Artificial intelligence-generated badges for search

Machine learned models generate badges to enhance search results by describing product attributes, addressing the inefficiencies of traditional search systems and providing users with insightful, organized, and efficient search outcomes.

JP2024163030AActive Publication Date: 2024-11-21GOOGLE LLC

Patent Information

Application Number
JP2024066802
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-04-17
Publication Date
2024-11-21
Estimated Expiration
2044-04-17

AI Technical Summary

Technical Problem

Traditional search results pages are verbose, unorganized, and time-consuming, providing minimal information and making it difficult for users to discern which products are better suited for specific uses based on location, purpose, time, or user type.

Method used

Utilizing machine learned models to process web data and generate badges that describe specific uses, advantages, and disadvantages of products, which are then used to rank and annotate search results, providing intuitive and tailored search interfaces.

Benefits of technology

Enhances search results by providing labeled and diverse search outcomes, reducing redundancy and computational cost through badge clustering, and enabling users to make informed decisions quickly.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024163030000001_ABST
    Figure 2024163030000001_ABST
Patent Text Reader

Abstract

To provide systems and methods for generating and utilizing artificial intelligence-generated badges, which may include processing web information associated with a subject to determine particular qualities of the subject.SOLUTION: Qualities can then be utilized to generate one or more badges. The badges can then be utilized for search result determination and display. The badges may be utilized for search result ranking and may be utilized to annotate search results in a search result interface.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] Priority claim This application claims priority to U.S. Provisional Application No. 63 / 501,123, which has a filing date of May 9, 2023. Applicants claim priority to and the benefit of each such application and incorporate by reference herein in their entireties all such applications.

[0002] The present disclosure relates generally to artificial intelligence generated badges for search. More specifically, the present disclosure relates to generating badges for search results based on processing web information associated with a subject matter using one or more machine learning models to determine specific uses and / or benefits for that particular subject matter, which badges can then be utilized to rank and / or annotate the search results. [Background technology]

[0003] Different objects and environments may have different uses, pros and cons. For example, different products may be better for particular locations and / or particular users. However, discerning which products are superior for some uses can be difficult when reviewing a traditional search result page.

[0004] For example, traditional search results may provide multiple web resources to a user based on traditional text query processing, but the search result list alone may provide minimal information to a user unless the user selects a search result and is navigated to the associated web page. Navigation between search result pages to different landing pages can be time consuming and overall unproductive. Additionally, traditional search result pages can be redundant and / or unorganized. [Prior art documents] [Non-patent literature]

[0005]

Non-patent document 1

Non-patent document 2

Non-patent document 3

Non-patent document 4

Non-patent document 5

Non-patent document 6

[0006] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the description that follows, or may be learned from the description, or may be learned through practice of the embodiments.

[0007] One exemplary aspect of the present disclosure is directed to a computing system. The system may include one or more processors and one or more non-transitory computer-readable media collectively storing instructions that, when executed by the one or more processors, cause the computing system to perform operations. The operations may include obtaining web data associated with a particular product. The web data may include web information associated with the particular product. The operations may include processing the web data with one or more machine-learned models to determine one or more specific uses associated with the particular product. The one or more specific uses may be determined based on the web information. The operations may include generating one or more badges based on the one or more specific uses. In some implementations, the one or more badges can describe the one or more specific uses. The operations may include storing the one or more badges. The one or more badges may be stored with data describing an association with the particular product. The operations may include obtaining a search query. In some implementations, the search query may be associated with a product type. The particular product may be of the product type. The operations may include providing a search result interface based on the search query and the one or more badges.

[0008] In some implementations, the web data may include user reviews of a particular product. The one or more specific uses may be determined based on the frequency of the term in the web information, sentiment analysis, and semantic understanding. The one or more specific uses may be associated with at least one of a scenario for using the particular product, a purpose for using the particular product, a time for using the particular product, or a type of user using the product.

[0009] In some implementations, the operations may include processing one or more badges with the embedding model to generate one or more respective badge embeddings in the embedding space, and determining a plurality of search results for display in a search result interface based on the one or more badge embeddings. Determining the plurality of search results may include processing a search query with the embedding model to generate a query embedding, determining that the query embedding is associated with the badge embedding, and providing product search results in the search result interface that describe the particular product. The operations may further include processing a plurality of other badges associated with a plurality of other products with the embedding model to generate a plurality of other badge embeddings, determining one or more badge clusters based on the one or more badge embeddings and the plurality of other badge embeddings, and determining one or more search results in the search result interface based on the one or more badge clusters.

[0010] In some implementations, providing a search result interface based on the search query and the one or more badges may include determining that one or more badges are associated with the search query and obtaining product data associated with the particular product. The product data may include one or more links to one or more web resources associated with the particular product. The search result interface may include product search results. The product search results may include data describing the product and the one or more badges. In some implementations, the one or more machine-learned models may include a natural language processing model. The one or more particular uses may be determined based at least in part on sentiment analysis. The web information may include product descriptions and answers to frequently asked questions.

[0011] Another exemplary aspect of the present disclosure is directed to a computer-implemented method. The method may include determining, by a computing system including one or more processors, one or more web resources associated with the object. The method may include processing, by the computing system, one or more content items of the one or more web resources with one or more machine-learned models to determine at least one of one or more advantages or one or more disadvantages associated with the object. The method may include generating, by the computing system, one or more badges based on at least one of the one or more advantages or one or more disadvantages associated with the object. In some implementations, the one or more badges may include generated text labels. The method may include obtaining, by the computing system, a search query from a user computing system. The method may include determining, by the computing system, that the object or at least one of the one or more badges is associated with the search query, and providing, by the computing system, a particular object search result for display in a search result interface. The particular object search result may include data describing the object and user interface elements describing the one or more badges.

[0012] In some implementations, determining, by the computing system, that the object or at least one of the one or more badges is associated with the search query may include processing, by the computing system, the search query with a search engine to determine a plurality of search results, and determining, by the computing system, a set of badges associated with the plurality of search results. The set of badges may include one or more badges. Determining, by the computing system, that the object or at least one of the one or more badges is associated with the search query may include providing, by the computing system, a set of search results in a search result interface based on the set of badges.

[0013] In some implementations, determining, by the computing system, that the object or at least one of the one or more badges is associated with the search query may include determining, by the computing system, a set of badges associated with the search query. The set of badges may include one or more badges. Determining, by the computing system, that the object or at least one of the one or more badges is associated with the search query may include determining, by the computing system, respective search results for each particular badge in the set of badges, and providing, by the computing system, the respective set of search results in a search result interface based on the set of badges.

[0014] In some implementations, the method may include indexing, by a computing system, one or more badges with data describing the object. Determining the one or more web resources may include obtaining, by the computing system, data describing the object, processing, by the computing system, with a search engine, the data describing the object to determine a set of object-specific search results, and selecting, by the computing system, one or more particular object-specific search results from the set of object-specific search results. In some implementations, the one or more web resources may include a web marketplace listing for the object.

[0015] Another example aspect of the present disclosure is directed to one or more non-transitory computer-readable media collectively storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations. The operations may include obtaining a search query. The search query may be associated with a particular object type. The operations may include processing the search query to determine a plurality of badges associated with the search query. In some implementations, the plurality of badges may include a plurality of particular benefits associated with a plurality of different objects of the particular object type. The operations may include determining a subset of the plurality of badges for display. The operations may include obtaining a plurality of search results associated with the subset of the plurality of badges. The plurality of search results may include one or more respective search results for each particular badge of the subset of the plurality of badges. The operations may include providing a search result interface for display. In some implementations, the search result interface may include a plurality of search results. Each of the plurality of search results may be annotated with a particular badge associated with the respective search result.

[0016] In some implementations, a plurality of badges may be generated by processing a plurality of reviews for each of a plurality of different objects. The search result interface may include a first panel for a plurality of search results and a second panel for a model-generated response. The model-generated response may be generated by processing the search query with a language model to generate a model-generated response. The model-generated response may be responsive to the search query. The language model may include a text-to-text generative model.

[0017] In some implementations, the search results may include product search results associated with a particular set of web resources. The search result interface may include product search results, general search results, and a natural language response. The natural language response may be generated using a machine-learned generative model. The general search results may be determined using a search engine.

[0018] Another example aspect of the present disclosure is directed to a computing system for providing search results based on badges determined by a machine-learned model. The system may include one or more processors and one or more non-transitory computer-readable media collectively storing instructions that, when executed by the one or more processors, cause the computing system to perform operations. The operations may include obtaining input data. The input data may include a search query. The search query may be associated with a subject of the search. The operations may include processing the search query to determine a plurality of preliminary search results. In some implementations, the plurality of preliminary search results may include a plurality of content items responsive to the search query. The operations may include processing at least a subset of the plurality of content items with the machine-learned model to determine a plurality of badges associated with a subject of the search. The plurality of badges may be associated with a plurality of terms determined to be associated with the subject. The operations may include determining a plurality of particular search results associated with the plurality of badges. In some implementations, each particular search result may be associated with a respective badge of the plurality of badges. The operations may include providing the plurality of particular search results for display along with the plurality of badges.

[0019] In some implementations, the plurality of preliminary search results may include one or more web resources including user reviews. One or more of the plurality of badges may be determined based on the reviews provided by the user. Each particular search result of the plurality of particular search results may be provided for display with a respective user interface element describing the respective badge. In some implementations, the machine-learned model may include a natural language processing model. In some implementations, the operations may include processing the search query with the language model to generate a model-generated response, the model-generated response being responsive to the search query, and providing the model-generated response in a search result interface adjacent to the plurality of particular search results. The model-generated response may be determined by processing one or more of the plurality of preliminary search results with the language model.

[0020] In some implementations, the plurality of badges may be determined based at least in part on a sentiment analysis performed by a machine learning model. The plurality of badges may be determined based at least in part on a determined frequency of one or more terms. The subject matter may include a product type. The plurality of badges may be associated with qualities associated with different products of the product type. In some implementations, each particular search result of the plurality of particular search results may include a unique search result determined to be responsive to the search query and a respective badge.

[0021] Another exemplary aspect of the present disclosure is directed to a computer-implemented method for searching categories determined by a machine-learned model. The method may include obtaining, by a computing system including one or more processors, input data. The input data may include a search query. In some implementations, the search query may be associated with a subject of the search. The method may include processing, by the computing system, the search query to determine a plurality of preliminary search results. The plurality of preliminary search results may include a plurality of content items responsive to the search query. The method may include processing, by the computing system, at least a subset of the plurality of content items with the machine-learned model to determine a plurality of badges associated with a plurality of topics determined to be associated with the subject. The method may include determining, by the computing system, a plurality of specific search results associated with the plurality of badges. In some implementations, each specific search result may be associated with a respective badge of the plurality of badges. The method may include providing, by the computing system, the plurality of specific search results for display in a search result interface along with the plurality of badges.

[0022] In some implementations, the search result interface may include a query input box, a plurality of specific search results each with a respective badge of the plurality of badges, and a text-to-text generative model output. The text-to-text generative model output may be generated by processing the search query with the text-to-text generative model. The plurality of topics may describe one or more descriptors that differentiate web resources associated with the subject matter. In some implementations, the plurality of preliminary search results may include trusted web resources associated with web domains stored in a verified database.

[0023] In some implementations, the multiple badges may be determined based on determining a multiple number of products associated with the subject matter, determining a respective product description for each of the multiple products, determining a multiple number of differentiators associated with the multiple products, and determining the multiple badges based on the multiple differentiators. The multiple differentiators may describe qualities that differentiate a particular product from one or more other products associated with the subject matter.

[0024] Another example aspect of the present disclosure is directed to one or more non-transitory computer-readable media collectively storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations. The operations may include obtaining input data. The input data may include a search query. In some implementations, the search query may be associated with a product type. The operations may include processing the input data to determine a plurality of preliminary search results. The plurality of preliminary search results may include a plurality of content items associated with the product type. The operations may include processing at least a subset of the plurality of content items with a machine-learned model to determine a plurality of badges associated with a subject of the search. In some implementations, the plurality of badges may be associated with a plurality of attributes determined to be associated with at least a subset of objects in the product type. The operations may include determining a plurality of specific search results associated with the plurality of badges. Each specific search result may be associated with a respective badge of the plurality of badges. The operations may include providing the plurality of specific search results for display along with the plurality of badges.

[0025] In some implementations, the plurality of attributes may include one or more attributes associated with validity for a particular set of objects of the product type for a unique use. Each of the plurality of specific search results may be associated with a respective product of the product type. In some implementations, the operations may include obtaining a badge selection associated with a particular badge of the plurality of badges and providing a plurality of badge-specific search results associated with the particular badge.

