Generating multi-order text query results using a context orchestration engine

Abstract

The present disclosure is directed to a system, method, and non-transitory computer-readable medium for generating responses to multi-order text queries using a context orchestration engine. For example, the disclosed system generates context-defining query subcomponents from a multi-order text query, where the context-defining query subcomponents indicate contextual data sources associated with respective portions of the multi-order text query. Furthermore, the disclosed system provides or transmits the context-defining query subcomponents to a large-scale language model for domain-specific computer code associated with each context-defining query subcomponent. The disclosed system can further execute the generated computer code for each context-defining query subcomponent to access the indicated contextual data sources to generate component-specific results. The disclosed system can also generate multi-order results for the multi-order text query from the component-specific results.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 486,217, filed February 21, 2023, and U.S. Patent Application No. 18 / 309,496, filed April 28, 2023. Each of the foregoing applications is incorporated herein by reference in its entirety. [Background technology]

[0002] background Advances in computing devices and network technologies have led to various innovations in machine learning and network-based digital assistants. For example, local and web-based digital assistant applications can perform various functions in response to single-order text queries, including finding a single answer from a database and generating a single-order content item. However, despite these advances, existing digital assistant systems continue to suffer from many shortcomings, particularly in terms of flexibility and accuracy.

[0003] As described above, certain existing digital assistant systems lack flexibility. More specifically, some existing systems are limited to generating responses for single-order text queries. Specifically, many existing systems are rigidly focused on processing or analyzing single-order text queries that specify a single task, a single source, and / or a single output for generating a response. However, such existing systems are unable to flexibly accommodate higher-order (e.g., more than single-order) text queries that require multifaceted response generation across multiple tasks, data sources, and / or various output combinations. Indeed, solving higher-order problems and generating responses to higher-order text queries has long been pursued in the networking and machine learning industries but has proven difficult or impossible given the rigid nature of conventional systems.

[0004] Due at least in part to their lack of flexibility, some existing digital assistant systems are inaccurate. Indeed, as suggested, some existing systems are unable to generate responses to higher-order text queries. Accordingly, many existing systems generate incomplete (e.g., targeting only a single aspect of the text query) and / or irrational, erroneous responses to such higher-order text queries. Summary of the Invention

[0005] The present disclosure describes one or more embodiments of a system, method, and non-transitory computer-readable storage medium that provide benefits and / or solve one or more of the aforementioned and other problems in the art. For example, the disclosed system provides a novel system for generating a response to a multi-order text query using a context orchestration engine. For example, the disclosed system generates a first context-defining query subcomponent from a multi-order text query utilizing the context orchestration engine, and the first context-defining query subcomponent indicates a first context data source for responding to the first context-defining query subcomponent. Furthermore, the disclosed system provides or transmits the first context-defining query subcomponent to a large-scale language model for domain-specific computer code associated with the first context-defining query subcomponent. The disclosed system can further execute the generated computer code for the first context-defining query subcomponent to access the indicated first context data source to generate a first result for the first context-defining query subcomponent. Additionally, the disclosed system identifies a second result for a second context-defining query subcomponent generated from the multi-order text query, the second result indicating a second contextual data source. Additionally, the disclosed system utilizes the first result and the second result to generate aggregated results in response to the multi-order text query. Further features of the disclosed system are described below. [Brief explanation of the drawings]

[0006] This disclosure describes one or more example implementations of the systems and methods with additional specificity and detail by reference to the accompanying drawings, the following paragraphs briefly describing these drawings.

[0007] [Figure 1] FIG. 1 illustrates a schematic diagram of an example environment of a multi-order query results system, according to one or more embodiments.

[0008] [Figure 2A] , [Figure 2B] 2A and 2B illustrate an exemplary overview of a multi-order query results system that uses a context orchestration engine to generate aggregated results for multi-order text queries, according to one or more embodiments.

[0009] [Figure 3] FIG. 3 illustrates an example architecture diagram of a multi-order query results system that resolves multi-order text queries and executes computer code, according to one or more embodiments.

[0010] [Figure 4A] , [Figure 4B] 4A-4B illustrate an example multi-order query results system that generates context-defining subcomponents from a multi-order text query, according to one or more embodiments.

[0011] [Figure 4C] , [Figure 4D] 4C-4D illustrate example code generated in response to a multi-order query results system that provides context-defining query subcomponents to a large-scale language model, according to one or more embodiments.

[0012] [Figure 5] FIG. 5 illustrates an exemplary diagram of a multi-order query results system implemented at the client device level and the general environment level, and its interaction with the application layer, according to one or more embodiments.

[0013] [Figure 6] FIG. 6 illustrates an exemplary diagram of a multi-order query results system rendering from various contextual data sources, according to one or more embodiments.

[0014] [Figure 7] FIG. 7 illustrates an example diagram of a multi-order query results system receiving an unanswerable multi-order text query according to one or more embodiments.

[0015] [Figure 8] FIG. 8 illustrates an exemplary diagram of implementing a multi-order query results system with an internal context search engine, according to one or more embodiments.

[0016] [Figure 9] FIG. 9 shows an exemplary diagram of implementing a multi-order query results system using an expert identification engine, according to one or more embodiments.

[0017] [Figure 10] FIG. 10 shows an example diagram of implementing a multi-order query results system using a video transcription query engine, according to one or more embodiments.

[0018] [Figure 11] FIG. 11 illustrates an exemplary graphical user interface of a multi-order query results system that provides responses according to one or more embodiments.

[0019] [Figure 12] FIG. 12 illustrates an example series of operations performed by a multi-order query results system, according to one or more embodiments.

[0020] [Figure 13]FIG. 13 illustrates a block diagram of an exemplary computing device, according to one or more embodiments.

[0021] [Figure 14] FIG. 14 illustrates an example environment of a networked system having a multi-order query results system according to one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0022] Detailed Description This disclosure describes one or more embodiments of a multi-order query result system that can generate results in response to multi-order text queries utilizing a context orchestration engine integrated with a large-scale language model. For example, the multi-order query result system provides contextualized results for queries received from a client device. In particular, the multi-order query result system decomposes a multi-order text query into multiple context-defining query subcomponents and utilizes a large-scale language model to generate computer code for the subcomponents. For example, the multi-order query result system can generate results for multi-order text queries (e.g., queries having multiple steps that point to multiple contextual data sources). The results generated from the multi-order query result system include decisions (e.g., answers) responsive to questions or actions (e.g., execution of computer functions). Furthermore, the results generated by the multi-order query result system can then be provided to a query client device as a response, such that the multi-order query result system notifies the query client device about the results (e.g., decisions or actions performed).

[0023] To illustrate, as an example, a multi-order query result system may receive a multi-order text query such as, "When is the next meeting with the head of accounting?" In response, the multi-order query result system may generate a response to this multi-order text query by accessing a first contextual data source corresponding to scheduled meetings for the user account and a second contextual data source corresponding to the user account ontology, and further generating a result (e.g., a decision) that combines data from both contextual data sources to indicate dates and times.

[0024] As described above, a multi-order query result system can generate results for a multi-order text query. To elaborate, the multi-order query result system receives a multi-order text query from a client device (e.g., as a typed question or a spoken question received via a microphone). From the multi-order text query, the multi-order query result system can extract or generate context-defining query subcomponents (e.g., decompose the multi-order text query). For example, the multi-order query result system can utilize a context orchestration engine (e.g., one or more computer applications for software / network container orchestration that decomposes the components of a multi-order text query and indicates various contextual data sources) to process or analyze the multi-order text query. In some cases, the multi-order query result system utilizes the context orchestration engine via a large-scale language model to split or partition the multi-order text query into multiple subcomponents, each of which indicates (or invokes or references) its own action (or step) and / or its own contextual data source to generate its respective result (e.g., a result specific to the context-defining query subcomponent).

[0025] In one or more embodiments, the multi-order query results system further generates or determines a contextual data source for each of the context-defining query subcomponents. More specifically, the multi-order query results system generates a domain-specific language (e.g., plain language description and / or computer code referencing the contextual data source) that corresponds to and / or indicates the contextual data source (e.g., external application / system / database).

[0026] In some cases, the multi-order query result system further generates domain-specific computer code for generating results corresponding to each of the context-defining query subcomponents. For example, the multi-order query result system generates a computer code segment for each query subcomponent, where each computer code segment is specific to a context data source that stores data for responding to that query subcomponent. In some cases, the multi-order query result system generates the domain-specific computer code segments by providing context data (e.g., a domain-specific language) to a large-scale language model. Specifically, the multi-order query result system provides or transmits a multi-order text query to a large-scale language model (e.g., ChatGPT or other large-scale language model), which decomposes the multi-order text query into query subcomponents and generates executable computer code associated with each query subcomponent. In effect, the large-scale language model generates an executable computer code segment for each query subcomponent, where the computer code segment is specific to each of the context data sources.

[0027] In some embodiments, the multi-order query results system further executes computer code from the large-scale language model. In particular, the multi-order query results system utilizes a context orchestration engine to execute computer code generated for each of the context-defining query subcomponents. In effect, the multi-order query results system executes multiple computer code segments, each computer code segment including instructions for accessing a respective context data source to generate results corresponding to the query subcomponent. In some cases, the multi-order query results system further generates aggregate results for the multi-order text query by combining (e.g., compiling or summarizing) the component-specific results generated via each computer code segment.

[0028] Furthermore, in one or more embodiments, the multi-order query results system integrates computer software applications from various environments. For example, the multi-order query results system can integrate applications specific to an organizational ecosystem (e.g., a particular work entity). In doing so, the multi-order query results system provides results of multi-order text queries that are contextualized for a particular organizational ecosystem. Thus, the multi-order query results system acts as a powerful contextual search engine for a particular organization.

