Destination-specific prompts for transport services
The network system addresses the lack of destination-specific information in on-demand transport services by providing contextually relevant prompts within the transport app, enhancing user experience and reducing inefficiencies.
Patent Information
- Application Number
- PCT/US2026/027678
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2026-05-11
- Filing Date
- 2026-05-11
- Publication Date
- 2026-11-12
AI Technical Summary
Existing on-demand transport services fail to provide destination-specific information to users during their journey, requiring users to switch between applications and manually search for relevant information, leading to inefficiencies and increased battery consumption.
A network system that programmatically determines and displays destination-specific prompt objects on the user's device during the transport service, based on the context of the request and user profile, enabling interactive responses without the need for separate applications.
Users receive contextually relevant information and actions directly within the transport service application, conserving battery power and reducing the need for manual searches, while enhancing the user experience by integrating destination-specific information and services.
Smart Images

Figure US2026027678_12112026_PF_FP_ABST
Abstract
Description
DESTINATION-SPECIFIC PROMPTS FOR TRANSPORT SERVICESCROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims benefit of priority to each of (i) U.S. Patent Application No. 19 / 673,974, filed May 11, 2026, and (ii) Provisional U.S. Patent Application No. 63 / 803,536, filed May 9, 2025, the aforementioned priority application being hereby incorporated by reference in its entirety.TECHNICAL FIELD
[0002] Examples include a network system for providing destination-specific prompt objects for transport services.BACKGROUND
[0003] Increasingly, requesters of on-demand transport services rely on mobile computing devices to specify destinations and to communicate with network services that arrange transport between locations within a geographic region. Common destinations for transport services include airports, train stations, sports and entertainment venues, hotels, retail districts, residential locations, and other places of interest within a metropolitan region. Each such destination is associated with a corresponding range of activities, sublocations, venues, and follow-on services that may be of interest to a requester at, near, or upon arrival at the destination.
[0004] On-demand transport services typically progress through a series of stages, beginning with the requester submitting a transport request and ending with the requester arriving at the destination. The interval between submission of the transport request and arrival at the destination presents an interval during which the requester is often on the requester device but is not interacting with the service application beyond viewing limited information about the trip in progress.BRIEF DESCRIPTION OF DRAWINGS
[0005] FIG. 1A illustrates a network system for providing an on-demand transport service, according to one or more embodiments.
[0006] FIG. IB illustrates an example of a prompt subsystem, according to one or more embodiments.
[0007] FIG. 2A illustrates an example method for providing destination-specific prompt objects for transport services, according to one or more embodiments.
[0008] FIG. 2B illustrates an example method for generating destination-specific prompt objects, according to one or more embodiments.
[0009] FIG. 3A through FIG. 31 illustrate examples of a user interface for a requester device, according to one or more embodiments.
[0010] FIG. 4 is a block diagram that illustrates a computer system upon which one or more embodiments described herein may be implemented.
[0011] FIG. 5 is a block diagram illustrating an example user device for use with examples as described.DETAILED DESCRIPTION
[0012] Examples include a network system that provides prompt objects to requester devices in connection with corresponding requesters receiving transport services to corresponding destinations. The prompt objects can be displayed on requester devices to enable the requesters to receive information that is specific to the destination.
[0013] In examples, the network system causes a requester device to display a set of prompt objects, in response to a service state condition associated with the requester’s transport request being determined to satisfy a predetermined condition. For example, the network system can cause the requester device to display the set of prompt objects in response to the service state coinciding with the corresponding requester being inside a transport vehicle and on-route to the destination.
[0014] In examples, the set of prompt objects are determined for each requester based at least in part on a context of the requester’s transport request or transport service being provided to the requester. The context can include, for example, a current time or an estimated time of arrival for the requester to arrive at the destination, a type of transport service requested, and environmental conditions at the time the transport service is provided (e.g., weather, traffic).
[0015] Further, in examples, the network system can maintain a collection of prompt objects for a particular location (e.g., frequent destination amongst users in a geographic region), where each prompt object of the collection pertains to, for example, a specific topic or activity that is relevant to the destination of the requester's transport service. The prompt objects of the collection can vary by topic, type (e.g., information providing, action-enabling), format or other characteristics. Each prompt object can be associatedwith a corresponding response item. Based on the type of prompt object, the response item can include, for example, information items (e.g., text-based content), direct links (e.g., URLs) to a resource, or an interactive interface that enables the requester to perform an action or receive additional information, in connection with the connector’s arrival at the destination.
[0016] For each transport request that specifies a particular location, the network system can operate to select a set of prompt objects from a collection of predetermined prompt objects for the particular location. The selection of prompt objects for a given transport request can be based on, for example, a (i) context associated with the transport request (e.g., estimated time of arrival to destination) or transport service being provided, (ii) historical activity of the requester, including activities of the requester after or in connection with receiving transport services, (iii) preferences / or settings of the user, and / or the destination, and / or a sub-location of the destination location (e.g., specific entrance to a museum or park). Additionally, each of the selected set of prompt objects can be associated with a priority or ranking, such that the higher ranked prompt objects are prominently displayed, or initially made visible. In some examples, individual prompt objects can also be determined dynamically, such as at the time the transport service is initiated or being provided, based on information determined from a source (e.g., website) associated with the particular destination.
[0017] In at least some examples, each prompt object is associated with a response item. The response item can be specifically responsive to the corresponding prompt object. Based on the prompt object type (e.g., information providing, action-enabling), the response can include content (e.g., textual content that provides information regarding a question or topic of the prompt object), direct links (e.g., to airline booking engine) to enable the service provider to perform an action indicated by the prompt object, or an interactive interface that is based on the selected prompt object. Further, the response items can be formatted, or otherwise configured for a device form factor of the user.
[0018] Requesters typically use a service application on their respective mobile device to request transport services. Examples recognize that when individuals request service to a destination, the destination is often a place of interest to the requester, and further that requesters are often open or accepting of destination-specific information when they are receiving transport services to the destination. Previously, service requesters used alternative applications to view destination-specific information, and many times, information that they would be interested in was not readily available. For example, thetask of identifying what restaurants are near a departure gate at the airpoil is not trivial, and could require the requester to find a map of the airport online. Further, the user would have to switch between mobile device applications, specifically, between the service application that provides them with information about their transport service (e.g., estimated time of arrival) and their browser (to search and view destination information).
[0019] In contrast, examples surface destination-specific information or actions for requesters in the service application, where the requesters can view the information along with information about the travel service they are receiving. Thus, for example, the user can use a single application (the service application) to view the destination specific information while receiving a transport service. As a result, the user conserves battery power and is provided information of interest in context of their transport service they are receiving.
[0020] Examples described herein provide that a network system, while a transport request is being fulfilled, programmatically determines a set of prompt objects that is specific to the destination of the transport request and to a context of the transport service, and causes the prompt objects to be displayed on the requester device in a manner that is selectable to enable the requester to receive a response item, or perform a destinationspecific action, without operating a separate application.
[0021] Among other technical advantages, examples described enable a network system to surface destination-specific information and actions on a requester device while a transport request is being fulfilled, without requiring the requester to operate a separate application or perform an independent search. By selecting a subset of prompt objects from a larger collection that is associated with the destination, and by basing the selection on a context of the transport service and on profile information of the requester, examples reduce the volume of data transmitted to the requester device and the rendering load on the requester device, particularly in implementations where the requester device has a limited form factor (e.g., mobile device). Further, by associating each prompt object with a corresponding response item that is specifically responsive to the prompt object and that is formatted for the device fomr factor of the requester, examples enable the service application to deliver content and actions that are appropriate for the requester device in connection with arrival at the destination, without the rendering inefficiencies that result from displaying content that is not contextually relevant. Still further, examples enable the service application running on the requester device to bridge the transport service with related services (e.g., delivery, ticketing, lodging) at the destination, by surfacing action-enabling prompt objects that, when selected, cause the requester device to display an interactive interface for performing an action in connection with the requester’s arrival at the destination.
[0022] In examples, a network system comprises one or more processors and memory resources to store a set of instructions, where the one or more processors execute the set of instructions to perform operations comprising: receiving, over one or more networks, a transport request for a requester operating a requester device, the transport request specifying a destination and a transport service for transporting the requester to the destination; the transport request being associated with a service state that indicates a progression towards fulfillment of the transport request, coinciding with the service provider arriving at the destination; detecting when the service state satisfies a predetermined condition; and in response to detecting the service state satisfies the predetermined condition, causing the requester device to display a set of prompt objects, where each prompt object of the set is selectable to enable the requester to receive information that is specific to the destination and responsive to the prompt object.
[0023] In examples, detecting when the service state satisfies the predetermined condition includes detecting a service state coinciding with the requester being inside a transport vehicle and on-route to the destination. In further examples, the operations comprise determining the set of prompt objects based at least in part on a context of the transport request or transport service being provided. The context can include a current time or an estimated time of arrival for the requester to arrive at the destination. The context can also include a type of the transport service provided to the requester. In examples, the requester is associated with a profile, the profile including historical information about at least one of (i) transport services that the requester has previously received, or (ii) activities of the requester in connection with transport services the requester has previously requested, and the set of prompt objects is determined based at least in part on the historical information.
[0024] In further examples, the operations comprise associating a collection of prompt objects with the destination, where determining the set of prompt objects includes selecting the set of prompt objects from the collection, based at least in part on one of (i) a context of the transport service, or (ii) a profile of the requester. In examples, each prompt object of the collection is associated with a corresponding response item, the corresponding response item being optimized for a device form factor of the user. In further examples, the operations comprise determining a ranking for the selected set ofprompt objects, and causing the requester device to display the set of prompt objects in accordance with the ranking, where the ranking is based at least in part on one of the context of the transport service, or the profile of the requester. Examples extend to a non-transitory computer-readable medium that stores instructions, which when executed by one or more processors of a computing system, cause the computer system to perform such operations, and to a corresponding computer-implemented method.
[0025] One or more examples described herein provide that methods, techniques, and actions performed by a computing device are performed programmatically, or as a computer-implemented method. Programmatically, as used, means through the use of code or computer-executable instructions. These instructions can be stored in one or more memory resources of the computing device. A programmatically performed step may or may not be automatic.
[0026] Additionally, one or more examples described herein can be implemented using programmatic modules, engines, or components. A programmatic module, engine, or component can include a program, a sub-routine, a portion of a program, or a software component or a hardware component capable of performing one or more stated tasks or functions. As used herein, a module or component can exist on a hardware component independently of other modules or components. Alternatively, a module or component can be a shared element or process of other modules, programs, or machines.
