Communication data intelligence delivery method

Abstract

Described herein are exemplary devices, apparatuses, systems, methods, and non-transitory storage media for transmitting results of analysis tasks. In some embodiments, messages from communications applications on a user device are received (e.g., via an application on the user device). Information associated with the messages are provided to machine-learning models to output results of the analysis tasks. The results may be transmitted to the user device.

Description

COMMUNICATION DATA INTELLIGENCE DELIVERY METHODCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 594,164, filed on October 30, 2023, the entire disclosure of which is herein incorporated by reference for all purposes.TECHNICAL FIELD

[0002] This disclosure generally relates to the field of artificial intelligence (Al) and its use in enterprises, and more particularly to using machine-learning models to output results of analysis tasks based on communications on a user device.BACKGROUND

[0003] Organizations such as business enterprises are increasingly adopting artificial intelligence (Al) to analyze data by a variety of software applications to provide insights and intelligence. For example, these applications receive information in messages communicated over different communication channels, such as voice, SMS, and messaging applications. Consumer messaging applications (e.g., iMessage, WhatsApp, WeChat, Signal, Line, Telegram) are increasingly being used for business. But these messaging applications lack functionalities that allow Al to use messages from these applications in a business setting, for example, to provide insights and intelligence about clients. Thus, it is desirable to capture messages from different applications and allow Al to determine business insights and intelligence using the captured messages.SUMMARY

[0004] Messaging applications (e.g., consumer messaging applications) lack functionalities that allow Al to use messages from these applications in a business setting, even though these messengers are increasingly used for business. Described herein are exemplary devices, apparatuses, systems, methods, and non-transitory storage media that allow Al to use messages from these messaging applications, for example, to provide business intelligence. In some embodiments, the intelligence is provided via a companion or web application on a user device. The application may be part of an overall platform that captures communications in messaging applications, analyzes the information, and provides the intelligence to the user. The application may be integrated with the underlying OS of the device.

[0005] Embodiments of the present disclosure provide numerous technical advantages. For example, the disclosed systems and methods allow communications in different messaging applications, including consumer applications, to be captured more efficiently and reliably. Because the communications are captured more efficiently and reliably, information in the communications may be extracted (e.g., by constructing embeddings from the messages) and provided to machine-learning models for performing analysis tasks, such as determining business intelligence. The disclosed systems and methods eliminate a need for more complicated and less reliable implementations, such as utilizing a separate system or a human, to capture the communications for performing the machine-learning tasks. As a result, data is more efficiently received and handled to generate more accurate results in a faster and less complex manner while consuming less power.

[0006] In some embodiments, a method for transmitting results for one or more analysis tasks to a user device comprises receiving at a message capture platform a plurality of messages from a plurality of communication applications on a user device, constructing a plurality of embedding representations of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations, providing the embeddings to one or more trained machine-learning models configured to output one or more results for one or more analysis tasks, and transmitting the one or more results for the one or more analysis tasks to a user device.

[0007] In some embodiments, the user device is associated with an organization, and the plurality of communication applications is associated with communication platforms external to the organization.

[0008] In some embodiments, the plurality of communication applications is associated with a plurality of communication platforms, and the message capture platform is configured to receive the plurality of messages via respective devices associated with the plurality of communication platforms.

[0009] In some embodiments, the message capture platform comprises a data connector for the receiving the plurality of messages from with the plurality of communication platforms.

[0010] In some embodiments, the method further comprises receiving, from the user device, one or more statements associated with the one or more analysis tasks, in response to receiving the one or more statements, constructing second embeddings of the one or more statements, and providing the second embeddings to the one or more trained machinelearning models.

[0011] In some embodiments, the method further comprises displaying, on a display of the user device, results of previous analysis tasks.

[0012] In some embodiments, the user device is associated with an organization, and the one or more results of the one or more analysis tasks comprise an analysis of a user external to the organization.

[0013] In some embodiments, the plurality of messages comprises: a text message, an email message, a chat message, an audio message, a video message, or any combination thereof.

[0014] In some embodiments, the one or more results comprise one or more of a recommendation and an observation.

[0015] In some embodiments, the user device is associated with an organization, the method further comprising determining whether the plurality of messages meets access control requirements of the organization. The plurality of messages is received in accordance with a determination that the plurality of messages meets the access control requirements.

[0016] In some embodiments, the user device is associated with an organization, and the embeddings are provided to the one or more trained machine-learning models in accordance with a determination that the embeddings meet access control requirements of the organization.

[0017] In some embodiments, each embedding of the embeddings is associated with one or more of a corresponding sender identity and corresponding recipient identity.

[0018] In some embodiments, the method further comprises receiving, from the user device, an input for initiating the one or more analysis tasks. The embeddings are provided to the one or more trained machine-learning models in response to receiving the input.

[0019] In some embodiments, the embeddings are provided to the one or more trained machine-learning models in accordance with a determination to initiate the one or more analysis tasks.

[0020] In some embodiments, the user device is associated with an organization, the method further comprising receiving, from the user device, a second plurality of messages from users internal to the organization.

[0021] In some embodiments, a system comprises one or more processors configured to perform any of the above methods.

[0022] In some embodiments, a non-transitory computer-readable medium stores one or more instructions, which, when executed by one or more processors of a system, cause the system to perform any of the above methods.

[0023] Although examples of the disclosure are described with respect to an organization and its employees, it should be appreciated that the described systems and methods may be used for capturing communications and performing analysis associated with other kinds of organizations and groups.