[0026] Other aspects of the present disclosure are directed to various systems, apparatus, non-transitory computer-readable media, user interfaces, and electronic devices.

[0027] These and other features, aspects, and advantages of various embodiments of the present disclosure will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain related principles.

[0028] Detailed descriptions of embodiments directed to persons skilled in the art are set forth herein and refer to the accompanying figures. [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 is a block diagram of an exemplary badge generation and retrieval system according to an exemplary embodiment of the present disclosure. [Diagram 2] 1 is a block diagram of an exemplary search system according to an exemplary embodiment of the present disclosure. [Diagram 3] FIG. 2 is a flowchart diagram of an example method for performing badge generation and retrieval, according to an example embodiment of the present disclosure. [Figure 4] 1 is a diagram of an exemplary search results interface with a knowledge panel according to an exemplary embodiment of the present disclosure. [Diagram 5]FIG. 13 is a diagram of an example search results interface with adjacent panels for model-generated responses, badged results, and general results, according to an example embodiment of the present disclosure. [Figure 6] 1 is a diagram of an example search results interface with a badge search result tile according to an example embodiment of the present disclosure. [Figure 7] FIG. 2 is a flowchart diagram of an example method for performing badge generation and retrieval, according to an example embodiment of the present disclosure. [Figure 8] 1 is a flowchart diagram of an example method for performing a badged search result search, according to an example embodiment of the present disclosure. [Figure 9A] FIG. 2 is a block diagram of an exemplary computing system for performing badge generation and retrieval, according to an exemplary embodiment of the present disclosure. [Figure 9B] FIG. 2 is a block diagram of an exemplary computing system for performing badge generation and retrieval, according to an exemplary embodiment of the present disclosure. [Figure 10] FIG. 2 is a flow chart diagram of an example method for performing search-initiated badge generation, according to an example embodiment of the present disclosure. [Figure 11] FIG. 1 is a block diagram of an exemplary badge generation and indexing system according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Reference numbers that are repeated among the figures identify like features in various implementations.

[0031] In general, the present disclosure is directed to generating badges for objects and / or environments based on processing web data with an artificial intelligence system. In particular, the systems and methods disclosed herein can utilize one or more machine-learned models to process web information associated with a subject matter to determine specific uses, advantages, and / or disadvantages associated with the subject matter. The specific uses, advantages, and / or disadvantages can be utilized to generate badges that describe the specific uses, advantages, and / or disadvantages. The badges can then be utilized to rank search results when returning them and / or to annotate the search results with labels determined by the artificial intelligence.

[0032] For example, web data associated with an object or environment (e.g., web information (e.g., user reviews)) may be obtained. The web data may be processed with one or more machine-learned models to determine attributes associated with a particular object or environment (e.g., specific uses, advantages, and / or disadvantages). One or more badges may be generated based on the attributes, and the one or more badges may be indexed with the data associated with the particular object (e.g., the one or more badges may be indexed with web resource information associated with the particular object or environment). The indexed badges may then be ranked in response to receiving a search query. The ranking of the indexed badges may determine which search results and / or how they are provided to a user. The badges determined to be relevant to the search query may be provided for display along with data associated with one or more respective web resources (e.g., respective search results).

[0033] Badges generated using and / or based on artificial intelligence can provide users with insight into the qualities of different objects and / or environments that may traditionally be determined based on tedious and time-consuming manual review of various resources. Badges can further be utilized to provide a set of search results that are both responsive to the search results and diverse. Badges can be clustered to determine similar and / or redundant badges. Clusters can then be utilized to provide diverse, non-redundant results and / or to provide search results and badges from particular clusters based on the clusters' response to a search query.

[0034] Different objects and environments may have different uses, pros and cons. For example, different products may be better for particular locations and / or particular users. However, discerning which products are superior for some uses can be difficult when reviewing a traditional search result page.

[0035] The systems and methods disclosed herein can process web information, including web reviews associated with a product, using one or more machine-learned models to determine attributes associated with the product. One or more badges describing the one or more attributes can then be generated and indexed with data associated with the product (e.g., one or more web resources associated with the product). The one or more badges can be provided as user interface elements when providing data associated with the product to provide an indicator to a user of the one or more determined attributes of the product.

[0036] The one or more badges may be associated with a particular use, a particular advantage, and / or a particular disadvantage. In some implementations, the one or more badges may be generated based on a determined difference between a particular object or environment as compared to other objects or environments in the same object class (or type) or environment class (or type). The one or more badges may be provided as text labels on a search results page and may be selectable to redirect to search results pages associated with multiple objects or environments determined to share that particular attribute.

[0037] In some implementations, one or more badges may be associated with a particular use, which may be associated with where (e.g., scenario for use), why (e.g., purpose for use), when (e.g., time for use), and / or who (e.g., type of user for use). A use badge may be useful to indicate to a user the particular use for which an object is to be used, which may be specialized and / or advantageous.

[0038] For example, different kayaks may be better suited for different locations (e.g., lakes (e.g., calm water, flat water, etc.), ocean, whitewater, rivers, bays, waves, etc.), different purposes (e.g., fishing, recreation, touring, scuba diving, duck hunting, voyages, camping, expeditions, etc.), different times (e.g., winter, summer, fall, spring, day, night, etc.), and / or different users (e.g., children, beginners, larger people, tandems, dogs, shorter people, solo use, heavier people, etc.). Additionally and / or alternatively, different outfits may be configured for different locations (e.g., school, work, going out, parties, formals, beach, etc.), different purposes (e.g., casual use (e.g., any occasion), holidays, travel, special occasions, prom, graduation, exercise, date night, etc.), different times (e.g., hot season, cold season, specific holidays, winter, summer, fall, spring, day, night, etc.), and / or different users (e.g., wedding guests, maternity, different body types, children, infants, young adults, bigger people, dogs, shorter people, heavier people, nurses, lawyers, doctors, mechanics, etc.). In some implementations, user reviews may be processed to determine that different strollers may be associated with use in different locations (e.g., car seat, all-terrain, beach, amusement park, travel, jogging, hiking, shopping, city use, airplane, etc.), for different purposes (e.g., daily use, active, etc.), for different times (e.g., hot season, cold season, winter, summer, fall, spring, day, night, etc.), and / or for different users (e.g., for newborns, for twins, for tall parents, for triplets, toddlers, for older children, for short people, for grandparents, etc.).

[0039] Additionally and / or alternatively, different downhill skis may be more advantageous for different locations (e.g., on piste (e.g., resort), backcountry (e.g., off piste), moguls, park, icy conditions, bad snow, big mountain, steep, forest, narrow terrain, etc.), different purposes (e.g., powder, all mountain, carving, freeride (e.g., touring), racing (e.g., high speed), quick turns, etc.), different times (e.g., early season, late season, winter, after snow, after freeze, summer, fall, spring, day, night, etc.), and / or different users (e.g., beginners, casual skiers, competitive skiers, pros, children, bigger people, smaller people, awkward users, agile users, etc.). In some implementations, user reviews may be processed to determine that different vacuum cleaners may be associated with use in different locations (e.g., cars, recreational vehicles, stairs, hardwood floors, tile floors, mattresses, garages, carpets, fireplaces, small areas, furniture, sofas, etc.), for different purposes (e.g., pet hair, ashes, bugs, computers, long hair, step ladders, removing dirt, etc.), for different times (e.g., pollen season, winter, summer, fall, spring, daytime, night, etc.), and / or for different users (e.g., shorter people, taller people, children, people with children, people with allergies, etc.).

[0040] The systems and methods of the present disclosure provide several technical effects and benefits. As an example, the systems and methods can provide a search system that can identify and present search results associated with specific uses and / or benefits. For example, the systems and methods disclosed herein can utilize one or more machine learning models to determine specific uses and / or specific benefits associated with an object and / or environment, and the determined specific uses and / or specific benefits can then be utilized to provide intuitive and / or tailored search results to a user.

[0041] Another technical benefit of the systems and methods of the present disclosure is the ability to leverage artificial intelligence generated badges to provide diverse and labeled search results. In particular, badges may be generated and stored based on processing web information (e.g., web reviews) associated with particular objects and / or environments. A search query may then be received, thereby causing the search system to rank the various indexed badges. A set of badges and associated search results may be provided to a user in a search result interface to provide labeled search results responsive to the search query.

[0042] Another example of the technical effects and benefits relates to improved computational efficiency and increased functionality of computing systems. For example, the systems and methods disclosed herein can leverage badge embeddings to determine badge clusters. A badge cluster can describe a group of badges that are associated with the same or similar attributes, uses, advantages, and / or disadvantages. The systems and methods can then utilize the badge clusters to ensure that redundant badges are not provided to a user, thus limiting the computational cost of generating and providing search results, because the systems and methods limit retrieval to only a subset of each cluster determined to have an association with the search query.

[0043] Exemplary embodiments of the present disclosure will now be described in further detail with reference to the figures.

[0044] 1 illustrates a block diagram of an exemplary badge generation and retrieval system 10 according to an exemplary embodiment of the present disclosure. In some implementations, the badge generation and retrieval system 10 is configured to receive and / or obtain web data 12 describing web information associated with a particular object (e.g., a particular product) or environment, and generate, determine, and / or provide a badge 16 describing determined attributes (or qualities) of the particular object or environment as a result of receiving the web data 12. Thus, in some implementations, the artificial intelligence generated badge retrieval system 10 may include one or more machine-learned models 14 operable to determine specific uses, advantages, and / or disadvantages associated with the particular object or environment.

[0045] In particular, web data 12 associated with a subject (e.g., a particular object or environment) may be obtained. The web data 12 may include web information associated with the subject. The web information may include marketplace listings, descriptions, user reviews, frequently asked questions, marketing information, and / or social media posts. The web data may be obtained by determining web resources associated with the subject (e.g., top search results determined when searching for the subject using a search engine).

[0046] The web data 12 may be processed with one or more machine-learned models 14 to generate one or more badges 16. The one or more machine-learned models 14 may be trained and / or configured for natural language processing, sequence determination, sentiment analysis, semantic analysis, and / or one or more classifications. The one or more machine-learned models 14 may be trained to identify attributes (e.g., specific uses, advantages, and / or disadvantages) associated with a subject matter. The one or more machine-learned models 14 may include generative models (e.g., generative language models (e.g., large-scale language models, which may include autoregressive language models)). The one or more badges 16 may describe the identified attributes. The one or more badges 16 may be stored (and / or indexed) with data (e.g., one or more web resources, textual data, and / or embedded data) describing the subject matter.

[0047] A search query 18 (e.g., a text query, an image query, and / or a multimodal query) may be obtained. The search query 18 may include one or more search terms. The one or more search terms may be associated with a subject (e.g., terms that describe a subject, a use for a subject, and / or an object type associated with a subject).

[0048] A search query 18 may be processed using search engine 20 to determine that one or more badges 16 are associated with the search query 18. Based on the association of one or more badges 16 with the search query 18, one or more search results associated with the subject matter and / or badges 16 may be obtained and provided for display via search result interface 22.

[0049] The search result interface 22 may include badged search results along with one or more user interface elements describing one or more respective badges. In some implementations, the search result interface may include model-generated responses, knowledge panels, badged search results, general search results, and / or search improvement suggestions. In some implementations, the badges 16 may be utilized as section headings for one or more search results. For example, a set of products (associated with a set of search results) may share a first badge. The set of products may then be provided for display under and / or in a panel header that includes the badge description (or title).

[0050] 2 illustrates a block diagram of an exemplary search system 200 according to an exemplary embodiment of the present disclosure. The search system 200 is similar to the badge generation and search system 10 of FIG. 1, except that the search system 200 further includes an embedding model 224 for generating badge embeddings 226.

[0051] In particular, web data 212 associated with a subject (e.g., a particular object or environment) may be obtained. The web data 212 may include web information associated with the subject. The web information may include marketplace listings, descriptions, user reviews, frequently asked questions, marketing information, and / or social media posts. The web data may be obtained by determining web resources associated with the subject (e.g., top search results determined when searching for the subject with a search engine). For example, a query 230 describing the subject may be provided to the search engine 220 to determine a number of preliminary search results. The multiple preliminary search results may be processed to obtain the web data 212. In some implementations, a subset of content associated with the multiple preliminary search results may be extracted to generate the web data 212.

