendors 160, all connected over a network 110.
  • the client system 102 includes one or more client applications 104 and a display 106.
  • the server system 120 includes a communication module 122, a recommendation module 124, a data analysis module 126, a purchasing module 128, a product comparison module 130, a product database 140, a recommendation database 142, and a user profile database 150.
  • the network 110 may consist of any one or more of any of a variety of networks, including local area networks (LAN), wide area networks (WAN), wireless networks, wired networks, the Internet, or any combination of such networks.
  • the client system 102 includes one or more client applications 104.
  • the one or more client applications 104 include, but are not limited to, a web browsing application for connecting to the server system 120.
  • the client system 102 also includes a display 106.
  • the client system is a computing device with the display integrated directly the device itself, such as a laptop, a smart phone, and a tablet computer.
  • the display is connected to, but not integrated into the client system. For example, desktop computer systems often do not have an integrated display and instead connect to a standalone display.
  • the client system 102 receives a recommendation
  • the recommendation 116 includes information identifying a recommended product or service, details further explaining the product or service, a recommendation identifier that uniquely identifies this recommendation, and, optionally, a time limit for the recommendation.
  • the recommendation is received over any viable communication medium.
  • the recommendation message can be transmitted via e-mail, text, voice mail, social media message, an instant message, a message through a messaging service internal to the server system, or through the messaging service of another web service or web site.
  • the client system 102 responds to the recommendation 116 by sending a response message 118 to the server system 120.
  • the response message 118 is returned to the sever system 120 via the same communication method that was used to send the recommendation 116. For example, if the recommendation 116 was received through an email message, the client system then uses the email messaging system to send a response message 118.
  • the client system 102 user a different communication method to send a response message 118.
  • the recommendation 116 is sent as an instant message through a chat program. Instead of responding through the chat program, the user sends a response message via an email.
  • the response message 118 includes an identifier for the recommendation message 116 received by the client system 102, an identifier for the user of the client system 102, and an indication indicating whether the user wishes to purchase the recommended product or service.
  • the response message 118 does not include an identifier for the user and the server system 120 determines the identity of the user based on the metadata associated with the response message 118.
  • the server system 120 can determine the user's identity based on the email address or telephone number associated with the response message 118.
  • the indication indicating the user's intent to buy is a text string such as "Yes" or "Buy.” In other
  • the user indicates permission to purchase the recommended product or service by including a secret personal identification code (PIN) that is known only to the user.
  • PIN personal identification code
  • the response message 118 also includes information identifying the users preferred method of payment.
  • the response message 118 is encrypted.
  • the client system 102 transmits an indication of purchasing intent 114 to the server system 120.
  • An indication of purchasing intent 114 is information transferred to the server system 120 that includes a product or category of product (or a service or category of service) the user wishes to purchase.
  • the product is as specific as the book “Ready Player One” or as broad as “Jeans” or "Online data backup service.”
  • the indication of purchasing intent 114 includes information further refining the desired product or service.
  • an indication of purchasing intent 114 could include the price of the product, brands or vendors favored by the user, colors, styles, size of the product, options included with the product, quantity of the product available, material used to fabricate the product, the number of units, the pattern of the product design, whether the product is local, the level of service associated with the product, whether the vender allows custom modifications, whether the vendor allows special requests of any kind, whether the product comes with a warranty, the assembly status of the product (for example, pre-assembled, partially assembled, or unassembled), the artist or maker associated with the product, the format of the product, or the version of the product, whether the price of the product has been reduced as part of a sale, whether the product has been discontinued,, a specific time frame, a discount percentage, a material, an average review score on a review website such as MetaCritic, or any other feature of a product or service.
  • the each product in the product database includes some or all of the information listed above.
  • the indication of purchasing intent is a
  • the server system 120 attempts to find a product or service that matches the requested features. Once a matching product is found, the server system 120 purchases the product and arranges for delivery to the user of the client system 102.
  • the server system 120 includes a communication module 122, a recommendation module 124, a data analysis module 126, a purchasing module 128, a product comparison module 130, a product database 140, a recommendation database 142, and a user profile database 150.
  • the communication module is configured to send and receive communications over the network 110 to one or more client systems 102 and one or more vendors 160.
  • the communication module 122 handles all communication with the one or more client systems 102. In some implementations, the communication module 122 handles all communication with the one or more client systems 102. In some
  • the communication module 122 receives a recommendation 116 from the recommendation module 124 to send to a client system 102. In some implementations, the communication module 122 is able to use one or more of several different communication methods to transmit the recommendation 116 to the client system 102.
  • the server system 120 stores contact information for each user in the user profile database 150.
  • the communication module 122 determines the communication method based on past communications with the user of the client system. Thus, the communication module 122 chooses the communication method that the user of the client system 102 uses most often when communicating with the server system. For example, if a user communicates with the server system 120 through email in 75% of communications, the server system 120 will use an email messaging system to deliver recommendations 116 to the user.
  • each user selects a preferred communication method and this preference is stored in the user profile database 150. For example, a user selects text messaging as the preferred method for receiving messages and in response the
  • the communication module 122 will then use text messages to send recommendations 116 to the user, unless directed otherwise. In some implementations, the communication module 122 will use multiple communication methods to send recommendations to the user.
  • the communication module 122 chooses the communication method based on the time and date that the recommendation is to be sent. For example, the communication module 122 uses email messages to deliver
  • each user selects time and data preferences for the communication module 122 to use and these preferences are stored in the user profile database 150.
  • the communication module 122 receives response messages 118 from client systems 102.
  • each response message 118 is transmitted to the data analysis module 126.
  • each response message 118 is transmitted to the recommendation module 124 before it is transmitted to the data analysis module 126.
  • a copy of the response message 118 is transmitted to both the recommendation module 124 and the data analysis module 126.
  • the communication module 122 receives an indication of purchasing intent 114 from a client system 102.
  • the communication module 122 transmits the indication of purchasing intent 114 to the recommendation module 124.
  • the recommendation module 124 is configured to transmit recommendations 116 to the client system 102.
  • the recommendation module 124 determines which recommendations 116 to send to a user of a client system 102 based on known user interests, currently popular products, products chosen by editors and content customizers associated with the server system 120, and products or services recommended and/or purchased by other users of the server system 120.