[0027] Moreover, examples described herein can generally require the use of specialized computing devices, including processing and memory resources. For example, one or more examples described may be implemented, in whole or in part, on computing devices such as servers, desktop computers, cellular or smartphones, laptop computers, printers, digital picture frames, network equipment (e.g., routers), wearable computing devices, and tablet devices. Memory, processing, and network resources may all be used in connection with the establishment, use, or performance of any example described herein (including with the performance of any method or with the implementation of any system). For instance, a computing device coupled to a data storage device storing the computer program and configured to execute the program corresponds to a specialpurpose computing device. Furthermore, any computing systems referred to in the specification may include a single processor or may be architectures employing multiple processor designs for increased computing capability.
[0028] Still further, one or more examples described herein may be implemented through the use of instructions that are executable by one or more processors. These instructionsmay be carried on a computer-readable medium. Machines shown or described with figures below provide examples of processing resources and computer-readable mediums on which instructions for implementing examples described can be carried and / or executed. In particular, the numerous machines shown with examples described include processor(s) and various forms of memory for holding data and instractions. Examples of computer-readable mediums include permanent memory storage devices, such as hard drives on personal computers or servers. Other examples of computer storage mediums include portable storage units, such as CD or DVD units, flash memory (such as carried on smartphones, multifunctional devices or tablets), and magnetic memory. Computers, terminals, network enabled devices (e.g., mobile devices, such as cell phones) are all examples of machines and devices that utilize processors, memory, and instructions stored on computer-readable mediums. Additionally, examples may be implemented in the form of computer-programs, or a computer usable carrier medium capable of carrying such a program.
[0029] NETWORK SYSTEM
[0030] FIG. 1 A illustrates a network system for providing an on-demand transport service, according to one or more embodiments. In some examples, a network system 100 enables users to operate mobile computing devices to receive transport services. The transport service provided can be provided by providers operating vehicles and / or autonomous vehicles (collectively “providers”, “service providers” or “provider vehicles”). A transport request may be fulfilled by a provider vehicle which operates to transport the requester from a service start location (e.g., pickup location) to a service end location (e.g., destination or drop-off location). In variations, examples described with the network system 100 can be applied to other types of transport services, such as, for example, group transport (e.g., rider has friends or family who accompany the rider on the trip), pooled transport (e.g., driver picks up additional riders who separately request the transport service, typically with different pickup locations and / or drop-off locations), bus transport (e.g., driver transports multiple riders in large-capacity vehicle, sometimes while following a pre-determined route), or delivery transport (e.g., service provider picks up and delivers an item).
[0031] With reference to FIG. 1A, the network system 100 executes processes represented by a requester device interface 110, a provider device interface 112, a request handler 120, a service data store 130, a matching engine 140, and a prompt subsystem 150. Each service requester can operate a corresponding requester device 102 to utilizethe network system 100. In examples, each requester can operate a service application 106, running on the corresponding requester device 102, to access information, generate service requests and receive services from the network system 100. Additionally, the service applications 106 can display interactive prompt objects 111, where each prompt object 111 is a selectable feature that represents a topic or search term. The prompt objects 111 that are displayed to the requester are selected by the network system 100 based on a determination of relevance between the topic represented by the prompt object, and a transport service received by the user. Accordingly, the prompt objects 111 are specific to the destination of the service request, as well as to a context of the service request or transport service provided. Each prompt object 111 can be interactive and can include or be provided with content that includes destination-specific information. As an addition or alternative, each prompt object 111 can be interactive to enable user input for selection and / or parametric selection, and based on the interaction, the prompt object 111 can provide destination- specific information and content that reflects the sclcction(s) of the requester.
[0032] In implementation, a requester operates a service application 106 to transmit a transport request 101 to the network system 100. The transport request 101 can specify service parameters, including a service start and a service end location, as well as other information (e.g., time of pickup, if not immediate). The requester device interface 110 receives the transport request 101 communicated through the requester device 102. The request handler 120 generates a job order 125 that corresponds to a record of the transport request. The job order 125 can include a service state 135, having a value that represents a progression state for fulfillment of the service request. The service data store 130 maintains the job order 125 as a record, in association with a set of contextual parameters, where service state 135 is updated and used to find matching service providers.
[0033] In examples, each job order 125 is associated with a status and with service information. The status of each job order 125 may reflect, for example, whether the job order is “open” (e.g., unassigned to a service provider), initially assigned (e.g., service provider has been assigned, but the service provider has not arrived at the start location), or assigned (e.g., service provider is on-route or has arrived at start location).
[0034] In further examples, the service state 135 of the job order 125 can correspond to one of multiple defined phases. The phases can include (i) a matching phase, coinciding with the network system 100 receiving the transport request 101 and the matching engine 140 performing matching operations to identify an available service provider; (ii) an en-route phase, coinciding with a matched service provider operating a provider vehicle to travel toward the start location; and (iii) an on-trip phase, coinciding with the requester being inside the provider vehicle and the provider vehicle being on-route to the destination. The service data store 130 can update the service state 135 of the job order 125 as the job order 125 transitions between phases, based on data received from the requester device 102 and from the provider device 104. The service state 135 can also reflect, in examples, sub-phases within a particular phase, such as a sub-phase within the on-trip phase that coincides with the provider vehicle being within a threshold travel time or distance of the destination.
[0035] In examples, permission-based activity monitoring can be performed with respect to the activities of the user. The monitoring can be implemented to develop a user profile that includes information about preferences of the user. The monitoring can identify, for example, service requests for food deliveries and / or groceries. Based on the food deliveries, the profile interface 168 can determine preferences of the user regarding a price level for restaurant food, a preference or propensity of the requester to eat from specific chains or establishments, a preference of the requester to eat a particular type of cuisine, and / or habits of the requester with respect to eating, drinking or other types of delivery items.
[0036] With further reference to FIG. 1 A, provider device 104 can correspond to a mobile device of a service provider on which a provider service application runs to facilitate the provider in providing transport services. The service application 108 can execute on the provider device 104 to transmit the current location of the service provider. The provider device interface 112 can communicate with the provider to track the current location of the service provider, and to determine a current service state of the provider (e.g., available, offline, on-trip, etc.). The provider device interface 112 can store the current location of the provider with the service data store 130, along with provider status information (e.g., provider is unavailable or offline, online, etc.). The provider device interface 112 can also communicate with autonomous vehicles, either directly via communication to an in-vehicle computer of the vehicle, or through a network service (e.g., third-party) that manages the autonomous vehicle, an in-vehicle device of an autonomous vehicle. Based on the communications, the provider device interface 112 receives the current location and status of the service provider, which in turn is stored in the service data store 130.
[0037] MATCHING ENGINE
[0038] The matching engine 140 implements one or more matching processes to match open transport requests with available service providers. The matching engine 140 can implement the matching process(es) at repeated time intervals (e.g., every 10-, 30- or 60-seconds). The matching engine 140 can match each open job order 125 with one or multiple available provider vehicles, based on factors such as proximity between the start location of the transport request and the cunent location of the available service providers. Once matching is performed for an open job order 1 5, the provider interface 112 transmits, depending on implementation, an invitation or assignment to a matched service provider, where the invitation identifies the matched job order 125 and additional service information (e.g., expected fare, start location, expected time-to-arrival for service provider to arrive at start location, etc.). Once a transport request is matched, the matching engine updates the service state or value 135 of the job order 125, which can also be associated with the requester for purpose of providing prompt objects 111 and response entries 113, as described below.
[0039] Once matching is complete, a service provider or vehicle (e.g., autonomous vehicle) can be directed to a service start location to pickup and transport the requester to a specified destination of the transport request 101. After matching is complete, the requester can be informed of the match and of the matched service provider. Further, the requester can be provided information about the provider’s progress towards the pickup location. Upon arrival, the requester can enter the vehicle to receive the transport stage. The network system 100 can update the service data store 130 and communicate the updates to the service application 106 of the requester device 102. The updates can identify the service state 135 of the requester.
[0040] In examples, the service application 106 of the requester device 102 can enable or promote prompt objects 111 based in part on the service state associated with the rider, as well as the location and / or contextual information. The prompt objects 111 can be enable the user to view and retrieve information, and to initiate an interactive process to receive information about the destination, in a manner that is optimized to identify relevant information for an intent or interest of the user. In examples, the prompt objects 111 are provided on a display of the requester device 102, based on prompt data 121 communicated by the prompt subsystem 150.
[0041] PROMPT SUBSYSTEM
[0042] FIG. IB illustrates an example of prompt subsystem 150, according to one or more embodiments. According to examples, the prompt subsystem 150 can include processes transmit prompt data 121 to the requester device 102, where the prompt data 121 includes data for interactive prompt objects 111 that are relevant to a destination of the transport service that the requester is receiving. The prompt subsystem 150 can also transmit response data 123, in a manner that causes the requester device 102 to display response entries 113, where the response entries 11 include destination specific information relevant to the destination of the transport service of the user, as well as other elements (e.g., actionable elements). Based on the prompt data 121 and the response data 123, the requester device 102 generates an initial set of prompt objects 111, and then based on user interaction with the prompt objects 111, the requester device 102 generates interactive response entries 113, as well as additional prompt objects 111. The prompt objects 111 and response entries 113 can be displayed on the requester device 102 while the user is receiving transport to the destination, such that the user receives information for use with the destination while the user is receiving transport to the destination.
[0043] The prompt subsystem 150 can include processes for determining places of interest, activities of interest, preferred types of venues (e.g., particular types of restaurants), activities users typically perform through the service application and particular context of such activities, and various other information. In examples, processes represented by places determination component 152 can analyze historical data 149 regarding completed transport services, to identify places representing destinations for transport services. The determined places can be stored in a place data store 165, along with a respective geoindex 167. Each place of the place store can include a record identifier, and one or more information items that are relevant to the place. Depending on implementation and the type of place (e.g., airport or stadium, city block, home), the information items can be based on analysis of information form multiple users or an individual user. The historical data 149 can include, for example, information about completed service requests, including common destinations for geographic regions and subregions, as well as activities performed through the service application in connection with the requested transport requests. The historical data 149 can include information about completed transport services for transporting persons, as well as delivery services for providing food and / or shopping items to requesters. Based on implementation, the historical data 149 can also identify, for example, preferred venues at or near specificdestinations, types of venues (e.g., types of cuisine), and / or activities that requesters typically perform, in connection with using the service application 106 and / or receiving transport services.
[0044] The places determination component 152 can identify, using historical information 149 or other resources, places and locations of interest for a given geographic region or subregion. Depending on implementation, the places of interest can include, multi- and / or single venue locations. In some examples, the identified places of interest can be associated with a service request destination that is different than the location of the place of interest. As an example, a destination of interest can correspond to a store or venue in the middle of a city block. The places determination component 152 can analyze the historical data 149 to determine the typical drop-off locations for the destination, and infer, based on data collected with the completed service request, that some users may specify the drop-off location when requesting transport to reach the destination, which may be mid-block. As another example, historical data 149 can indicate that many requesters specify a commuting location when their ultimate destination is a larger multi-venue place. For example, in the case of a large airport, there may be multiple bus or train stops (e.g., express airport stops for public bus or train transit) in the surrounding regions which are commonly used to reach the airport. In such cases, the places determination component 152 can correlate service request destinations that correspond to an express stop for public transport to a particular place of interest (e.g., airport, event center, etc.).