[0029] Additionally, in one or more embodiments, the multi-order query results system integrates computer software applications from third-party applications. For example, the multi-order query results system can integrate applications such as photo applications, calendar applications, ride-sharing services, flight booking services, browser history, email services, stored content items, hotel services, and organizational ontologies. In particular, the integration of third-party applications enables the multi-order query results system to provide a personalized contextual search engine for individuals. Additionally, in some embodiments, the multi-order query results system links with its context orchestration engine within a content management system. For example, the multi-order query results system links to a video transcription query engine, an expert identification engine, and / or other internal contextual search engines.

[0030] As alluded to above, a multi-order query result system can provide several improvements or advantages over existing video editing systems. For example, a multi-order query result system can provide improved flexibility over existing systems. While many existing systems are limited to generating responses to single-order queries, a multi-order query result system can accommodate multiple-order queries. For example, a multi-order query result system overcomes the limitations of conventional systems by generating, from a multi-order text query, a first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent. Furthermore, the multi-order query result system generates a first result by utilizing computer code specific to the first context data source, executable to respond to the first context-defining query subcomponent. Furthermore, the multi-order query result system identifies a second result for a second context-defining query subcomponent generated from the multi-order text query. The multi-order query result system can further utilize the first result and the second result to generate aggregate results in response to the multi-order text query.

[0031] At least in part by improving flexibility over conventional video editing systems, the multi-order query result system can also improve accuracy. Specifically, the multi-order query result system can accurately generate responses to multi-order text queries. For example, by generating multiple context-defining query subcomponents (e.g., decomposing a multi-order text query into manageable components), the multi-order query result system accurately generates aggregate result responses to the multi-order text queries. In particular, each context-defining query subcomponent also results in corresponding computer code that is executable to respond to each context-defining query subcomponent. Thus, the multi-order query result system accurately responds to multi-order text queries.

[0032] Additionally, the multi-order query result system further improves accuracy by integrating various contextual data sources. For example, the multi-order query result system can adapt to a user account's specific contextual data sources, including account-specific contextual data sources, organizational contextual data sources (e.g., company / organization ontologies), and / or application-specific contextual data sources. Thus, the multi-order query result system can generate accurate responses for individual user accounts by generating and executing computer code specific (e.g., contextualized) to the contextual data sources indicated by and / or specific to the user account. For example, depending on the context of the search (e.g., organizational or personal), the multi-order query result system accurately generates results due to the user account's access to various contextual data sources.

[0033] As indicated by the foregoing discussion, the present disclosure utilizes various terms to describe the features and advantages of the multi-order query results system. Further details regarding the meaning of these terms as used in the present disclosure are provided below.

[0034] As described above, the multi-order query result system generates a first context-defining query subcomponent from a multi-order text query. As used herein, "multi-order text query" refers to a non-first-order text query. For example, a multi-order text query includes multiple contexts that define query subcomponents. For example, a query such as "Who did I spend the most time with this month?" may include multiple subcomponents. Illustratively, this example query includes the following subcomponents: 1) determining basic details of the querying user; 2) all meetings the user attended in the past month; 3) all attendees of each meeting in the past month; and 4) other subcomponents to determine combinations of the aforementioned subcomponents (e.g., aggregating the results of the first few components and selecting people who match the multi-order text query).

[0035] The multi-order query result system generates a first context-defining query subcomponent from the multi-order text query. As used herein, a "query subcomponent," "subcomponent," or "component" refers to a subpart of the multi-order text query defined by a context. In some examples, each component decomposed by the multi-order query result system indicates a context data source. For example, the first context-defining query subcomponent indicates a first context data source.

[0036] As used herein, a "contextual data source" refers to a location or system that contains data. In particular, contextual data sources include databases, native applications, web applications, spreadsheets, files, websites, browsers, online platforms, and other sources of structured and unstructured data. For example, contextual data sources include structured and unstructured data supporting various applications utilized on computing devices. Thus, contextual data sources may include both internal or external data at an organizational, individual, or application level.

[0037] As described above, the multi-order query result system provides the first context-defining query subcomponent to a large-scale language model. As used herein, a "large-scale language model" refers to a model capable of processing and generating natural language text. In particular, the large-scale language model is trained on a large amount of data to learn the patterns and rules of language. Thus, after training, the large-scale language model can generate text with a similar style and content to the input data. Examples of large-scale language models include BLOOM, Bard AI, LaMDA, or DialoGPT. In some embodiments, the large-scale language model may include a model that is considered to include artificial intelligence features.

[0038] As described above, the multi-order query results system provides a first context-defining query subcomponent to a large-scale language model to generate computer code. As used herein, "computer code" refers to a set of instructions written in a programming language that a computing device can interpret and execute to perform a specific task. In particular, computer code includes a series of statements and functions that perform specific operations. Furthermore, computer code includes statements written in a specific syntax that can be translated into machine code executed by a computing device. Thus, the multi-order query results system generates computer code corresponding to the context data source. For example, the multi-order query results system generates computer code specific to the context data source and executable to respond to a specific context-defining query subcomponent.

[0039] Also, as noted above, the multi-order query results system utilizes domain-specific computer code. As alluded to in the previous paragraph, domain-specific computer code refers to computer code that is specific to a contextual data source. Thus, domain-specific computer code indicates that the computer code is uniquely tailored to a context-defining subcomponent and a particular contextual data source that corresponds to the context-defining subcomponent.

[0040] As described above, the multi-order query result system executes computer code to generate a first result for a first context-defining query subcomponent of a multi-order text query. As used herein, "result" refers to the multi-order query system generating a rating or performing an action. In some examples, a multi-order text query causes the multi-order query result system to make a determination, such as who an employee's manager is. In some examples, a multi-order text query causes the multi-order query result system to perform an action, such as sending an email to a particular email address.

[0041] As mentioned above, some examples include a multi-order query results system in which the results perform an action. As used herein, "action" includes running a program, activating a function within a program, or causing an application to input or output data. In particular, an action can cause an event to occur, such as scheduling a calendar event, sending an email, sending a message, retrieving a file from a content management system, booking a flight, booking a hotel, reserving a rideshare vehicle, and other actions performed by an application.

[0042] In addition to generating results, the multi-order query result system generates aggregated results. For example, the aggregated results include multiple results. In particular, for each context-defining query subcomponent, the multi-order query result system generates a result. Furthermore, the multi-order query result system utilizes each generated result to generate aggregated results for the multi-order text query. Thus, for a multi-order text query, the multi-order query result system combines the generated results to form the aggregated result.

[0043] As part of generating the aggregated results, the multiple order query results system may also provide a response to the client device. As used herein, a "response" includes data (e.g., visual or audible data) presented on the client device related to the multiple order query. In particular, the response includes an indication of the aggregated results. For example, the multiple order query results system provides a display on a graphical user interface of the client device of a response indicating the aggregated results.

[0044] Further, in one or more embodiments, the multi-order query result system provides sample data to the large-scale language model. For example, the multi-order query result system receives a request from the large-scale language model for sample data. As used herein, "sample data" includes examples of multi-order queries, subcomponents of multi-order queries, and executable computer code. For example, the multi-order query result system receives a request for sample data in response to a large-scale language model that is unable to respond to a multi-order text query. Thus, the multi-order query result system providing sample data to the large-scale language model enables the large-scale language model to determine subcomponents and executable computer code for similar multi-order text queries. Furthermore, the multi-order query result system utilizes the sample data to train the large-scale language model to identify and decompose multi-order text queries into manageable subcomponents. Furthermore, in response to receiving a multi-order text query, the multi-order query result system provides the sample data to the large-scale language model to further train the large-scale language model to generate computer code specific to the various subcomponents.

[0045] As described above, the multi-order query results system integrates various applications. As used herein, an "application" refers to a computer program or set of computer programs designed to perform a particular function or set of functions. In particular, an application typically enables computer communication with other applications or computer systems via an application programming interface (i.e., API). As described above, an application may be a native application or a web-based application designed to perform a particular task or function.

[0046] Additionally, as mentioned, the multi-order query results system integrates applications from an organizational ecosystem. For example, an "organizational ecosystem" includes a computer system or systems associated with an entity comprised of multiple individuals or multiple groups. In particular, various types of software applications are utilized within an organizational ecosystem. Thus, an organizational ecosystem includes all software applications utilized within a particular organization. Additionally, the multi-order query results system integrates third-party applications. For example, third-party applications include computer programs or software components developed by entities not within the organization. In particular, third-party applications include, for example, calendar applications, messaging applications, ride-sharing applications, hotel applications, airline applications, and photo applications.

[0047] Additionally, as used herein, the term “digital content item” (or simply “content item”) refers to a digital object or digital file containing information that can be interpreted by a computing device (e.g., a client device) to present the information to a user. A digital content item can include a file, such as a digital text file, a digital image file, a digital audio file, a web page, a website, a digital video file, a web file, a link, a digital document file, or some other type of file or digital object. A digital content item can have a specific file type or file format, which can differ for different types of digital content items (e.g., digital documents, digital images, digital videos, or digital audio files). In some cases, a digital content item can refer to a remotely stored (e.g., cloud-based) item or link (e.g., a link to a cloud-based item or a web-based content item) and / or a content clip that shows (or links to) a discrete selection or segmented portion of content from a web page or some other content item or source. A digital content item can be editable or modifiable and can be shareable from one user account (or client device) to another. In some cases, a digital content item can be modified by multiple user accounts (or client devices) simultaneously and / or at different times.