  • the server system 120 is more likely to recommend products to a first user that have been recommended and/or purchased by users who are socially connected to the first user. For example, if Bob's profile lists Frank as a friend, and Frank recommends a men's wear product, the server system 120 will be more likely transmit that recommendation to Bob than user Alan, whose profile does not identify Frank as a trusted friend.
  • the recommendation module 124 transmits recommendations to the communication module 122 to be sent to the client system 102 over a network 110.
  • the recommendation module 124 receives response messages 118 from client systems 102 through the communication module 122.
  • the recommendation module 124 identifies the recommendation message 116 to which the response message 118 corresponds.
  • the recommendation module 124 transmits the response message 118 to the data analysis module 126.
  • the recommendation module 124 receives an indication of purchasing intent 114 from the communication module 122.
  • An indication of purchasing intent 114 includes, at the very least, information describing a product, a category of product, a service, or a category of service that a user associated a client system 102 wants to purchase.
  • the recommendation module 124 determines whether any products in the product database 140 or the recommendation database 142 match the product or service described in the indication of purchasing intent 114. In accordance with a determination that a product in the product database 140 or the recommendation database 142 matches the product or server described in the indication of purchasing intent 114, the recommendation module 124 transmits the indication of purchasing intent 114 and the information identifying the determined matching product or service to the purchasing module 128 for purchase.
  • the recommendation module 124 transmits the indication of purchasing intent 114 to the product comparison module 130. For example, if a user sends an indication of intent to purchase 114 a 128 GB solid state drive for $80 or less to the server system 120, the recommendation module 124 checks to see if any matching product is listed in the products database 140 or the recommendation database 142. If so, the purchasing module 128 purchases the product on behalf of the user of the client system 102.
  • the data analysis module 126 determines the identity of the user who sent the response message 118.
  • the identity of the user can be determined by determining the communication method used to transmit the message and identifying message related metadata associated with the user.
  • the metadata is a phone number, a source email address, an instant messaging ID, or other identifying metadata associated with the response message.
  • the server system 120 then matches the identified message related metadata to metadata stored for users in the user profile database 150. For example, a response message 118 received via email will have an associated source email address. The server system 120 compares the source email address against email addresses stored in the user profile database 150 and associated with specific users. When the server system 120 determines that the source email address matches an email associated with a respective user, the server system 120 is able to determine that the response message 118 is from the respective user.
  • the response message 118 includes a user identification number that identifies the user that sent the response message 118.
  • the response message may also include a secret personal identification number (PIN) that allows the data analysis module 126 to firmly establish the identity of the user who sent the response message 118.
  • PIN personal identification number
  • each recommendation has a unique recommendation code that can be used to identify the user without additional information. In other implementation, multiple users all receive the same recommendation with the same recommendation code and the data analysis module 126 relies on user ID information to identify the user.
  • the data analysis module 126 determines what action should be taken in response to receiving the response message 118.
  • the data analysis module 126 determines whether the response message 118 includes a textual indication of the user's intent (e.g. the word "Buy").
  • the user customizes the response needed to trigger a purchase decision. For example, a user can customize the service provided by the server system 120 by establishing that a valid purchase request will include the word "coconut.” This allows the user to choose a confirmation method most convenient to the user and affords an additional layer of security.
  • the purchasing module 128 is configured to receive a response message 118 from a client system 102 indicating intent to purchase a product. In some implementations, the purchasing module 128 receives this message from the communication module 122. In some implementations, the purchasing module 128 receives this response message 118 from the data analysis module 126. Based on the received message, the purchasing module 128 determines the product to be purchased. In some implementations, the purchasing module 128 selects a vendor to supply the product to be purchased. In some implementations, each product is only available from a single vendor. In other implementations, the products database 140 lists multiple possible vendors for each product. The purchasing module 128 compares prices and delivery options.
  • the purchasing module 128 then enlists the communication module 122 to purchase the desired product from the determined vendors 160 available over the network 110.
  • the product comparison module 130 receives an indication of purchasing intent 114 from the recommendation module 124. In some implementations, the product comparison module 130 analyzes the information included in the indication of purchasing intent 114 and determines acceptable alternatives to the requested item. In some implementations, acceptable alternatives are determined by allowing a percentage variance from the requested value. For example, if the indication of purchasing intent lists a 23 inch monitor for less than $200, the product comparison module 130 determines that a 22 inch monitor for less than $150 or a 24 inch monitor for less than $250 are reasonable alternatives. In some implementations, for qualities of a product that cannot be measure numerically, like color, the product comparison module 130 stores lists of common acceptable alternatives. For example, for the color red, the product comparison module 130 lists vermillion, rose, and maroon as alternatives.
  • the product comparison module 130 sends the alternatives to the recommendation module 130 to be sent to users as recommendations 116. If no alternatives can be found, or the user rejects the suggested alternatives, the indication of purchasing intent 114 is stored in the user profile database 150 as pre-established intent data 152.
  • the product comparison module 130 determines whether the user-generated recommendations are received by the recommendation module 124 and are stored in the recommendation database 142.
  • the product comparison module 130 determines whether the newly added product matches any pre-established intent data 152. In accordance with a determination that a new user-generated recommendation or product matches stored pre-established intent data 152, the product comparison module 130 sends the pre-established intent data and the matching product or recommendation data to the purchasing module 128 for purchase.
  • the product database 140 contains information for products that may be purchased through the server system 120. In some implementations the products in the product database 140 are added by partner vendors 160. In some
  • the products in the database 140 are added by users and recommenders in the server system 120.
  • the products database 140 includes information for each product, including, but not limited to, the price of the product, its specification (size, color, etc), the vendor or vendors from which it is available, whether the item is in stock, and whether it is available for delivery.
  • the client system 102 sends a response message 116 to the server system 120 and the purchasing module 128 uses the information stored in the product database 140 to purchase the selected product.
  • the product database 140 searches websites of vendors, or other databases maintained by vendors that are available over a network 110, for the desired product. The product database 140 then determines which vendor offers the most favorable terms (e.g. price, delivery, in stock) and purchases the product.
  • the recommendation database 142 stores
  • the recommendation database 142 maintains a list of all recommendations ever made by any users of the database, how successful those recommendations were (what percentage of users purchased the recommended product when given this recommendation), whether the user who recommended the product purchased the product, and information concerning the request for recommendation that prompted the recommendation. In other implementations, only a portion of total recommendations are retained in the recommendation database 142 at any given time, based on, among other factors, how long ago the recommendation was made, whether the product is still available, the trustworthiness of the recommending user, and how popular the recommendation has been.