[0024] The embodiments disclosed are only examples, and the scope of this disclosure is not limited to them. Particular embodiments may include all, some, or none of the components, elements, features, functions, operations, or steps of the embodiments disclosed above. Embodiments according to the invention are in particular disclosed in the attached claims directed to a method, a storage medium, a system, and a computer program product, wherein any feature mentioned in one claim category, e.g., method, can be claimed in another claim category, e.g., system, as well. The dependencies or references back in the attached claims are chosen for formal reasons only. However, any subject matter resulting from a deliberate reference back to any previous claims (in particular multiple dependencies) can be claimed as well, so that any combination of claims and the features thereof are disclosed and can be claimed regardless of the dependencies chosen in the attached claims. The subjectmatter which can be claimed comprises not only the combinations of features as set out in the attached claims but also any other combination of features in the claims, wherein each feature mentioned in the claims can be combined with any other feature or combination of other features in the claims. Furthermore, any of the embodiments and features described or depicted herein can be claimed in a separate claim and / or in any combination with any embodiment or feature described or depicted herein or with any of the features of the attached claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 illustrates an exemplary architecture for communicating results of analysis tasks, in accordance with some embodiments.

[0026] Figure 2 illustrates an exemplary method for communicating results of analysis tasks , in accordance with some embodiments.

[0027] Figure 3 illustrates an exemplary user interface, in accordance with some embodiments.

[0028] Figure 4 illustrates an exemplary system, in accordance with some embodiments.DESCRIPTION OF EXAMPLE EMBODIMENTS

[0029] In the following description of embodiments, reference is made to the accompanying drawings which form a part hereof, and in which it is shown by way of illustration specific embodiments which can be practiced. It is to be understood that other embodiments can be used, and structural changes can be made without departing from the scope of the disclosed embodiments.

[0030] Messaging applications (e.g., consumer messaging applications) lack functionalities that allow Al to use messages from these applications in a business setting, even though these messengers are increasingly used for business. Described herein are exemplary devices, apparatuses, systems, methods, and non-transitory storage media that allow Al to use messages from these messaging applications, for example, to provide business intelligence. In some embodiments, the intelligence is provided via a companion or web application on a user device. The application may be part of an overall platform that captures communications in messaging applications, analyzes the information, and provides the intelligence to the user. The application may be integrated with the underlying OS of the device.

[0031] Embodiments of the present disclosure provide numerous technical advantages. For example, the disclosed systems and methods allow communications in different messaging applications, including consumer applications, to be captured more efficiently and reliably. Because the communications are captured more efficiently and reliably, information in the communications may be extracted (e.g., by constructing embeddings from the messages) and provided to machine-learning models for performing analysis tasks, such as determining business intelligence. The disclosed systems and methods eliminate a need for more complicated and less reliable implementations, such as utilizing a separate system or a human, to capture the communications for performing the machine-learning tasks. As a result, data is more efficiently received and handled to generate more accurate results in a faster and less complex manner while consuming less power.

[0032] In some embodiments, a method for transmitting results for one or more analysis tasks to a user device comprises receiving at a message capture platform a plurality of messages from a plurality of communication applications on a user device, constructing a plurality of embedding representations of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations, providing the embeddings to one or more trained machine-learning models configured to output one ormore results for one or more analysis tasks, and transmitting the one or more results for the one or more analysis tasks to a user device.

[0033] Although examples of the disclosure are described with respect to an organization and its employees, it should be appreciated that the described systems and methods may be used for capturing communications and performing analysis associated with other kinds of organizations and groups.

[0034] Figure 1 illustrates an exemplary architecture 100 for transmitting results of analysis tasks, in accordance with some embodiments. Architecture 100 shows an example of how communications on different communication channels are used for analysis tasks.

[0035] In some embodiments, the architecture 100 describes components for performing steps and implementing features described with respect to method 200. The component operations of architecture 100 may be performed by components described with respect to system 400. It should be appreciated that the components and interactions between components illustrated in and described with respect to Figure 1 are exemplary, and that the system for managing communications may include different components and interactions than illustrated and described.

[0036] As illustrated in Figure 1, the user 102 may receive output of analysis tasks and communicate messages via device 104. In some embodiments, the device 104 is a device of the user 102. In some embodiments, the device 104 is a device of an organization that the user 102 belongs to (e.g., user 102 is an employee of the organization). In some embodiments, the messages comprise a text message, an email message, a chat message, an audio message, a video message, or any combination thereof.

[0037] In some embodiments, the device 104 comprises companion application 106 and communications applications 1O8A-1O8N (e.g., the applications are installed on the device 104). In some embodiments, the communication applications comprise communication applications on platforms external to the organization of the user (e.g., iMessage, WhatsApp, WeChat, Signal, Line, Telegram). In some embodiments, the communication applications comprise communication applications on platforms internal to the organization of the user (e.g., Microsoft Teams, Slack, Leap Work). In some embodiments, the user 102 uses the communication applications 1O8A-1O8N via the companion application 106. For example, the companion application 106 may provide a unified interface for the user to communicate via the communication applications 1O8A-1O8N (e.g., by selecting the user interface object 304 corresponding to the user’s contacts and in response, allowing the user to provide and receive messages via corresponding communication applications).

[0038] The communications on communication applications are transmitted to capture platform 116 via respective devices 110A-1 ION. Although not explicitly illustrated, it should be appreciated that more than one application may transmit communications to one of devices 110A-110N. The devices 110A-110N may be servers of communication platforms (e.g., Meta, Apple, communication provider, SMS, transcribed voice) associated with the communication applications. In some embodiments, the capture platform 116 comprises a data connector, which is configured to connect to the devices 110A-1 ION via, for example, a JSON scheme. In some embodiments, the capture platform 116 is configured to receive communications from the communication applications and transmit the communications to the device 114 in real time. Features of devices 110A-1 ION may be implemented as part of device 104 (e.g., as part of companion application 106).

[0039] In some embodiments, the architecture 100 is part of an application framework that is configured to provide a machine-learning-based analysis of communications in a central communication platform. For example, the framework receives messages from clients of an enterprise to employees of the enterprise (e.g., via communication applications 1O8A-1O8N), which were communications in the central communication platform. The application framework then constructs embedding representations of the received messages by converting each message into one or more embedding representations.