[0048] Additionally, as used herein, the term "application session" (or simply "session") refers to a use case within a client application. For example, an application session refers to a set of activities performed within a single login of a client application or content management system application. As another example, an application session refers to a set of activities performed within a single visit of an application or a single access of a content item. In some cases, a session requires a login (and thus different logins can separate different sessions), but in other cases, a session does not require a login and instead refers to a use case between closures or terminations (of an application or web page), or between visits that are at least a threshold time interval (or separated by device power off or sleep mode).

[0049]

[0023] Additional details regarding the multiple order query results system will now be provided with reference to the figures. For example, Figure 1 illustrates a schematic diagram of an exemplary system environment for implementing a multiple order query results system 102 according to one or more implementations. An overview of the multiple order query results system 102 will be described in conjunction with Figure 1. Thereafter, a more detailed description of the components and processing of the multiple order query results system 102 will be provided in conjunction with subsequent figures.

[0050] As shown, the environment includes a server 104, a database 114, a server 116 with a large-scale language model 118, and a client device 108. Each of the components of the environment can communicate over a network 112, which can be any suitable network over which computing devices can communicate. Exemplary networks are described in more detail below in connection with Figures 13-14.

[0051] As described above, the exemplary environment includes a client device 108. The client device 108 may be one of a variety of computing devices, including a smartphone, a tablet, a smart TV, a desktop computer, a laptop computer, a virtual reality device, an augmented reality device, or another computing device such as those described in connection with FIGS. 13-14 . The client device 108 may communicate with the server 104 over a network 112. For example, the client device 108 may receive user input from a user interacting with the client device 108 (e.g., via a client application 110), for example, to access, generate, modify, or share multiple-order responses to a multiple-order text query, or to select a user interface element (e.g., to indicate a contextual data source) for interacting with the content management system 106. Additionally, the multiple-order query results system 102 on the server 104 may receive information regarding various interactions with content items and / or user interface elements based on the input received by the client device 108.

[0052] As shown, the client device 108 may include a client application 110. In particular, the client application 110 may be a web application, a native application installed on the client device 108 (e.g., a mobile application, a desktop application, etc.), or a cloud-based application in which all or a portion of the functionality is performed by the server 104. Based on instructions from the client application 110, the client device 108 may present or display information including a user interface for interacting with (or collaborating regarding) generating a multi-order query response. Using the client application, the client device 108 may perform (or request to perform) various operations, such as indicating contextual data sources and / or generating a response to a multi-order text query.

[0053] As shown in FIG. 1 , the exemplary environment also includes a server 104. The server 104 may generate, track, store, process, receive, and transmit electronic data, such as multi-order text queries, results, actions, decisions, responses, query component-specific computer code, interactions with interface elements, and / or interactions between user accounts or client devices. For example, the server 104 may receive from the client device 108 an indication of a user interaction that defines a multi-order text query. Additionally, the server 104 may transmit data to the client device 108 in the form of a response to the multi-order text query. Indeed, the server 104 may communicate with the client device 108 to send and / or receive data via the network 112. In some implementations, the server 104 comprises a distributed server, where the server 104 includes several server devices distributed across the network 112 and located in different physical locations. The server 104 may comprise one or more content servers, application servers, container orchestration servers, communication servers, web hosting servers, machine learning servers, and other types of servers.

[0054] 1 , the server 104 may also include a multiple-order query results system 102 as part of a content management system 106. The content management system 106 may communicate with client devices 108 to perform various functions associated with client applications 110, such as managing user accounts, defining multiple-order text queries, and / or specifying contextual data sources. Indeed, the content management system 106 may include a network-based smartphone cloud storage system for managing, storing, and maintaining content items and associated data across multiple user accounts. In some embodiments, the multiple-order query results system 102 and / or the content management system 106 utilize a database 114 to store and access information such as content items, contextual data sources, multiple-order text queries, results of multiple-order text queries, responses to multiple-order text queries, and other information.

[0055] As further shown, the environment includes a server 116 that hosts a large-scale language model 118. In particular, the large-scale language model 118 communicates with the server 104, the client device 108, and / or the database 114. For example, the multi-order query results system 102 provides domain-specific language segments to the large-scale language model 118, which indicate contextual data sources for generating results for various query subcomponents. Indeed, the large-scale language model 118 may include a machine learning model powered by a neural network or other machine learning architecture for generating responses to text queries. For example, the large-scale language model 118 may reference a ChatGPT model that accesses contextual data sources and generates computer-executable code segments for generating responses to query subcomponents.

[0056] 1 illustrates the multiple order query results system 102 located on the server 104, in some implementations the multiple order query results system 102 may be implemented by (e.g., located in whole or in part by) one or more other components of the environment. For example, the multiple order query results system 102 may be implemented by the client device 108 and / or a third-party system. For example, the client device 108 and / or the third-party system may download all or a portion of the multiple order query results system 102 for implementation independent of or together with the server 104.

[0057] 1 , the environment may have a different arrangement of components and / or a different number or set of components overall. For example, the client device 108 may communicate directly with the multi-order query results system 102, bypassing the network 112. The environment may also include one or more third-party systems, each corresponding to a different contextual data source. In addition, the environment may include a database 114 located external to the server 104 (e.g., communicating via the network 112) or located on the server 104 and / or the client device 108. In some cases, the server 104 and / or the client device 108 may host or house all or a portion of the large-scale language model 118.

[0058] 2A illustrates an overview of a multi-order query results system 102 that generates aggregated results, according to one or more embodiments. For example, FIG. 2 illustrates a multi-order query results system 102 that generates aggregated result responses for multi-order text queries. Further details regarding the various operations illustrated in FIG. 2 are provided subsequently with reference to subsequent figures.

[0059] As shown, FIG. 2A illustrates a multiple-order query results system 102 that processes the multiple-order text queries 200 described above. For example, a user of a client device creates or generates the multiple-order text queries 200 via text generation or by speaking into a microphone on the client device. In particular, the multiple-order query results system 102 receives and processes the generated text queries or voice queries. In the case of voice queries, the multiple-order query results system 102 processes and converts the voice queries into text queries. For example, in response to receiving the multiple-order text queries 200, the multiple-order query results system 102 initiates a process to decompose the multiple-order text queries 200.

[0060] As further shown, FIG. 2A illustrates the multi-order query results system 102 decomposing the multi-order text query 200. For example, FIG. 2A illustrates the multi-order query results system 102 generating a first context-defining query subcomponent 202 and a second context-defining query subcomponent 204. In particular, the multi-order query results system 102 generates the first context-defining query subcomponent 202 and the second context-defining query subcomponent 204 by identifying different subportions of the multi-order text query 200. For example, the multi-order query results system 102 provides the multi-order text query 200 to a large-scale language model that identifies various subcomponents of the multi-order text query 200 based on previously received sample data. Specifically, the multi-order query results system 102 trains the large-scale language model on the sample data to identify different subcomponents as part of the multi-order text query 200.

[0061] 2A further illustrates the context definition subcomponents, already discussed above, pointing to different data sources. For example, FIG. 2A illustrates that a first context definition query subcomponent 202 points to a first context data source 206, and a second context definition query subcomponent 204 points to a second context data source 208. In particular, the multi-order query results system 102 executes computer code specific to each context data source to generate the results.

[0062] 2A illustrates a multi-order query results system 102 that generates the above-described first result 210 and second result 212. For example, the multi-order query results system 102 generates the first result 210 by executing computer code specific to the first contextual data source 206 and generates the second result 212 by executing computer code specific to the second contextual data source 208. In particular, the first result 210 is responsive to the first context-defining query subcomponent 202, and the second result 212 is responsive to the second context-defining query subcomponent 204.

[0063] 2A also illustrates the multi-order query results system 102 generating the aforementioned aggregated results 214. For example, FIG. 2A illustrates the multi-order query results system 102 generating the aggregated results 214 by combining a first result 210 and a second result 212. In particular, the aggregated results 214 are responsive to a multi-order text query.

[0064] 2B also illustrates an overview of a multi-order query results system 102 that generates aggregated results, according to one or more embodiments. For example, FIG. 2B, which is similar to FIG. 2A, illustrates a multi-order text query 216. As previously discussed in FIG. 2A and similarly illustrated in FIG. 2B, the multi-order query results system 102 generates a first context-defining query subcomponent 218 that indicates a first contextual data source 220 and generates a first result 222.

[0065] In contrast to Figure 2A, Figure 2B illustrates the multi-order query results system 102 providing a first result 222 from the multi-order text query 216 to a second context-defining query subcomponent 224 generated by the multi-order query results system 102. Specifically, the multi-order query results system 102 generates the second context-defining query subcomponent 224 based on the first result 222, and the second context-defining query subcomponent 224 indicates a second context data source 226. Additionally, Figure 2B illustrates the multi-order query results system 102 generating a second result 228 from the second context data source 226. Furthermore, based on the first result 222 and the second result 228, the multi-order query results system 102 generates an aggregate result 230.

[0066] In other words, as shown, the multi-order query results system 102 utilizes the output of the first context-defining query subcomponent 218 as input to generate the output of a subsequent subcomponent. For example, the computer code for a subsequent step may invoke or depend on the output generated by a previous subcomponent. As shown, the multi-order query results system 102 utilizes the first result 222 to generate the second result 228.

[0067] 3 illustrates additional details regarding the multi-order query results system 102, which generates various subcomponents and executes computer code to generate aggregated results, according to one or more embodiments. In particular, the multi-order query results system can utilize a context orchestration engine to generate responses to multi-order text queries. For example, as described above, aspects of the context orchestration engine include the multi-order query results system decomposing multi-order text queries and generating computer code specific to the corresponding contextual data sources.