  • the user profile database 150 contains user profiles for users who have registered to use the service provided by the server system 120.
  • a user profile includes the name, ID, demographic information (gender, age, location, etc), purchasing history, social network information (including username and passwords for one or more social networking sites), and trust information.
  • the user profile includes contact information submitted by the user or stored by the system after contact by the user including but not limited to email addresses, phone numbers, user names, instant message user IDs, and social networking sites user information sufficient to allow the service to access each of the user's social networking sites.
  • the communication module 122 uses information stored in the user profile database 150 to send recommendation messages 116 to the client system 102.
  • the user profile database 150 includes pre- established intent data 152.
  • Pre-established intent data 152 includes products and/or services that a user has previously indicated a desire to purchase.
  • Pre-established intent data includes the product, service, or category of product or service that the user desires to purchase.
  • the pre-established intent data also includes a budget for each particular product or service and/or a budget for all purchases.
  • the pre-established intent data 152 if the pre-established intent data 152 includes a budget for all items combined, the pre- established intent data 152 also includes priority data for each item to allow prioritizing of the purchases.
  • a user's budget is fixed for a given time period and resets at the beginning of each time period. For example, a user may set a budget of $100 a month and then the budget will reset back to $100 at the beginning at each month, regardless of how much of the budget was used in the last month.
  • the vendors 160 are commercial organizations with products to sell.
  • the vendors 160 can receive orders to purchase products from the server system 120 and fulfill those orders.
  • FIG. 2 is a block diagram illustrating a client system 102, in accordance with some implementations.
  • the client system 102 typically includes one or more processing units (CPU's) 202, one or more network interfaces 210, memory 212, and one or more communication buses 214 for interconnecting these components.
  • the client system 102 includes a user interface 204.
  • the user interface 204 includes an associated display device 104 and optionally includes an input means such as a keyboard, mouse, a touch sensitive display, or other input buttons 208.
  • the display device 106 includes an audio device or other information delivery device.
  • some client systems use a microphone and voice recognition to supplement or replace the keyboard.
  • Memory 212 includes high-speed random access memory, such as DRAM,
  • Memory 212 may optionally include one or more storage devices remotely located from the CPU(s) 202. Memory 212, or alternately the non- volatile memory device(s) within memory 212, includes a non-transitory computer readable storage medium. In some implementations, memory 212 or the computer readable storage medium of memory 212 stores the following programs, modules and data structures, or a subset thereof:
  • an operating system 216 that includes procedures for handling various basic system services and for performing hardware dependent tasks
  • a network communication module 218 that is used for connecting the client system 102 to other computers via the one or more communication network interfaces 210 (wired or wireless) and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, and so on;
  • a display module 220 for enabling display of media content on a display 106
  • a browser application 224 for sending indications of purchasing intent to a server system ( Figure 1, 120) and displaying the information (for example web pages) returned by the server system ( Figure 1, 120) or a smart phone or other computer system application that performs the same function; o a recommendation module 226 for enabling a user to send a request for a
  • FIG. 3 is a block diagram illustrating a server system 120, in accordance with some implementations.
  • the server system 120 typically includes one or more processing units (CPU's) 302, one or more network interfaces 304, memory 306, and one or more communication buses 308 for interconnecting these components.
  • CPU's processing units
  • network interfaces 304
  • memory 306
  • communication buses 308 for interconnecting these components.
  • Memory 306 includes high-speed random access memory, such as DRAM,
  • Memory 306 may optionally include one or more storage devices remotely located from the CPU(s) 302. Memory 306, or alternately the non-volatile memory device(s) within memory 306, includes a non-transitory computer readable storage medium. In some implementations, memory 306 or the computer readable storage medium of memory 306 stores the following programs, modules and data structures, or a subset thereof:
  • an operating system 310 that includes procedures for handling various basic system services and for performing hardware dependent tasks
  • a network communication module 122 that is used for connecting the server system 120 to other computers via the one or more communication network interfaces 304 (wired or wireless) and one or more communication networks, such as the Internet, other wide area networks, local area networks, metropolitan area networks, and so on;
  • server application module(s) 314 for enabling the server system 120 to perform the functions offered by the server system 120, including but not limited to: o a recommendation module 124 for determining recommendations to send to a client system ( Figure 1, 102), sending the recommendation, and receiving response messages (Figure 1, 118) from client systems ( Figure 1, 102); o a data analysis module 126 for analyzing the text of a response message
  • a purchasing decision module 128 for receiving a response message 118 from a client system ( Figure 1, 102) that indicates a user's intention to purchase a good or service through the server system ( Figure 1, 120) and for purchasing the good or service from one of the vendors ( Figure 1, 160); and o a product comparison module 130 for comparing products stored in the product database ( Figure 1, 140) and products stored as recommendations in the recommendation database 142 to determine if they are equivalent to a received indication of purchasing intent 114 or stored pre-established intent data; and
  • server data module(s) 330 for storing data related to the server system 120, including but not limited to: o user profile information database 150 including user preferences and interests, user contact information, and user history, including past user purchases, searches, page views, previous product recommendations, previous product reviews, social connections of the user, and any other information ;related to the user; o pre-established intent data 152 including information describing, for each user of the server system 120, products and services that they have previously indicated an intent to purchase but that have not yet been purchased by the server system 12 on the user's behalf, and other information associated with the stored intent, such as budgets and time tables; o product information 140 including information for products that may be
  • ⁇ recommendation information 142 including a plurality of stored user- generated recommendations, the recommended products, where and how those products can be purchased, and product specifications.
  • Figure 4 depicts a block diagram of an exemplary data structure for a user profile database 150 for storing information related to users of the server system ( Figure 1, 120).
  • the user profile database 150 includes a plurality of user profiles 402-1 to 402-P, each of which corresponds to a user registered with the server system ( Figure 1, 120).
  • each user profile 402 contains a user profile ID 404, a user history 406, trust information 408, recommendations 410 made by the user, user contact information 412, and pre-established intent data 152.
  • user profile ID 404 is a value that uniquely identifies a specific user of the server system ( Figure 1, 120). In some implementations, this value is chosen by the user and is a user name. In other implementations, this value is assigned to the user by the server system ( Figure 1, 120) as part of the registration process.
  • the user history 406 stores a history of the user's past interactions with the server system ( Figure 1, 120) including past user purchases, searches, page views, previous product recommendations, previous product reviews, and social connections of the user including previously recorded trust information for other users and/or social information received from social networking sites.