[0045] PROMPT AND RESPONSE DETERMINATION
[0046] In examples, the prompt determination component 154 can evaluate places from the place data store 165 to determine labels 151, as well as response information items 153 associated with corresponding labels 151. The prompt determination component 154 can evaluate the labels 151 and the corresponding responsive information items for various metrics representing, for example, answerability, usefulness, appropriateness, relevance, accuracy and other metrics. The prompt determination component 154 can include rule-based logic, machine learning models, and / or LLMs (or services) to evaluate and refine the labels 151 and their respective information items 153.
[0047] A prompt and response item store (“PRI store”) 155 stores each determined label 151 with a corresponding information item 153. The refined labels and their respective information items can form the content of the prompts and their corresponding response items when rendered on the requester device 102. Each label 151 and information item 153 can be associated with a location of interest. Each location of interest can beassociated with a collection of multiple labels (and thus prompts). Further, one or more of the locations of interest can be associated with multiple destinations for transport services (e.g., direct transport to the location of interest, as well as transport to express public transit). Further, in examples, each label 151 can be associated with one or multiple information items 153. Additionally, each label 151 and / or information item 153 can include variants, such as alternative languages or wording to accommodate specific aspects of the individual user. Each label 151 and / or its variants can provide a basis for a set of prompt objects 111 that are selected for display by prompt data 121. Likewise, each information item 153 and its respective variant(s) can alternatively be referenced herein as a response data 123 that is rendered as response entries 113 on the requester device 102.
[0048] As an addition or alternative, the prompt data 121 can be based on a set of userspecific labels 151, which can be stored specifically for use with the user. For example, the labels 151 can be determined based on preferences and prior activities of the requester, based on similar contextual information and / or trip parameters (e.g., when service start location is requester’s work and they are traveling home). 1'he labels 151 can be communicated to the requester device 102 as prompt data 121, via the requester interface 110, where corresponding interactive prompt objects 111 are rendered.
[0049] The places determination component 152 determines locations / places of interest for a prompt determination component 154. The prompt determination component 154 can utilize logic to determine aspects of potential interest relating to each identified location or place of interest. The aspects of interest can include, for example, information that visitors to the location / place of interest frequently or typically like to know in advance. With respect to an airport, for example, the information can include (i) a map or walking directions to guide a user from a vehicle drop-off point to their gate, (ii) available restaurants and stores, (iii) lounge areas, and (iv) play areas, exhibits or places of interest.
[0050] The response item determination 156 can generate one or multiple information items that form the content of the response entries 113 on requester devices 102. The response item determination 156 can include processes that access web resources associated with the location of interest, to identify information items that correlate to and are responsive to respective labels. The response item determination 156 can also utilize historical data 149 associated with user transport requests to determine information of interest (e.g., preferred types of cuisines for users with kids, etc.). The information items can be formatted, or otherwise selected, to succinctly provide information that is directlyrelevant to the label. In examples, each label can be paired with a set of one or more information items which are directly responsive to the label. Further, the information items can be transmitted to enable interactive elements for enabling the user to perform a targeted action with regards to the item.
[0051] ON-THE-FLY PROMPT OBJECTS AND RESPONSE ENTRIES
[0052] Still further, in additional examples, the prompt determination component 154 can generate or configure prompt data 121 on-the-fly (e.g., without stored labels 151) and / or in real-time, responsive to a determination of a service state and / or other condition (e.g., user enters selected vehicle for transport). The prom2pt data 121 can provide prompt objects 111 for requester device 102 that are specific to one or more user-specific parameters. For example, the prompt data 121 can cause the requester device 102 to generate prompt objects 111 that are specific to the user’s destination, the user’s current trip parameters (e.g., service start location, arrival time, service type), the user’s profile (e.g., preference of the user, user’s service profile linked for food orders and item deliveries, purchasing history, etc.), current contextual information (e.g., weather, traffic conditions, time, etc.) and linked events of the current trip (e.g., user flight information, for trip to airport). In such examples, the prompt data 121 can be based in part, or leverage, the PRI store 155, including the determines labels 151 and response items 153. The prompt determination component 154 can use, for example, labels and information items to generate highly specific, personalized prompt data 121 for the user (e.g., specific sublocation where a name brand product is sold, etc.).
[0053] The response item component 156 can also include logic to implement actionable response elements with the response entries 113 on the requester device 102, where the actionable entries display current, destination-specific, personalized and / or contextually relevant information for the user. The response item component 156 can pre-process response data 123 to cause the requester device 102 to generate the interactive response entries 113. Alternatively, the response item component 156 can pre-store response data 123, or cause the requester device to cache response data 123, where the response data 123 is rendered as response entries on the requester device 102. In this way, when a user interacts with a prompt object 111 , the interaction causes a corresponding set of response entries 113 (e.g., 2-3 entries for restaurants near the user’s departure) to be determined on-the-fly, where the response data is displayed on a user interface as a response entry 113, optionally with actionable elements.
[0054] By way of example, when the user’s destination is a museum, the prompt determination component 154 can perform real-time processes to identify sublocations within the museum where a specific exhibit is provided - one that based on prior user activity or interest, is likely to be of interest to the user. The sublocations can be determined in real-time even when, for example, a label 151 and information items 153 are provided for the museum with the PRI store 155. The response item component 156 can implement real-time processes that gather information and determine action items that are of likely of interest to the user. The prompt data 121 can identify sublocations based on labels 151, as well as real-time information that identifies a specific location of an exhibit. The response data 123 can also include information regarding the exhibit (e.g., if the user selects the corresponding prompt object 111) as well as response entries 113 that are based on information items determined on-the-fly. The response entries 113 can also be based on information items stored with the respective label 151 (e.g., location of restroom). The prompt objects 111 and response entries 113 can also use respective labels 151 and response items 153 of the PRI store 155 to generate actionable elements for facilitate the user to, for example, purchase tickets on-route, find coffee or plan their trip in advance of their arrival.
[0055] PROMPT OBJECT SELECTION PROCESS
[0056] In examples, the service store interface 162 interfaces with the service data store 130, to monitor the service state 135 of the job order 125 for the corresponding transport request 101. Based on the monitoring, the service store interface 162 determines when a value of the service state 135 or other service-related condition is determined to satisfy a predetermined condition. For example, the service provider interface 112 can monitor the location of the service vehicle as the service vehicle travels towards the service start location to pick up the requester. Once the requester is determined to enter the vehicle, the requester and / or provider interface 110, 112 can update the service state 135 of the transport request, to reflect, for example, that the provider vehicle 104 is on-route to the destination of the service request 101. In variations, the service state 135 can be updated to reflect that the user has entered the provider vehicle. Numerous variations can be implemented for defining the predetermined condition. For example, the predetermined condition can be tied to a relative distance or location of the requester or provider vehicle, relative to the service start location or destination of the service request 101. In such implementations, the relative location of the requester or service provider can be determined from the respective requester device 102 or provider device 104, which canrepeatedly transmit location data from their respective satellite component (e.g., global positioning system ("GPS") component). Upon determining that the predetermined condition is satisfied with respect the service state of the transport request (e.g., the requester has entered the provider vehicle, and / or the requester is on-route to the destination), the service store interface 162 can trigger the query interface 160 to generate prompt data 121 for the requester device 102, in connection with the transport service being provided.
[0057] In examples, the predetermined condition that triggers the query interface 160 to generate the prompt data 121 corresponds to the service state 135 transitioning into the on-trip phase, as described elsewhere herein. In variations, the predetermined condition can correspond to (i) the service state 135 being in the en-route phase (when the vehicle to transport the requester is traveling to pickup the requester) and the provider vehicle being within a threshold distance of the start location, (ii) the service state 135 being in the on-trip phase and the provider vehicle being within a threshold travel time of the destination, or (iii) the service state 135 being in the on-trip phase and the provider vehicle entering a geofenced area associated with the destination. In further examples, the service store interface 162 can trigger the query interface 160 to generate, additionally or alternatively, a post-arrival set of prompt objects upon the service state 135 transitioning to a value reflecting the requester arriving at the destination, where the post-arrival set of prompts can include prompt objects (or respective response entries 113) that are selectable to perform a follow-on action (e.g., placing a delivery order to the destination, scheduling a return transport).
[0058] In some examples, the service store interface 162 can perform the monitoring after initially determining that the destination of the service request 101 matches to a location of interest, where the user may be receptive to prompt objects 111 to receive information and destination-specific actionable items. The service store interface 162 can include logic that parses each transport request 101 to identify a corresponding destination, and references the destination against the locations of interest to determine whether the destination corresponds to, or is likely to correspond to, a location of interest. For example, the destination may specify directly, a location of interest (e.g., "SFO"), or alternatively, the destination of the service request can specify a location that is different from a location of interest, but may likely be associated with or correlative to a location of interest (e.g., common drop-off point near location of interest, location of express public transit to a location of interest, etc.). The service store interface 162 can crossreference the destination of individual service requests against locations of interest, such as may be identified as an index with the PRI store 155, to determine whether the user is traveling to a location of interest.
[0059] The query interface 160 generates a prompt query of the PRI store 155, based at least in part on the destination of the service request 101. Based on the prompt query, the query interface 160 can determine a set of multiple labels, from a larger collection of labels 151 that are specifically associated with the determined location of interest. The query interface 160 can transmit, via the requester interface 110, prompt data 121 corresponding to each label of the determined set, where the prompt data 121 is rendered as corresponding interactive prompt objects 111 on the requester device 102. The query interface 160 can implement logic to select or otherwise determine specific labels or prompts for the requester device 102. In examples, the query interface 160 can implement selection logic to determine a context associated with the corresponding service request 101, and then uses the determined context to determine the most relevant labels 151 for the service request that is being fulfilled. For example, the service store interface 162 can determine, from the corresponding job order 125 of the service request 101, contextual parameters associated with the service request, (e.g., estimated pickup time, estimated time of arrival, time of day, day a week or month, weather, traffic etc.). Each label can be associated with contextual parameters that define a context (e.g., time of day, etc.) for when the particular labels 151 (and therefore the corresponding prompt data 121) are relevant or not relevant. By way of example, if the estimated time of arrival for the requester is late in the evening or otherwise off-hours, then the query interface 160 selects relevant labels to exclude those that are for venues which are closed. Accordingly, the relevance determination of the query interface 160 can weight labels that reflect venues or activities which are more likely to be of interest to visitors of the location of interest, given a particular context (e.g., the context of weather, on hot days, ice cream store is of greater interest than on cold days).