[0068] As shown in FIG. 3 , the multi-order query results system 102 receives a multi-order text query 300 from a client device (e.g., client device 108). In response to receiving the multi-order text query 300, the multi-order query results system 102 utilizes a domain-specific language generator 302 (e.g., as a container or component of a context orchestration engine) to generate a domain-specific language from the multi-order text query. Specifically, the multi-order query results system 102 provides the generated domain-specific language from the multi-order text query to a large-scale language model 304. For example, in some embodiments, the multi-order query results system 102 utilizes the large-scale language model 304 to receive the domain-specific language from the multi-order text query, and later identifies or extracts multiple steps (e.g., subcomponents) from the multi-order text query. The multi-order query results system 102 then receives the identified or extracted steps (e.g., subcomponents) from the large-scale language model 304 (e.g., the large-scale language model identifies and extracts the subcomponents from the multi-order text query 300). Additionally, the multi-order query results system 102 returns the received subcomponents to the large-scale language model 304 for generating computer code, which is described in more detail below.

[0069] In some embodiments, the multiple-order query results system 102 determines, detects, or identifies different context-defining query subcomponents, each of which requires its own unique action and / or contextual data source for response. The multiple-order query results system 102 further applies a domain-specific language generator 302 to generate a domain-specific language for each of the query subcomponents. In effect, the multiple-order query results system 102 identifies or extracts multiple steps (e.g., step 1, step 2, ..., step N) from the multiple-order text query 300, where each different step has a different context and / or each requires a different action. In some cases, the multiple-order query results system 102 generates a separate domain-specific language segment for (e.g., representing or defining) each of the steps. Each domain-specific language component can define its own step or action corresponding to its own contextual data source as a subpart for answering the overall multiple-order text query.

[0070] The multi-order query results system 102 further provides the different domain-specific language segments (e.g., for each subcomponent of the multi-order text query 300) to the large-scale language model 304 (e.g., by providing the entire multi-order text query or by providing the subcomponents). Indeed, the multi-order query results system 102 provides the different domain-specific language segments to the large-scale language model 304 that has been trained (using other domain-specific language examples) to generate results for each of the different steps. For example, FIG. 3 illustrates the first context-defining query subcomponent 306 as the first step, the second context-defining query subcomponent 310 as the second step, and the Nth context-defining subcomponent 314 as the Nth step. Specifically, the large-scale language model 304 generates computer code corresponding to each step or from each of the domain-specific language segments of the context-defining subcomponents. Thus, the multi-order query results system 102 generates computer code 308 for the first step, computer code 312 for the second step, and computer code 316 for the Nth step. In particular, the multi-order query results system 102 utilizes a large-scale language model 304 to generate computer code for each step corresponding to a context definition subcomponent.

[0071] 3, the multiple order query results system 102 executes computer code to generate aggregated results 320 for the multiple order text query, according to one or more embodiments. In particular, the multiple order query results system 102 generates each computer code segment corresponding to each context-defining query subcomponent (e.g., for each step). As shown, the multiple order query results system 102 performs an operation 318 of executing the computer code segment to execute an event for each defined step. Indeed, for each step, the multiple order query results system 102 accesses a particular context data source specified by the computer code executed to execute the step.

[0072] 3 illustrates a multi-order query result system 102 executing computer code 308 for a first step, computer code 312 for a second step, and computer code 316 for an Nth step. In particular, to generate a first result 324 in response to the first context-defining query subcomponent 306, the multi-order query result system 102 accesses a first contextual data source 326. Additionally, to generate a second result 330 in response to the second context-defining query subcomponent 310, the multi-order query result system 102 accesses a second contextual data source 332. Similarly, to generate an Nth result 336, the multi-order query result system 102 accesses an Nth contextual data source 338. The multi-order query result system 102 aggregates the first result 324, the second result 330, and the Nth result 336 to generate an aggregated result 320. As described further below, in some embodiments, the multi-order query results system 102 uses results from a particular query subcomponent as input for finding additional results. Thus, the aggregated result 320 may be a combination of the first result 324, the second result 330, and the Nth result 336, while in other examples the aggregated result 320 is a final result based on previous results from each of the query subcomponents 306-314.

[0073] 4A-4B illustrate exemplary context-defining query subcomponents for a multi-order text query, according to one or more embodiments. For example, FIG. 4A illustrates multi-order text query 400. In particular, multi-order text query 400 reads, "When is my next meeting with my boss?" For example, utilizing the process described above in FIGS. 2A-3, multi-order query results system 102 generates various context-defining query subcomponents.

[0074] As shown in FIG. 4A, the multi-order query results system 102 generates a first context-defining query subcomponent 402 corresponding to the first step of the multi-order text query 400. Specifically, the first context-defining query subcomponent 402 indicates a query type with context regarding basic details of the user. Additionally, the output for the first context-defining query subcomponent 402 indicates the employee's name and employee type / category. Additionally, FIG. 4A also shows a second context-defining query subcomponent 404. Specifically, the multi-order query results system 102 in the second context-defining query subcomponent 404 determines the user's manager within the context of the organization of which the user is a part.

[0075] In addition to the first and second context-defining query subcomponents, FIG. 4A also illustrates a third context-defining query subcomponent 406 and a fourth context-defining query subcomponent 408. Specifically, for the third context-defining query subcomponent 406, the multi-order query results system 102 determines the next scheduled meeting with the user (e.g., an employee) and the user's manager. Thus, as discussed above, in this context, the multi-order query results system 102 utilizes results from the first context-defining query subcomponent 402 and the second context-defining query subcomponent 404 to determine the third context-defining query subcomponent 406. Furthermore, FIG. 4A illustrates the fourth context-defining query subcomponent 408 as aggregating previous results from the other context-defining query subcomponents.

[0076] Figure 4B illustrates the multiple order query results system 102 receiving a different multi-order text query 410 than the multi-order text query shown in Figure 4A. For example, Figure 4B illustrates a multi-order text query 410 that reads "Schedule a meeting with an internal expert in the generation LLM topic." In particular, the multi-order text query 410 shown in Figure 4B includes a user requesting an action to be performed by the multiple order query results system 102.

[0077] As further shown, FIG. 4B illustrates a first context-defining query subcomponent 412. Similar to FIG. 4A, the first context-defining query subcomponent 412 includes determining basic details of the querying user. In contrast to FIG. 4A, the second context-defining query subcomponent 414 illustrates the determination of internal experts within the organizational context in the generated LLM. Furthermore, FIG. 4B illustrates a third context-defining query subcomponent 416, which determines available time slots for the querying user and the identified experts within a calendar context. Furthermore, a fourth context-defining query subcomponent 418 performs an action to select an expert and an available time. Furthermore, a fifth context-defining query subcomponent 420 includes the multi-order query results system 102 creating a calendar invitation with the identified user and expert at a preferred time slot. For example, the fifth context-defining query subcomponent 420 is an aggregate result generated by the multi-order query results system 102. Thus, the action of creating a calendar invitation with the identified user and expert at a preferred time slot includes a first action that indicates a component-specific action within a specific context data source.

[0078] 4C-4D illustrate a multi-order query results system 102 that generates computer code to execute to generate results in response to various context-defining subcomponents, according to one or more embodiments. For example, FIG. 4C illustrates computer code for performing the task of obtaining the next meeting time for a user with another employee. Specifically, for the example given in FIG. 4A, the computer code shown in FIG. 4C relates to determining the next meeting time with the user's manager. As described above, the multi-order query results system 102 provides the multi-order text query or context-defining query subcomponents to a large-scale language model, which generates computer code specific to that context-defining query subcomponent. As another example, FIG. 4D illustrates additional computer code for determining all meetings attended by the querying user within the past month. In particular, the computer code shown in FIG. 4D determines all meetings attended in the current month, the month before the current month, and a specified month.

[0079] 4A-4D illustrate various examples in which a multi-order text query is decomposed into various context-defining query subcomponents and computer code corresponding to the multi-order text query. Although not shown in FIGS. 4A-4D, in one or more embodiments, the multi-order query result system provides the sample data comprising FIGS. 4A-4D. In particular, the multi-order query result system provides the sample data shown in FIGS. 4A-4D to the large-scale language model. As described above, the multi-order query result system utilizes the sample data to train the large-scale language model to accurately generate results in response to the multi-order text query. For example, the multi-order query result system provides millions of sample data (e.g., such as that shown in FIGS. 4A-4D) to train the large-scale language model on the most frequently used multi-order text queries. Due to the nature of the large-scale language model, the multi-order query result system does not need to provide exhaustive sample data. In particular, the multi-order query result system provides generalized sample data from which the large-scale language model can infer variations and deviations from the provided sample data.

[0080] FIG. 5 illustrates an exemplary architecture diagram of a context orchestration engine of a multi-order query results system 102, according to one or more embodiments. Indeed, as described above, the multi-order query results system 102 utilizes a context orchestration engine to generate results for a multi-order text query. In particular, FIG. 5 illustrates implementing the multi-order query results system 102 for receiving a multi-order text query and generating results for the multi-order text query. As shown, the context orchestration engine of the multi-order query results system 102 can include various architectural components, including an application layer 500, an application programming interface (hereinafter, API 502), an intelligence layer 504, and a training and testing layer 506.

[0081] As shown, application layer 500 includes various types of software applications. For example, FIG. 5 shows organizational applications 508, client device applications 510, third-party applications 512, and content management system applications 514. Notably, each of the above applications further includes an application container that houses multiple applications within each application category. For example, multi-order query results system 102 houses applications and their corresponding contextual data sources for intra-organizational applications (e.g., applications developed in-house) and extra-organizational applications (applications developed by third parties but used within the organization).