  • trust information 408 includes data describing the social connections of the user and includes a trust level for other users of the server system ( Figure 1, 120).
  • a trust level is a value representing the degree to which a user trusts the opinions and recommendations of another user.
  • trust information is explicitly submitted by the users, in other situations the server system ( Figure 1, 120) infers trust information from the actions of users, and in yet other situations trust information includes information from both user submissions and server inferences.
  • recommendation 410 data includes product purchases and product recommendations previously submitted by the user.
  • contact information 412 includes a list of contact information for contacting the user through a plurality of communication methods and information describing if and when the server system ( Figure 1, 120) should use that method.
  • the contact information 412 includes an email address, a phone number, and a social network ID for the user. The user may select that the server system ( Figure 1, 120) should never use social network messaging to contact to user and should use email address at all times except for the weekend and that a text message to a mobile phone should be used on the weekend.
  • the contact information 412 includes login and password information for one or more social networking sites.
  • pre-established intent data 152 is data previously submitted by the user indicating the user's intent to purchase a particular product.
  • the pre-established intent data 142 includes intent ID number 420, product category 422, budget data 424, deadline information 426, and product specifications 428.
  • the intent ID number 420 uniquely identifies each pre-established intent data record 142.
  • the product category 422 identifies the category of product to be purchased.
  • the product category 422 can be very broad, such as men's pants, or very narrow, such as a racquetball racquet.
  • budget data 424 includes an amount of money the user is willing to spend on the product identified by the pre-established intent data 152 record. In some
  • a user profile 150 includes an overall budget for all purchases.
  • the budget data 424 includes priority data to establish which products should be higher priority to purchase given the account budget.
  • the budget data 424 represents a monthly or recurring budget.
  • deadline information 426 determines the time window in which the product can be purchased. In some implementations, there no time limit and the pre-established intent data 152 record is valid until a matching product is found. In some implementations, once the specified deadline has passed, the pre-established intent data record 152 is removed.
  • product specifications 428 include any criteria by which potential products can be distinguished, including the price range specified by the user, brands or vendors favored by the user, colors, styles, size of the product, options included with the product, the amount the price is currently discounted, quantity of the product available, material used to fabricate the product, the number of units, the pattern of the product design, whether the product is local, the level of service associated with the product, whether the vender allows custom modifications, whether the vendor allows special requests of any kind, whether the product comes with a warranty, the assembly status of the product (for example, pre-assembled, partially assembled, or unassembled), the artist or maker associated with the product, the format of the product, or the version of the product, and any other feature or characteristic that the user desires for the requested recommendation.
  • the assembly status of the product for example, pre-assembled, partially assembled, or unassembled
  • the artist or maker associated with the product the format of the product, or the version of the product, and any other feature or characteristic that the user desires for the requested recommendation.
  • the product specifications 428 can include preferences for delivery options such as the speed of delivery, the delivery provider, the delivery service provider, delivery insurance availability, the delivery period, white glove delivery options, in store pick-up options, method of delivery (electronic or physical), the return policy, the pre-order policy, or any other delivery option that may be preferred by a user.
  • the product specifications 428 include gift options such as the availability to ship to multiple addresses, whether the product can be gift- wrapped, whether a gift note or card can be included, and whether a gift receipt is available.
  • one or more of the user preferences 412 can be mandatory features for any recommended product.
  • the product specifications 428 are compared against information stored in the product database, wherein the product database includes the same categories of information as the product specification 428.
  • Figure 5 is a flow diagram illustrating the process for clickless purchasing in accordance with some implementations.
  • Each of the operations shown in Figure 5 may correspond to instructions stored in a computer memory or computer readable storage medium.
  • Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders).
  • the method described in Figure 5 is performed by the server system ( Figure 1, 120).
  • the server system detects commercial intent from a user registered with the server system ( Figure 1 , 120) (512).
  • detecting commercial intent includes recording and analyzing the online actions of a user registered with the server system ( Figure 1, 120), including by not limited to page views, clicks, searches, and n some implementations, information posted publicly on social networking sites and comments posted in general.
  • information posted publicly on social networking sites and comments posted in general includes not limited to page views, clicks, searches, and n some implementations, information posted publicly on social networking sites and comments posted in general.
  • the server system ( Figure 1, 120) only records online actions if the user has explicitly given permission to the server system ( Figure 1, 120) to do so.
  • the server system ( Figure 1, 120) determines a product relevant to a user (502).
  • the relevant product is determined by receiving a user- generated recommendation and matching it to the user's preferences.
  • the relevant product is determined in response to a specific request from the user.
  • a product is determined relevant to a user based on the selection by an editor or product manager associated with the server system ( Figure 1, 120).
  • the server system ( Figure 1, 120) when determining a product relevant to the detected commercial intent, identifies one or more product categories of interest to the user of the server system based on the detected commercial intent (514). For example, if the detected commercial intent is based on the user browsing websites that specialize in selling camping gear, the server system ( Figure 1, 120) determines that identify tents, backpacks, and sleeping bags as relevant product categories. In some implementations, the server system ( Figure 1, 120) selects a product from the one or more product categories of interest to the user of the computer (518). In some implementations, selecting a product from the one or more product categories includes the server system ( Figure 1, 120) determining a plurality of products that match the one or more identified product categories. For example, the server system ( Figure 1, 120) generates a list of camping backpacks, tents, and sleeping bags.
  • the server system ( Figure 1, 120) ranks the plurality of products based on information about the user gathered by the computer system (520). For example, the server system ( Figure 1, 120) uses information concerning the users past browsing and purchasing histories, web searches, recommendations, and any other important information that can be used to evaluate and rank potential products. In some implementations, the server system ( Figure 1, 120) uses information concerning the users past browsing and purchasing histories, web searches, recommendations, and any other important information that can be used to evaluate and rank potential products. In some
  • the server system ( Figure 1, 120) selects the highest ranked product in the plurality as the product relevant to the detected commercial intent 522.
  • the server system ( Figure 1, 120) sends a recommendation message to the user, wherein the recommendation message includes an option to purchase the recommended product (504).
  • the recommendation message is sent as an email message.
  • the recommendation message is sent as a text message.
  • the recommendation message is sent by any method convenient to the user including, but not limited to, a voice mail, an instant message via an instant messaging service, a letter, or a message on a social networking platform such as Facebook or Linkedln.
  • the server system receives a response message from the user, the response message including authorization from the user to purchase the recommended product (506).
