[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121738-en":3,"doc-seo-121738-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121738,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",6,"Technology","Machine Learning Based Virtual Concierge for Planning Group Activities","Planning group activities such as shared trips is hindered by conflicting constraints and variables, making it hard to find options that all members can agree on. This disclosure presents a virtual concierge that collects multiple potentially conflicting inputs from group members and generates optimized, tailored recommendations. The system can use large language models for language understanding and natural interaction, using efficient prompt-generation tuned via techniques such as adapter layers and few-shot prompt tuning. Machine learning supports generating recommendation sets from different members’ preferences.","Technical Disclosure Commons  \nDefensive Publications Series  \nAugust 2023  \nMachine Learning Based Virtual Concierge for Planning Group Activities  \nCliff Chin Ngai Sze Russell Goldenbroit  \nElisabeth Jeremko  \nFollow this and additional works at: [https://www.tdcommons.org/dpubs_series](https://www.tdcommons.org/dpubs_series)  \nRecommended Citation  \nSze, Cliff Chin Ngai; Goldenbroit, Russell; and Jeremko, Elisabeth, \"Machine Learning Based Virtual Concierge for Planning Group Activities\", Technical Disclosure Commons,(August 25, 2023)  \n[https://www.tdcommons.org/dpubs_series/6178](https://www.tdcommons.org/dpubs_series/6178)  \nThis work is licensed under a Creative Commons Attribution 4.0 License.  \nThis Article is brought to you for free and open access by Technical Disclosure Commons. It has been accepted for inclusion in Defensive Publications Series by an authorized administrator of Technical Disclosure Commons.  \nMachine Learning Based Virtual Concierge for Planning Group Activities  \nABSTRACT  \nWhen a group of individuals attempt to plan a group activity such as a joint trip to a common destination, the presence of conflicting constraints makes it difficult to arrive at a plan that is agreeable to all. This disclosure describes a virtual concierge that accepts as input multiple, potentially conflicting constraints from multiple individuals planning collective travel (or other group activity) and outputs optimized recommendations tailored for the individuals in the group. The virtual concierge application can leverage large language models (LLM) for  \nlanguage understanding and for natural user interactions. The virtual concierge can generate  \nprompts for an LLM that has been efficiently tuned using techniques such as adapter layers, few  \nshot prompt tuning, etc. Machine learning (ML) can be used to generate a set of  \nrecommendations based on the preferences of different individuals in the group.  \nKEYWORDS  \n● Virtual concierge  \n● Virtual assistant  \n● Machine learning  \n● Large language model (LLM)  \n● Group travel  \n● Group activity  \n● Travel planning  \n● Multifactor optimization  \n● Complex optimization  \nPublished by Technical Disclosure Commons, 2023 2  \nBACKGROUND  \nWhen a group of individuals attempt to plan a joint trip to a common destination (or another activity together), the presence of conflicting constraints or variables (e.g., cost constraints, origin locations, activity preferences, etc.) makes it difficult to arrive at a plan that is agreeable to all. With a complex set of constraints, the complete set of available options needed to arrive at informed decisions may be difficult to find or may be overlooked, resulting in a  \nsuboptimal plan or no feasible plan at all.  \nWhile travel websites that enable searching for travel tickets, hotels, and other services  \ncan be used to plan for a group of individuals, such planning requires manual effort and is  \ntedious. Also, manually created plans are only feasible if the members of the group have some  \nflexibility with their travel plans. Currently, a group of individuals with multiple starting points  \nand a common destination may choose to engage a travel agency or a (human) advisor, who  \naccounts for the multiple inputs (time, budget, origin/destinations, etc.), searches for results for  \nvarious combinations of options, and summarizes the set of optimal options. Hiring a human  \nadvisor for such labor-intensive and time-consuming tasks can be expensive.  \nDESCRIPTION  \nThis disclosure describes a virtual concierge that accepts as input multiple, potentially  \nconflicting requests from multiple individuals planning collective travel or other joint activity  \nand outputs optimized recommendations that take into account preferences of various individuals in the group. The virtual concierge can be offered as a service provided by a virtual assistant, or  \nvia a separate software application, e.g., web or mobile application. The virtual concierge  \nap","cbCaivFHWrarwyJf","https://ap.wps.com/l/cbCaivFHWrarwyJf","pdf",185829,1,8,"English","en",105,"# Background\n## Challenges in group travel planning\n# Description\n## Virtual concierge system overview\n## Example user journey and interface inputs","[{\"question\":\"What problem does the virtual concierge address for group planning?\",\"answer\":\"It addresses how conflicting constraints and variables across group members make it difficult to produce a plan that everyone can agree on, often leading to suboptimal or infeasible plans.\"},{\"question\":\"How does the virtual concierge handle inputs from multiple people?\",\"answer\":\"It accepts multiple, potentially conflicting constraints or requests from different individuals and produces optimized recommendations that account for prioritized group requirements.\"},{\"question\":\"How are large language models used in the virtual concierge?\",\"answer\":\"The virtual concierge can leverage LLMs for language understanding and natural user interactions, and it can generate prompts for an LLM tuned using methods such as adapter layers and few-shot prompt tuning.\"}]","Machine Learning Based Virtual Concierge for Planning Group Activities | PDF",1785806572,20,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-based-virtual-concierge-for-planning-group-activities","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-based-virtual-concierge-for-planning-group-activities/121738/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the virtual concierge address for group planning?","Question",{"text":75,"@type":76},"It addresses how conflicting constraints and variables across group members make it difficult to produce a plan that everyone can agree on, often leading to suboptimal or infeasible plans.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the virtual concierge handle inputs from multiple people?",{"text":80,"@type":76},"It accepts multiple, potentially conflicting constraints or requests from different individuals and produces optimized recommendations that account for prioritized group requirements.",{"name":82,"@type":73,"acceptedAnswer":83},"How are large language models used in the virtual concierge?",{"text":84,"@type":76},"The virtual concierge can leverage LLMs for language understanding and natural user interactions, and it can generate prompts for an LLM tuned using methods such as adapter layers and few-shot prompt tuning.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":29,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":29,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":106,"slug":136},19,"General","general"]