[0060] Further, in examples, the query interface 160 can access via profile interface 168, profile information from a requester profile store 172. For example, the service request 101 can include an identifier of the requester. The identifier can be communicated to the profile interface 168, which in turn retrieves a profile data set from the requester profile store 172. The represented data set can indicate interest, or a level of interest in specific categories, for the user, based on observed or historical information with respect to the user, as well as settings or used user provided information. The representative data set caninclude a quantitative value (e.g., vector embedding) and / or labels. In examples, the labels 151 can be associated with profile representative data, reflecting, for example, interest levels of users, where the profile representative data is based on the representative data set of users who have shown interest in the particular label (e.g., through feedback input) in the past. The query interface 160 can match, or determine similarities between the profile representative data associated with the labels 151 and the representative data set of the requester.
[0061] Based on the context, the representative data set and the location of interest (as may be determined by the destination), the query interface 160 selects the labels 151 of the collection associated with the location of interest, and causes corresponding prompt data 121 to be transmitted to the requester devices 102. The prompt data 121 in turn can be displayed as a select set of interactive prompt objects 111 on the requester device 102 (e.g., via the service application 106). When the requester selects an individual prompt, the query interface 160 identifies the information item that is associated with the corresponding label, and then transmits, through the requester interface, response data 123, corresponding to an interactive response item displayed on the requester device 102.
[0062] In further examples, the query interface 160 can determine a ranking for the selected set of labels 151 to reflect a ranking of corresponding prompt objects 111. The ranking can configure the selection of prompt objects 111 that are displayed on the requester device 102. The ranking can be determined based at least in part on (i) the context of the transport request 101 or transport service being provided (e.g., higher ranking for labels that are most relevant for the estimated time of arrival), (ii) the profile data of the requester, which can be retrieved via the profile store 172, third-party sources and / or requester device 102, where the ranking can be based on user preference or behavior or (iii) a combination thereof. The query interface 160 can cause the higher-ranked prompt objects 111 to be displayed prominently within a region of the service application 106 (e.g., displayed first in a horizontally scrollable list, displayed in a primary region of an interactive panel), and the lower-ranked prompt objects 111 to be displayed less prominently or to be made accessible through scrolling input received at the requester device 102.
[0063] DESTINATION-SPECIFIC DATA STORE BUILD
[0064] In examples, processes represented by places determination component 152 produce and update place data store 165. The place data store 165 can provide place data for response information items 153, as well as for labels, map interfaces and the like. Inexamples, the place data store 165 can aggregate information in a series of stages. The stages can include a place data generation stage, a place web search stage, an HTML fetch stage for official websites, a URL extraction stage, an HTML fetch stage for related URLs, one or more content extraction stages (e.g., a menu extraction stage and an entity extraction stage), a geoindex assembly stage, a data quality postprocessing stage, a deduplication stage, and a merge stage. Each of the stages can be implemented as a programmatic component, or as a set of programmatic processes, that operates on the output of one or more upstream stages and provides input to one or more downstream stages.
[0065] In examples, the place data generation stage produces an initial set of place records, utilizing public records, map data, historical data 149 of prior transport-related services and other sources of information. The place web search stage performs web searches with respect to individual places identified by the upstream stage, to obtain associated web content for each place. The associated web content can include, for example, identifiers for websites associated with the place (e.g., an official website), brief descriptive content (e.g., blurbs), and other publicly available content that further describes or relates to the place.
[0066] In examples, the backend process includes an HTML fetch stage that operates with respect to websites (e.g., official websites or authoritative links). For individual places, the HTML fetch stage retrieves content from websites associated with the place. The HTML fetch stage can extract content of various forms, including (i) raw HTML, (ii) content rendered or formatted as Markdown, and (iii) links (e.g., URLs) referenced from the official website. The extracted content provides a content base from which subsequent stages can perform additional or deeper enrichment with respect to the place.
[0067] The backend process can include a URL extraction stage that processes the content retrieved from the official website to identify URLs (e.g., deep links) that are relevant to the corresponding place. In examples, the URL extraction stage utilizes a large language model (LLM), called in batch, to select a subset of the URLs (e.g., a top set of URLs) that are determined to be relevant for purpose of further or deeper enrichment of the place. By way of example, the URLs can be ranked or scored through use of the LLM based on contextual relevance to the place, and the URLs of a top set (e.g., a top number, or those exceeding a threshold relevance) can be selected for downstream processing. As an addition or variation, the URL extraction stage can apply additional filters or rules to limit the URLs that are propagated downstream, such as to exclude URLs that aredetermined to be unreliable or otherwise unsuited for use as a source of enrichment content.
[0068] In examples, the process implements a second HTML fetch stage that operates with respect to the related URLs identified by the URL extraction stage. For each related URL, the HTML fetch stage retrieves content from the related URL and performs a deeper content extraction with respect to the related URL. The retrieved content can provide additional information about the place, including information that is not necessarily reflected in, or accessible from, the official website associated with the place.
[0069] In examples, the process includes one or more content extraction stages that operate on the content retrieved through the HTML fetch stages. The content extraction stages can include a menu extraction stage and an entity extraction stage. The menu extraction stage can be implemented to identify, parse, and structure menu content (e.g., menu items, descriptions, prices, and the like) from corresponding pages. The entity extraction stage can be implemented to identify and structure entities of interest from non-menu pages. As described with the example, the menu extraction stage and the entity extraction stage can each be implemented through use of an LLM, called in batch, to perform the corresponding extractions.
[0070] The process can include a geoindex assembly stage that operates to assemble the output of the upstream stages into a geoindex 167 (e.g., places_geoindex). In examples, the geoindex assembly stage operates to produce a first version of the geoindex 167 (e.g., geoindex vl), where the geoindex aggregates the place records together with the corresponding enrichment data determined for each place. As an addition or variation, the geoindex assembly stage generates and incorporates additional data with respect to each place, including embeddings (e.g., vector representations for use in semantic retrieval) and ranking metadata. The embeddings and ranking metadata can be utilized by the query interface 160 in connection with retrieval and ranking operations performed in response to the service request 101.
[0071] In examples, the process includes a data quality postprocessing stage that operates on the assembled geoindex 167 to normalize and standardize select fields of the place records. The data quality postprocessing stage can be implemented through use of an LLM, called in batch, to normalize fields such as place names, addresses, and hours of operation. The data quality postprocessing stage can also operate to extract additional fields from the place records, such as a canonical name (e.g., canonical_name) and abusiness name (e.g., business_name) for each place. The normalized and extracted fields can be utilized by downstream stages, including for purposes of deduplication and merge.
[0072] In examples, the process includes a deduplication stage (e.g., place_dedup) that operates on the geoindex 167 following the data quality postprocessing stage. The deduplication stage can be implemented to operate in multiple phases. In a first phase, the deduplication stage performs an exact match between place records based on the canonical name of each record. Place records that match in the first phase can be flagged or otherwise associated as duplicates. In a second phase, the deduplication stage performs deduplication with respect to place records that share an address but otherwise lack a definitive identifier (e.g., address-only pairs). In examples, the second phase of deduplication can be implemented through use of an LLM, where the LLM evaluates whether the address-only pairs reflect the same place. By way of example, the LLM can take into account contextual information associated with each record, such as place name variants, business descriptors, and content extracted from the corresponding wcbsitc(s), in determining whether the address-only pairs reflect the same place.
[0073] The process can include a merge stage (e.g., place_merge) that operates to integrate the output of the deduplication stage with additional metadata. In examples, the merge stage joins the deduplicated place records with semantic taxonomy tags (e.g., categorical or topical tags determined for each place). The merge stage can also operate to rebuild the place name (e.g., place_name) for each record, normalize remaining fields of the place record, and write the resulting records to a subsequent version of the geoindex (e.g., geoindex vl.0.1). The resulting geoindex 167 can provide the place data set that is queried by the places determination component 152 and accessed by the response item detemrination 156, to support the prompt and response item generation described elsewhere herein.
[0074] In examples, the response item 153 generated by the response item determination 156 for a particular label 151 can be of an action-enabling type, where an actionable element of the response item 153 is selectable to cause the requester device 102 to display an interactive interface for performing a destination-specific action, destination-specific actions enabled through the interactive interface can include, for example, (i) purchasing admissions to an attraction or exhibit at the destination (e.g., a skip-the-line admission to a museum or other landmark), (ii) initiating a check-in to lodging at the destination (e.g., a hotel for which the destination corresponds to a property of the lodging), (iii) placing an order for delivery of food or items at the destination (e.g., from a venue at or near thedestination, such as a delivery from a restaurant to a hotel destination upon arrival of the requester), and (iv) reserving a follow-on service for use at or near the destination (e.g., a ground transport reservation, a table reservation at a venue at or near the destination). The interactive feature can be transmitted to the requester device 102 by the response item determination 156 in response to the requester selecting the corresponding prompt object 111, and the interactive interface can be formatted for the device form factor of the requester device 102.
[0075] VENUE AND INTERACTIVE WORKFOW EXAMPEES
[0076] In some examples, the selection and transmission of the response data 123 can be used as an input signal for the prompt determination component 154 to determine additional prompt data 121, which in turn causes the response item component 156 to pre-process additional response data 123 for the additional prompt objects 111 that are communicated to the requester device 102. In such examples, the prompt determination component 154 and the response item component 156 can utilize, for example, machinelearning processes, artificial intelligence resources (e.g., LLM or LLM interface) and / or other processes that are triggered when a particular service state or condition is detected on the requester device 102. For example, in response to a determination that the user is receiving a transport service (e.g., service state reflects on-route state to a destination), the prompt determination component 154 and the response item component 156 determine a set of topics that are relevant to the destination of the transport service, using machinelearning processes, artificial intelligence resources, based on input signals that include, for example, real-time contextual information, user profile information (e.g., user preferences for food based on food delivery, etc.), and / or information linked to the transport service (e.g., flight information, including specific gate, time of departure, and flight destination).
[0077] By way of example, the network system 100 can link a trip the user is taking from an airport (e.g., from SFO to Hawaii) with a transport the user requests to the airport two hours before their departure time. The linking of the current transport service with flight information can be created by, for example, the user scheduling transport to the airport through a service of the network system 100 at the time they purchase the airfare, through manual entry through the service application (e.g., feature in service application 106 to schedule transport for timely arrival for particular flight) or through manual input. In such examples, the prompt determination component 154 can automatically generate and transmit prompt data 121 to cause the requester device 102 to display one or more promptobjects 111 representing information about the destination of their flight, such as the weather at their flight destination, places to eat when they land at their destination, or transport services the requester can use to travel from the airport at their flight destination to their lodging. The flight-destination specific prompt objects 111 can be displayed with other prompt objects 111 that may be specific to, for example, the airport that is the destination of their current transport service. The user’ s selection of individual prompt objects 111 can cause the requester device 102 to display response entries 113 (communicated as response data 123 responsively or previously), communicated by the network system 100, where the response entries 113 reflect the relevant information. The response entries 113 can also include actionable elements (e.g., links, service application action calls, etc.) that the user can interact with to take action (e.g., schedule transport servicer from airport at flight destination to lodging) or view information (e.g., see stores near hotel at destination).