[0052] The web data 212 may be processed with one or more machine-learned models 214 (e.g., one or more generative models) to generate one or more badges 216. The one or more machine-learned models 214 may include one or more natural language processing models (e.g., a language prediction model, a summarization model, one or more sentiment analysis models, and / or one or more trend prediction / analysis models (e.g., one or more sequence prediction models)). The one or more machine-learned models 214 may be trained and / or configured for natural language processing, sequence determination, sentiment analysis, semantic analysis, and / or one or more classifications. The one or more machine-learned models 214 may be trained to identify attributes (e.g., specific uses, advantages, and / or disadvantages) associated with the subject matter. The one or more badges 216 may describe the identified attributes. The one or more badges 216 may be stored (and / or indexed) with data describing the subject matter (e.g., one or more web resources, textual data, and / or embedded data).

[0053] In some implementations, one or more badges 216 may be processed with an embedding model 224 to generate one or more badge embeddings 226. The one or more badge embeddings 226 may describe topic relationships for a particular badge. The badge embeddings 226 may be utilized to determine similar embeddings and / or generate badge clusters for search. The embedding model 224 may be trained to generate similar embeddings for badges, search results, and / or queries associated with similar topics.

[0054] A search query 218 (e.g., a text query, an image query, and / or a multimodal query) may be obtained. The search query 218 may include one or more search terms. The one or more search terms may be associated with a subject (e.g., a term that describes a subject, a use for a subject, and / or an object type associated with a subject).

[0055] A search query 218 may be processed with a search engine 220 to determine that one or more badges 216 are associated with the search query 218. Based on the one or more badges 216 being associated with the search query 218, one or more search results associated with the subject matter and / or the badges 216 may be obtained and provided for display via a search result interface 222. In some implementations, the one or more search results may be determined based at least in part on one or more badge embeddings 226 (e.g., a search query may be embedded and embedding neighbors (e.g., badge embeddings and / or search result embeddings) for the generated query embedding may be utilized to determine one or more associated badges and / or one or more associated search results).

[0056] The search result interface 222 may include badged search results along with one or more user interface elements that describe one or more respective badges. In some implementations, the search result interface may include model-generated responses, knowledge panels, badged search results, general search results, and / or search improvement suggestions.

[0057] For example, the search result interface 222 may include a model-generated response that may be generated by processing the search query 218 and / or one or more preliminary search results with a generative model 228 (e.g., a response / summary natural language processing model). The generative model 228 may include a text-to-text generative model, an image-to-text generative model, an image generative model, and / or one or more other models.

[0058] 3 shows a flow chart diagram of an exemplary method for performing in accordance with an exemplary embodiment of the present disclosure. Although FIG. 3 shows steps performed in a particular order for purposes of illustration and explanation, the method of the present disclosure is not limited to the specifically shown order or arrangement. Various steps of method 300 can be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure.

[0059] At 302, the computing system can obtain web data associated with a particular product. The web data can include web information associated with the particular product. The web data can include user reviews of the particular product. In some implementations, the web information can include product descriptions and answers to frequently asked questions.

[0060] At 304, the computing system may process the web data with one or more machine-learned models to determine one or more specific uses associated with the particular product. The one or more specific uses may be determined based on the web information. In some implementations, the one or more specific uses may be determined based on the frequency of terms in the web information, sentiment analysis, and semantic understanding. The one or more specific uses may be associated with at least one of a scenario for using the particular product, a purpose for using the particular product, a time for using the particular product, or a type of user using the product. In some implementations, the one or more machine-learned models may include a natural language processing model. The one or more specific uses may be determined based at least in part on sentiment analysis.

[0061] At 306, the computing system can generate one or more badges based on one or more specific uses. The badges can describe one or more specific uses. The one or more specific uses can be associated with where (e.g., scenario), why (e.g., purpose), when (e.g., time), and / or who (e.g., type of customer). The specific uses can be utilized as badges for products. In some implementations, the badges can be processed with an embedding model to generate one or more badge embeddings in the embedding space. The badge embeddings can be utilized to determine badge clusters (e.g., groups of badges that are targeted to similar and / or equal uses). The badge clusters can be utilized during search. For example, the search system can surface only one or a small subset of badges in a particular cluster to limit redundancy. Alternatively and / or additionally, the search system can rank based on clusters and / or provide badges based on cluster family members being highly ranked. In some implementations, the badge embedding may be utilized to determine when the badge and the respective search result may be surfaced in a search result interface.

[0062] At 308, the computing system can store the one or more badges. The one or more badges can be stored along with data describing an association with a particular product. In some implementations, the one or more badges can be stored in a badge database along with one or more links to one or more web resources associated with the subject matter of the badge.

[0063] At 310, the computing system may obtain a search query. The search query may be associated with a product type. In some implementations, a particular product may be of the product type. The search query may include a text query, an image query, a multimodal query, and / or another type of query. One or more badges may be generated at a first time, and the search query may be obtained at a second time. The second time may be after the first time.

[0064] At 312, the computing system can provide a search result interface based on the search query and the one or more badges. Providing the search result interface based on the search query and the one or more badges can include determining that one or more badges are associated with the search query and obtaining product data associated with the particular product. The product data can include one or more links to one or more web resources associated with the particular product. The search result interface can include product search results. The product search results can include data describing the product and the one or more badges.

[0065] In some implementations, the computing system can process the one or more badges with the embedding model to generate one or more respective badge embeddings in the embedding space and determine a plurality of search results for display in a search result interface based on the one or more badge embeddings. Determining the plurality of search results can include processing a search query with the embedding model to generate a query embedding, determining that the query embedding is associated with the badge embedding, and providing, in the search result interface, product search results that describe particular products.

[0066] In some implementations, the computing system can use the embedding model to process a plurality of other badges associated with a plurality of other products to generate a plurality of other badge embeddings, determine one or more badge clusters based on the one or more badge embeddings and the plurality of other badge embeddings, and determine one or more search results in a search result interface based on the one or more badge clusters.

[0067] 4 illustrates a diagram of an example search results interface 400 with a knowledge panel, in accordance with an example embodiment of the present disclosure. In particular, the search results interface 400 may include a search query input box 402, a number of search results 404 with respective badges 406, and / or a knowledge panel 408.

[0068] The search query input box 402 may be configured to receive a query input from a user. The search query input box 402 may receive free-form text input, selection input, data file input, and / or one or more other inputs (e.g., multi-modal input).

[0069] The plurality of search results 404 may be determined by processing the query entered in the search query input box 402. The plurality of search results 404 may be determined based on a keyword search, an embedded search, a badge ranking and search, a badge cluster ranking, and / or a feature search. The plurality of search results 404 may be provided for display along with one or more badge indicators 406 that describe one or more respective badges for a particular search result. In some implementations, each search result of the plurality of search results 404 may include a search result title, a search result description, a badge indicator 406, and / or one or more media content items (e.g., an image thumbnail).

[0070] The knowledge panel 408 may include model-generated responses that may be generated by processing the search query and / or one or more datasets with a generative model (e.g., a generative language model (e.g., a large-scale language model)). In some implementations, the knowledge panel 408 may include one or more media content items (e.g., one or more images), topic summaries, and / or other data obtained from a knowledge database. The data provided in the knowledge panel 408 may be associated with topics determined to be responsive to the search query.

[0071] The multiple search results 404 may be adjacent to the knowledge panel 408 and / or may be in a separate panel.

[0072] 5 illustrates a diagram of an example search results interface 500 with adjacent panels for model-generated responses, badged results, and general results, in accordance with an example embodiment of the present disclosure. In particular, the search results interface 500 may include a search query input box 502, a number of badged search results 504, a number of general search results 512, and / or a model-generated response 508. The model-generated responses 508, the number of badged search results 504, and / or the number of general search results 512 may be adjacent to one another and / or in separate panels.

[0073] The search query input box 502 may be configured to receive a query input from a user. The search query input box 502 may receive free-form text input, selection input, data file input, and / or one or more other inputs (e.g., multi-modal input).

[0074] The badged search results 504 may be determined by processing the query entered in the search query input box 502. The badged search results 504 may be determined based on a keyword search, an embedded search, a badge ranking and search, a badge cluster ranking, and / or a feature search. The badged search results 504 may be provided for display along with one or more badge indicators 506 that describe one or more respective badges for a particular search result. In some implementations, each search result of the search results 504 may include a search result title, a search result description, a badge indicator 506, and / or one or more media content items 510 (e.g., an image thumbnail).

[0075] The model-generated responses 508 may be generated by processing the search query and / or one or more datasets with a generative model. In some implementations, the model-generated responses 508 may include one or more media content items (e.g., one or more images), topic summaries, and / or other response data.

[0076] The general search results 512 may include general search results that may not include indexed badges. The general search results 512 may be determined based on a text search, a feature search, and / or an embedded search.

[0077] The badged search results 504 may be product search results with indexed badges. Each of the badged search results 504 may be associated with one or more actions (e.g., a purchase action, a reservation action, and / or one or more other actions).

[0078]

[0023] Figure 6 illustrates a diagram of an example search result interface 600 with badge search result tiles, according to an example embodiment of the present disclosure. In particular, the search result interface 600 of Figure 6 may include similar display data types as the search result interface 500 of Figure 5, however, the search result interface 600 of Figure 6 may include different search result formats for badged search results 604 and general search results 612.

[0079] For example, the search result interface 600 may include a search query input box 602, a number of badged search results 604 in a tile format, a number of general search results 612, and / or a model-generated response 608. The model-generated response 608, the number of badged search results 604, and / or the number of general search results 612 may be adjacent to one another and / or in separate panels.

[0080] The search query input box 602 may be configured to receive a query input from a user. The search query input box 602 may receive free-form text input, selection input, data file input, and / or one or more other inputs (e.g., multi-modal input).

[0081] The badged search results 604 may be determined by processing the query entered in the search query input box 602. The badged search results 604 may be provided as tiles in a horizontal line and may be provided in a carousel interface. The badged search results 604 may be determined based on a keyword search, an embedded search, a badge ranking and search, a badge cluster ranking, and / or a feature search. The badged search results 604 may be provided for display with one or more badge indicators 606 that describe one or more respective badges for a particular search result. In some implementations, each search result of the search results 604 may include a search result title, a badge indicator 606, and / or one or more media content items 610 (e.g., an image thumbnail and / or a video thumbnail).

[0082] The model-generated responses 608 may be generated by processing the search query and / or one or more datasets with a generative model. In some implementations, the model-generated responses 608 may include one or more media content items (e.g., one or more images), topic summaries, and / or other response data.

[0083] The general search results 612 may include general search results that may not include indexed badges. The general search results 612 may be determined based on a text search, a feature search, and / or an embedded search.

[0084] The badged search results 604 may be product search results with indexed badges. Each of the badged search results 604 may be associated with one or more actions (e.g., a purchase action, a reservation action, and / or one or more other actions).

[0085] 7 shows a flow chart diagram of an exemplary method for performing in accordance with an exemplary embodiment of the present disclosure. Although FIG. 7 shows steps performed in a particular order for purposes of illustration and explanation, the method of the present disclosure is not limited to the specifically shown order or arrangement. Various steps of method 700 can be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure.

[0086] At 702, the computing system can determine one or more web resources associated with the object. The one or more web resources may include a web marketplace listing for the object. The one or more web resources may include a review database that stores and / or provides user reviews for one or more products and / or places. In some implementations, the one or more web resources may include a product fact sheet, a marketplace listing, a review platform, a social media platform, an encyclopedia resource, and / or another accessible web resource.

[0087] In some implementations, determining the one or more web resources may include obtaining data describing the object, processing the data describing the object with a search engine to determine a set of object-specific search results, and selecting one or more particular object-specific search results from the set of object-specific search results.

[0088] At 704, the computing system may process one or more content items of one or more web resources with one or more machine-learned models to determine at least one of one or more advantages or one or more disadvantages associated with the object. The one or more advantages and / or one or more disadvantages may be determined by processing, parsing, and / or interpreting user reviews associated with the object. The processing and parsing may include natural language processing, sentiment analysis, and / or semantic analysis. The determination may include an interpolation of trends among the multiple reviews.

[0089] At 706, the computing system can generate one or more badges based on at least one of the one or more advantages or one or more disadvantages associated with the object. The one or more badges can include generated text labels. The badges can be padded such that similar advantages have similar badge paddings and can be clustered for later use in determining similar badges and / or similar search results.

[0090] In some implementations, a computing system can index one or more badges with data that describes the object.

[0091] At 708, the computing system may obtain a search query from a user computing system. The search query may be obtained from a user computing system that may not be associated with one or more web resources. The search query may include one or more search terms associated with an object type and / or topics that may be associated with the object.