[0082] As previously mentioned, the application layer 500 includes a content management system application 514. In particular, the content management system application 514 includes an application within the content management system 106. Thus, the multi-order query results system 102 implements the ability to generate results for multi-order text queries for the application of the content management system 106. More details regarding a specific implementation of the multi-order query results system 102 within the content management system application 514 are provided below in the description of Figures 8-10.

[0083] FIG. 5 also illustrates an application programming interface (API 502). For example, API 502 includes a set of protocols, routines, and tools for building applications. In particular, API 502 provides a way for various software components, applications, or systems to communicate and exchange data with each other, regardless of the type of programming language, operating system, or hardware platform used in each application environment. For example, API 502 may include a set of rules that define how different software components interact, the format and structure of data exchange, the syntax and parameters of calls, and methods for authentication. Specifically, API 502 includes a prompt API layer for real-time data extraction, preprocessing, model selection, and prompt formatting, further providing to intelligence layer 504.

[0084] 5, the multi-order query results system 102 includes an intelligence layer 504 for training large-scale language models (and / or other machine learning models) to generate results for the context-defined query subcomponent of the multi-order text query (e.g., formulated by the prompt API layer). As shown, the intelligence layer 504 includes a client device-specific model 516. In other words, the client device-specific model 516 includes a fine-tuning layer that is fine-tuned / trained to generate computer code specific to the contextual data source and / or multi-order text query from a particular user account.

[0085] In one or more embodiments, the multiple order query results system 102 receives the multiple order text query and extracts relevant subcomponents and associated data for the multiple order text query from the application layer 500 via the API 502. In particular, based on extracting the subcomponents and associated data, the multiple order query results system 102 generates tailored computer code for the extracted subcomponents based on contextual data sources corresponding to the associated data.

[0086] Additionally, as shown, the intelligence layer 504 also includes a general insight model 518. In other words, the general insight model 518 includes one or more foundation models trained / tuned for all user accounts. In effect, the multi-order query results system 102 is pre-trained on several contextual data sources that are more universally accessible by many user accounts (e.g., internet-based data sources). The multi-order query results system 102 is also fine-tuned (e.g., via a fine-tuning layer) on a user-account-specific basis to generate responses from contextual data sources that vary by user account (e.g., email accounts, calendars, or organizational ontologies).

[0087] 5 , the multi-order query results system 102 includes a training and testing layer 506. For example, as described above, the multi-order query results system 102 is pre-trained on several contextual data sources and fine-tuned based on the specific contextual data source. For example, the training and testing layer 506 provides training of client device-specific models 516 and general insight models 518 to generate accurate results for multi-order text queries. In particular, the multi-order query results system 102 can obtain or accept various inputs from the training and testing layer 506, such as: i) an employee knowledge base, ii) employee desktop and browser activity, iii) employee communications, iv) employee calendar data, v) digital form signature data, vi) file sharing services, and / or vii) third-party connector APIs.

[0088] 6 shows an example diagram of contextual data sources associated with a user account in a content management system 106, according to one or more embodiments. As shown, the multiple order query results system 102 can identify, detect, or determine a contextual data source 612 associated with a user account 600. For example, the multiple order query results system 102 can determine related applications integrated with or directed by a client device of the user account 600 to identify the contextual data source 612.

[0089] 6 illustrates a user account 600 that includes applications 602. Specifically, applications 602 further include an organization application 604, a third-party application 606, a content management system application 608, and a client device application 610. For example, for each of applications 602, the multiple order query results system 102 determines a corresponding contextual data source for the user account 600. Furthermore, in addition to the multiple order query results system 102 determining a corresponding contextual data source for each application of the user account 600, the multiple order query results system 102 can also receive an example domain-specific language and / or example computer code for accessing data stored in a given contextual data source to generate results to the multiple order text query.

[0090] In some cases, the multi-order query results system 102 identifies or detects contextual data sources, such as a messaging data source that stores messages and message data for a messaging service / application. Other contextual data sources (linked to a user account) include: i) an email application / service that stores emails and email data, ii) stored content items and content item data (e.g., documents, images, videos, etc.) associated with the user account, iii) browser history, iv) a conferencing application / service that stores conferencing data for video and / or audio conferencing, v) a calendar application / service that stores calendar events and event data for the user account, vi) an organizational chart or ontology that defines user-account relationships within an organizational hierarchy, vii) a hotel application / server / database, viii) a ride-share application / server / database, ix) an airline application / server / database, x) past decisions, xi) future goals, xii) a social media application / server / database, and / or xiii) user activity history within the content management system 106.

[0091] 7 illustrates an exemplary flow diagram for generating aggregate results from a multi-order text query, according to one or more embodiments. For example, FIG. 7 illustrates the multi-order query results system 102 receiving the multi-order text query 702 from a client device 700 and providing the multi-order text query 702 to a large-scale language model 704, as described above. Additionally, FIG. 7 illustrates the multi-order query results system 102 via the large-scale language model 704 generating individual subcomponents of the multi-order text query 702, as described above. For example, FIG. 7 illustrates computer code 714 for a first context-defining query subcomponent 706, computer code 716 for a second context-defining query subcomponent 708, computer code 718 for a third context-defining query subcomponent 710, and computer code 720 for a fourth context-defining query subcomponent 712.

[0092] Additionally, in one or more embodiments, the multiple order query results system 102 may generate different subcomponents of the multiple order text query, some of which point to the same contextual data source. In particular, as shown in Figure 7, the multiple order query results system 102 generates a first result 730 corresponding to the first contextual data source 722, a second result 732 corresponding to the second contextual data source 724, a third result 734 corresponding to the first contextual data source 722, and a fourth result 736 corresponding to the third contextual data source 726. Additionally, Figure 7 illustrates the multiple order query results system 102 generating an aggregate result 738 from a combination of the above results.

[0093] 7 also illustrates an example flow for receiving an unanswerable multi-order text query. For example, in response to the multi-order query results system 102 providing the multi-order text query to the large-scale language model 704, the large-scale language model 704 can perform operation 740. Specifically, operation 740 includes making a determination that the multi-order text query 702 is unanswerable. For example, a determination that the multi-order text query 702 is unanswerable can include the large-scale language model 704 not understanding how to decompose the multi-order text query into its individual subcomponents. Additionally, a multi-order text query 702 being unanswerable can also include the multi-order query results system 102 having insufficient sample data for the particular query.

[0094] As described above, in response to the multiple order query results system 102 determining that the multiple order text query 702 is unanswerable, the multiple order query results system 102 transmits a request. In particular, the multiple order query results system 102 transmits a request for data samples 742 to the client device 700 described above. For example, the multiple order query results system 102 transmits a request 742 to the client device 700 that reads, "Please send me domain-specific language for each subcomponent of the multiple order text query."

[0095] 7 , in one or more embodiments, the multi-order query results system 102 iteratively sends the request 742 to the client device 700 until it reaches a determination that the multi-order text query 702 is answerable. In some embodiments, the multi-order query results system 102 determines that the large-scale language model generates incorrect or incomplete computer code for one or more steps (or does not generate computer code at all). For example, the multi-order query results system 102 receives an indication from the large-scale language model that the model has not been trained to generate a particular code segment and / or does not have training to interact with a particular contextual data source. Accordingly, the multi-order query results system 102 generates and provides domain-specific language examples to provide to the large-scale language model to train the large-scale language model to generate code segments corresponding to context-defining query subcomponents of the question and / or to interact with a particular contextual data source.

[0096] 8 illustrates a multi-order query results system 102 operating within a content management system 106 application. For example, FIG. 8 illustrates a multi-order query results system 102 operating within an internal context engine that aggregates content from a user account and the user's colleagues. In particular, FIG. 8 illustrates a multi-order query results system 102 that utilizes an internal context engine to perform content aggregation operations 800. For example, the multi-order query results system 102 utilizes an internal context engine to aggregate content from multiple data sources.

[0097] In addition to performing operation 800, the multiple order query results system 102 also performs operation 802. Specifically, operation 802 includes extracting content from the aggregated content into specific containers. Any type of content can be extracted from the aggregated content. For example, FIG. 8 shows that operation 802 includes extracting content item 802a, author 802b, focus time 802c, path 802d, and content tag 802e. Furthermore, each of the extracted categories enables the multiple order query results system 102 to utilize a context engine to make intelligent decisions.

[0098] 8 further illustrates a multi-order query results system 102 that utilizes a context engine to perform an operation of vector encoding 804. In particular, the operation of vector encoding 804 includes performing an operation of vectorizing 806 the extracted content. For example, the multi-order query results system 102 utilizing the context engine places each of the extracted content categories in an embedding space to determine various relationships between the extracted content. Further, as shown, the multi-order query results system 102 utilizes the context engine to perform an operation 808 of storing the vectorized content in a data source. Specifically, the multi-order query results system 102 utilizes the stored vectorized content to make context recommendations, cluster topics together, and respond to queries related to the extracted content.

[0099] As described above, the multiple order query results system 102 operates within an internal context engine. For example, FIG. 8 illustrates the multiple order query results system 102 receiving a query 812 and utilizing a data source that stores vectorized content. In particular, the multiple order query results system 102 draws from the data source that stores vectorized content and generates aggregated results 814. Thus, the multiple order query results system 102 operates within an internal context engine to provide users of client devices with additional precision and efficiency in an effort to improve their workflow.