  • the response message includes the ID of the user, a value identifying the recommendation to which the user is responding, and an indication that the user wishes to purchase the product.
  • the response message is sent as an email message.
  • the response message is sent as a text message.
  • the response message is sent using a different communication method than the
  • the server system ( Figure 1, 120) sends a
  • recommendation message as a text message.
  • the user sends a response message as an email address, including information that identifies the user, the product to be purchased, and in some implementations, the purchasing method and the delivery method preferences.
  • the sever system in response to receiving the response message, purchases the recommended product on behalf of the user (508). In accordance with some implementations, the server system ( Figure 1, 120) then arranges for the delivery of the purchased product to the user (510).
  • Figure 6 is a flow diagram illustrating the process for using recommendations to fulfill pre-established intent in accordance with some implementations.
  • Each of the operations shown in Figure 6 may correspond to instructions stored in a computer memory or computer readable storage medium.
  • Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders).
  • the method described in Figure 6 is performed by the server system ( Figure 1, 120).
  • the server system ( Figure 1, 120) receives a recommendation for a product or service from a first user (602). In some implementations, the server system ( Figure 1, 120) determines whether a second user has pre- indicated intent to purchase a product or service in a category of product or service that includes the recommended product or service (604). In some implementations, the server system ( Figure 1, 120) stores trust information for both the first user and the second user.
  • the server system ( Figure 1, 120) based on the stored trust data for the second user, determines whether second user has a preexisting trust level for the first user (606). In accordance with some implementations, the server system ( Figure 1, 120), in accordance with a determination that the second user has a pre-existing trust level for the first user, determines whether the trust level exceeds a predefined trust level (608). In accordance with a determination that the trust level from the second user to the first user does not exceed the predefined trust level, the server system ( Figure 1, 120) ignores the recommendation. Thus, in some implementations, the server system ( Figure 1, 120) will only purchase products on behalf of the second user based on recommendations from users the second user trusts. In some implementations, users can indicate trust in specific product categories. Then, the server system ( Figure 1, 120) will only purchase products in a specific category on behalf of the second user based on
  • the server system determines whether the second user has set a budget limit for purchases (612). In some implementations, a separate budget is set for each pre-established purchasing intent record. In other implementations, a user sets a budget for all purchases and ranks pre-established purchasing intent records by priority.
  • each user of the server system ( Figure 1, 120) has an associated list of approved recommenders.
  • the server system ( Figure 1, 120) in accordance with a determination that a budget limit has been set; determines whether the cost of the recommended product or service exceeds the amount remaining in the allotted budget (614). In accordance with a determination that the cost of the recommended product does not exceed the amount remaining in the allotted budget, the server system ( Figure 1, 120) determines whether the recommending first user is on the list of approved recommenders for the second user (616). If the recommending user is on the second users approved recommenders list, the server system ( Figure 1, 120) purchases the recommended product on behalf of the user without further input from the user (616).
  • Figure 7 is a flow diagram illustrating the process for responding to commercial intent from a user in accordance with some implementations.
  • Each of the operations shown in Figure 7 may correspond to instructions stored in a computer memory or computer readable storage medium.
  • Optional operations are indicated by dashed lines (e.g., boxes with dashed-line borders).
  • the method described in Figure 7 is performed by the server system ( Figure 1, 120).
  • the server system ( Figure 1, 120) receives an indication of intent from a user to purchase a good or service within a specific category (702). In some implementations, based on the received indication of intent, the server system ( Figure 1, 120) identifies recommendations from other users of the server system for goods or services that fall within the category indicated by the users (704). In some implementations, the server system ( Figure 1, 120) requests recommendations from other users of the server system ( Figure 1, 120) in response to the received intent to purchase.
  • the indication of intent includes a list of product attributes that describe the product the user desires to purchase. In some implementations, each product attribute has a value associated with the product attribute. For example, if the indication of intent includes a list of attribute values that include size, type, and color, the attributes may have values such a type: men's shoes, size: 12, and color: brown.
  • the server system ( Figure 1, 120) compares the list of the product attributes included in the indication of intent with the product attributes of the products or services included in each recommendation in the plurality of recommendations (708). In some implementations, the server system ( Figure 1, 120) generates a match score for each respective recommendation in the plurality of recommendations based on the comparison of the product attributes included in the indication of intent with the product attributes of the products or services included in each respective recommendation in the plurality of recommendations.
  • the match score represents a measurement of how many of attributes the product or service included in the respective recommendation are also included in the indication of intent and how closely the attributes value match.
  • the server system orders the plurality of recommendations based on the generated match scores (710), such that the highest match score (e.g., the best match) is listed first and the lowest match score (e.g., the worst match) is listed last.
  • the highest match score e.g., the best match
  • the lowest match score e.g., the worst match
  • the server system ( Figure 1, 120) based on the recommendations, selects a specific product or service and purchases the selected product or service on the user's behalf. In some implementations, the server system ( Figure 1, 120) selects the product based on the whether the user who submitted the indication of intent has a recorded trust level for the user who submits the recommendation. In some implementations, the server system ( Figure 1, 120) selects the product or service with the highest generated match score (712). In some implementations, the user has a trust level for more than one submitter, and the server system ( Figure 1, 120) selects the recommendation associated with the submitter that is most trusted by the user.
  • first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another.
  • a first contact could be termed a second contact, and, similarly, a second contact could be termed a first contact, without departing from the scope of the present implementations.
  • the first contact and the second contact are both contacts, but they are not the same contact.
  • the phrase “if it is determined” or “if (a stated condition or event) is detected” may be construed to mean “upon determining” or “in response to determining” or “upon detecting (the stated condition or event)” or “in response to detecting (the stated condition or event),” depending on the context.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Certains modes de réalisation concernent un procédé permettant d'activer un achat sans clic. Le procédé est exécuté sur un système de serveur ayant un ou plusieurs processeurs et une mémoire enregistrant un ou plusieurs programmes à exécuter par le ou les processeurs. Le système du serveur détecte l'intention commerciale d'un utilisateur du système informatique. En réponse à la détection d'une intention commerciale, le système du serveur détermine un produit pertinent pour l'intention commerciale détectée d'un utilisateur. Le système du serveur envoie un message de recommandation à l'utilisateur, le message de recommandation comprenant une option d'achat du produit. Le système du serveur reçoit ensuite un message de réponse de l'utilisateur, le message comprenant l'autorisation de l'utilisateur d'acheter le produit recommandé. Le système du serveur achète ensuite le produit recommandé au nom de l'utilisateur et fournit le produit acheté à l'utilisateur.
PCT/US2013/041705 2012-05-17 2013-05-17 Systèmes de commerce sans clic WO2013173792A1 (fr)