[0092] At 710, the computing system may determine that at least one of the object or one or more badges is associated with the search query. For example, the badges may be ranked based on the received search query and then utilized to determine which search results will be provided. Alternatively and / or additionally, multiple search results may be determined based on the search query and the badges and their respective search results may be determined and provided based on the search results.

[0093] In some implementations, determining that at least one of the object or the one or more badges is associated with the search query may include processing the search query with a search engine to determine a plurality of search results, determining a set of badges associated with the plurality of search results, and providing a particular set of search results in a search result interface based on the set of badges. The set of badges may include one or more badges.

[0094] Alternatively and / or additionally, determining that the object or at least one of the one or more badges is associated with the search query may include determining a set of badges associated with the search query, determining respective search results for each particular badge in the set of badges, and providing the respective set of search results in a search result interface based on the set of badges. The set of badges may include one or more badges.

[0095] At 712, the computing system can provide the specific object search results for display in the search result interface. The specific object search results can include data describing the object and user interface elements describing one or more badges.

[0096] 8 shows a flow chart diagram of an exemplary method for performing in accordance with an exemplary embodiment of the present disclosure. Although FIG. 8 shows steps performed in a particular order for purposes of illustration and explanation, the method of the present disclosure is not limited to the specifically shown order or arrangement. Various steps of method 800 can be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure.

[0097] At 802, the computing system may obtain a search query. The search query may be associated with a particular object type. The search query may include text data, image data, latent coding data, audio data, and / or multimodal data. The search query may be manually generated and / or automatically generated based on one or more user interactions. The search query may be automatically generated to determine search results for suggesting to a user. Alternatively and / or additionally, the search query may include a model-generated query, which may be generated based on a user providing a prompt to a generative model.

[0098] At 804, the computing system can process the search query to determine a plurality of badges associated with the search query. The plurality of badges can include a plurality of particular benefits associated with a plurality of different objects of a particular object type. In some implementations, the plurality of badges can be generated by processing a plurality of reviews for each of a plurality of different objects.

[0099] At 806, the computing system may determine a subset of the plurality of badges to display. The determination may be based on badge ranking, which may include text-based ranking, embedding-based ranking, node-based ranking, and / or machine-learned model-based ranking. In some implementations, multiple badge clusters may be ranked, and then badges associated with the most relevant badge clusters may be ranked. The subset may include a limited number of badges (e.g., one or two) from a badge cluster to allow for a diverse and non-redundant display of badges and search results.

[0100] At 808, the computing system can obtain a plurality of search results associated with the subset of the plurality of badges. The plurality of search results can include one or more respective search results for each particular badge in the subset of the plurality of badges.

[0101] At 810, the computing system can provide a search result interface for display. The search result interface can include a plurality of search results. Each of the plurality of search results can be annotated with a particular badge associated with the respective search result. In some implementations, the search result interface can include a first panel for the plurality of search results and a second panel for the model-generated response. The model-generated response can be generated by processing the search query with a language model to generate a model-generated response. The model-generated response can be responsive to the search query. The language model can include a text-to-text generative model. Alternatively and / or additionally, the model-generated response can be generated by processing one or more search results (e.g., content of one or more web resources) associated with the search query to generate a summary response. In some implementations, the natural language response can be determined based on model inference using the language model without further input. The badged search results can be associated with a product. Additionally and / or alternatively, the badged search results can be associated with a particular action (e.g., a purchase action). Each of the badges can be associated with a particular use associated with a particular product.

[0102] In some implementations, the plurality of search results may include a plurality of product search results associated with a particular set of web resources. The search result interface may include a plurality of product search results, a plurality of general search results, and a natural language response. The natural language response may be generated using a machine learning generative model. In some implementations, the plurality of general search results may be determined using a search engine.

[0103] 9A illustrates a block diagram of an example computing system 100 for performing badge generation and retrieval in accordance with an example embodiment of the present disclosure. The system 100 includes a user computing system 102, a server computing system 130, and / or a third party computing system 150 communicatively coupled via a network 180.

[0104] The user computing system 102 may include any type of computing device, such as, for example, a personal computing device (e.g., a laptop or desktop), a mobile computing device (e.g., a smartphone or tablet), a gaming console or controller, a wearable computing device, an embedded computing device, or any other type of computing device.

[0105] The user computing system 102 includes one or more processors 112 and a memory 114. The one or more processors 112 may be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and may be a single processor or multiple processors operatively connected. The memory 114 may include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 114 may store data 116 and instructions 118 that are executed by the processor 112 to cause the user computing system 102 to perform operations.

[0106] In some implementations, the user computing system 102 can store or include one or more machine-learned models 120. For example, the machine-learned models 120 can be or otherwise include various machine-learned models, such as neural networks (e.g., deep neural networks) or other types of machine-learned models including nonlinear and / or linear models. The neural networks can include feedforward neural networks, recurrent neural networks (e.g., long short-term memory recurrent neural networks), convolutional neural networks, or other forms of neural networks.

[0107] In some implementations, one or more machine-learned models 120 may be received from the server computing system 130 over the network 180, stored in the user computing device memory 114, and then used or otherwise implemented by one or more processors 112. In some implementations, the user computing system 102 may implement multiple parallel instances of a single machine-learned model 120 (e.g., to perform parallel machine-learned model processing across multiple instances of input data and / or detected features).

[0108] More specifically, the one or more machine-learned models 120 may include one or more detection models, one or more classification models, one or more segmentation models, one or more augmentation models, one or more generative models, one or more natural language processing models, one or more optical character recognition models, and / or one or more other machine-learned models. The one or more machine-learned models 120 may include one or more transformer models. The one or more machine-learned models 120 may include one or more neural radiance field models, one or more diffusion models, and / or one or more autoregressive language models.

[0109] One or more machine-learned models 120 may be utilized to detect one or more object features. The detected object features may be classified and / or embedded. The classification and / or embedding may then be utilized to perform a search to determine one or more search results. Alternatively and / or additionally, one or more detected features may be utilized to determine that an indicator (e.g., a user interface element indicating the detected feature) will be provided to indicate that the feature has been detected. A user may then select the indicator to cause the feature classification, embedding, and / or search to be performed. In some implementations, the classification, embedding, and / or search may be performed before the indicator is selected.

[0110] In some implementations, the one or more machine-learned models 120 may process image data, text data, audio data, and / or latent coding data to generate output data, which may include image data, text data, audio data, and / or latent coding data. The one or more machine-learned models 120 may perform optical character recognition, natural language processing, image classification, object classification, text classification, audio classification, context determination, action prediction, image correction, image enhancement, text enhancement, sentiment analysis, object detection, error detection, inpainting, video stabilization, audio correction, audio enhancement, and / or data segmentation (e.g., mask-based segmentation).

[0111] The machine-learned model may be or include one or more machine-learned models or model components. Exemplary machine-learned models may include neural networks (e.g., deep neural networks). Exemplary machine-learned models may include non-linear or linear models. Exemplary machine-learned models may use other architectures instead of or in addition to neural networks. Exemplary machine-learned models may include decision tree-based models, support vector machines, hidden Markov models, Bayesian networks, linear regression models, k-means clustering models, etc.

[0112] Exemplary neural networks may include feedforward neural networks, recurrent neural networks (RNNs) including long short-term memory (LSTM) based recurrent neural networks, convolutional neural networks (CNNs), diffusion models, generative adversarial networks, or other forms of neural networks. Exemplary neural networks may be deep neural networks. Some exemplary machine-learned models may leverage attention mechanisms such as self-attention. For example, some exemplary machine-learned models may include multi-head self-attention models.

[0113] The machine-learned model may include a single or multiple instances of the same model configured to operate on data from the input. The machine-learned model may include an ensemble of different models that can interact collaboratively to process data from the input. For example, the machine-learned model may employ a mixed-expert structure. See, e.g., Zhou et al., Mixture-of-Experts with Expert Choice Routing, arXiv:2202.09368v2 (October 14, 2022).

[0114] The input can generally include or otherwise represent various types of data. The input can include one type or many different types of data. The output can be the same type of data or a different type of data compared to the input. The output can include one type or many different types of data.

[0115] Exemplary data types for input or output include natural language text data, software code data (e.g., source code, object code, machine code, or any other form of computer-readable instructions or programming language), machine code data (e.g., binary code, assembly code, or other form of machine-readable instructions that can be directly executed by a central processing unit of a computer), assembly code data (e.g., a low-level programming language that uses symbolic representations of machine code instructions to program a processing unit), genetic data or other chemical or biochemical data, image data, audio data, audiovisual data, tactile data, biometric data, medical data, financial data, statistical data, geographic data, astronomical data, historical data, sensor data in general (e.g., digital or analog values, such as voltages or other absolute or relative level measurements, from real or artificial inputs, such as from audio sensors, light sensors, displacement sensors, etc.), etc. Data can be raw or processed and can be in any format or schema.

[0116] In a multimodal input or output, example combinations of data types include image data and audio data, image data and natural language data, natural language data and software code data, image data and biometric data, sensor data and medical data, etc. It should be understood that there may be any combination of data types in the input or output.

[0117] An exemplary input may include one or more data types, such as the exemplary data types described above. An exemplary output may include one or more data types, such as the exemplary data types described above. The data type of the input may be the same as or different from the data type of the output. It should be understood that the exemplary data types described above are provided for illustrative purposes only. Data types contemplated within the scope of this disclosure are not limited to those examples described above.

[0118] In some implementations, one or more machine-learned models 120 can process web information (e.g., user reviews, descriptions, and / or other content) to determine one or more uses, one or more advantages, and / or one or more disadvantages associated with a particular object or environment. The determined one or more uses, one or more advantages, and / or one or more disadvantages can then be utilized to generate one or more badges for the respective object or environment.

[0119] In some implementations, the one or more machine-learned models 120 may include one or more embedding models. The one or more embedding models may process one or more badges to generate one or more badge embeddings in the embedding space. The one or more badge embeddings may be utilized for embedding-based search and / or to determine badge relationships (e.g., similar embeddings). For example, badge clusters may be determined based on the badge embeddings. The badge clusters may describe badges associated with similar topics.

[0120] The embedding model may be trained on a set of question and answer training examples. For example, the embedding model may be trained to process example questions to generate question embeddings. The question embeddings may be compared against one or more other embeddings associated with questions with similar answers. One or more parameters of the embedding model may be adjusted based on a gradient descent output of a loss function that evaluates the difference between the embeddings. The embedding model may be trained to output similar embeddings for questions with similar answers and different embeddings for questions with different answers. In some implementations, the embedding model may be trained on other training datasets.

[0121] In some implementations, the one or more machine-learned models 120 may include generative models that may be trained to process search queries and / or one or more content items to generate model-generated responses. The model-generated responses may include predicted natural language responses and / or summary responses. The generative models may include text generation models (e.g., text-to-text autoregressive language models), image generation models (e.g., text-to-image diffusion models), and / or one or more other generative models.

[0122] Additionally or alternatively, one or more machine-learned models 140 may be included in or otherwise stored and implemented by a server computing system 130 that communicates with the user computing system 102 according to a client-server relationship. For example, the machine-learned models 140 may be implemented by the server computing system 130 as part of a web service (e.g., a viewfinder service, a visual search service, an image processing service, an ambient computing service, and / or an overlay application service). Thus, one or more models 120 may be stored and implemented in the user computing system 102 and / or one or more models 140 may be stored and implemented in the server computing system 130.

[0123] The user computing system 102 may also include one or more user input components 122 that receive user input. For example, the user input component 122 may be a touch-sensitive component (e.g., a touch-sensitive display screen or touchpad) that is sensitive to the touch of a user input object (e.g., a finger or stylus). The touch-sensitive component can be useful for implementing a virtual keyboard. Other exemplary user input components include a microphone, a traditional keyboard, or other means by which a user can provide user input.

[0124] In some implementations, the user computing system may store and / or provide one or more user interfaces 124, which may be associated with one or more applications. The one or more user interfaces 124 may be configured to receive input and / or provide data for display (e.g., image data, text data, audio data, one or more user interface elements, augmented reality experiences, virtual reality experiences, and / or other data for display). The user interfaces 124 may be associated with one or more other computing systems (e.g., the server computing system 130 and / or the third-party computing system 150). The user interfaces 124 may include a viewfinder interface, a search interface, a generative model interface, a social media interface, and / or a media content gallery interface.