[0100] FIG. 9 illustrates a multi-order query results system 102 operating within an expert identification engine. For example, similar to FIG. 8, FIG. 9 illustrates a multi-order query results system 102 utilizing an expert identification engine to perform an operation 900 of aggregating content. In particular, the multi-order query results system 102 utilizes the expert identification engine to aggregate content from multiple data sources. In addition to aggregating content, the multi-order query results system 102 also performs an operation 902 of extracting. Specifically, operation 902 includes an operation 904 in which the multi-order query results system 102 determines experts associated with a particular topic. Additionally, the multi-order query results system 102 performs an operation 906 of storing the extracted expert identifications in a data source. Specifically, the multi-order query results system 102 accesses the data source to further generate results in response to the multi-order text query.

[0101] As shown, Figure 9 illustrates a multiple-order query results system 102 that receives a query 908 and utilizes a data source in which expert identification information is stored. In particular, the multiple-order query results system 102 utilizes the data source to generate an aggregated result 910. For example, the query 908 includes the query, "How do I apply for a corporate credit card?" The multiple-order query results system 102 identifies experts related to the topic of applying for a corporate credit card and generates an aggregated result 910 that identifies experts on that topic. Additionally, the multiple-order query results system 102 can generate an aggregated result 910 that shows a list of experts ranked in order of expertise. In other examples, the aggregated result 910 shows a single expert.

[0102] FIG. 10 illustrates a multi-order query results system 102 operating within a video transcription query engine. For example, FIG. 10 illustrates operation 1002 of the multi-order query results system 102 utilizing a video transcription query engine to perform extraction. In particular, the multi-order query results system 102 utilizes the video transcription query engine to extract data from digital conferences (e.g., digital video camera calls or digital calls). For example, the multi-order query results system 102 utilizes the video transcription query engine to extract body language, conference content, and other cues present within the digital conference. Specifically, the multi-order query results system 102 utilizes the video transcription query engine to extract action items discussed during the digital conference, various participants, their perspectives, topics, and other conference-related items.

[0103] 10 further illustrates the multi-order query results system 102 utilizing a video transcription query engine to perform operation 1004 of assigning extracted data to various contextual data sources. In particular, for content corresponding to an action item, the multi-order query results system 102 utilizes the video transcription query engine to assign the action item to contextual data sources specific to the digital conference. Furthermore, FIG. 10 illustrates the multi-order query results system 102 receiving a query 1006. In response to receiving the query 1006, the multi-order query results system 102 utilizes the contextual data sources corresponding to the extracted data of the video transcription query engine to generate aggregated results 1008.

[0104] As an example, if query 1006 includes the question, "What should I do after my meetings today?", the multi-order query results system 102 utilizes corresponding contextual data sources to generate a list of action items to be done after meetings held today and provides aggregate results 1008 to the querying user. Thus, the multi-order query results system 102 operating within a video transcription query engine enables users of client devices to receive answers to their questions more accurately and effectively.

[0105] 11 illustrates a graphical user interface of a multi-order query results system 102 according to one or more embodiments. For example, FIG. 11 illustrates a client device 1101 that provides options for generating answers to be displayed via a graphical user interface 1103. In particular, FIG. 11 illustrates a multi-order text query 1100, "When will my boss arrive at the office?". Additionally, the graphical user interface 1103 displays an aggregate result 1102 that reads, "Answer: Your boss, Jane, will arrive around 1:30 PM."

[0106] FIG. 11 further illustrates evidence of operation for generating aggregate results 1102 within a graphical user interface 1103 of a client device 1101. For example, FIG. 11 illustrates the multiple order query results system 102 generating various subcomponents of a multiple order text query 1100 and providing them for display via a graphical user interface 1103. Specifically, the various subcomponents include flight information 1104, rideshare 1106, traffic conditions 1108, and availability 1110. For example, each of components 1104-1108 shown on the graphical user interface 1103 indicates to the querying user how the multiple order query results system 102 determined that the boss will arrive around 1:30 PM. Additionally, availability 1110 allows the querying user to further determine when to meet with the boss.

[0107] 1-11, corresponding text, and examples provide several different systems and methods for generating aggregated results for received multi-order text queries. In addition to the foregoing, implementations may also be described in terms of flowcharts that include operational steps in a method for achieving a particular result. For example, FIG. 12 illustrates an example sequence of operations for generating aggregated results.

[0108] While Figure 12 illustrates operations according to some implementations, alternative implementations may omit, add, rearrange, and / or modify any of the operations illustrated in Figure 12. The operations of Figure 12 may be performed as part of a method. Alternatively, a non-transitory computer-readable medium may comprise instructions that, when executed by one or more processors, cause a computing device to perform the operations of Figure 12. In yet another implementation, a system may perform the operations of Figure 12.

[0109] As shown in FIG. 12 , the sequence of operations 1200 may include an operation 1210 of generating, from the multi-order text query, a first context-defining query subcomponent indicating a first context data source; an operation 1220 of providing the first context-defining query subcomponent to a large-scale language model for generating computer code; an operation 1230 of executing the computer code from the large-scale language model to generate a first result; an operation 1240 of identifying a second result for the second context-defining query subcomponent generated from the multi-order text query; and an operation 1250 of utilizing the first result and the second result to generate an aggregate result.

[0110] In particular, operation 1210 includes generating a first context-defining query subcomponent from the multi-order text query received from the client device, the first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent; operation 1220 includes providing the first context-defining query subcomponent to a large-scale language model for generating computer code specific to the first context data source and executable for responding to the first context-defining query subcomponent; operation 1230 includes executing the computer code from the large-scale language model using the first context data source accessed via the computer network to generate a first result to the first context-defining query subcomponent of the multi-order text query; operation 1240 includes identifying a second result to a second context-defining query subcomponent generated from the multi-order text query, the second context-defining query subcomponent indicating the second context data source; and operation 1250 includes generating an aggregate result to the multi-order text query utilizing the first result and the second result.

[0111] Further, in one or more embodiments, the series of operations 1200 includes providing the multi-order text query to a large-scale language model to generate a first context-defining query subcomponent. Further, in one or more embodiments, the series of operations 1200 includes determining that the multi-order text query is a non-first-order text query. Further, in one or more embodiments, the series of operations 1200 includes identifying a third result for a third context-defining query subcomponent generated from the multi-order text query indicating the first contextual data source, and generating an aggregate result for the multi-order text query using the first result, the second result, and the third result.

[0112] Further, in one or more embodiments, the series of operations 1200 includes sending the first context-defining query subcomponent to a large-scale language model, causing the large-scale language model to generate computer code in a domain-specific computer language specific to the first context data source indicated by the first context-defining query subcomponent. Further, in one or more embodiments, the series of operations 1200 includes determining the first context-defining query subcomponent or an action of the first context-defining query subcomponent. Further, in one or more embodiments, the series of operations 1200 includes performing a first action, the first action including an action specific to a component in the first context data source.

[0113] Further, in one or more embodiments, the series of operations 1200 includes receiving a request for sample data from the large-scale language model for generating a first result, and providing the sample data to the large-scale language model for training the large-scale language model to generate the first result corresponding to the first context-defining query subcomponent. Further, in one or more embodiments, the series of operations 1200 includes, in response to generating an aggregated result to the multi-order text query using the first result and the second result, providing a response to the client device indicating the aggregated result. Further, in one or more embodiments, the series of operations 1200 includes a first application within the organizational ecosystem. Further, in one or more embodiments, the series of operations 1200 includes a third-party application not within the organizational ecosystem.

[0114] Further, in one or more embodiments, the series of operations 1200 includes generating, from the multi-order text query received from the client device, a first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent; providing the first context-defining query subcomponent to a large-scale language model for generating domain-specific computer code specific to the first context data source and executable to respond to the first context-defining query subcomponent; executing the domain-specific computer code from the large-scale language model to access the first context data source over a computer network for generating a first result for the first context-defining query subcomponent of the multi-order text query; the domain-specific computer code generating a component-specific result utilizing data stored in the first context data source; identifying a second result for a second context-defining query subcomponent generated from the multi-order text query; and the second context-defining query subcomponent indicating a second context data source and utilizing the first result and the second result to generate an aggregate result for the multi-order text query.

[0115] Further, in one or more embodiments, the series of operations 1200 includes determining that the first context-defining query subcomponent is unanswerable and sending a request to the client device to provide additional context for the first context-defining query subcomponent, the additional context comprising an indication of an additional context data source. Further, in one or more embodiments, the series of operations 1200 includes determining that the first context-defining query subcomponent is unanswerable in response to receiving, from a large-scale language model, a request for sample data for generating component-specific results corresponding to the first context-defining query subcomponent of the multi-order text query, and providing, to the large-scale language model, the context sample data for training the large-scale language model to generate component-specific results corresponding to the first context-defining query subcomponent of the multi-order text query.

[0116] Components of the multiple order query results system 102 may include software, hardware, or both. For example, components of the multiple order query results system 102 may include one or more instructions stored on a computer-readable storage medium and executable by processors of one or more computing devices. When executed by one or more processors, the computer-executable instructions of the multiple order query results system 102 may cause the computing devices to perform the methods described herein. Alternatively, components of the multiple order query results system 102 may comprise hardware, such as a dedicated processing device, for performing a particular function or group of functions. Additionally or alternatively, components of the multiple order query results system 102 may include a combination of computer-executable instructions and hardware.

[0117] Additionally, components of the multi-order query results system 102 that perform the functions described herein may be implemented, for example, as part of a standalone application, as a module of an application, as a plug-in of an application, including a content management application, as a library function or function that can be called by other applications, and / or as a cloud computing model. Thus, components of the multi-order query results system 102 may be implemented as part of a standalone application on a personal computing device or a mobile device.