[0040] The device 104 may be in communication with device 114. For example, information provided to companion application 106 may be communicated to device 114, and the device 114 may be configured to transmit output of analysis tasks to device 104 via the companion application 106. The device 114 may be in communication with the capture platform 116. For example, the device 114 may receive communications received by the capture platform 116, which may comprise the communication on the communication applications 1O8A-1O8N.

[0041] In some embodiments, the device 114 is configured to provide communication data intelligence (e.g., a recommendation or an observation based on analysis on the received messages, one or more results for one or more analysis tasks). For example, the device 114 is configured to construct embeddings based on the received communications.

[0042] In some embodiments, an embedding comprises a vector representation that can be obtained by inputting a message into a machine-learning model. The machine-learning model is configured to receive the message, which may include text, audio, and image data, and output the vector representation of the input message to construct the embedding. This machine-learning model may be a self-supervised model.

[0043] In some embodiments, the embeddings comprise information that would be utilized by a model (e.g., LLM) for executing analysis tasks, as described in more detail herein. In some embodiments, the embeddings constitute data associated with individual platform users (e.g., internal user of an organization, an external user, a chat participant, a contact), which cannot be housed in Al models due to privacy and data scope concerns.

[0044] The embedding representations may be stored in a database (e.g., in device 114), and each embedding representation may be associated with a corresponding sender identity (e.g., identity of the client sending the message associated with the embedding representation) or a corresponding recipient identity (e.g., identity of the employee receiving the message associated with the embedding representation). The sender identity may be the identity of the user 102, and the recipient identities may be the identities of the clients. The identities may be determined from information in the received messages.

[0045] The embeddings may be stored in embedding databases based on properties (e.g., attributes) and the data of the embeddings itself. The properties may depend on the type of data being stored and may be provided via communication applications 1O8A-1O8N, their respective devices 110A-110N, or both. For instance, persona embeddings may have one set of attributes while embeddings of messages may have a different set of attributes. For example, for knowledge base embeddings, attributes may be represented as: - 'name': the name of the knowledge base (e.g., Confluence, CRM, SharePoint, etc.), - 'access_level': who has access to this knowledge base (e.g., internal, client-facing), - 'content_type': types of content stored (e.g., documents, financial reports), and - 'linked_to': array of Persona IDs who use or contribute to this knowledge base.

[0046] In some embodiments, constructing the embeddings comprise processing the received communications, such as removing noise in the data and normalizing the data. The device 114 may provide the embeddings to one or more machine-learning models to perform analysis tasks and the one or more machine-learning models may output results of the analysis tasks.

[0047] For example, the user 102 would like a recommendation for interacting with a client. The user 102 may provide this request to companion application 106, and in response, the device 104 transmits the request to device 114 for performing an analysis task that determines the recommendation for interacting with the client. Based on the request, the device 114 may provide embeddings corresponding to received communications associated with the client (e.g., conversations between the user 102 and the client on the communicationapplications 1O8A-1O8N) to one or more machine-learning models. The machine-learning models may determine that the client likes to watch sports. In accordance with this determination, the device 114 outputs the recommendation of inviting the client to a sporting event and transmits the recommendation to the device 104. The received recommendation may be displayed on the device 104 via companion application 106.

[0048] The disclosed systems and methods allow communications in different messaging applications, including consumer applications, to be captured more efficiently and reliably. Because the communications are captured more efficiently and reliably, information in the communications may be extracted (e.g., by constructing embeddings from the messages) and provided to machine-learning models for performing analysis tasks, such as determining business intelligence.

[0049] To provide the intelligence, the device 114 may need a constant stream of communication, as data input and a way to deliver this intelligence to the user 102. Since applications 1O8A-1O8N may comprise native messaging applications that cannot be modified to add this functionality, the companion application 106 and capture platform 116 can provide the communications to the device 114 instead, allowing the device 114 sufficient data to perform analysis and provide the intelligence.

[0050] In some embodiments, the companion application 106 is configured to communicate with the communication applications 1O8A-1O8N. For example, after the device 104 receives intelligence from the device 114, the intelligence may be displayed on the device 104 via the companion application 106. The companion application 106 may provide the user 102 an option to use this intelligence on the communication applications 1O8A-1O8N. For instance, the intelligence is determined based on communications with a client on one or more of the communication applications 1O8A-1O8N, and the intelligence comprises a recommended response to a client. The recommended response may be presented to the client on the companion application 106, and the companion application 106 may provide the user 102 the option to use this recommended response on the one or more of the communication applications 1O8A-1O8N to respond to the client.

[0051] In some embodiments, the embeddings are provided to the one or more trained machine-learning models (e.g., for performing one or more analysis tasks) in accordance with a determination with a determination that the embeddings meet access control requirements of the user’s organization. For instance, to enforce the data sharing policies and data access requirements, an organization may need to set up one or more “ethical walls” between its business units, which may be information barrier protocols within an organization designedto prevent exchange or access of information that could lead to conflicts of interest within an organization or between the organization and its clients. The organization may comprise different departments, and ethical walls are implemented within or between the different departments to enforce data sharing policies and access control requirements.

[0052] For example, in a financial institution, an ethical wall may be set up between the wealth management department and the investment banking department to prevent information from being shared between the two business units. This way, information about a client known to the wealth management is not communicated to the investment banking department and cannot be access by the investment banking department for performing a task (and vice versa), even if the investment banking department may also serve the same client in a different capacity. Using this example, embeddings retrieved for a wealth management department employee (e.g., user 102) analysis task comprises information accessible to the wealth management department and does not comprise information from the investment banking department due to the ethical wall between the two departments.

[0053] In some embodiments, the device 114 is configured to receive one or more statements associated with the one or more analysis tasks from device 104. In response to receiving the one or more statements, the device 114 is configured to construct embeddings of the one or more statements and provide the embeddings to one or more trained machinelearning models for performing analysis tasks. For example, using the sports example above, the user 102 provides an input (e.g., to a user interface of the companion application 106) indicating that the client likes basketball. The input is transmitted from device 104 to device 114 and embeddings are constructed based on this statement.