[0125] The user computing system 102 may include and / or receive data from one or more sensors 126. The one or more sensors 126 may be housed in a housing component that houses one or more processors 112, memory 114, and / or one or more hardware components that may cause one or more software packets to be stored and / or executed. The one or more sensors 126 may include one or more image sensors (e.g., cameras), one or more lidar sensors, one or more audio sensors (e.g., microphones), one or more inertial sensors (e.g., inertial measurement units), one or more biological sensors (e.g., heart rate sensors, pulse sensors, retinal sensors, and / or fingerprint sensors), one or more infrared sensors, one or more location sensors (e.g., GPS), one or more touch sensors (e.g., conductive touch sensors and / or mechanical touch sensors), and / or one or more other sensors. The one or more sensors may be utilized to obtain data associated with the user's environment (eg, an image of the user's environment, a record of the environment, and / or the user's location).

[0126] The user computing system 102 may include and / or be a part of a user computing device 104. The user computing device 104 may include a mobile computing device (e.g., a smartphone or tablet), a desktop computer, a laptop computer, a smart wearable, and / or a smart appliance. Additionally and / or alternatively, the user computing system may acquire data from and / or generate data with one or more user computing devices 104. For example, a smartphone camera may be utilized to capture image data describing the environment, and / or an overlay application of the user computing device 104 may be utilized to track and / or process data being provided to the user. Similarly, one or more sensors associated with a smart wearable may be utilized to acquire data about the user and / or about the user's environment (e.g., image data may be acquired with a camera housed in the user's smart glasses). Additionally and / or alternatively, data may be acquired and uploaded from other user devices that may be dedicated to data acquisition or generation.

[0127] The server computing system 130 includes one or more processors 132 and a memory 134. The one or more processors 132 may be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and may be a single processor or multiple processors operatively connected. The memory 134 may include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 134 may store data 136 and instructions 138 that are executed by the processor 132 to cause the server computing system 130 to perform operations.

[0128] In some implementations, the server computing system 130 includes or is otherwise implemented by one or more server computing devices. In instances in which the server computing system 130 includes multiple server computing devices, such server computing devices may operate according to a sequential computing architecture, a parallel computing architecture, or some combination thereof.

[0129] As described above, the server computing system 130 can store or otherwise include one or more machine-learned models 140. For example, the models 140 can be or otherwise include a variety of machine-learned models. Exemplary machine-learned models include neural networks or other multi-layer nonlinear models. Exemplary neural networks include feed-forward neural networks, deep neural networks, recurrent neural networks, and convolutional neural networks. Exemplary models 140 are described with reference to FIG. 9B.

[0130] Additionally and / or alternatively, the server computing system 130 may include and / or be communicatively connected to a search engine 142 that may be utilized to crawl one or more databases (and / or resources). The search engine 142 may process data from the user computing system 102, the server computing system 130, and / or the third-party computing system 150 to determine one or more search results associated with the input data. The search engine 142 may perform term-based searches, label-based searches, Boolean-based searches, image searches, embedding-based searches (e.g., nearest neighbor searches), multi-modal searches, and / or one or more other search techniques.

[0131] The server computing system 130 may store and / or provide one or more user interfaces 144 for obtaining input data and / or providing output data to one or more users. The one or more user interfaces 144 may include one or more user interface elements, which may include input fields, navigation tools, content chips, selectable tiles, widgets, data display carousels, dynamic animations, information popups, image augmentation, text to speech, speech to text, augmented reality, virtual reality, feedback loops, and / or other interface elements.

[0132] User computing system 102 and / or server computing system 130 can train models 120 and / or 140 through interaction with a third party computing system 150 that is communicatively coupled via network 180. Third party computing system 150 can be separate from server computing system 130 or can be part of server computing system 130. Alternatively and / or additionally, third party computing system 150 can be associated with one or more web resources, one or more web platforms, one or more other users, and / or one or more contexts.

[0133] Exemplary machine-learned models may include generative models (e.g., large-scale language models, foundational models, visual language models, image generation models, text-to-image models, audio generation models, and / or other generative models).

[0134] Training and / or tuning a machine-learned model may include obtaining training instances. The set of training data may include multiple training instances split among multiple datasets (e.g., training dataset, validation dataset, or test dataset). The training instances may be labeled or unlabeled. Runtime inference may form the training instances when the model is trained (e.g., online training / learning) using an evaluation of the model's performance in that runtime instance. Exemplary data types for training instances, and various tasks associated with them, are described throughout this disclosure.

[0135] Training and / or tuning may include processing the training instances using one or more machine-learned models to generate output. The output may be obtained directly from the one or more machine-learned models or may be a downstream result of a chain of processing operations that includes the output of the one or more machine-learned models.

[0136] The training and / or tuning may include receiving an evaluation signal associated with the output. The evaluation signal may be obtained using a loss function. Various determinations of loss may be used, such as mean squared error, likelihood loss, cross-entropy loss, hinge loss, contrastive loss, or various other loss functions. The evaluation signal may be calculated using known ground truth labels (e.g., supervised learning), predicted or estimated labels (e.g., semi-supervised or self-supervised learning), or without labels (e.g., unsupervised learning). The evaluation signal may be a reward (e.g., in the case of reinforcement learning). The reward may be calculated using a machine-learned reward model configured to generate a reward based on the received output. The reward may be calculated using feedback data describing human feedback on the output.

[0137] The training and / or tuning may include updating the machine-learned model using the evaluation signal. For example, values ​​for parameters of the machine-learned model may be learned in some embodiments using various training or learning techniques, such as, for example, backpropagation. For example, the evaluation signal may be backpropagated from an output (or another source of the evaluation signal) through the machine-learned model to update one or more parameters of the model (e.g., based on a gradient of the evaluation signal with respect to the parameter value). For example, a system including one or more machine-learned models may be trained in an end-to-end manner. Gradient descent techniques may be used to iteratively update parameters over several training iterations. In some implementations, performing backpropagation may include performing truncated backpropagation through time. The training and / or tuning may include implementing several generalization techniques (e.g., weight decay, dropout, etc.) to improve the generalization ability of the model being trained.

[0138] In some implementations, the above training loop may be implemented to train a machine learning model from an initialized state to a fully trained state (e.g., when the model exhibits a desired performance profile, such as based on accuracy, precision, recall, etc.).

[0139] In some implementations, the above training loop may be implemented for a particular stage of the training procedure. For example, in some implementations, the above training loop may be implemented to pre-train the machine-learned model. Pre-training may include, for example, large-scale training across potentially noisy data to achieve a wide range of performance levels across various tasks / data types. In some implementations, the above training loop may be implemented to fine-tune the machine-learned model. Fine-tuning may include, for example, smaller-scale training on higher quality (e.g., labeled, curated, etc.) data. Fine-tuning may affect all or a portion of the parameters of the machine-learned model. For example, various parts of the machine-learned model may be "frozen" during some training stages. For example, parameters associated with the embedding space may be "frozen" during fine-tuning (e.g., to preserve information learned from a wider domain than is present in the fine-tuning dataset). Exemplary fine-tuning techniques include reinforcement learning. Reinforcement learning may be based on user feedback on model performance during use.

[0140] The third party computing system 150 may include one or more processors 152 and memory 154. The one or more processors 152 may be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and may be a single processor or multiple processors operatively connected. The memory 154 may include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 154 may store data 156 and instructions 158 that are executed by the processor 152 to cause the third party computing system 150 to perform operations. In some implementations, the third party computing system 150 includes or is otherwise implemented by one or more server computing devices.

[0141] Network 180 may be any type of communications network, such as a local area network (e.g., an intranet), a wide area network (e.g., the Internet), or some combination thereof, and may include any number of wired or wireless links. In general, communications over network 180 may be carried over any type of wired and / or wireless connections using a wide variety of communications protocols (e.g., TCP / IP, HTTP, SMTP, FTP), encodings or formats (e.g., HTML, XML), and / or protection schemes (e.g., VPN, Secure HTTP, SSL).

[0142] The machine-learned models described herein may be used in a variety of tasks, applications, and / or use cases.

[0143] In some implementations, an input to the machine-learned model of the present disclosure may be image data. The machine-learned model may process the image data to generate an output. As an example, the machine-learned model may process the image data to generate an image recognition output (e.g., recognition of the image data, latent embedding of the image data, an encoded representation of the image data, a hash of the image data, etc.). As another example, the machine-learned model may process the image data to generate an image segmentation output. As another example, the machine-learned model may process the image data to generate an image classification output. As another example, the machine-learned model may process the image data to generate an image data modification output (e.g., alteration of the image data, etc.). As another example, the machine-learned model may process the image data to generate an encoded image data output (e.g., an encoded and / or compressed representation of the image data, etc.). As another example, the machine-learned model may process the image data to generate an upscaled image data output. As another example, the machine-learned model may process the image data to generate a prediction output.

[0144] In some implementations, the input to the machine-learned models of the present disclosure may be text or natural language data. The machine-learned models may process the text or natural language data to generate an output. As an example, the machine-learned models may process the natural language data to generate a language encoding output. As another example, the machine-learned models may process the text or natural language data to generate a latent text embedding output. As another example, the machine-learned models may process the text or natural language data to generate a translation output. As another example, the machine-learned models may process the text or natural language data to generate a classification output. As another example, the machine-learned models may process the text or natural language data to generate a text segmentation output. As another example, the machine-learned models may process the text or natural language data to generate a semantic intent output. As another example, the machine-learned models may process the text or natural language data to generate an upscaled text or natural language output (e.g., text or natural language data that is of higher quality than the input text or natural language). As another example, the machine-learned models may process the text or natural language data to generate a prediction output.

[0145] In some implementations, the input to the machine-learned model of the present disclosure may be audio data. The machine-learned model may process the audio data to generate an output. As an example, the machine-learned model may process the audio data to generate a speech recognition output. As another example, the machine-learned model may process the audio data to generate a speech translation output. As another example, the machine-learned model may process the audio data to generate a latent embedding output. As another example, the machine-learned model may process the audio data to generate an encoded audio output (e.g., an encoded and / or compressed representation of the audio data, etc.). As another example, the machine-learned model may process the audio data to generate an upscaled audio output (e.g., audio data that is of higher quality than the input audio data, etc.). As another example, the machine-learned model may process the audio data to generate a text representation output (e.g., a text representation of the input audio data, etc.). As another example, the machine-learned model may process the audio data to generate a predicted output.

[0146] In some implementations, the input to the machine-learned models of the present disclosure may be sensor data. The machine-learned models may process the sensor data to generate an output. As an example, the machine-learned models may process the sensor data to generate a recognition output. As another example, the machine-learned models may process the sensor data to generate a prediction output. As another example, the machine-learned models may process the sensor data to generate a classification output. As another example, the machine-learned models may process the sensor data to generate a segmentation output. As another example, the machine-learned models may process the sensor data to generate a segmentation output. As another example, the machine-learned models may process the sensor data to generate a visualization output. As another example, the machine-learned models may process the sensor data to generate a diagnostic output. As another example, the machine-learned models may process the sensor data to generate a detection output.

[0147] In some cases, the input includes visual data and the task is a computer vision task. In some cases, the input includes pixel data for one or more images and the task is an image processing task. For example, the image processing task may be image classification, where the output is a set of scores, each score corresponding to a different object class and representing a likelihood that one or more images show an object belonging to the object class. The image processing task may be object detection, where the image processing output identifies one or more regions in one or more images and, for each region, a likelihood that the region shows an object of interest. As another example, the image processing task may be image segmentation, where the image processing output defines, for each pixel in one or more images, a respective likelihood for each category in a predetermined set of categories. For example, the set of categories may be foreground and background. As another example, the set of categories may be object classes. As another example, the image processing task may be depth estimation, where the image processing output defines, for each pixel in one or more images, a respective depth value. As another example, the image processing task may be motion estimation, where the network input includes multiple images and the image processing output defines, for each pixel of one of the input images, the scene motion represented in pixels between images in the network input.

[0148] In some implementations, the task may be a generation task, and one or more machine-learned models (e.g., 120 and / or 140) may be configured to output content that is generated in view of one or more inputs. For example, the inputs may be data of one or more modalities that encode or otherwise represent a context for generating additional content.

[0149] In some implementations, the task may be a text completion task. The machine-learned model may be configured to process inputs representing text data and generate outputs representing additional text data that complete a text sequence that includes the input. For example, the machine-learned model may be configured to generate outputs to complete a sentence, paragraph, or portion of text that follows a portion of text represented by the input.