[0118] Embodiments of the present disclosure may comprise or utilize special purpose or general purpose computers including computer hardware such as, for example, one or more processors and system memory, as described in more detail below. Implementations within the scope of the present disclosure also include physical and other computer-readable media for carrying or storing computer-executable instructions and / or data structures. In particular, one or more of the processes described herein may be embodied, at least in part, in a non-transitory computer-readable medium and implemented as instructions executable by one or more computing devices (e.g., any of the media content access devices described herein). Generally, a processor (e.g., a microprocessor) receives instructions from a non-transitory computer-readable medium (e.g., a memory, etc.) and executes those instructions, thereby performing one or more processes, including one or more of the processes described herein.

[0119] Computer-readable media may be any available media that can be accessed by a general-purpose or special-purpose computer system. Computer-readable media that store computer-executable instructions are non-transitory computer-readable storage media (devices). Computer-readable media that carry computer-executable instructions are transmission media. Thus, by way of example and not limitation, implementations of the present disclosure may comprise at least two distinctly different types of computer-readable media: non-transitory computer-readable storage media (devices) and transmission media.

[0120] Non-transitory computer-readable storage media (devices) include RAM, ROM, EEPROM, CD-ROM, solid state drives (SSD) (e.g., RAM-based), flash memory, phase-change memory (PCM), other types of memory, other optical disk storage, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store desired program code means in the form of computer-executable instructions or data structures and that can be accessed by a general-purpose or special-purpose computer.

[0121] A "network" is defined as one or more data links that enable the transfer of electronic data between computer systems and / or modules and / or other electronic devices. When information is transferred or provided to a computer over a network or another communications connection (wired, wireless, or a combination of wired or wireless), the computer properly views the connection as a transmission medium. Transmission media can be used to carry desired program code means in the form of computer-executable instructions or data structures and can include networks and / or data links that can be accessed by a general-purpose or special-purpose computer. Combinations of the above should also be included within the scope of computer-readable media.

[0122] Furthermore, upon reaching various computer system components, program code means in the form of computer-executable instructions or data structures may be automatically transferred from transmission media to non-transitory computer-readable storage media (devices) (or vice versa). For example, computer-executable instructions or data structures received over a network or data link may be buffered in RAM within a network interface module (e.g., a "NIC") and then ultimately transferred to computer system RAM and / or less volatile computer storage media (devices) in the computer system. Thus, it should be understood that non-transitory computer-readable storage media (devices) may be included in computer system components that also (or primarily) utilize transmission media.

[0123] Computer-executable instructions include, for example, instructions and data that, when executed by a processor, cause a general-purpose computer, a special-purpose computer, or a special-purpose processing device to perform a particular function or group of functions. In some implementations, computer-executable instructions are executed on a general-purpose computer, transforming the general-purpose computer into a special-purpose computer that implements elements of the present disclosure. Computer-executable instructions may be, for example, binaries, intermediate format instructions such as assembly language, or source code. While the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the features or acts described above. Rather, the described features and acts are disclosed as exemplary forms of implementing the claims.

[0124] Those skilled in the art will appreciate that the present disclosure may be practiced in networked computing environments having many types of computer system configurations, including personal computers, desktop computers, laptop computers, message processors, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, tablets, pagers, routers, switches, etc. The present disclosure may also be practiced in distributed system environments where tasks are performed by both local and remote computer systems that are linked through a network (either by wired data links, wireless data links, or a combination of wired and wireless data links). In a distributed system environment, program modules may be located in both local and remote memory storage devices.

[0125] Implementations of the present disclosure may also be implemented in a cloud computing environment. Herein, "cloud computing" is defined as a model for enabling on-demand network access to a shared pool of configurable computing resources. For example, cloud computing may be used in markets to provide ubiquitous, convenient, on-demand access to a shared pool of configurable computing resources. The shared pool of configurable computing resources can be rapidly provisioned through virtualization, released with low management effort or service provider interaction, and then scaled accordingly.

[0126] A cloud computing model may consist of various characteristics, such as, for example, on-demand self-service, broad network access, resource pooling, rapid scalability, and scalable services. A cloud computing model may also expose various service models, such as, for example, Software as a Service (SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS). A cloud computing model may also be deployed using different deployment models, such as private cloud, community cloud, public cloud, and hybrid cloud. As used herein and in the claims, a "cloud computing environment" is an environment in which cloud computing is employed.

[0127] FIG. 13 illustrates a block diagram of an exemplary computing device 1300 (e.g., server 104 and / or client device 108) that may be configured to perform one or more of the processes described above. It will be understood that the server 104 and / or client device 108 may comprise one or more computing devices, such as computing device 1300. As illustrated by FIG. 13, computing device 1300 may comprise a processor 1302, a memory 1304, a storage device 1306, an I / O interface 1308, and a communication interface 1310, which may be communicatively coupled by a communication infrastructure 1312. While an exemplary computing device 1300 is illustrated in FIG. 13, the components illustrated in FIG. 13 are not intended to be limiting. In other implementations, additional or alternative components may be used. Moreover, in some implementations, computing device 1300 may include fewer components than those illustrated in FIG. 13. The components of computing device 1300 illustrated in FIG. 13 will now be described in further detail.

[0128] In particular implementations, the processor 1302 includes hardware for executing instructions, such as those that make up a computer program. By way of example and not limitation, to execute instructions, the processor 1302 may retrieve (or fetch) instructions from an internal register, an internal cache, memory 1304, or a storage device 1306, decode them, and execute them. In particular implementations, the processor 1302 may include one or more internal caches for data, instructions, or addresses. By way of example and not limitation, the processor 1302 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in an instruction cache may be copies of instructions in memory 1304 or a storage device 1306.

[0129] The memory 1304 may be used to store data, metadata, and programs for execution by the processor. The memory 1304 may include one or more of volatile and non-volatile memory, such as random access memory (RAM), read only memory (ROM), solid state drive (SSD), flash, phase change memory (PCM), or other types of data storage. The memory 1304 may be internal or distributed memory.

[0130] The storage device 1306 includes a storage device for storing data or instructions. By way of example and not limitation, the storage device 1306 may comprise the non-transitory storage media described above. The storage device 1306 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. The storage device 1306 may include removable or non-removable (or fixed) media, as appropriate. The storage device 1306 may be internal or external to the computing device 1300. In certain implementations, the storage device 1306 is a non-volatile solid-state memory. In other implementations, the storage device 1306 includes a read-only memory (ROM). Where appropriate, this ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0131] The I / O interface 1308 enables a user to provide input to, receive output from, and otherwise transcribe data from, the computing device 1300. The I / O interface 1308 may include a mouse, a keypad or keyboard, a touchscreen, a camera, an optical scanner, a network interface, a modem, other known I / O devices, or a combination of such I / O interfaces. The I / O interface 1308 may include one or more devices for presenting output to a user, including, but not limited to, a graphics engine, a display (e.g., a display screen), one or more output drivers (e.g., a display driver), one or more audio speakers, and one or more audio drivers. In some implementations, the I / O interface 1308 is configured to provide graphical data to a display for presentation to a user. The graphical data may represent one or more graphical user interfaces and / or any other graphical content, depending on the particular implementation.

[0132] The communications interface 1310 may include hardware, software, or both. In any event, the communications interface 1310 may provide one or more interfaces for communications (e.g., packet-based communications, etc.) between the computing device 1300 and one or more other computing devices or networks. By way of example and not limitation, the communications interface 1310 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wired-based network, or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network such as WI-FI.

[0133] Additionally or alternatively, the communication interface 1310 may facilitate communication with one or more portions of an ad-hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or the Internet, or a combination of two or more of these. One or more portions of one or more of these networks may be wired or wireless. By way of example, the communication interface 1310 may enable communication with a wireless PAN (WPAN) (e.g., a BLUETOOTH WPAN, etc.), a Wi-Fi network, a Wi-Max network, a cellular telephone network (e.g., a Global System for Mobile Communications (GSM) network, etc.), or other suitable wireless network, or a combination thereof.

[0134] Additionally, communication interface 1310 may facilitate communication of various communication protocols, including data transmission media, communication devices, Transmission Control Protocol (TCP), Internet Protocol (IP), File Transfer Protocol (FTP), Telnet, Hypertext Transfer Protocol (HTTP), Hypertext Transfer Protocol Secure (HTTPS), Session Initiation Protocol (SIP), Simple Object Access Protocol (SOAP), Extensible Mark-up Language (XML) and variations thereof, Simple Mail Transfer Protocol (SMTP), Real-Time Transport Protocol (RTP), User Datagram Protocol (UDP), Global System for Mobile (GSM) communication technology, Code Division Multiple Access (CDMA) technology, Time Division Multiple Access (TDMA) technology, Short Message Service (SMS), Multimedia Message Service (MMS), Radio Frequency (RF) signaling technology, Long Term Evolution (LTE) technology, wireless communication technology, in-band and out-of-band signaling technology, and other suitable communication networks and technologies.

[0135] Communications infrastructure 1312 may include hardware, software, or both that couple together components of computing device 1300. By way of example and not limitation, communications infrastructure 1312 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a front-side bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infiniband interconnect, a low-pin-count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a serial advanced technology attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus, or any combination thereof.

[0136] 14 is a schematic diagram illustrating an environment 1400 in which one or more implementations of the multiple order query results system 102 may be implemented. For example, the multiple order query results system 102 may be part of a content management system 1402 (e.g., content management system 106). The content management system 1402 may generate, store, manage, receive, and transmit digital content (e.g., digital content items). For example, the content management system 1402 may send and receive digital content to and from client devices of client devices 1406 over a network 1404. In particular, the content management system 1402 may store and manage a collection of digital content. The content management system 1402 may manage the sharing of digital content among computing devices associated with multiple users. For example, the content management system 1402 may facilitate a user sharing digital content with another user of the content management system 1402.