[0078] In some examples, the destination identified by the places determination component 152 can correspond to a multi-venue location for which the prompt determination component 154 maintains sub location information. By way of example, the multi-venue location can correspond to a sports or entertainment venue (e.g., stadium, arena, concert hall) for which the prompt determination component 154 maintains identifiers for multiple gates, entrances, sublocations of seating areas, and concessions within the venue. In such examples, the prompt determination component 154 can generate labels 151 and / or prompt data 121 corresponding to (i) a particular gate or entrance identifier that is correlated to a sublocation within the venue (e.g., a gate that is closest to a seating area indicated by the requester’s profile or by an input received through the service application 106), and (ii) concessions, merchandise, or services available at sublocations within the venue. The corresponding response item determination 156 can provide a set of response entries 113 that are determined based on on-the-fly determinations and / or stored response items 153, where the response entries 113 include, for the gate or entrance label, directional information from a vehicle drop-off point to the gate, and / or concession and sublocations or directions. Still further, in examples, the response entries 113 can include actionable elements, such as actionable element to enable the requester to place an order for pickup at a concession stand, located at a sublocation near the entrance of the venue or along a route of travel for the transport service.
[0079] In further examples, the destination identified by the places determination component 152 can correspond to a district or area associated with multiple individual venues (e.g., a nightlife district, a retail district, or a section of a city center), rather than a single multi-venue location. For destinations of this type, the prompt determination component 154 can maintain a collection of labels 151 that correspond to individual venues within the district, and the response item determination 156 can generate response items 153 for each label 151 that include current availability information for the corresponding venue (e.g., whether the venue is currently open, whether tables are available, whether reservations are required). As an addition or variation, the prompt determination component 154 can maintain a list of resources (e.g., deep links) to generate topics or labels 151 on-the-fly, and the topic or labels can incorporate or otherwise integrate the predetermined labels 151 and information items 153. In examples, the query interface 160 can select, for example, a set of labels 151 for a district destination based at least in part on the context of the transport request 101, including the current time and the estimated time of arrival, such that the labels selected reflect venues that are likely to be open and available at the estimated time of arrival of the requester.
[0080] The prompt determination component 154 can implement multiple processes to determine the types of information that are of interest to the user. The prompt determination component 154 can use surveys, historical data provided through user interaction with the service application while at the particular locations, websites and resources associated with the location of interest, and / or a large language model (LLM) or services to determine the types of information or activity that visitors to a particular location or place of interest are frequently interested in. Further, the prompt determination component 154 can utilize content determination component 158 to generate labels or topics, which can correspond to, or include, descriptive terms, icons, or elements that are descriptive of the corresponding type of information or activity that is of potential interest. Further, based on implementation, the prompt determination component 154 can determine the labels 151 and / or topics for use as prompt data 121 on-the-fly and / or through pre-determined processes. As described, the topical and label determinations used with prompt data 121 can provide, or cause the requester device 102 to provide, the content aspect of an interactive prompt (see also FIG. 3A through FIG. 3F as examples).
[0081] HOME AND TRAVEL MODE EXAMPLES
[0082] In further examples, the places determination component 152 can identify, as a place of interest for a particular requester, a residence of the requester (e.g., a destinationlabeled “Home” in the profile of the requester or in a setting of the service application 106). When the destination of the transport request 101 corresponds to the residence of the requester, the prompt subsystem 150 can generate prompt data 121 for generating one or more prompt objects 111 on the requester device 102 that are specific to a residence destination of the requester. The prompt data 121 can be based on, for example, the types of follow-on services or items that are commonly accessed by users at, or in connection with arrival at, a residence (e.g., grocery delivery, pharmacy delivery, household items, prepared food delivery). The prompt data 121 can generate one or more prompts that include user-specific preferences, such as a service or action the user prefers or commonly performs when arriving at their home. The prompt determination component 154 can determine prompt data 121 for one or more prompts based on prior activity of the requester through the service application 106 in connection with arrival at the residence. The prompt determination component 154 can determine prompt data 121 on-the-fly (e.g., in real-time), for individual users receiving transport services, based in part on their respective profile information (e.g., as stored with the profile store 172) and / or contextual information.
[0083] In some examples, the network system 100 implements a travel mode in connection with the requester device 102 receiving an input that specifies a destination through the service application 106. The travel mode can correspond to a state of the service application 106 in which the destination is used as a parameter to retrieve, from the network system 100 or a related service, information items associated with the destination. The information items can include resources for transport (e.g., the transport request 101 itself), as well as resources or actionable elements for delivery (e.g., food or shopping items to be delivered to the destination or to the residence of the requester upon arrival), reservations (e.g., reservations at a venue at or near the destination), and ticketing (e.g., admissions for an event at or near the destination). When the requester device 102 is in the travel mode, the prompt subsystem 150 can determine prompt data 121 and labels 151 for the destination based at least in part on the resources made available through the related service for the destination, such that the prompt objects 111 rendered on the requester device 102 reflect the resources of the related service that are available for the destination.
[0084] SEARCH AND CHAT
[0085] In examples, the prompt subsystem 150 can enable user-generated prompting, through use of natural language interfaces such as search a search interface or chatinterface. As illustrated by examples of FIG. 3F through FIG. 31, the prompt subsystem 150 can leverage the place data store 165, including geoindex 167, and the PRI store 155 to provide search and chat features through the service application 106. As described below, such interfaces 350, 370 (see FIG. 3F-3I) can leverage, for the geoindex 167 to return query results that are filtered or otherwise keyed for a destination.
[0086] METHODOLOGY
[0087] FIG. 2A illustrates an example method for providing destination-specific prompts for transport services, according to one or more embodiments. FIG. 2B illustrates an example method for generating destination-specific prompts, according to one or more embodiments. In describing example methods of FIG. 2A, FIG. 2B, reference may be made to elements of FIG. 1 A and FIG. IB for purpose of illustrating implementation of a step or sub-step being described.
[0088] With reference to FIG. 2A, at 210, network system 100 receives, over one or more networks, a transport request from a requester device operated by a requester. The transport request can be transmitted through a service application executing on the requester device. The transport request can include, as service parameters, a start location and a destination. Additional service parameters provided with the transport request include a service time (e.g., desired pickup or drop-off time) a service level (e.g., priority), a type of service or vehicle (e.g., group transport, luxury vehicle, etc.), special instructions for the service provider, access needs (e.g., wheelchair access), and / or vehicle environment or sound preferences.
[0089] As described in examples, in response to receiving the transport request, the network system 100 initiates a series of events that result in the requester being picked up at a start location and transported to a destination. The network system 100 associates a service state with the transport request to track a progression of the transport request towards fulfilment. In examples, a job order is created for the service request and stored in the service data store 130, where the job order can track the service state 135 of the service request (which can also be associated with the user), and the value of the service state 135 indicates the progression towards fulfillment of the transport request (or job order). The service request can be matched with a service provider using a matching process. The matched service provider may also accept the service request. Once the matched service provider accepts, the network system 100 can communicate with the respective devices of the requester and service provider to track the progression of the job order. Upon the occurrence of predetermined events, the network system 100 updates thevalue of the service state to reflect the progression of the service request towards fulfillment. The service state can include multiple values, such as, for example, state values reflecting (i) a transport provider being selected, (ii) the transport provider being on-route to or arriving at the service start location, (iii) the requester entering the vehicle of the selected provider, (iv) the requester being in vehicle and on-route to the destination, and (v) the requester arriving at the destination.
[0090] In step 220, the network system 100 detects when the service state 135 satisfies a predetermined condition for providing prompt object 111 (see FIG. IB, and FIG. A-FIG.3E) to the requester. As a precondition, the network system 100 can automatically match the destination to a list of locations which are associated with a collection of prompt objects. As described with an example of FIG. 2B and other examples, certain places of a geographic region can be associated with a corresponding collection of prompt objects. For example, in a given metropolitan region, places such as airports, train stations, event centers, museums, parks, and / or other places of interest can be associated with corresponding collections of prompt objects. Additionally, collections of prompt object 11 lean be associated with corresponding areas of interest. For example, the "downtown area" of a city can be associated with a collection of prompt objects.
[0091] In examples, the predetermined condition can be defined at least in part by the value of the service state. The predetermined condition may correspond to the service state indicating the requester has entered the vehicle and is on-route to the destination. In variations, the predetermined condition can be defined by other parameters or events, such as (i) the requester's vehicle being within a threshold travel time or distance of the destination, or (ii) the requester's vehicle exceeding a threshold travel time or distance from the start location. Still further, in additional examples, the predetermined condition can be based on an estimated arrival time of the service provided to the start location, or detection of the service provider heading towards the start location.
[0092] In examples, the operations performed at step 220 can include (i) retrieving the service state 135 of the job order 125 from the service data store 130 and determining the phase indicated by the service state 135 (e.g., matching phase, en-route phase, on-trip phase); (ii), evaluating one or more contextual parameters associated with the transport request 101, including a current time, an estimated time of arrival at the destination, a type of transport service, weather, traffic, and a day of week or month; and (iii) comparing the phase and the contextual parameters against the definition of the predetermined condition. In examples, the predetermined condition is satisfied when theservice state 135 is in the on-trip phase. In variations, the predetermined condition is satisfied when the service state 135 is in the on-trip phase and the contextual parameters indicate the provider vehicle is within a threshold travel time of the destination.
[0093] In step 230, in response to detecting the service state satisfies the predetermined condition, the network system 100 causes the requester device 102 to display a set of prompt objects 111, where each prompt object 111 of the set is selectable to enable the requester to receive response entries 113 (e.g., see response entry 328 in FIG. 3A-FIG.3F). As described with examples, each response entry 113 can include information that is specifically tailored for the destination and / or user. The response entry 113 can also include or actionable elements for performing an action that is specific to the destination and responsive to the prompt. For example, the network system 100 can transmit prompt data 121 to the requester device 102, where the prompt data represents a select set of prompt objects 111. The set of prompts can be selected from a collection of labels 151, or determined on-thc-fly, where the collection of labels 151 arc associated with the destination of the service request. In examples, a given location can be associated with a collection of labels 151, and the network system 100 selects, as prompt objects 111, a subset of the collection for the requester device 102. By way of illustration, there may be tens or hundreds or thousands of labels in a collection for an airport or stadium, and the subset selected for the requester device 102 can range between one and eight, based on implementation.