[0054] In the future, the user 102 (or another user) would like a recommendation for interacting with this client. The user may provide this request to companion application 106, and in response, the device 104 transmits the request to device 114 for performing an analysis task that determines the recommendation for interacting with the client. Based on the request, the device 114 may provide embeddings corresponding to received communications associated with the client (e.g., conversations between the user 102 and the client on the communication applications 1O8A-1O8N) and the embeddings constructed based on the one or more statements (e.g., the input indicating the client likes basketball) to one or more machine-learning models. The machine-learning models may determine that the client likes to watch sports, specifically basketball. In accordance with this determination, the device 114 outputs the recommendation of inviting the client to a basketball game and transmits therecommendation to the device 104. The received recommendation may be displayed on the device 104 via companion application 106.

[0055] In some embodiments, the capture platform 116 may be part of device 104. For example, the capture platform 116 may be a feature of the companion application 106 for receiving messages on the different communication applications. In some embodiments, the capture platform 116 may be part of device 114, such that a same device would receive the messages on the different communication applications and performs analysis tasks based on the received messages.

[0056] In some embodiments, the messages from the communication applications 108A- 108N are received according to a determination of whether the messages meet access control requirements of the user’s organization. For example, the messages are communicated to device 114 as illustrated for compliance of the organization’s policies for recording communications with external parties (e.g., for future auditing). As another example, the messages are received in accordance with a determination that the messages are related to business. Messages that are determined not to be related to business (e.g., the user 102’ s nonbusiness messages) may not be communicated to the device 114.

[0057] In some embodiments, the machine-learning models for the analysis task are not trained based on restricted information (e.g., private information of a client, confidential information, sensitive information) because in some instances, the models may not forget this information or be able to delete this information. Therefore, it may be advantageous to provide the embeddings from the different communication applications, which may include sensitive, confidential, and / or private information, to the trained machined-learning model, in lieu of training the machine-learning model with this information to avoid the information being retained by the model or affecting model operation.

[0058] In some embodiments, the trained machine-learning model is selected from a plurality of machine learning models based on the identified task. For example, a machinelearning model most appropriate for executing the analysis task is selected (e.g., by device 114). Examples of machine-learning models for executing the analysis tasks are described in more detail herein.

[0059] Additional examples of the analysis tasks are described in more detail below. The analysis task may comprise authorship analysis for an external user of the plurality of external user (e.g., a client). In this example, the device 114 may receive (e.g., from device 104 via companion application 106) a current message from the external user and retrieves the appropriate embeddings. The embeddings may correspond to previous messages from theexternal user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 executes the analysis task by providing the retrieved embeddings and the current message to the trained machine-learning model and receiving, from the trained machine-learning model, an output indicative of a stylistic difference between the current message and the previous messages from the external user. The stylistic difference may indicate whether the current message is authored by the external user. In some embodiments, access control for this task can be configured via an application or configured via an external user’s SSO or other access control systems.

[0060] As an example of authorship analysis, in response to identification of the task as comprising authorship analysis (e.g., on a continuous basis as messages are received from an external user as required by the organization’s information security program, or after the internal user provides the message “tell me if it’s the same user” to the companion application), messages sent by the external user (that the authorship analysis is performed on) are pulled from the embeddings database, and the application queries the appropriate model (e.g., a model for determining authorship) with the current message (the message the authorship analysis is performed on) and the older messages, to compare the authorship style. The result (e.g., authorship mismatch, authorship match) of the analysis may be reported to the internal user via a graphical user interface. The number of messages pulled may be defined by the internal user (e.g., based on settings) or automatically. For example, the user may provide the message “give me last 200 messages of this user” to the application to compare the style of these 200 messages to style of the current message via the model.

[0061] In this example and the examples of analysis tasks below, the current message may be provided to the machine-learning model as a context associated with the analysis task, and the machine-learning model would take this context into account while the analysis task is executed. Additionally, prior to providing the current message to the machinelearning model, the current message may be converted into embeddings, and the embeddings converted from the current message are additionally provided to the machine-learning model for executing the analysis tasks.

[0062] The analysis task may comprise a sentiment analysis for an external user of the plurality of external users (e.g., a client). In this example, the device 114 may retrieve embeddings corresponding to previous messages from the external user to one or more internal users of the internal user group (e.g., from the communication applications 108A- 108N). The device 114 executes the analysis task by providing the retrieved embeddings tothe trained machine-learning model and receives, from the trained machine-learning model, the sentiment analysis of the external user. The analysis may indicate a sentiment of the external user. The sentiment of the user may be quantified by a sentiment score.

[0063] As an example of sentiment analysis, in response to identification of the analysis task as comprising sentiment analysis (e.g., via user input, on a continuous basis as messages are received by the internal user, after a threshold amount of time (e.g., as configured by the internal user)), messages of one or more conversations between the internal user and the external user (that the sentiment analysis is performed on) are pulled (e.g., from embeddings database). The pulled conversations are analyzed by a machine-learning model (e.g., LLM) to understand the sentiments of the one or more conversations. Based on this analysis, a sentiment score or a sentiment analysis (e.g., the client is satisfied) is determined and displayed on a graphical user interface.

[0064] The analysis task may comprise summarization. As an example, summarization comprises summarizing a current message from a client. In this example, the device 114 receives (e.g., from device 104 via companion application 106) a current message from the external user (e.g., the current message from the client) and retrieves the appropriate embeddings. The embeddings may correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from the communication applications 1O8A-1O8N). The device 114 executes the analysis task by providing the retrieved embeddings and the current message to the trained machine-learning model and receives, from the trained machine-learning model, a summary of the current message. The summary of the current message may be displayed on a graphical user interface.