Applications Claiming Priority (30)

Application Number Priority Date Filing Date Title
US201261648578P 2012-05-17 2012-05-17
US201261648591P 2012-05-17 2012-05-17
US201261648582P 2012-05-17 2012-05-17
US201261648564P 2012-05-17 2012-05-17
US201261648566P 2012-05-17 2012-05-17
US201261648588P 2012-05-17 2012-05-17
US61/648,566 2012-05-17
US61/648,564 2012-05-17
US61/648,582 2012-05-17
US61/648,591 2012-05-17
US61/648,588 2012-05-17
US61/648,578 2012-05-17
US201261688655P 2012-05-18 2012-05-18
US61/688,655 2012-05-18
US13/769,181 2013-02-15
US13/769,181 US20130317941A1 (en) 2012-05-17 2013-02-15 Trust Graph
US13/986,606 2013-05-16
US13/896,292 US10740779B2 (en) 2012-05-17 2013-05-16 Pre-establishing purchasing intent for computer based commerce systems
US13/986,612 US20130311337A1 (en) 2012-05-17 2013-05-16 Universal consumption service
US13/896,292 2013-05-16
US13/986,608 US20130311621A1 (en) 2012-05-17 2013-05-16 Universal Communications Infrastructure
US13/896,310 2013-05-16
US13/986,607 US9875483B2 (en) 2012-05-17 2013-05-16 Conversational interfaces
US13/986,607 2013-05-16
US13/896,318 US20130311260A1 (en) 2012-05-17 2013-05-16 Reward Structures
US13/986,608 2013-05-16
US13/896,318 2013-05-16
US13/986,606 US20130311573A1 (en) 2012-05-17 2013-05-16 Progressively asking for increasing amounts of user and network data
US13/896,310 US9799046B2 (en) 2012-05-17 2013-05-16 Zero click commerce systems
US13/986,612 2013-05-16