[0150] In some implementations, a task may be an instruction following the task. The machine-learned model may be configured to process inputs representing instructions to perform a function and generate outputs that advance a goal of fulfilling the instruction function (e.g., at least one step of a multi-step procedure to perform the function). The outputs may represent data of the same or different modality as the input. For example, the input may represent text data (e.g., natural language instructions for a task to be performed), and the machine-learned model may process the input to generate outputs representing text data responsive to the instructions (e.g., natural language responses, programming language responses, machine language responses, etc.). The input may represent image data (e.g., image-based instructions for a task to be performed, possibly accompanied by text instructions), and the machine-learned model may process the input to generate outputs representing text data responsive to the instructions (e.g., natural language responses, programming language responses, machine language responses, etc.). One or more outputs may be iteratively or recursively generated to sequentially process and accomplish steps toward achieving the requested function. For example, an initial output may be executed by an external system or processed by the machine-learned model to complete an initial step of performing the function. Multiple steps may be performed to obtain a final output that is responsive to an initial command.

[0151] In some implementations, the task may be a question answering task. The machine-learned model may be configured to process an input representing a question to answer and generate an output that advances the goal of returning an answer to the question (e.g., at least one step of a multi-step procedure to perform a function). The output may represent data of the same or different modality as the input. For example, the input may represent text data (e.g., natural language instructions for a task to be performed), and the machine-learned model may process the input to generate an output representing the text data responsive to the question (e.g., a natural language response, a programming language response, a machine language response, etc.). The input may represent image data (e.g., image-based instructions for a task to be performed, possibly accompanied by text instructions), and the machine-learned model may process the input to generate an output representing the text data responsive to the question (e.g., a natural language response, a programming language response, a machine language response, etc.). One or more outputs may be generated iteratively or recursively to sequentially process and accomplish steps toward answering the question. For example, the initial output may be executed by an external system or processed by a machine-learned model to complete an initial step (e.g., querying a database, performing a calculation, running a script, etc.) to obtain an answer to a question. Multiple steps may be performed to obtain a final output that is responsive to the question.

[0152] In some implementations, the task may be an image generation task. The machine-learned model may be configured to process inputs representing a context for a desired portion of the image content. The context may include text data, image data, audio data, etc. The machine-learned model may be configured to generate outputs representing image data indicative of an image related to the context. For example, the machine-learned model may be configured to generate pixel data for the image. Values ​​for channels associated with pixels in the pixel data may be selected based on the context (e.g., based on probabilities determined based on the context).

[0153] In some implementations, the task may be an audio generation task. The machine-learned model may be configured to process inputs representing a context for a desired portion of audio content. The context may include text data, image data, audio data, etc. The machine-learned model may be configured to generate outputs representing the audio data related to the context. For example, the machine-learned model may be configured to generate waveform data in the form of an image (e.g., a spectrogram). Values ​​for channels associated with pixels of the image may be selected based on the context. The machine-learned model may be configured to generate waveform data in the form of a sequence of individual samples of a continuous waveform. Values ​​of the sequence may be selected based on the context (e.g., based on probabilities determined based on the context).

[0154] In some implementations, the task may be a data generation task. The machine-learned model may be configured to process inputs that represent a context for a desired portion of data (e.g., data from various data domains, such as sensor data, image data, multimodal data, statistical data, etc.). The desired data may be, for example, synthetic data for training other machine-learned models. The context may include any data type. The machine-learned model may be configured to generate outputs that represent data that is consistent with the desired data. For example, the machine-learned model may be configured to generate data values ​​for populating a dataset. A value for a data object may be selected based on the context (e.g., based on a probability determined based on the context).

[0155] A user computing system may include several applications (e.g., applications 1-N). Each application may include its own respective machine learning library and machine learned model. For example, each application may include a machine learned model. Exemplary applications include a text messaging application, an email application, a dictation application, a virtual keyboard application, a browser application, etc.

[0156] Each application may communicate with several other components of the computing device, such as, for example, one or more sensors, a context manager, a device state component, and / or additional components. In some implementations, each application may communicate with each device component using an API (e.g., a public API). In some implementations, the API used by each application is specific to that application.

[0157] The user computing system 102 may include several applications (e.g., applications 1-N). Each application is in communication with a central intelligence layer. Exemplary applications include a text messaging application, an email application, a dictation application, a virtual keyboard application, a browser application, etc. In some implementations, each application can communicate with the central intelligence layer (and the models stored therein) using an API (e.g., a common API across all applications).

[0158] The central intelligence layer may include several machine-learned models. For example, a respective machine-learned model (e.g., a model) may be provided to each application and managed by the central intelligence layer. In other implementations, two or more applications may share a single machine-learned model. For example, in some implementations, the central intelligence layer may provide a single model (e.g., a single model) to all of the applications. In some implementations, the central intelligence layer is included within or otherwise implemented by an operating system of the computing system 100.

[0159] The central intelligence layer can communicate with a central device data layer, which can be a centralized repository of data for the computing system 100. The central device data layer can communicate with several other components of the computing device, such as, for example, one or more sensors, a context manager, a device state component, and / or additional components. In some implementations, the central device data layer can communicate with each device component using an API (e.g., a private API).

[0160] FIG. 9B illustrates a block diagram of an exemplary computing system 50 that performs badge generation and retrieval, according to an exemplary embodiment of the present disclosure. In particular, the exemplary computing system 50 can include one or more computing devices 52 that can be utilized to acquire and / or generate one or more datasets, which can be processed by the sensor processing system 60 and / or the output determination system 80 to provide a user with feedback that can provide information about features in the one or more acquired datasets. The one or more datasets can include image data, text data, audio data, multimodal data, latent coding data, and the like. The one or more datasets can be acquired via one or more sensors associated with the one or more computing devices 52 (e.g., one or more sensors in the computing device 52). Additionally and / or alternatively, the one or more datasets can be stored data and / or retrieved data (e.g., data retrieved from a web resource). For example, images, text, and / or other content items can be interacted with by the user. The interacted content items can then be utilized to generate one or more decisions.

[0161] The one or more computing devices 52 may acquire and / or generate one or more datasets based on image capture, sensor tracking, data storage retrieval, content download (e.g., downloading images or other content items from web resources via the Internet), and / or via one or more other techniques. The one or more datasets may be processed using a sensor processing system 60. The sensor processing system 60 may perform one or more processing techniques using one or more machine-learned models, one or more search engines, and / or one or more other processing techniques. The one or more processing techniques may be performed in any combination and / or individually. The one or more processing techniques may be performed serially and / or in parallel. In particular, the one or more datasets may be processed using a context determination block 62, which may determine a context associated with one or more content items. The context determination block 62 may identify and / or process metadata, user profile data (e.g., preferences, user search history, user browsing history, user purchase history, and / or user input data), previous interaction data, global trend data, location data, time data, and / or other data to determine a particular context associated with the user. A context may be associated with an event, a determined trend, a particular action, a particular type of data, a particular environment, and / or another context associated with the user and / or the retrieved or acquired data.

[0162] The sensor processing system 60 may include an image pre-processing block 64. The image pre-processing block 64 may be utilized to adjust one or more values ​​of the acquired and / or received image to prepare the image to be processed by one or more machine-learned models and / or one or more search engines 74. The image pre-processing block 64 may resize the image, adjust saturation values, adjust resolution, remove and / or add metadata, and / or perform one or more other operations.

[0163] In some implementations, the sensor processing system 60 may include one or more machine-learned models, which may include a detection model 66, a segmentation model 68, a classification model 70, an embedding model 72, and / or one or more other machine-learned models. For example, the sensor processing system 60 may include one or more detection models 66 that may be utilized to detect particular features in a processed dataset. In particular, one or more images may be processed with the one or more detection models 66 to generate one or more bounding boxes associated with detected features in the one or more images.

[0164] Additionally and / or alternatively, one or more segmentation models 68 may be utilized to segment one or more portions of a dataset from one or more datasets. For example, one or more segmentation models 68 may utilize one or more segmentation masks (e.g., one or more segmentation masks generated manually and / or based on one or more bounding boxes) to segment a portion of an image, a portion of an audio file, and / or a portion of text. Segmentation may include isolating one or more detected objects and / or removing one or more detected objects from an image.

[0165] The one or more classification models 70 may be utilized to process image data, text data, audio data, latent coding data, multimodal data, and / or other data to generate one or more classifications. The one or more classification models 70 may include one or more image classification models, one or more object classification models, one or more text classification models, one or more audio classification models, and / or one or more other classification models. The one or more classification models 70 may process the data to determine one or more classifications.

[0166] In some implementations, data may be processed with one or more embedding models 72 to generate one or more embeddings. For example, one or more images may be processed with one or more embedding models 72 to generate one or more image embeddings in the embedding space. The one or more image embeddings may be associated with one or more image features of the one or more images. In some implementations, the one or more embedding models 72 may be configured to process multimodal data to generate multimodal embeddings. The one or more embeddings may be utilized for classification, retrieval, and / or learning embedding spatial distributions.

[0167] The sensor processing system 60 may include one or more search engines 74 that may be utilized to perform one or more searches. The one or more search engines 74 may crawl one or more databases (e.g., one or more local databases, one or more global databases, one or more private databases, one or more public databases, one or more proprietary databases, and / or one or more comprehensive databases) to determine one or more search results. The one or more search engines 74 may perform feature matching, text-based search, embedding-based search (e.g., k-nearest neighbor search), metadata-based search, multimodal search, web resource search, image search, text search, and / or application search.

[0168] Additionally and / or alternatively, the sensor processing system 60 may include one or more multimodal processing blocks 76 that may be utilized to aid in processing the multimodal data. The one or more multimodal processing blocks 76 may include generating multimodal queries and / or multimodal embeddings for processing by one or more machine-learned models and / or one or more search engines 74.

[0169] The output of the sensor processing system 60 may then be processed with an output determination system 80 to determine one or more outputs for provision to a user. The output determination system 80 may include heuristic-based decisions, machine-learned model-based decisions, user-selection-based decisions, and / or context-based decisions.

[0170] The output determination system 80 may determine how and / or where to provide one or more search results in the search result interface 82. Additionally and / or alternatively, the output determination system 80 may determine how and / or where to provide one or more machine-learned model outputs in the machine-learned model output interface 84. In some implementations, the one or more search results and / or the one or more machine-learned model outputs may be provided for display via one or more user interface elements. The one or more user interface elements may be overlaid on top of the displayed data. For example, one or more detection indicators may be overlaid on top of a detected object in a viewfinder. The one or more user interface elements may be selectable to perform one or more additional searches and / or one or more additional machine-learned model processes. In some implementations, the user interface elements may be provided as dedicated user interface elements for a particular application and / or may be provided uniformly across different applications. The one or more user interface elements may include pop-up displays, interface overlays, interface tiles and / or chips, carousel interfaces, audio feedback, animations, interactive widgets, and / or other user interface elements.

[0171] Additionally and / or alternatively, data associated with the output of the sensor processing system 60 may be utilized to generate and / or provide an augmented reality experience and / or a virtual reality experience 86. For example, one or more acquired datasets may be processed to generate one or more augmented reality rendering assets and / or one or more virtual reality rendering assets, which may then be utilized to provide an augmented reality experience and / or a virtual reality experience 86 to a user. The augmented reality experience may render information associated with an environment into a respective environment. Alternatively and / or additionally, objects related to the processed dataset may be rendered into the user environment and / or the virtual environment. The rendering dataset generation may include training one or more neural radiance field models to learn three-dimensional representations for one or more objects.

[0172] In some implementations, one or more action prompts 88 may be determined based on the output of the sensor processing system 60. For example, a search prompt, a purchase prompt, a create prompt, a reservation prompt, a call prompt, a redirect prompt, and / or one or more other prompts may be determined to be associated with the output of the sensor processing system 60. The one or more action prompts 88 may then be provided to the user via one or more selectable user interface elements. In response to selection of the one or more selectable user interface elements, a respective action of the respective action prompt may be executed (e.g., a search may be performed, a purchasing application programming interface may be utilized, and / or another application may be opened).

[0173] In some implementations, one or more datasets and / or outputs of the sensor processing system 60 may be processed with one or more generative models 90 to generate model-generated content items, which may then be provided to a user. Generation may be prompted based on user selection and / or may be performed automatically (e.g., automatically based on one or more conditions that may be associated with not identifying a threshold amount of search results).

[0174] The one or more generative models 90 may include a language model (e.g., a large-scale language model and / or a visual language model), an image generation model (e.g., a text-to-image generation model and / or an image augmentation model), an audio generation model, a video generation model, a graph generation model, and / or other data generation models (e.g., other content generation models). The one or more generative models 90 may include one or more transformer models, one or more convolutional neural networks, one or more recurrent neural networks, one or more feedforward neural networks, one or more generative adversarial networks, one or more self-attention models, one or more embedding models, one or more encoders, one or more decoders, and / or one or more other models. In some implementations, the one or more generative models 90 may include one or more autoregressive models (e.g., machine-learned models trained to generate predicted values ​​based on prior behavioral data) and / or one or more diffusion models (e.g., machine-learned models trained to generate predicted data based on generating and processing distribution data associated with input data).