[0065] In some embodiments of summarization, the provided embeddings include only embeddings associated with the current message. In some embodiments of summarization, the embeddings include embeddings associated with the current message and embeddings associated with messages related to the current message. For example, the embeddings associated with the current message are used for substance of the summarization, while the embeddings associated with the relevant messages (e.g., recent messages, messages including information about personas in the conversation) are used to provide context (e.g., set the tone of the summarization).

[0066] The analysis task may comprise response composition. As an example, response composition comprises generating a suggested response to a client. In this example, thedevice 114 receives (e.g., from device 104 via companion application 106) a current message from an external user (e.g., a current message from the client) and retrieves the appropriate embeddings. The embeddings may correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings and the current message to the trained machine-learning model and receives, from the trained machine-learning model, a composed message for responding to the current message. For example, the device 114 receives, from the machine-learning model, the suggested response to the client. The composed message may be displayed on a graphical user interface.

[0067] As an example of response composition, in response to identification of the analysis task as comprising response composition (e.g., via user input, on a continuous basis as messages are received by the internal user, after a threshold amount of time (e.g., as configured by the internal user)), conversation history between the internal user and the external user (that the response is composed for) and persona embeddings are pulled. In some embodiments, conversation history between a second internal user (e.g., a colleague in a same department) and the external user are also pulled, to provide additional intelligence for improving the quality of the response composition. This data is provided to one or more machine-learning models. Based on the output of the one or more machine-learning models, one or more suggested responses to the external user are displayed on a graphical user interface for the internal user to select. In some embodiments, the conversation history is also displayed.

[0068] The analysis task may comprise an action recommendation with respect to an external user. As an example, the analysis task comprises an action recommendation for the client. In some embodiments, the recommended action comprises suggesting a product or service to the external user or initiating a conversation with the external user. In this example, the device 114 retrieves the appropriate embeddings. The embeddings may correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings to the trained machinelearning model and receives, from the trained machine-learning model, a recommended action with respect to the external user. The recommended action may be displayed on a graphical user interface.

[0069] The analysis task may comprise fact checking. As an example, fact checking comprises determining factual validity of information associated with the client (e.g., information provided by the client in a current message), which may be used for fraud mitigation. In this example, the device 114 receives a current message from an external user and retrieving the appropriate embeddings. The embeddings may correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings and the current message to the trained machinelearning model and receives, from the trained machine-learning model, a verification of the current message. For example, the device 114 receives a determination that the information in the current message is factually valid. The verification of the current message may be displayed on a graphical user interface.

[0070] As an example of fact checking, in response to identification of the task as comprising fact checking, a machine-learning model (e.g., LLM, which may be fine-tuned with institutional knowledge or have access to outside knowledge sources, such as the internet, financial databases) is used by the application, and the message is being checked with the model to understand if the fact in the message is correct. The result (e.g., valid facts, invalid facts) of the analysis may be reported to the internal user via a graphical user interface.

[0071] The analysis task may comprise product or service recommendation for an external user. In this example, the device 114 retrieves the appropriate embeddings. The embeddings correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings to the trained machine-learning model and receives, from the trained machine-learning model, a product or a service recommendation for the external user. The produce or service recommendation may be display on a graphical user interface.

[0072] The analysis task may comprise an analysis of an external user. For example, the analysis task comprises an analysis of a client. In this example, the device 114 receives the appropriate embeddings. The embeddings correspond to previous messages from the external user to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings to the trained machine-learning model and receives, from the trainedmachine-learning model, the analysis of the external user. The analysis of the external user may be displayed on a graphical user interface.

[0073] The analysis task may be obtained based on a query of the internal user of the organization. For example, the query is made via the internal user’s conversation with a personal assistant (e.g., a chatbot on, for example, companion application 106). In this example, the device 114 retrieves the appropriate embeddings. The embeddings may correspond to previous messages to one or more internal users of the internal user group (e.g., from communication applications 1O8A-1O8N). The device 114 may execute the analysis task by providing the retrieved embeddings to the trained machine-learning model and receives, from the trained machine-learning model, a response to the query of the internal user. For example, the device 114 receives the response of the query and communicate the response to the user via the personal assistant. The response to the query may be display on a graphical user interface.

[0074] Further examples of the analysis tasks are described in U.S. Patent Application No. 18 / 482,787, the entire disclosure of which is herein incorporated by reference for all purposes.

[0075] Figure 2 illustrates an exemplary method 200 for transmitting results of analysis tasks (e.g., to a user device), in accordance with some embodiments. In some embodiments, the steps of method 200 are performed by one or more components described with respect to Figure 1 and / or components of system 400. It should be appreciated that steps described with respect to Figure 2 are exemplary. The method 200 may include fewer steps, additional steps, or different order of steps than described. Additional examples of method 200 are described with respect to Figures 1 and 3, and it is appreciated that the steps of method 200 leverage the features and advantages described with respect to these Figures.

[0076] In some embodiments, the method 200 comprises receiving at a message capture platform a plurality of messages from a plurality of communication applications on a user device (step 202). For example, as described with respect to Figure 1, a plurality of messages from communication applications 1O8A-1O8N are received by capture platform 116. As discussed, the capture platform 116 may be part of device 104 (e.g., part of companion application 106) or a different device. In some embodiments, the plurality of messages comprises a text message, an email message, a chat message, an audio message, a video message, or any combination thereof.

[0077] In some embodiments, the method 200 comprises constructing a plurality of embedding representations of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations (step 204). For example, as described with respect to Figure 1, the device 114 constructs a plurality of embedding representations of the messages received from communications applications 1O8A-1O8N by converting each message into one or more embedding representations. In some embodiments, the embeddings are associated with one or more of a corresponding sender identity (e.g., identity of user 102) and corresponding recipient identity (e.g., identity of a client).

[0078] In some embodiments, the method 200 comprises providing the embeddings to one or more trained machine-learning models configured to output one or more results for one or more analysis tasks (step 206). In some embodiments, the one or more results comprise one or more of a recommendation and an observation. For example, as described with respect to Figure 1, the embeddings constructed by device 114 (e.g., based on messages from the communication applications 1O8A-1O8N) are provided to one or more trained machine-learning models for outputting an observation or recommendation about a client.