Publications (1)

Publication Number Publication Date
WO2013173792A1 true WO2013173792A1 (fr) 2013-11-21

Family

ID=49584360

Family Applications (3)

Application Number Title Priority Date Filing Date
PCT/US2013/041714 WO2013173799A1 (fr) 2012-05-17 2013-05-17 Structures de récompense
PCT/US2013/041705 WO2013173792A1 (fr) 2012-05-17 2013-05-17 Systèmes de commerce sans clic
PCT/US2013/041702 WO2013173790A1 (fr) 2012-05-17 2013-05-17 Graphiques de confiance

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/US2013/041714 WO2013173799A1 (fr) 2012-05-17 2013-05-17 Structures de récompense

Family Applications After (1)

Application Number Title Priority Date Filing Date
PCT/US2013/041702 WO2013173790A1 (fr) 2012-05-17 2013-05-17 Graphiques de confiance

Country Status (1)

Country Link
WO (3) WO2013173799A1 (fr)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106101202B (zh) 2009-09-30 2019-09-24 柯蔼文 用于社交图数据分析以确定社区内的连接性的系统和方法
US20110099164A1 (en) 2009-10-23 2011-04-28 Haim Zvi Melman Apparatus and method for search and retrieval of documents and advertising targeting
US9922134B2 (en) 2010-04-30 2018-03-20 Www.Trustscience.Com Inc. Assessing and scoring people, businesses, places, things, and brands
US9578043B2 (en) 2015-03-20 2017-02-21 Ashif Mawji Calculating a trust score
US20170235792A1 (en) 2016-02-17 2017-08-17 Www.Trustscience.Com Inc. Searching for entities based on trust score and geography
US9679254B1 (en) 2016-02-29 2017-06-13 Www.Trustscience.Com Inc. Extrapolating trends in trust scores
US9721296B1 (en) 2016-03-24 2017-08-01 Www.Trustscience.Com Inc. Learning an entity's trust model and risk tolerance to calculate a risk score
US10180969B2 (en) 2017-03-22 2019-01-15 Www.Trustscience.Com Inc. Entity resolution and identity management in big, noisy, and/or unstructured data