[0175] One or more generative models 90 may be trained to process input data and generate model-generated content items, which may include predicted words, pixels, signals, and / or other data. The model-generated content items may include new content items that are not identical to any existing work. The one or more generative models 90 may leverage learned expressions, sentences, and / or probability distributions to generate the content items, which may include phrases, plots, settings, objects, characters, beats, lyrics, and / or other aspects not included in the existing content items.

[0176] The one or more generative models 90 may include a visual language model. The visual language model may be trained, tuned, and / or configured to process image data and / or text data to generate natural language output. The visual language model may leverage a pre-trained large-scale language model (e.g., a large-scale autoregressive language model) along with one or more encoders (e.g., one or more image encoders and / or one or more text encoders) to provide detailed natural language output that emulates natural language constructed by humans.

[0177] Visual language models may be utilized for zero-shot image classification, few-shot image classification, image captioning, multimodal query distillation, multimodal question and answering, and / or may be tuned and / or trained for multiple different tasks. Visual language models may perform visual question answering, image caption generation, feature detection (e.g., content monitoring (e.g., for inappropriate content), object detection, scene recognition, and / or other tasks.

[0178] The visual language model may leverage a pre-trained language model, which may then be tuned for multi-modality. The training and / or tuning of the visual language model may include image-text matching, masked language modeling, multi-modal fusion with cross-attention, contrastive learning, prefix language model training, and / or other training techniques. For example, the visual language model may be trained to process an image to generate predicted text that is similar to ground truth text data (e.g., a ground truth caption for the image). In some implementations, the visual language model may be trained to replace masked tokens of a natural language template with text tokens that describe features shown in the input image. Alternatively and / or additionally, the training, tuning, and / or model inference may include multi-layer concatenation of visual and text embedding features. In some implementations, the visual language model may be trained and / or tuned through jointly learning image embeddings and text embedding generation, which may include training and / or tuning the system to map embeddings to a joint feature embedding space that maps text features and image features to a shared embedding space. The joint training may include image-text pair parallel embedding and / or may include triplet training. In some implementations, images may be utilized and / or processed as a prefix to the language model.

[0179] The one or more generative models 90 may be stored on the device and / or may be stored on a server computing system. In some implementations, the one or more generative models 90 may perform on-device processing to determine the suggested searches, suggested actions, and / or suggested prompts. The one or more generative models 90 may include one or more compact visual language models that may include fewer parameters than the visual language models stored and operated by the server computing system. The compact visual language models may be trained via distillation training. In some implementations, the visual language models may process the display data to generate suggestions. The display data may include a single image describing a screenshot and / or may include image data, metadata, and / or other data describing a period of time preceding the currently displayed content (e.g., applications, images, videos, messages, and / or other content viewed within the past 30 seconds). The user computing device may generate and store a rolling buffer window (e.g., 30 seconds) of data describing the displayed content in a buffer. As time passes, the data may be deleted. The rolling buffer window data may be utilized to determine a context, which may be leveraged for query, content, action, and / or prompt suggestions.

[0180] In some implementations, the generative model 90 may include a machine-learned sequence processing model. The exemplary system may pass an input to the sequence processing model. The sequence processing model may include one or more machine-learned components. The sequence processing model may process data from the input to obtain an input sequence. The input sequence may include one or more input elements obtained from the input. The sequence processing model may process the input sequence using a prediction layer to generate an output sequence. The output sequence may include one or more output elements generated based on the input sequence. The system may generate an output based on the output sequence.

[0181] A sequence processing model may include one or more machine-learned model components configured to ingest, generate, or otherwise reason over sequences of information. For example, some exemplary sequence processing models in the text domain are referred to as "large-scale language models" or LLMs. See, for example, PaLM 2 Technical Report, Google, https: / / ai.google / static / documents / palm2techreport.pdf(nd). Other exemplary sequence processing models can operate in other domains, such as, for example, the image domain, see, e.g., Dosovitskiy et al., An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, arXiv:2010.11929v2 (June 3, 2021), the audio domain, see, e.g., Agostinelli et al., MusicLM: Generating Music From Text, arXiv:2301.11325v1 (January 26, 2023), the biochemical domain, see, e.g., Jumper et al., Highly accurate protein structure prediction with AlphaFold, 596 Nature 583 (August 26, 2021). The sequence processing model can process one or more types of data simultaneously. The sequence processing model may include relatively large models (e.g., more parameters, computationally expensive, etc.), relatively small models (e.g., fewer parameters, computationally lightweight, etc.), or both.

[0182] In general, a sequence processing model can use data from an input to obtain an input sequence. For example, the input sequence can include a representation of data from the input in a format understood by the sequence processing model. One or more machine-learned components of the sequence processing model can take the data from the input, parse the data into pieces that fit the processing architecture of the sequence processing model (e.g., via "tokenization"), and project the pieces into an input space associated with a prediction layer (e.g., via "embedding").

[0183] A sequence processing model can take data from an input and parse the data into a sequence of elements to obtain an input sequence. For example, a portion of the input data from an input can be decomposed into pieces that collectively represent the content of that portion of the input data. Those pieces can provide the elements of a sequence.

[0184] In some implementations, processing the input data may include tokenization. For example, a tokenizer may process a given portion of an input source and output a series of tokens that represent that portion of the input source (e.g., corresponding to input elements). Various techniques of tokenization may be used. For example, a text input source may be tokenized using a byte-pair encoding (BPE) technique. See, for example, Kudo et al., SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations), pp. 66-71 (October 31-November 4, 2018), https: / / aclanthology.org / D18-2012.pdf. An image-based input source may be tokenized by extracting and serializing patches from the image.

[0185] In general, any data type can be serialized and processed into an input sequence.

[0186] A prediction layer can predict one or more output elements based on input elements. A prediction layer can include one or more machine-learned model architectures, such as one or more layers of learned parameters, that manipulate and transform inputs to extract higher-level meaning from and relationships between input elements. In this way, for example, an exemplary prediction layer can predict new output elements in light of the context provided by the input sequence.

[0187] The prediction layer can evaluate associations between portions of the input sequence and particular output elements. These associations can inform predictions of the likelihood that a particular output will follow the input context. For example, consider the text snippet "The carpenter's toolbox was small and heavy. It was full of ___." An exemplary prediction layer can identify that "It" points back to the "toolbox" by determining the relationship between the respective embeddings. An exemplary prediction layer can also link "It" to attributes of the toolbox, such as "small" and "heavy." Based on these associations, the prediction layer can assign a higher probability to the word "nails" than to the word "sawdust," for example.

[0188] A transformer is an example architecture that may be used in the prediction layer. See, for example, Vaswani et al., Attention Is All You Need, arXiv:1706.03762v7 (August 2, 2023). A transformer is an example of a machine-learned model architecture that uses an attention mechanism to compute associations between items within a context window. The context window may include a sequence that includes an input sequence and potentially one or more output elements. A transformer block may include one or more attention layers and one or more post-attention layers (e.g., a feedforward layer such as a multilayer perceptron).

[0189] The prediction layer may include other machine-learned model architectures in addition to or instead of transformer-based architectures. For example, recurrent neural networks (RNNs) and long short-term memory (LSTM) models, as well as convolutional neural networks (CNNs) may also be used. In general, the prediction layer may utilize various types of artificial neural networks that can understand or generate sequences of information.

[0190] The output sequence may include or otherwise represent the same or different data types as the input sequence. For example, the input sequence may represent text data and the output sequence may represent text data. The input sequence may represent image, audio, or audiovisual data and the output sequence may represent text data (e.g., describing the image, audio, or audiovisual data). It should be understood that the prediction layer, and any other intermediate model components of the sequence processing model, may be configured to receive different data types in the input sequence and output different data types in the output sequence.

[0191] An output sequence can have various relationships with an input sequence. An output sequence can be a continuation of an input sequence. An output sequence can supplement an input sequence. An output sequence can translate, transform, extend, or otherwise modify an input sequence. An output sequence can reply to, evaluate, validate, or otherwise respond to an input sequence. An output sequence can implement (or describe instructions for implementing) instructions provided via the input sequence.

[0192] The output sequence may be generated autoregressively. For example, in some applications, the output of one or more prediction layers may be passed through one or more output layers (e.g., softmax layers) to obtain a probability distribution over the output vocabulary (e.g., text or symbol vocabulary) conditional on the set of input elements in the context window. In this manner, the output sequence may be generated autoregressively, for example, by sampling a possible next output element, adding the element to the context window, and regenerating the probability distribution based on the updated context window, as well as sampling the possible next output element.

[0193] The output sequence may also be generated in a non-autoregressive manner. For example, multiple output elements of the output sequence may be predicted jointly without explicit sequential conditioning on each other. See, e.g., Saharia et al., Non-Autoregressive Machine Translation with Latent Alignments, arXiv:2004.07437v3 (November 16, 2020).

[0194] An output sequence may include one or more portions or elements. In an exemplary content generation configuration, an output sequence may include multiple elements (e.g., text sentences, discretized waveform values, computer code, etc.) corresponding to multiple portions of the generated output sequence. In an exemplary classification configuration, an output sequence may include a single element associated with a classification output. For example, an output called "vocabulary" may include a set of classes into which the input sequence will be classified. For example, a vision transformer block may pass latent state information to a multi-layer perceptron that outputs possible class values ​​associated with an input image.

[0195] The output determination system 80 may process one or more data sets and / or the output of the sensor processing system 60 using a data augmentation block 92 to generate augmented data. For example, one or more images may be processed using the data augmentation block 92 to generate one or more augmented images. Data augmentation may include data correction, data cropping, removal of one or more features, addition of one or more features, resolution adjustment, lighting adjustment, saturation adjustment, and / or other enhancements.

[0196] In some implementations, one or more data sets and / or outputs of the sensor processing system 60 may be stored based on the determination in a data storage block 94.

[0197] The output of the output determination system 80 may then be provided to a user via one or more output components of the user computing device 52. For example, one or more user interface elements associated with the one or more outputs may be provided for display via a visual display of the user computing device 52.

[0198] The process may be performed iteratively and / or continuously, with one or more user inputs to provided user interface elements conditioning and / or influencing the successive processing loops.

[0199] 10 shows a flow chart diagram of an exemplary method for performing according to an exemplary embodiment of the present disclosure. Although FIG. 10 shows steps performed in a particular order for purposes of illustration and explanation, the method of the present disclosure is not limited to the specifically shown order or arrangement. Various steps of method 1000 can be omitted, rearranged, combined, and / or adapted in various ways without departing from the scope of the present disclosure.

[0200] At 1002, a computing system can obtain input data. The input data can include a search query. In some implementations, the search query can be associated with a subject of the search. The search query can be associated with a product type.

[0201] At 1004, the computing system can process the search query to determine a plurality of preliminary search results. The plurality of preliminary search results may include a plurality of content items responsive to the search query. In some implementations, the plurality of preliminary search results may include a plurality of content items associated with a product type. The plurality of preliminary search results may include one or more web resources including user reviews. The plurality of preliminary search results may include trusted web resources associated with web domains stored in a verified database.

[0202] At 1006, the computing system may process at least a subset of the plurality of content items with the machine-learned model to determine a plurality of badges associated with a subject of the search. The plurality of badges may be associated with a plurality of terms determined to be associated with the subject. In some implementations, the plurality of badges may be associated with a plurality of topics determined to be associated with the subject. The plurality of badges may be associated with a plurality of attributes determined to be associated with at least a subset of objects in a product type. The plurality of attributes may include one or more attributes associated with effectiveness for a particular set of objects of a product type for a unique use. In some implementations, one or more of the plurality of badges may be determined based on reviews provided by a user. The machine-learned model may include a natural language processing model. The plurality of badges may be determined based at least in part on a sentiment analysis performed by the machine-learned model. In some implementations, the plurality of badges may be determined based at least in part on a determined frequency of one or more terms. The badge determination may be based on a frequency with which a term is used, sentiment analysis, semantic understanding, and / or contextual data. The subject may include a product type. The plurality of badges may be associated with qualities associated with different products of the product type. Topics can describe one or more descriptors that differentiate the Web resources associated with the subject.

[0203] In some implementations, the multiple badges may be determined based on determining a multiple number of products associated with the subject matter, determining a respective product description for each of the multiple products, determining a multiple number of differentiators associated with the multiple products, and determining the multiple badges based on the multiple differentiators. The multiple differentiators may describe qualities that differentiate a particular product from one or more other products associated with the subject matter.