[0079] In some embodiments, the method 200 comprises receiving, from the user device, an input for initiating the one or more analysis tasks, and the embeddings are provided to the one or more trained machine-learning models in response to receiving the input. For example, the analysis tasks are initiated in response to the user 102 provided an input to the companion application 106, and in response to initiation of the analysis tasks, the appropriate embeddings are provided to the machine-learning models for obtaining results.

[0080] In some embodiments, the embeddings are provided to the one or more trained machine-learning models in accordance with a determination to initiate the one or more analysis tasks. For example, as described with respect to Figure 1, the analysis tasks are automatically initiated (e.g., determined by device 104 based on, for example, context of interaction between the user 102 and the companion application 106), and in response to initiation of the analysis tasks, the appropriate embeddings are provided to the machinelearning models for obtaining results.

[0081] In some embodiments, the method 200 comprises transmitting the one or more results for the one or more analysis tasks to a user device (step 208). For example, as described with respect to Figure 1, the results of the analysis tasks are transmitted to device 104.

[0082] In some embodiments, the user device is associated with an organization, and the plurality of communication applications is associated with communication platforms external to the organization. For example, as described with respect to Figure 1, the communication applications 1O8A-1O8N are associated with external communication platforms such as iMessage, WhatsApp, WeChat, Signal, Line, and Telegram. In some embodiments, the plurality of messages comprises messages from users internal to the organization (e.g., via Microsoft Teams, Slack, Leap Work).

[0083] In some embodiments, the plurality of communication applications is associated with a plurality of communication platforms, and the message capture platform is configured to receive the plurality of messages via respective devices associated with the plurality of communication platforms. For example, as described with respect to Figure 1, the communication applications 1O8A-1O8N are associated with communication platforms such as iMessage, WhatsApp, WeChat, Signal, Line, Telegram, Microsoft Teams, Slack, and Leap Work, and the capture platform 116 is configured to receive the plurality of messages on these different platforms via devices 110A-1 ION. In some embodiments, the message capture platform comprises a data connector for the receiving the plurality of messages from with the plurality of communication platforms. For example, as described with respect to Figure 1, the capture platform 116 comprises a data connector.

[0084] In some embodiments, the method 200 comprises receiving, from the user device, one or more statements associated with the one or more analysis tasks. For example, as described with respect to Figure 1, the user device receives a statement regarding a client liking basketball, which may be used for future recommendations to the user. In some embodiments, the method 200 comprises in response to receiving the one or more statements, constructing second embeddings of the one or more statements, and providing the second embeddings to the one or more trained machine-learning models. Using the same example, as described with respect to Figure 1, embeddings are constructed based on the statement that the client likes basketball, and for a future analysis task, the embeddings are provided to machine-learning models for outputting a recommendation for interacting with the client.

[0085] In some embodiments, the user device is associated with an organization, and the one or more results of the one or more analysis tasks comprise an analysis of a user external to the organization. For example, as described with respect to Figure 1, the observations and recommendations provided to the device 104 are associated with interaction with a client of the user’s organization.

[0086] In some embodiments, the method 200 comprises determining whether the plurality of messages meets access control requirements of the organization, and the plurality of messages is received in accordance with a determination that the plurality of messages meets the access control requirements. For example, as described with respect to Figure 1, the messages from communication applications 1O8A-1O8N are received according to the organization’s access control requirements.

[0087] In some embodiments, the embeddings are provided to the one or more trained machine-learning models in accordance with a determination that the embeddings meet access control requirements of the organization. For example, as described with respect to Figure 1, the embeddings (e.g., constructed based on the received messages, constructed based on one or more statements provided by the user) are provided to the machine-learning models (for outputting a recommendation or an observation) according to the user’s associated ethical walls.

[0088] In some embodiments, the method 200 comprises displaying, on a display of the user device, results of previous analysis tasks. For example, as described with respect to Figure 3, one or more of the user interfaces present the results of previous analysis tasks.

[0089] Figure 3 illustrate exemplary user interfaces, in accordance with some embodiments. In some embodiments, the user interfaces described with respect to Figure 3 are user interfaces of companion application 106. In some embodiments, the user interfaces are displayed on a display of a device, such as device 104. It should be appreciated that the user interfaces are exemplary, and that different configurations of user interfaces, user interface objects, and interactions may be used to receive results of analysis tasks.

[0090] As illustrated, Figure 3 comprises user interface 300, which comprises user interface objects 302-312. In some embodiments, the user interface object 302 is configured to receive an input for the user (e.g., user 102). The input may be provided for future analysis tasks. For example, the input comprises a feedback that would affect how a future analysis tasks is performed. As a more specific example, the user 102 may provide a feedback indicating that a client likes basketball. This feedback would be provided to device 114, and future recommended interactions with this client may involve a recommendation to discuss basketball.

[0091] In some embodiments, the user interface objects 304 correspond to the user’s contacts. For examples, the contacts may be contacts from the communication applications 1O8A-1O8N. In some embodiments, in response to a selection of an object associated with acontact, the user interface is updated to allow the user to communicate with the contact, for example, via one or more of the communication applications 1O8A-1O8N.

[0092] In some embodiments, the user interface object 306 and 308 show results of previous analysis tasks. The results of previous analysis tasks may be provided by device 114. For example, as illustrated, the user interface object 306 shows a summary of a previous conversation with a client. The user may select “view more” to expand the message associated with the user interface object 306, which may include a recommendation based on the summary of the previous conversation.