[0094] In examples, the criteria for selecting which labels of the collection are to be used for generating prompt objects 111 include, for example, (i) a context of the service request or transport service provided (e.g., current time, time request was made, estimated time of arrival at the destination, day of week or month, weather, etc.), a type of the transport service being provided to the requester, profile information of the requester, and / or other service parameters associated with the transport request. In examples, the profile information can include historical activities and preferences of the user. The profile information can extend to information determined for the user from multiple types of services provided through the network system 100. For example, the network system 100 can be implemented to provide food, grocery or shopping item delivery to the user. The permission-based activity of the user in connection with good, grocery or shopping services can be used to develop the user profile, to determine preferences of the user with respond to, for example, type of restaurant they are most likely to be interested in, whether they are likely to have coffee, and / or whether they like to shop and what type ofbrands or products the user is interested in. Still further, based on the historical activities of the user with respect to services provided through the network system 100, if the type of requested transport service is a luxury vehicle, the network system 100 can make an inference that the user has a preference for leisure, in which case one or more of the prompts can be selected based on a venue's association with leisure (e.g., airline lounge for airport).
[0095] As additional examples, the profile information about the requester can also indicate a preference or tendency of the service provider with respect to inactivity or item of interest at the destination. For example, if the requester has a history of ordering prepared food from particular types of restaurants (e.g., through the service application, the user frequently orders Chinese food), then the network system 100 may infer the requester has an interest in Chinese cuisine, and the selection of prompts can include a criteria for identifying Chinese or Asian style restaurant at the particular destination. In additional examples, the criteria for selecting prompts can be based on information associated with a website or resource of the destination. For example, the destination is a museum, the network system 100 can, while the vehicle is in transit, check a website of the museum for information about new exhibits, and if a new exhibit or exhibit of interest is determined, then the prompt can be configured to highlight information about the new or interesting exhibit. By way of illustration, a requester may select a museum as the destination, and the network system may determine a new exhibit (e.g., baby alligators) is being showcased on the museum website. In response, at least one of the prompts can be generated by the network system 100 while the vehicle carrying the requester is on-route to the museum, and the prompt may focus on the new exhibit (e.g., "Albino Alligator?").
[0096] In examples, causing the requester device 102 to display the set of prompts can include sub-operations corresponding to (i) querying the PRI store 155 with the destination of the transport request 101 to retrieve the collection of labels 151 associated with the destination; (ii) applying selection logic to the retrieved collection based on the context of the transport request 101 and a profile of the requester, to determine a subset of the collection; (iii) determining a ranking for the subset based on the context, the profile, or a combination thereof; and (iv) transmitting prompt data 121 corresponding to the ranked subset to the requester device 102, where the prompt data 121 causes the service application 106 to render the prompt objects 111 in accordance with the ranking. In examples, the destination corresponds to a residence of the requester, and the network system 100 selects prompt objects 111 for the requester that correspond to follow-onservices at the residence (e.g., food delivery, grocery delivery, pharmacy delivery. Etc.), based on the user’s profile and preferences.
[0097] With reference to FIG. 2B, in step 250, the network system 100 identifies location(s) of interest within a geographic region (e.g., within or near a city). In examples, historical data identifying service parameters for completing transport services and a geographic region can be analyzed to identify common destinations for requesters of the geographic region. Additionally, certain types of places, such as airports or event centers, can be sought for individual regions.
[0098] In step 260, the network system 100 accesses resources (e.g., websites, Chamber of Commerce resources, etc.) associated with each identified location to determine aspects of interest about the identified location. The aspects of interest for the identified location can include sublocations within the location, and activities that a person may want to perform while at the identified location. By way of illustration, a sublocation for an airport or shopping center can correspond to a restaurant or store. An activity that a person can perform can include, for example, charging a device or walking to a particular sublocation (e.g., a requester walking to a particular gate, etc.). The prompt subsystem 150 can implement processes to analyze the associated resources of each of the identified locations to determine labels or categories for each identified location. For example, the predetermined categories of activities can include dining and shopping, as well as subcategories of each category (e.g., Asian cuisine, jewelry or department store, etc.). The information obtained from the associated resources can also sort sublocations within the location with a corresponding label or category.
[0099] In step 270, the network system 100 generates a collection of labels, each of which can be presented as an interactive prompt, as well as information items for respective labels, for each identified location of interest. For each location of interest, the collection of prompt objects 111 that can be generated by integrating the prompts with historical or known user activity. The prompts and responses can be structured and formatted for presentation on a form factor of a requester device (e.g., mobile device form factor). For example, the prompt objects can be configured to minimize wording, and use iconic representations (e.g., hamburger icon for fast food) to represent specific aspects in a particular identified location of interest.
[0100] In response to a prompt selection event, in step 280, a set of prompts (or labels 151, as may be stored on the network system 100) are selected and provided to a particular location of interest. The prompt selection event can correspond to a transportservice being initiated for a requester, such as the requester entering a transport vehicle, or a transport service being initiated for the requester. The selection of prompt objects 111 can be based on a context of the transport request (e.g., time of request or service, estimated arrival time to destination), including service request parameters (e.g., type of service the requester has received). The selection of prompt objects 111 can also be based on user-specific criteria. For example, a vector representation of the requester can be determined based on the requester’s prior activities through the service application of their respective user device. Prior activities of the requester can include, for example, activities the requester performed through the service application in the past, while receiving transport or at the destination. For example, if a prior activity of the requester at an airport was to reserve ground transportation at their arrival destination, then one of the prompts provided to the user may be selectable to open an interface for reserving the ground transport.
[0101] EXAMPLE INTERFACES
[0102] FIG. 3A through FIG. 31 illustrate examples of a user interface for a requester device, according to one or more embodiments. Examples such as shown by FIG. 3A through FIG. 3F can be implemented on a requester device, using data transmitted from the network system 100 such as described with FIG. 1 A. Accordingly, reference is made to elements of FIG. 1A and FIG. IB for purpose of illustrating suitable components or functionality for providing a user interface such as shown and described with FIG. 3A through FIG. 3F. The user interface 300 can be generated by the service application 106 of requester computing device 102, using data communicated by the network computer system 100 that provides the transport service. The user interface 300 can be configured to generate a travel assist interface 310 to provide destination specific information for the user for a transport service that the user is or will be receiving. As described, the 310 can be dynamically generated based on, for example, the service state associated with the requester. In implementation, the 310 can also be dynamically sized with a framework of the service application 106.
[0103] In examples, the user interface 300 is triggered to appear by, for example, detection of a service state of a user transport request by the service application 106. In this way, the user interface 300 can be generated responsive to, for example, a communication from the network computing system 100. Still further, the user interface 300 can be generated in a framework of the service application 106, while, for example, the user is in a vehicle to receive transport to their destination.
[0104] The user interface 300 can be interactive and dynamic, coinciding with a service state of the service request. In examples, content generated and displayed to the user via the user interface 300 can be based at least in part on data communicated by the network computer system 100. Further, the content can also be responsive to communications from a network system 100, so as to reflect, for example, one or more of (i) a progression of the service request being generated and transmitted from the requester device 102 to the network system 100, (ii) selection of the transport vehicle or provider for fulfilling the transport request, or (iii) transport of the selected vehicle or provider to the start location and then the destination. Communications from the network computer system 100 can therefore cause the user interface 300 to display specific content, and further to generate and configure the 310.
[0105] The functionality provided with the 310 can also vary based on factors such as user engagement, the service state of the user, the destination for the transport service the user is receiving, contextual information associated with the service state, and other factors. For example, as described below, the 310 can engage the user with prompt objects 322 to initiate an information workflow that provides the user with highly-specific information relating to the destination or their travel, in situations where the user may not know specifically what they are looking for. The 310 can also include a search interface 370 to prompt the user for search terms that provide specific information about the destination of the transport service in a more targeted manner. Still further, the 310 can provide a chat interface that can provide an alternative form of engagement for the user.
[0106] With reference to examples of FIG. 3A through FIG. 3D, the service application 106 provides the user interface 300 to engage the end user with information relevant to their destination. The user interface 300 can include an interactive panel 310, responsive to, for example, (i) the requester making a transport request to the network system 100, (ii) the requester being matched to a service provider, (iii) the requester being detected as being on-route, or otherwise in the matched vehicle, or (iv) the transport service being provided to the requester making a threshold progression towards the destination. The interactive panel 310 includes content corresponding to the user's transport request and service, such as, for example, their destination and their estimated arrival time.
[0107] The user interface 300 includes region 320 to display prompt objects 322.Multiple prompt objects 322 can be displayed, with each prompt object 322 pertaining to a query or topic that is relevant to the destination. The interactive panel 310 and / or region 320 can be scrollable vertically and / or horizontally, to provide interactive content for therequester. Each prompt object 322 can correspond to a selectable interactive element that, once selected, generates content that is based on, or corresponds to, a response item. In an example, each prompt object 322 can be in the form of an object (e.g., "pill"), comprising words, emojis, icons, symbols, graphic elements or assets, or the like, representing a topic or category of relevance to the destination, the requester and / or the requester's transport request. Thus, in the example shown, at least some of the prompt objects 322 specifically relate to the destination of the user's transport request (e.g., "SFO").
[0108] In examples, the set of prompt objects 322 pertain to topical queries that are selected for relevance to the particular destination and user. For example, the set of prompt objects 322 can include individual objects that convey information topics that are specific to the transport service being provided to the user The prompt objects 322 can be selected from a larger collection of prompt objects, based on the destination and user preference. The initial selection of prompt objects 322 can include individual selections that arc based on one more of (i) popular topics or prompt objects 322 (e.g., such as those that receive the most engagement or search queries), (ii) transport or travel preferences of the user, based on their past transports or past transports to the particular destination or destination type, (iii) requester preferences as to food and diet, as may be determined from food delivery or pickup requests, and / or (iv) shopping preferences of the user, based on recent purchases or preferences
[0109] The initial selection of prompt objects 322 for display on the device 102 can also be based on a context associated with the user's transport request. The context associated with the transport request can include, for example, a type of transport service that is requested or being provided, the current time, the time the transport request was made, the estimated time of arrival to the destination, the day of week or month, weather, the current state of traffic and the like. Thus, the set of prompts objects 322 may differ based on the contextual parameters and information determined for the requester's transport request. Further, the 310 can partially display a selected set of prompt objects 322, and allow user scrolling, navigation and searching to view additional prompt objects 322 of the particular selection.