[0204] At 1008, the computing system may determine a plurality of specific search results associated with the plurality of badges. Each specific search result may be associated with a respective badge of the plurality of badges. In some implementations, each specific search result of the plurality of specific search results may be provided for display with a respective user interface element describing the respective badge. Each specific search result of the plurality of specific search results may include a unique search result determined to be responsive to the search query and a respective badge. Each of the plurality of specific search results may be associated with a respective product of the product type.

[0205] At 1010, the computing system can provide a plurality of particular search results for display along with the plurality of badges. The plurality of particular search results can be provided for display in a search result interface. The search result interface can include a query input box, the plurality of particular search results with each respective badge of the plurality of badges, and a text-to-text generative model output. The text-to-text generative model output can be generated by processing the search query with the text-to-text generative model.

[0206] In some implementations, the computing system can process the search query with the language model to generate a model-generated response. The model-generated response can be responsive to the search query. The computing system can provide the model-generated response in a search result interface adjacent to a plurality of particular search results. The model-generated response can be determined by processing one or more of the plurality of preliminary search results with the language model.

[0207] Additionally and / or alternatively, the computing system may obtain badge selections associated with a particular badge among the plurality of badges and provide badge-specific search results associated with the particular badge among the plurality of badges.

[0208] 11 illustrates a block diagram of an example badge generation and indexing system 1100, according to an example embodiment of the present disclosure. In particular, the badge generation and indexing system 1100 may include obtaining and / or determining web information 1102 for processing. The web information 1102 may include user reviews, editorial reviews, TopN page titles, and / or buying guide page titles.

[0209] Web information 1102 may be processed with one or more use case models 1104 to determine one or more candidate use cases 1106 associated with the subject matter of the web information 1102. The one or more use case models 1104 may output the one or more candidate use cases 1106 along with determined statistics.

[0210] One or more candidate use cases 1106 may be processed with one or more embedding models to generate one or more candidate use case embeddings and / or one or more search result embeddings. One or more candidate use case embeddings may be compared to other embeddings (e.g., one or more search result embeddings) to determine embedding similarities 1110 with other use case embeddings, web result embeddings, and / or query embeddings.

[0211] Based on the determination of embedding similarity 1110, one or more badge clusters 1112 may be determined. Each badge cluster may be associated with a set of embeddings determined to be associated with a similar topic or type of topic. The badge clusters 1112 may then be stored for ranking and / or retrieval in response to a search query.

[0212] Additionally and / or alternatively, candidate use case pairs 1114 may be determined based on one or more candidate use cases 1106. The candidate use case pairs may be processed with a multi-task integration model 1116, which may generate an output that may be utilized to determine whether a first candidate use case and a second candidate use case are similar. The similarity determination may be utilized to determine and / or expand the clustering 1112. The multi-task integration model 1116 may be trained to identify complex and / or multi-task requests and to determine a set of actions to be performed to fulfill the multi-task requests. The multi-task integration model 1116 may be configured and / or trained to perform multi-task request fulfillment to reduce search instances required to reach a final resource requested by a user. In some implementations, the multi-task integration model 1116 may include one or more generative models (e.g., a generative language model, which may include one or more transformer models). The multi-task integration model 1116 may be utilized to determine whether two use cases are associated with similar tasks.

[0213] Clustering 1112 may be utilized to generate use case clusters. The use case clusters may be utilized to reduce redundancy and / or confusion when serving search results to a user. In particular, the search result interface may limit the number of badges from a given cluster during search result display (e.g., to one badge per cluster) to provide a diverse set of search results (and thus a diverse set of use cases) along with a diverse set of badges.

[0214] The techniques described herein refer to servers, databases, software applications, and other computer-based systems, as well as actions taken and information sent to and from such systems. The inherent flexibility of computer-based systems allows for a wide variety of possible configurations, combinations, and divisions of tasks and functions among components. For example, the processes described herein may be implemented using a single device or component, or multiple devices or components working in combination. Databases and applications may be implemented on a single system or distributed across multiple systems. Distributed components may operate sequentially or in parallel.

[0215] Although the present subject matter has been described in detail with respect to various specific exemplary embodiments thereof, each example is provided as an explanation, not a limitation of the present disclosure. Once a person skilled in the art arrives at the above understanding, he or she can easily create modifications, variations, and equivalents of such embodiments. Thus, the present disclosure does not exclude the inclusion of such modifications, variations, and / or additions to the present subject matter as would be readily apparent to a person skilled in the art. For example, features shown or described as part of one embodiment may also be used with another embodiment to produce a further embodiment. Thus, it is intended that the present disclosure covers such modifications, variations, and equivalents. [Explanation of symbols]

[0216] 10 Badge generation and search system, artificial intelligence generated badge search system 12, 212 Web Data 14, 214 Machine-learned models 16, 216 badges 18,218 Search Queries 20, 220 Search Engine 22, 222, 400, 500, 600 Search Results Interface 50 Computing Systems 52 Computing Devices, User Computing Devices 60 Sensor Processing System 62 Context Decision Block 64 Image Pre-processing Blocks 66 Detection Model 68 Segmentation Models 70 Classification Models 72 Embedded Model 74 Search Engines 76 Multimodal Processing Block 80 Output Determination System 82 Search Results Interface 84 Machine learning model output interface 86 Augmented and / or Virtual Reality Experiences 88 Action Prompt 90 Generative Model 92 Data Extension Block 94 Data Storage Blocks 100 Computing system, system 102 User Computing System 104 User Computing Devices 112, 132, 152 processors 114 Memory, user computing device memory 116, 136, 156 Data 118, 138, 158 instructions 120, 140 Machine learning models, models 122 User Input Components 124, 144 User Interface 126 Sensors 130 Server Computing System 134, 154 memory 142 Search Engines 150 Third Party Computing Systems 180 Network 200 Search System 224 Embedded Model 226 Badge Embedding 228 Generative Model 230 queries 402, 502, 602 Search query input box 404 Results 406 Badges, Badge Indicators 408 Knowledge Panel 504, 604 Badged Search Results, Search Results 506, 606 Badge Indicator 508, 608 Model generation response 510, 610 Media Content Items 512, 612 General search results 1100 Badge Generation and Indexing System 1102 Web Information 1104 Use Case Model 1106 Candidate use case 1110 Embedding Similarity 1112 Badge Cluster, Clustering 1114 Candidate Use Case Pairs 1116 Multitask Integration Model

Claims

1. 1. A computing system comprising: one or more processors; and one or more non-transitory computer-readable media collectively storing instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations including: obtaining web data associated with a particular product, the web data comprising web information associated with the particular product; processing the web data with one or more machine learning models to determine one or more specific uses associated with the particular product, the one or more specific uses being determined based on the web information; generating one or more badges based on the one or more particular uses, the one or more badges describing the one or more particular uses; storing the one or more badges, the one or more badges being stored with data describing an association with the particular product; obtaining a search query, the search query being associated with a product type and the particular product being of the product type; providing a search result interface based on the search query and the one or more badges. Including, the system.

2. The system of claim 1 , wherein the web data comprises user reviews of the particular product.

3. The system of claim 1 , wherein the one or more particular uses are determined based on a frequency of the term in web information, sentiment analysis, and semantic understanding.

4. The one or more particular uses A scenario for using said particular product; the purpose for which said particular product is to be used; the time to use the particular product, or The type of user who will be using the product The system of claim 1 , wherein the system is associated with at least one of:

5. The operation, processing the one or more badges with an embedding model to generate one or more respective badge embeddings within the embedding space; determining a plurality of search results for display in the search result interface based on the one or more badge embeddings; The system of claim 1 further comprising:

6. determining the plurality of search results, processing the search query with the embedding model to generate a query embedding; determining that the query embedding is associated with the badge embedding; providing, in the search result interface, product search results describing the particular product; The system of claim 5 , comprising:

7. The operation, processing a plurality of other badges associated with a plurality of other products using the embedding model to generate a plurality of other badge embeddings; determining one or more badge clusters based on the one or more badge embeddings and the plurality of other badge embeddings; determining one or more search results of the search result interface based on the one or more badge clusters; The system of claim 5 , further comprising:

8. providing the search result interface based on the search query and the one or more badges, determining that the one or more badges are associated with the search query; obtaining product data associated with the particular product, the product data comprising one or more links to one or more web resources associated with the particular product; Including, The system of claim 1 , wherein the search result interface comprises product search results, the product search results comprising data describing the product and the one or more badges.

9. 10. The system of claim 1, wherein the one or more machine-learned models comprise a natural language processing model, and the one or more specific uses are determined based at least in part on sentiment analysis.

10. The system of claim 1 , wherein the web information comprises product descriptions and answers to frequently asked questions.

11. 1. A computer-implemented method, comprising: determining, by a computing system having one or more processors, one or more web resources associated with the object; processing, by the computing system, one or more content items of the one or more web resources using one or more machine learning models to determine at least one of one or more advantages or one or more disadvantages associated with the object; generating, by the computing system, one or more badges based on the at least one of the one or more advantages or one or more disadvantages associated with the object, the one or more badges comprising a generated text label; receiving, by the computing system, a search query from a user computing system; determining, by the computing system, that at least one of the object or the one or more badges is associated with the search query; providing, by the computing system, specific object search results for display in a search result interface, the specific object search results comprising data describing the object and user interface elements describing the one or more badges; The method includes:

12. determining, by the computing system, that the at least one of the object or the one or more badges is associated with the search query, processing, by the computing system, the search query with a search engine to determine a plurality of search results; determining, by the computing system, a set of badges associated with the plurality of search results, the set of badges comprising the one or more badges; providing, by the computing system, a particular set of search results in the search result interface based on the set of badges; 12. The method of claim 11, comprising:

13. determining, by the computing system, that the at least one of the object or the one or more badges is associated with the search query, determining, by the computing system, a set of badges associated with the search query, the set of badges comprising the one or more badges; determining, by the computing system, respective search results for each particular badge in the set of badges; providing, by the computing system, the respective set of search results in the search result interface based on the set of badges; 12. The method of claim 11, comprising:

14. indexing, by the computing system, the one or more badges with data describing the object.

12. The method of claim 11, further comprising:

15. determining the one or more web resources, obtaining, by said computing system, data describing said object; processing, by the computing system, the data describing the object using a search engine to determine a set of object-specific search results; selecting, by the computing system, one or more particular object-specific search results from the set of object-specific search results; 12. The method of claim 11, comprising:

16. The method of claim 11 , wherein the one or more web resources comprise a web marketplace listing for the object.

17. One or more non-transitory computer-readable media collectively storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations, including: obtaining a search query, the search query being associated with a particular object type; processing the search query to determine a plurality of badges associated with the search query, the plurality of badges comprising a plurality of particular benefits associated with a plurality of different objects of the particular object type; determining a subset of the plurality of badges to display; obtaining a plurality of search results associated with the subset of the plurality of badges, the plurality of search results comprising one or more respective search results for each particular badge of the subset of the plurality of badges; providing a search result interface for display, the search result interface comprising the plurality of search results, each of the plurality of search results being annotated with the particular badge associated with the respective search result; [0023] In one or more non-transitory computer readable media,

18. 20. The one or more non-transitory computer-readable media of claim 17, wherein the plurality of badges are generated by processing a plurality of reviews for each of the plurality of different objects.

19. 18. The one or more non-transitory computer-readable media of claim 17, wherein the search result interface comprises a first panel for the plurality of search results and a second panel for a model-generated response, the model-generated response being generated by processing the search query with a language model to generate the model-generated response, the model-generated response being responsive to the search query, the language model comprising a text-to-text generative model.

20. the plurality of search results comprises a plurality of product search results associated with a particular set of web resources; 20. The one or more non-transitory computer-readable media of claim 17, wherein the search result interface comprises a plurality of product search results, a plurality of general search results, and a natural language response, the natural language response being generated using a machine-learned generative model, and the plurality of general search results being determined using a search engine.

Citation Information

Patent Citations

  • Product search device and program

    JP2012168925A

  • Action indicator for search behavior output elements

    JP2021523492A

Cited By

  • Method, apparatus and computer-readable recording medium for providing chatbot service for outputting customized change information

    JP2026091772A

  • Method, device, and computer-readable recording medium for providing a chatbot service that outputs customized trading information

    JP7740768B1

  • KNN Retrieval Method for Remote Sensing Images Using Visual Language Models

    JP7824714B1

  • Information processing device

    US12748745B2

  • Information processing device

    US20260037496A1