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010011235A1 (en) * 2000-01-29 2001-08-02 E-Net Co., Ltd. Apparatus for realizing personal shops in an electronic commerce business
KR20010076971A (ko) * 2000-01-29 2001-08-17 박규헌 지능형 장바구니 기능을 구비한 전자 상거래 시스템
JP2004326634A (ja) * 2003-04-28 2004-11-18 Hitachi Ltd ユーザ間の信頼関係を用いるお奨めデータ選択装置
JP2009123192A (ja) * 2007-10-22 2009-06-04 Yahoo Japan Corp ユーザ推薦システム、ユーザ推薦方法、商品情報出力システム、商品情報出力方法およびプログラム
US20100235256A1 (en) * 2006-04-29 2010-09-16 Chan Goo Kang System for online contents marketplace and the operation method thereof

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070043583A1 (en) * 2005-03-11 2007-02-22 The Arizona Board Of Regents On Behalf Of Arizona State University Reward driven online system utilizing user-generated tags as a bridge to suggested links
JP4841979B2 (ja) * 2006-03-17 2011-12-21 富士通株式会社 手数料最適化方法および手数料最適化プログラム
WO2008099978A1 (fr) * 2007-02-14 2008-08-21 Won-Young Song Commercialisation sur plusieurs réseaux de commerce électronique
US20110131106A1 (en) * 2009-12-02 2011-06-02 George Eberstadt Using social network and transaction information
US20090319436A1 (en) * 2008-06-18 2009-12-24 Delip Andra Method and system of opinion analysis and recommendations in social platform applications
JP5390642B2 (ja) * 2009-03-03 2014-01-15 グーグル・インコーポレーテッド ソーシャルネットワークのユーザに広告を提供する方法およびシステム
JP2011170471A (ja) * 2010-02-17 2011-09-01 Nippon Telegr & Teleph Corp <Ntt> ソーシャルグラフ生成方法、ソーシャルグラフ生成装置、およびプログラム
KR20110117475A (ko) * 2010-04-21 2011-10-27 중앙대학교 산학협력단 웹 기반 소셜 네트워크에서의 신뢰도 및 평판 추론장치 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010011235A1 (en) * 2000-01-29 2001-08-02 E-Net Co., Ltd. Apparatus for realizing personal shops in an electronic commerce business
KR20010076971A (ko) * 2000-01-29 2001-08-17 박규헌 지능형 장바구니 기능을 구비한 전자 상거래 시스템
JP2004326634A (ja) * 2003-04-28 2004-11-18 Hitachi Ltd ユーザ間の信頼関係を用いるお奨めデータ選択装置
US20100235256A1 (en) * 2006-04-29 2010-09-16 Chan Goo Kang System for online contents marketplace and the operation method thereof
JP2009123192A (ja) * 2007-10-22 2009-06-04 Yahoo Japan Corp ユーザ推薦システム、ユーザ推薦方法、商品情報出力システム、商品情報出力方法およびプログラム

Also Published As

Publication number Publication date
WO2013173790A1 (fr) 2013-11-21
WO2013173799A1 (fr) 2013-11-21

Similar Documents

Publication Publication Date Title
US9799046B2 (en) Zero click commerce systems
WO2013173792A1 (fr) Systèmes de commerce sans clic
US11250472B2 (en) Method and system for providing electronic marketing communications for a promotion and marketing service
US7603292B1 (en) Methods and systems for providing a gift registry
US20130211942A1 (en) Method for enabling a gift transaction
US20130317941A1 (en) Trust Graph
US20150278917A1 (en) Systems and methods for obtaining product recommendations
US10210559B2 (en) Systems and methods for recommendation scraping
US20150206155A1 (en) Systems And Methods For Private And Secure Collection And Management Of Personal Consumer Data
US20080154915A1 (en) Network-based recommendations
US20100280879A1 (en) Gift incentive engine
US10580056B2 (en) System and method for providing a gift exchange
US20150199770A1 (en) Social And Commercial Internet Platform for Correlating, Crowdsourcing, and Convening People and Products of Related Characteristics Into A Virtual Social Network
US20130226710A1 (en) Ad creation interface for an interpersonal electronic advertising system
US20100280913A1 (en) Gift credit matching engine
US20150278919A1 (en) Systems and Methods for a Catalog of Trending and Trusted Items
US10181147B2 (en) Methods and systems for arranging a webpage and purchasing products via a subscription mechanism
US20150206211A1 (en) Systems and Methods for Trusted Gifting
AU2012245584A1 (en) Method and apparatus for providing an electronic commerce platform
US20190266550A1 (en) Address Exchange Systems and Methods
JP6644988B2 (ja) システム、プログラム、方法およびコンピュータ可読媒体
US20190197464A1 (en) Address Exchange Systems and Methods
US11694247B2 (en) System and method for selling and customizing products and services via a network of computer systems
US20150278918A1 (en) Systems and Methods for Providing a Collections Search
KR20020048164A (ko) 소비자 가격 선택형 구매 서비스 제공 시스템 및 방법

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: 13791444

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: 13791444

Country of ref document: EP

Kind code of ref document: A1