[0110] In variations, the user interface 300 also includes prompt objects 322 that are specific to the transport services the user can receive. For example, one of the prompt objects 322 can pertain to alternative types of transport services (e.g., luxury) that the user may select, based on the current type of transport service being provided to the user. To illustrate, in a scenario where a user requests a standard type of transport service (e.g.,singular transport, using midsize sedan), one of the prompt objects 324 can include a label relating to, or being suggestive of, a premium or luxury transport service (e.g., "think Black car to SFO is too expensive?"). In some examples, the prompt object 324 can be selected for display based on a factors such as the destination, the service start location, the profile of the user, contextual information and a relative cost of the black car service versus the service the user selected for the current trip. When the user selects the prompt object 324, the response item generated with selection of the particular prompt object 324 may highlight or compare the difference between the luxury service and the service the requester is currently receiving. As shown by such scenario, the context used in selecting a particular prompt can include, for example, the type of transport service the requester is receiving, the cost for the transport service, alternative transport services that are available and possibly desirable to the requester, the expected distance and / or travel time for the transport service, etc.
[0111] With reference to an example of FIG. 3B, the user interface 300 is shown to generate content that is responsive to the selection of one of the prompt objects 322 (e.g., “Cheap Eats at SFO”). The responsive content can include response entries 328 that are associated with a topic of the selected prompt object 322. In the example provided, the response entries 328 can be determined from information resources associated with the destination (e.g., website for SFO), and the entries 328 can reflect a selection of venues available at the destination which match a criteria represented by "cheap eats"). For example, the network system 100 may correlate or represent fast food venues with "cheap food". The response entries 328 can include words, emojis, icons, symbols, graphic elements or assets, or the like. In an example shown, a graphic element or asset is associated with the response entries 328 to provide user-recognizable information, where the graphic element is selected, or preselected, for relevance to the venue and optimally sized in data and dimension, and devoid of representative data rich imagery that would lessen the amount of available space in a region of the 310.
[0112] Further, in examples, individual response entries 328 can be provided with highly relevant venue information 327, including destination and / or user-specific for a corresponding venue identified by an entry. The highly relevant venue information 327 can include, for example, hours of operation, indicia of what is available at the venue, and / or spatial information regarding the sublocation within the venue. The highly relevant venue information 3 1 can also include information that is specific to the destination (e.g., visual marker in region of destination where the corresponding venue is located),the transport service the user is receiving (e.g., relevant location of venue to drop-off location of user at destination), and / or the user (e.g., the relevant location of the venue to a gate, terminal, or expected sublocation of user after drop-off).
[0113] In examples, each entry 328 can also include an actionable element 329 that is selectable to enable the user to view additional information about the venue (e.g., menu, visual map of the location of the venue) and / or perform additional actions (e.g., access a site for the venue to place an order).
[0114] In additional examples, the selection of prompt objects 322 and / or response entries 328 (or other responsive content) can be based on historical information and / or preferences associated with the user profile. For example, the response entries 328 can include an establishment the user has previously frequented, a chain restaurant the user has previously ordered food delivery from, and / or establishments that are near a relevant sub-location of the user within the destination (e.g., near their specific gate).
[0115] As described with various examples, the selection of prompt objects 322 and the response entries 328 that are subsequently generated can be the result of an intelligent programmatic process that customizes the set of prompt objects 322 based on a user profile (e.g., preference, application usage history, etc.) of the requester, a context of the transport request and / or transport service provided, and / or the destination. As described in examples, in at least some implementations, machine-learning models processes and / or artificial intelligence can be used to select individual prompt objects 322 (or topics) for a particular transport request, user and destination.
[0116] In variations, the network computer system 100 and / or rider device 102 (e.g., executing service application 106) implement prompt determination component to determine topics for prompt objects 322 based on factors that include the destination for the transport service and other service parameters (e.g., pickup location or region, service type, vehicle type, etc.), contextual information (e.g., time, weather, etc.), and / or popularity metrics. In such examples, the prompt determination component can be based on rules, heuristics, machine learning algorithms and / or artificial intelligence. For example, prompt objects 322 can be determined as topics of interest for the user, and the topics can then be packaged as prompt objects 322 or other selectable objects that the user can interact with.
[0117] In examples in which machine-learning and artificial intelligence is used to determine the prompt objects 322, examples can optimize the selection / determination for factors such as relevance or interest to the user. The optimization can further includeongoing learning and tuning of models and processes. For example, the interactive panel 310 can include feedback functionality 325 to enable the user to provide feedback as to the relevance of the prompt objects 322 and or the corresponding response items 328. The feedback 325 can be recorded in association with contextual information (e.g., time of day, estimated arrival time, type of transport received), the destination, and / or the user identifier. As an addition or alternative, feedback for tuning results can be determined from user interaction following the results. The requester feedback and associated information can be used to update or tune the respective models and processes, such as by updating machine learned weights used in connection with the selection of prompt objects 322. Further, user responses to prompt objects 322 can also be used to gather information about the destination that may otherwise not be readily available to the network computer system 100. For example, if one of multiple entries 328 (e.g., venue at destination) selected responsive to a user selection of a prompt object 322 is associated with negative feedback (e.g., "thumbs down"), then the particular venue may be weighted down or removed from a list of prompt objects 322 for the destination. In cases where a particular venue is unexpectedly closed or undesirable, the network computer system 100 can reflect the change by reducing the presence of a corresponding entry 328 for the venue.
[0118] As shown by an example of FIG. 3A-3E, once the user selects a prompt object 322, additional prompt objects 322 can be returned along with the result entries 328 for the selected prompt object. The selection of prompt objects 322 can include one or more prompt objects which are selected based on the user’s prior selection (e.g., coffee after food, etc.). The selection of prompt objects 322 can also be modified based on a user’s interest, as well as the degree to which the result entries 328 are detected to match the user interest.
[0119] Further, as shown in FIG. 3C, the user can navigate or scroll the interactive panel 310 for prompt objects 322 and / or information items. Through scrolling / navigation, the user can view additional prompt objects 322 that were not previously displayed with the interactive panel 310. For example, the user can be prompted to request information for “cheap eats”, investigate options via result entries 328 (FIG. 3B), and through a series of interactions to select prompt objects 322 and result entries 328, view information about venues for fast food, tacos and milkshakes, as well as lounges.
[0120] In some examples, the selection of additional prompt objects 322 can be based in part on an assumption that the user is not interested or entirely satisfied in the response entries 328. For example, one of the additional prompts can identify another type ofvenue for food ("comfort food option") on the assumption that the user may not be interested in fast food.
[0121] FIG. 3D illustrates an example of a response entry 328 that is expanded based on, for example, user interaction. When expanded, the response entry 328A can be displayed with various forms of venue specific information. For the destination of a particular airport, an expanded response entry 328A can include destination and venue specific information, retrieved from, for example, particular airport's website, indicating the sublocation within the airport where the selected venue is located, as well as the hours of operation for the lounge area, and various other forms of information. Graphic elements or assets can also be used to reflect certain amenities that are known to be available (e.g., Wi-Fi or Internet access, etc.), such as a response items convey a requisite set of information in an optimal format and data size.
[0122] FIG. 3E illustrates another implementation of the interactive panel 310, displaying specific response items 328 about a corresponding selected prompt object 322A (“where to find milkshakes?). In an example of FIG. 3E and FIG. 3F, thumbnail images can be used to show the actual venue at the destination, where the thumbnail images are optimally sized and dimensioned to reflect the particular venue. Venue specific information 327 can also be provided with the entries 328. An example of FIG. 3E illustrates deeper understanding of the venue options, as the determination of which venues has milkshakes can require a process to ingest or parse the menu items of restaurants in the sub-region of the destination.
[0123] SEARCH INTERFACE EXAMPLES
[0124] FIG. 3F through FIG. 31 illustrate examples of interfaces for enabling usergenerated prompts from users. The user interface 300 can include one or more interfaces for receiving user-generated prompts, such as search entries or chat queries. With reference to FIG. 3F and FIG. 3G, a user-generated prompt interface 350 receives a chat inquiry, corresponding to a natural language input from the requester. FIG. 3F illustrates an example in which a natural language response 344 is provided in response to the query of the user. Additionally, based on implementation, the interactive interface 310 can be triggered to provide result entries 328 that satisfy at least one of a criteria or intent of the query. In additional examples, a map interface 360 can render a relevant region that includes, is near or is otherwise relevant to the destination of the transport service of the user.
[0125] FIG. 3G illustrates an alternative implement where the user interacts with the user-generated prompt interface 350 to display response entries 328 within the interactive interface 310. Based on implementation, map interface 360 is provided to visualize locations relative to one another, the destination of the user’s transport, and / or a relevant location to the user’s destination (e.g., user’s flight destination, when the transport destination is the airport). The response entries 328 can include highly relevant information about the respective venue and, with resources (e.g., direct link 349 to venue website) provided with the respective response entry 328. The user can continue to interact with the user-generated prompt interface 350 to provide additional natural language queries as prompts.
[0126] In examples, the user-generated prompt interface 350 can be surfaced in the service application in response to one or more factors, such as the service state of the requester, the type of destination for the transport request, the profile of the user, and / or contextual information. The user-generated prompt interface 350 can be enabled when the service application 106 is opened and / or when the user is associated with a particular service state (e.g., on-route to destination). The user-generated prompt interface 350 can be optimized for providing relevant information specific to the destination of the transport request or service, as well as to locations that are relevant to either the destination (e.g., surrounding area or businesses to the destination) or specifically to the user or user’ s purpose for the destination (e.g., user flight destination, when the user is on-route to the airport). As described with other examples, the user interface 300 can be configured for the destination, for user-specific profile information, and also for user-specific information related to the current trip. In the latter case, the service application 106 can be provided or otherwise determine, for example, the user’s travel plans (e.g., Hawaii). As an example, if the user requests “where are some good places to eat near the airport when we land” user-generated prompt interface 350 can tailor the response entries (including search results) for restaurants near the flight-destination airport, and / or suggest restaurants at the flight destination that meet the user’s cuisine of choice (e.g., spice) or dietary restrictions (e.g., vegetarian).
[0127] With reference to exampled of FIG. 3H and FIG. 31, the search interface 370 can utilize the destination of a transport service to, for example, (i) generate user- visible search prompts 372 for the user to perform a search (e.g., display the destination in a search bar), (ii) supplement (or augment) user search terms with one or more parameters that are based on the user destination (e.g., supplement “what is open right now” with“what is open right now at SFO”), (iii) filter search results based on one or more parameters associated with the destination, and / or (iv) optimize a search process performed by the user through the service application based on the destination parameters. By way of examples, the destination-specific information provided through a search process can include prompt-objects that are relevant to the search term, map interface 360 and / or other information about places associated with the destination of the transport request.