[0137] In particular, content management system 1402 can manage the synchronization of digital content across multiple client devices 1406 associated with one or more users. For example, a user can edit digital content using one of the client devices 1406. Content management system 1402 can cause one of the client devices 1406 to send the edited digital content to content management system 1402. Content management system 1402 then synchronizes the edited digital content on one or more additional computing devices.

[0138] In addition to synchronizing digital content across multiple devices, one or more implementations of content management system 1402 can provide efficient storage options for users with large collections of digital content. For example, content management system 1402 can store a collection of digital content on content management system 1402, while client device 1406 stores only reduced versions of the digital content. Users can navigate and view reduced versions of the digital content (e.g., thumbnails of digital images) on client device 1406. In particular, one way users can experience digital content is by viewing reduced versions of the digital content on client device 1406.

[0139] Another way a user can experience digital content is by selecting a scaled-down version of the digital content and requesting a full or high-resolution version of the digital content from content management system 1402. In particular, when a user selects a scaled-down version of the digital content, client device 1406 sends a request to content management system 1402 requesting digital content related to the scaled-down version of the digital content. Content management system 1402 can respond to the request by sending the digital content to client device 1406. Then, upon receiving the digital content, client device 1406 can present the digital content to the user. In this way, a user can access a large collection of digital content while minimizing the amount of resources used on client device 1406.

[0140] A client device in client devices 1406 may be a desktop computer, a laptop computer, a tablet computer, a personal digital assistant (PDA), an in-vehicle or off-vehicle navigation system, a handheld terminal, a smartphone or other cellular or mobile phone, or a mobile gaming device, other mobile device, or other suitable computing device. A client device in client devices 1406 may run one or more client applications, such as a web browser (e.g., Microsoft Windows Internet Explorer, Mozilla Firefox, Apple Safari, Google Chrome, Opera, etc.), or a native or dedicated client application (e.g., Dropbox Paper for iPhone or iPad, Dropbox Paper for Android, etc.), to access and view content over network 1404.

[0141] Network 1404 may represent a network or collection of networks (such as the Internet, a corporate intranet, a virtual private network (VPN), a local area network (LAN), a wireless local area network (WLAN), a cellular network, a wide area network (WAN), a metropolitan area network (MAN), or a combination of two or more such networks) through which client devices of client device 1406 may access content management system 1402 .

[0142] In the foregoing specification, the present disclosure has been described with reference to specific exemplary implementations thereof. Various implementations and aspects of the present disclosure(s) are described with reference to the details discussed herein, and the accompanying drawings illustrate various implementations. The above description and drawings are illustrative of the present disclosure and should not be construed as limiting the disclosure. Numerous specific details are set forth to provide a thorough understanding of various implementations of the present disclosure.

[0143] The present disclosure may be embodied in other specific forms without departing from its spirit or essential characteristics. The described implementations are to be considered in all respects as illustrative only and not restrictive. For example, the methods described herein may be performed with fewer or more steps / acts, or the steps / acts may be performed in a different order. Furthermore, the steps / acts described herein may be repeated or performed in parallel with each other or with different instances of the same or similar steps / acts. The scope of the present application is therefore indicated by the appended claims, rather than by the foregoing description. All changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.

[0144] The foregoing specification has been described with reference to certain exemplary implementations thereof. Various implementations and aspects of the present disclosure are described with reference to the details discussed herein, and the accompanying drawings illustrate various implementations. The above description and drawings are illustrative and should not be construed as limiting. Numerous specific details are set forth to provide a thorough understanding of various implementations.

[0145] Additional or alternative implementations may be embodied in other specific forms without departing from its spirit or essential characteristics. The described implementations are to be considered in all respects only as illustrative and not restrictive. The scope of the invention is, therefore, indicated by the appended claims rather than by the foregoing description. All changes that come within the meaning and range of equivalency of the claims are to be embraced within their scope.

Claims

1. 1. A computer-implemented method comprising: generating a first context-defining query subcomponent from a multi-order text query received from a client device, the first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent; providing the first context-defining query subcomponent to a large scale language model for generating computer code that is specific to the first context data source and that is executable to respond to the first context-defining query subcomponent; executing the computer code from the large-scale language model using the first context data source accessed over a computer network to generate first results for the first context-defining query subcomponent of the multi-order text query; identifying a second result for a second context-defining query subcomponent generated from the multi-order text query, the second result indicating a second context data source; utilizing the first results and the second results to generate aggregate results for the multi-order text query; 10. A computer-implemented method comprising:

2. 2. The computer-implemented method of claim 1, wherein generating the first context-defining query subcomponent further comprises providing the multi-order text query to the large-scale language model to generate the first context-defining query subcomponent.

3. The computer-implemented method of claim 1 , wherein generating the first context-defining query subcomponent includes determining that the multi-order text query is a non-first-order text query.

4. identifying a third result for a third context-defining query subcomponent generated from the multi-order text query indicating the first context data source; 2. The computer-implemented method of claim 1, further comprising: utilizing the first result, the second result, and the third result to generate the aggregated result for the multi-order text query.

5. 2. The computer-implemented method of claim 1, wherein providing the first context-defining query subcomponent to the large-scale language model to generate computer code comprises sending the first context-defining query subcomponent to the large-scale language model to cause the large-scale language model to generate the computer code in a domain-specific computer language specific to the first context data source indicated by the first context-defining query subcomponent.

6. The computer-implemented method of claim 1 , wherein generating the first result includes at least one of determining the first context-defining query subcomponent or taking an action on the first context-defining query subcomponent.

7. The computer-implemented method of claim 1 , wherein generating the first result comprises executing a first action comprising a component-specific action in the first contextual data source.

8. receiving a request for sample data from the large-scale language model for generating the first result; 2. The computer-implemented method of claim 1, further comprising: providing the large-scale language model with the sample data for training the large-scale language model to generate the first result corresponding to the first context-defining query subcomponent.

9. 2. The computer-implemented method of claim 1, further comprising, in response to generating the aggregated result for the multi-order text query using the first result and the second result, providing a response to the client device indicating the aggregated result.

10. The computer-implemented method of claim 1 , wherein the first contextual data source comprises a first application within an organizational ecosystem.

11. The computer-implemented method of claim 1 , wherein the second contextual data source comprises a third-party application not within an organizational ecosystem.

12. 1. A system comprising: at least one processor; and a non-transitory computer-readable medium containing instructions that, when executed by at least one processor, cause the system to: generating a first context-defining query subcomponent from a multi-order text query received from a client device, the first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent; providing the first context-defining query subcomponent to a large-scale language model for generating domain-specific computer code that is specific to the first context data source and that is executable to respond to the first context-defining query subcomponent; executing the domain-specific computer code from the large-scale language model using the first context data source accessed via a computer network, the domain-specific computer code generating component-specific results utilizing data stored in the first context data source to generate first results for the first context-defining query subcomponent of the multi-order text query; identifying a second result for a second context-defining query subcomponent generated from the multi-order text query, the second result indicating a second context data source; The system utilizes the first results and the second results to generate aggregate results for the multi-order text query.

13. When executed by the at least one processor, the instructions further cause the system to: determining that the multi-order text query is a non-first-order text query; The system of claim 12 , further comprising: identifying a third result for a third context-defining query subcomponent generated from the multi-order text query indicating the first contextual data source.

14. 14. The system of claim 13, wherein the instructions, when executed by the at least one processor, further cause the system to utilize the first result, the second result, and the third result to generate the aggregated result for the multi-order text query.

15. 13. The system of claim 12, wherein the instructions, when executed by the at least one processor, further cause the system to generate at least one of a decision associated with the first context-defining query subcomponent or an action for the first context-defining query subcomponent.

16. When executed by the at least one processor, the instructions further cause the system to: determining that the first context-defining query subcomponent is unanswerable; 13. The system of claim 12, further comprising causing the client device to send a request to provide additional context for the first context definition query subcomponent, the additional context including an indication of an additional contextual data source.

17. When executed by the at least one processor, the instructions further cause the system to: determining that the first context-defining query subcomponent of the multi-order text query is unanswerable in response to receiving a request for sample data from the large-scale language model for generating component-specific results corresponding to the first context-defining query subcomponent of the multi-order text query; 13. The system of claim 12, further comprising: providing context sample data to the large-scale language model for training the large-scale language model to generate the component-specific results corresponding to the first context-defining query subcomponent of the multi-order text query.

18. A non-transitory computer-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to: generating a first context-defining query subcomponent from a multi-order text query received from a client device, the multi-order text query being a non-first-order text query, the first context-defining query subcomponent indicating a first context data source for responding to the first context-defining query subcomponent; providing the first context-defining query subcomponent to a large-scale language model for generating computer code specific to the first context data source and executable to respond to the first context-defining query subcomponent; executing the computer code from the large-scale language model to access the first contextual data source via a computer network to generate first results for the first context-defining query subcomponent of the multi-order text query; identifying a second result for a second context-defining query subcomponent generated from the multi-order text query, the second result indicating a second context data source; A non-transitory computer-readable medium that utilizes the first result and the second result to generate aggregate results for the multi-order text query.

19. 20. The non-transitory computer-readable medium of claim 18, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to send the first context-defining query subcomponent to the large-scale language model and cause the large-scale language model to generate the computer code in a domain-specific computer language specific to the first context data source indicated by the first context-defining query subcomponent.

20. 20. The non-transitory computer-readable medium of claim 18, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to integrate a first application corresponding to the client device with a second application corresponding to an organizational ecosystem, wherein the first contextual data source comprises the first application and the second contextual data source comprises the second application.

Images