[0093] In some embodiments, the user interface objects 310 and 312 comprise objects for navigating the companion application 106. For example, selection of the user interface object 312 would initiate an analysis task. The user interface may be updated to request the user for a specific task, or the device may determine (e.g., based on the user’s past actions) the most suitable analysis task to perform. Upon a determination of the analysis task, the device of the companion application 106 communicates with the device 114, which may provide the embeddings constructed from the received communications to one or more machine-learning model for performing the analysis task. After the analysis task is performed, the results of the analysis task are transmitted from the device 114 to the device of the companion application 106, and the user interface may be updated to show the results.

[0094] Further examples of user interfaces associated with the operations herein are described in U.S. Patent Application No. 18 / 482,787, the entire disclosure of which is herein incorporated by reference for all purposes.

[0095] Figure 4 illustrates an example computer system 400. In some embodiments, a disclosed system comprises the computer system 400. In particular embodiments, one or more computer systems 400 perform one or more steps of one or more methods described or illustrated herein. In particular embodiments, one or more computer systems 400 provide functionality described or illustrated herein. In particular embodiments, software running on one or more computer systems 400 performs one or more steps of one or more methods described or illustrated herein or provides functionality described or illustrated herein. Particular embodiments include one or more portions of one or more computer systems 400. Herein, reference to a computer system may encompass a computing device, and vice versa, where appropriate. Moreover, reference to a computer system may encompass one or more computer systems, where appropriate.

[0096] This disclosure contemplates any suitable number of computer systems 400. This disclosure contemplates computer system 400 taking any suitable physical form. As example and not by way of limitation, computer system 400 may be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (such as, for example, a computer-on-module (COM) or system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a mobile telephone, a personal digital assistant (PDA), a server, a tablet computer system, or a combination of two or more of these. Where appropriate, computer system 400 may include one or more computer systems 400; be unitary or distributed; span multiple locations; span multiple machines; span multiple data centers; or reside in a cloud, which may include one or more cloud components in one or more networks. Where appropriate, one or more computer systems 400 may perform without substantial spatial or temporal limitation one or more steps of one or more methods described or illustrated herein. As an example and not by way of limitation, one or more computer systems 400 may perform in real time or in batch mode one or more steps of one or more methods described or illustrated herein. One or more computer systems 400 may perform at different times or at different locations one or more steps of one or more methods described or illustrated herein, where appropriate.

[0097] In particular embodiments, computer system 400 includes a processor 402, memory 404, storage 406, an input / output (I / O) interface 408, a communication interface 410, and a bus 412. Although this disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, this disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement.

[0098] In particular embodiments, processor 402 includes hardware for executing instructions, such as those making up a computer program. As an example and not by way of limitation, to execute instructions, processor 402 may retrieve (or fetch) the instructions from an internal register, an internal cache, memory 404, or storage 406; decode and execute them; and then write one or more results to an internal register, an internal cache, memory 404, or storage 406. In particular embodiments, processor 402 may include one or more internal caches for data, instructions, or addresses. This disclosure contemplates processor 402 including any suitable number of any suitable internal caches, where appropriate. As an example and not by way of limitation, processor 402 may include one or more instructioncaches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in the instruction caches may be copies of instructions in memory 404 or storage 406, and the instruction caches may speed up retrieval of those instructions by processor 402. Data in the data caches may be copies of data in memory 404 or storage 406 for instructions executing at processor 402 to operate on; the results of previous instructions executed at processor 402 for access by subsequent instructions executing at processor 402 or for writing to memory 404 or storage 406; or other suitable data. The data caches may speed up read or write operations by processor 402. The TLBs may speed up virtual-address translation for processor 402. In particular embodiments, processor 402 may include one or more internal registers for data, instructions, or addresses. This disclosure contemplates processor 402 including any suitable number of any suitable internal registers, where appropriate. Where appropriate, processor 402 may include one or more arithmetic logic units (ALUs); be a multi-core processor; or include one or more processors 402. Although this disclosure describes and illustrates a particular processor, this disclosure contemplates any suitable processor.

[0099] In particular embodiments, memory 404 includes main memory for storing instructions for processor 402 to execute or data for processor 402 to operate on. As an example and not by way of limitation, computer system 400 may load instructions from storage 406 or another source (such as, for example, another computer system 400) to memory 404. Processor 402 may then load the instructions from memory 404 to an internal register or internal cache. To execute the instructions, processor 402 may retrieve the instructions from the internal register or internal cache and decode them. During or after execution of the instructions, processor 402 may write one or more results (which may be intermediate or final results) to the internal register or internal cache. Processor 402 may then write one or more of those results to memory 404. In particular embodiments, processor 402 executes only instructions in one or more internal registers or internal caches or in memory 404 (as opposed to storage 406 or elsewhere) and operates only on data in one or more internal registers or internal caches or in memory 404 (as opposed to storage 406 or elsewhere). One or more memory buses (which may each include an address bus and a data bus) may couple processor 402 to memory 404. Bus 412 may include one or more memory buses, as described below. In particular embodiments, one or more memory management units (MMUs) reside between processor 402 and memory 404 and facilitate accesses to memory 404 requested by processor 402. In particular embodiments, memory 404 includesrandom access memory (RAM). This RAM may be volatile memory, where appropriate, this RAM may be dynamic RAM (DRAM) or static RAM (SRAM). Moreover, where appropriate, this RAM may be single-ported or multi-ported RAM. This disclosure contemplates any suitable RAM. Memory 404 may include one or more memories 404, where appropriate. Although this disclosure describes and illustrates particular memory, this disclosure contemplates any suitable memory.

[0100] In particular embodiments, storage 406 includes mass storage for data or instructions. As an example and not by way of limitation, storage 406 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these. Storage 406 may include removable or non-removable (or fixed) media, where appropriate. Storage 406 may be internal or external to computer system 400, where appropriate. In particular embodiments, storage 406 is non-volatile, solid-state memory. In particular embodiments, storage 406 includes 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. This disclosure contemplates mass storage 406 taking any suitable physical form. Storage 406 may include one or more storage control units facilitating communication between processor 402 and storage 406, where appropriate. Where appropriate, storage 406 may include one or more storages 406. Although this disclosure describes and illustrates particular storage, this disclosure contemplates any suitable storage.