[0128] The search interface 370 can also be provided with the map interface 360 depicting a geographic region associated with the transport request 101, and trip information that is specific to the requester and contextual to the transport request 101 (e.g., a drop-off time, a flight identifier, and a flight departure time, such as “Departing at 6:00 AM - Flight UA 5346”). The search interface 370 can include a search entry field 372 that is preconfigured with an indicator that reflects the destination, or a weight, domain or point of focus of the gcoindcx used for providing the user with search results while they are receiving transport. The preconfigured search entry field 372 can correspond to the destination of the transport request 101 (e.g., “Search places at SFO”), such that search input by the requester is scoped to the destination. The search interface 370 further displays a set of prompt objects 322 that are specific to the destination (e.g., “Asian cuisine options?”, “Where to find matcha?”, “Hawaiian cuisine options?”).Further, the preconfigured text of the search entry field 372 can be based on a prior search result or user input. The manner in which the search entry field 372 is preconfigured can therefore be based on context that includes the destination of the transport service requester is receiving, associated or relevant locations based on user-specific information (e.g., airline booking infomration for SFO, to show flight destination search entry field 372), and / or user-preferences specific to the destination or related locations. In examples, the prompt objects 322 and other content of the search interface 370 can be determined from the geoindex, including based on enrichment data, embeddings, and ranking metadata determined for the destination through the process described elsewhere herein.
[0129] In an example of FIG. 31, the search entry field 372 is configured to receive textual input from the requester, and to display a set of autocomplete suggestions (e.g., place names or terms determined from the geoindex for the destination) as the requester enters the textual input. The 320 can also display additional prompt objects 322 corresponding to topical queries (e.g., “Croissant shops?”) that are determined to be relevant to the textual input provided in the search interface 370. In at least someexamples, after each character entry (e.g., soft key strike) by the user, a search is updated (e.g., filtered) to reflect the additional information provided by the user entry. A candidate set of matching entries 373 can also be displayed to the user, where each candidate entry matches the search term at its current state (i.e., after the most recent character entry). The user can select the matching candidate entry before the user has completed the full search term. The selection of the matching search term can result in the performance of an operation through the search interface 370, such as the retrieval of content matching the selected entry. Further, in some examples, after each entry, the prompt objects 322 provided in the 320 changes to match a current candidate entry for the user’s search term.
[0130] HARDWARE DIAGRAM
[0131] FIG. 4 is a block diagram that illustrates a computer system upon which one or more embodiments described herein may be implemented. For example, in the context of FIG. 1 A, the network system 100 may be implemented using a network computer system or combination of network computer systems, such as described with an example of FIG.4. Additionally, methods such as described with examples of FIG. 2A and FIG. 2B can be implemented using a computer system such as described with an example of FIG. 4.
[0132] In one implementation, the computer system 400 includes one or more processors 410, memory resources 420, and a communication interface 430. The computer system 400 includes at least one processor 410 for processing information. The memory resources 420 may include a random-access memory (RAM) or other dynamic storage device, for storing information and instractions to be executed by the processor(s) 410. The memory resources 420 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor(s) 410. The computer system 400 may also include other forms of memory resources, such as static storage devices for storing static information and instructions for the processor 410. The memory resources 420 can store information and instructions, including instructions 442 for implementing a network system 100, such as described with an example of FIG. 1A. Additionally, the processor(s) 410 can execute the instructions 442 to implement methods such as described with example methods of FIG.2A and FIG. 2B.
[0133] The communication interface 430 can enable the computer system 400 to communicate with one or more networks 480 (e.g., cellular network) through use of the network link (wireless or wireline). Using the network link, the computer system 400 can communicate with one or more other computing devices and / or one or more other serversor data centers. In some variations, the computer system 400 can receive transport requests from requester devices via the network link 480. Additionally, the computer system 400 can receive information from provider devices, from which forecasts of provisioning levels, location bias and other aspects described herein may be determined.
[0134] Examples described herein are related to the use of the computer system 400 for implementing the techniques described herein. According to one embodiment, those techniques are performed by the computer system 400 in response to the processor 410 executing one or more sequences of one or more instructions contained in the memory resources 420. Such instructions may be read into the memory resources 420 from another machine-readable medium, such as the storage device. Execution of the sequences of instructions contained in the memory resources 420 causes the processor 410 to perform the process steps described herein. In alternative implementations, hardwired circuitry may be used in place of or in combination with software instructions to implement examples described herein. Thus, the examples described arc not limited to any specific combination of hardware circuitry and software.
[0135] USER DEVICE
[0136] FIG. 5 is a block diagram illustrating an example user device for use with examples as described. In an example, a user device 500 may be implemented as a requester device 102 that executes a designated service application 106 for use with an on-demand service as provided by a network system 100. In many implementations, a user device 500 can include a mobile computing device, such as a smartphone, tablet computer, laptop computer, VR or AR headset device, and the like. As such, the user device 500 can include typical telephony and / or tablet features such as a microphone 545, a camera 550, a satellite receiver 560, and a communication interface 510 to communicate with external entities using any number of wireless communication protocols. In certain aspects, the user device 500 can store a designated application (e.g., a service app 532) in a local memory 530. In variations, the memory 530 can store additional applications executable by one or more processors 540 of the user device 500, enabling access and interaction with one or more host servers over one or more networks 580.
[0137] In response to a user input 518 (e.g., input for cards, input to select response feature), the service app 532 can generate the user interface 300 (FIG. 3A-FIG. 31), to display prompt objects 111, 322, response entries 113, 328, and user-generated prompt interface 350. When the user device 500 is used as a requester device, the serviceapplication 106 executes to provide the user interface 300, such as shown with examples of FIG. 3A through FIG. 31.CONCLUSION
[0138] It is contemplated for examples described herein to extend to individual elements and concepts described herein, independently of other concepts, ideas or system, as well as for examples to include combinations of elements recited anywhere in this application. Although examples are described in detail herein with reference to the accompanying drawings, it is to be understood that the concepts are not limited to those precise examples. Accordingly, it is intended that the scope of the concepts be defined by the following claims and their equivalents. Furthermore, it is contemplated that a particular feature described either individually or as part of an example can be combined with other individually described features, or parts of other examples, even if the other features and examples make no mentioned of the particular feature. Thus, the absence of describing combinations should not preclude having rights to such combinations.
Claims
WHAT IS CLAIMED IS:
1. A network system comprising :one or more processors;memory resources to store a set of instructions;wherein the one or more processors execute the set of instructions to perform operations comprising:receiving, over one or more networks, a request for a transport service from a requester device, the request specifying a destination;determining when a service state associated with the request satisfies a predetermined condition; andin response to detecting the service state satisfies the predetermined condition, causing the requester device to display a set of prompt objects based at least in part on the destination, each prompt object of the set being interactive to enable the requester to receive information that is specific to the destination and based on a topic or label of the prompt object.
2. The network system of claim 1, wherein detecting when the service state satisfies the predetermined condition includes detecting that the requester is receiving the transport service within a vehicle that is matched to the request.
3. The network system of claim 1, wherein the operations further comprise:determining the set of prompt objects for the requester based at least in part on a context of the request or transport service being provided.
4. The network system of claim 3, wherein the context includes a current time or an estimated time of arrival for the requester to arrive at the destination.
5. The network system of claim 3, wherein the context includes a type of the transport service provided to the requester.
6. The network system of claim 1, wherein the requester is associated with a profile, the profile including historical information about at least one of (i) transport services that the requester has previously received, or (ii) activities the requester has previouslyperformed in connection with transport services the requester has previously requested, and wherein determining the set of prompt objects is based at least in part on the historical information.
7. The network system of claim 6, wherein the historical information of the profile includes prior food deliveries of the requester, and wherein determining the set of prompt objects includes determining one or more prompt objects for restaurants that are at or near the destination that are based on the prior food deliveries.
8. The network system of claim 1, wherein the operations further comprise:associating a collection of prompt objects with the destination;wherein determining the set of prompt objects includes selecting the set of prompt objects from the collection, based at least in part on one of (i) a context of the transport service, or (ii) a profile of the requester.
9. The network system of claim 8, wherein the operations further comprise:determining a ranking for the selected set of prompt objects, the ranking being based at least in part on one of the context of the transport service, or the profile of the requester; andcausing the requester device to display the set of prompt objects in accordance with the ranking.
10. A non-transitory computer-readable medium that stores instructions, which when executed by one or more processors of a computing system, cause the computer system to perform operations that include:receiving, over one or more networks, a request for a transport service from a requester device, the request specifying a destination;determining when a service state associated with the request satisfies a predetermined condition: andin response to detecting the service state satisfies the predetermined condition, causing the requester device to display a set of prompt objects based at least in part on the destination, each prompt object of the set being interactive to enable the requester to receive information that is specific to the destination and based on a topic or label of the prompt object.
11. The non-transitory computer- readable medium of claim 10, wherein detecting when the service state satisfies the predetermined condition includes detecting that the requester is receiving the transport service within a vehicle that is matched to the request.
12. The non-transitory computer- readable medium of claim 11, wherein the operations further comprise:determining the set of prompt objects for the requester based at least in part on a context of the request or transport service being provided.
13. The non-transitory computer- readable medium of claim 12, wherein the context includes a current time or an estimated time of arrival for the requester to arrive at the destination.
14. The non-transitory computer- readable medium of claim 12, wherein the context includes a type of the transport service provided to the requester.
15. The non-transitory computer- readable medium of claim 10, wherein the requester is associated with a profile, the profile including historical information about at least one of (i) transport services that the requester has previously received, or (ii) activities the requester has previously performed in connection with transport services the requester has previously requested, and wherein determining the set of prompt objects is based at least in part on the historical information.
16. The non-transitory computer-readable medium of claim 15, wherein the historical information of the profile includes prior food deliveries of the requester, and wherein determining the set of prompt objects includes determining one or more prompt objects for restaurants that are at or near the destination that are based on the prior food deliveries.
17. The non-transitory computer- readable medium of claim 10, wherein the operations further comprise:associating a collection of prompt objects with the destination;wherein determining the set of prompt objects includes selecting the set of prompt objects from the collection, based at least in part on one of (i) a context of the transport service, or (ii) a profile of the requester.
18. The non-transitory computer-readable medium of claim 17, wherein the operations further comprise:determining a ranking for the selected set of prompt objects, the ranking being based at least in part on one of the context of the transport service, or the profile of the requester; andcausing the requester device to display the set of prompt objects in accordance with the ranking.
19. A computer-implemented method comprising:receiving, over one or more networks, a request for a transport service from a requester device, the request specifying a destination;determining when a service state associated with the request satisfies a predetermined condition; andin response to detecting the service state satisfies the predetermined condition, causing the requester device to display a set of prompt objects based at least in part on the destination, each prompt object of the set being interactive to enable the requester to receive information that is specific to the destination and based on a topic or label of the prompt object.
20. The method of claim 19, wherein detecting when the service state satisfies the predetermined condition includes detecting that the requester is receiving the transport service within a vehicle that is matched to the request.