[0101] In particular embodiments, RO interface 408 includes hardware, software, or both, providing one or more interfaces for communication between computer system 400 and one or more RO devices. Computer system 400 may include one or more of these RO devices, where appropriate. One or more of these RO devices may enable communication between a person and computer system 400. As an example and not by way of limitation, an RO device may include a keyboard, keypad, microphone, monitor, mouse, printer, scanner, speaker, still camera, stylus, tablet, touch screen, trackball, video camera, sensors, magnetic detectors, another suitable RO device or a combination of two or more of these. An RO device may include one or more sensors. This disclosure contemplates any suitable RO devices and any suitable RO interfaces 408 for them. Where appropriate, RO interface 408 may include one or more device or software drivers enabling processor 402 to drive one or more of these ROdevices. I / O interface 408 may include one or more I / O interfaces 408, where appropriate. Although this disclosure describes and illustrates a particular I / O interface, this disclosure contemplates any suitable I / O interface.

[0102] In particular embodiments, communication interface 410 includes hardware, software, or both providing one or more interfaces for communication (such as, for example, packet-based communication) between computer system 400 and one or more other computer systems 400 or one or more networks. As an example and not by way of limitation, communication interface 410 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire -based network or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a WI-FI network. This disclosure contemplates any suitable network and any suitable communication interface 410 for it. As an example and not by way of limitation, computer system 400 may communicate with 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 one or more portions of 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. As an example, computer system 400 may communicate with a wireless PAN (WPAN) (such as, for example, a BLUETOOTH WPAN), a WI-FI network, a WLMAX network, a cellular telephone network (such as, for example, a Global System for Mobile Communications (GSM) network), or other suitable wireless network or a combination of two or more of these. Computer system 400 may include any suitable communication interface 410 for any of these networks, where appropriate. Communication interface 410 may include one or more communication interfaces 410, where appropriate. Although this disclosure describes and illustrates a particular communication interface, this disclosure contemplates any suitable communication interface.

[0103] In particular embodiments, bus 412 includes hardware, software, or both coupling components of computer system 400 to each other. As an example and not by way of limitation, bus 412 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 ElectronicsStandards Association local (VLB) bus, or another suitable bus or a combination of two or more of these. Bus 412 may include one or more buses 412, where appropriate. Although this disclosure describes and illustrates a particular bus, this disclosure contemplates any suitable bus or interconnect.

[0104] Herein, a computer-readable non-transitory storage medium or media may include one or more semiconductor-based or other integrated circuits (ICs) (such, as for example, field-programmable gate arrays (FPGAs) or application- specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard drives (HHDs), optical discs, optical disc drives (ODDs), magneto-optical discs, magneto-optical drives, floppy diskettes, floppy disk drives (FDDs), magnetic tapes, solid-state drives (SSDs), RAM-drives, SECURE DIGITAL cards or drives, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more of these, where appropriate. A computer-readable non-transitory storage medium may be volatile, non-volatile, or a combination of volatile and non-volatile, where appropriate.

[0105] In some embodiments, a non-transitory computer readable storage medium stores one or more programs, and the one or more programs includes instructions. When the instructions are executed by an electronic device (e.g., computer system 400) with one or more processors and memory, the instructions cause the electronic device to perform the methods described with respect to Figures 1-3.

[0106] In some embodiments, a method for transmitting results for one or more analysis tasks to a user device comprises receiving at a message capture platform a plurality of messages from a plurality of communication applications on a user device, constructing a plurality of embedding representations of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations, providing the embeddings to one or more trained machine-learning models configured to output one or more results for one or more analysis tasks, and transmitting the one or more results for the one or more analysis tasks to a user device.

[0107] In some embodiments, the user device is associated with an organization, and the plurality of communication applications is associated with communication platforms external to the organization.

[0108] In some embodiments, the plurality of communication applications is associated with a plurality of communication platforms, and the message capture platform is configuredto receive the plurality of messages via respective devices associated with the plurality of communication platforms.

[0109] In some embodiments, the message capture platform comprises a data connector for the receiving the plurality of messages from with the plurality of communication platforms.

[0110] In some embodiments, the method further comprises receiving, from the user device, one or more statements associated with the one or more analysis tasks, in response to receiving the one or more statements, constructing second embeddings of the one or more statements, and providing the second embeddings to the one or more trained machinelearning models.

[0111] In some embodiments, the method further comprises displaying, on a display of the user device, results of previous analysis tasks.

[0112] In some embodiments, the user device is associated with an organization, and the one or more results of the one or more analysis tasks comprise an analysis of a user external to the organization.

[0113] In some embodiments, the plurality of messages comprises: a text message, an email message, a chat message, an audio message, a video message, or any combination thereof.

[0114] In some embodiments, the one or more results comprise one or more of a recommendation and an observation.

[0115] In some embodiments, the user device is associated with an organization, the method further comprising determining whether the plurality of messages meets access control requirements of the organization. The plurality of messages is received in accordance with a determination that the plurality of messages meets the access control requirements.

[0116] In some embodiments, the user device is associated with an organization, and the embeddings are provided to the one or more trained machine-learning models in accordance with a determination that the embeddings meet access control requirements of the organization.

[0117] In some embodiments, each embedding of the embeddings is associated with one or more of a corresponding sender identity and corresponding recipient identity.

[0118] In some embodiments, the method further comprises receiving, from the user device, an input for initiating the one or more analysis tasks. The embeddings are provided to the one or more trained machine-learning models in response to receiving the input.

[0119] In some embodiments, the embeddings are provided to the one or more trained machine-learning models in accordance with a determination to initiate the one or more analysis tasks.

[0120] In some embodiments, the user device is associated with an organization, the method further comprising receiving, from the user device, a second plurality of messages from users internal to the organization.

[0121] In some embodiments, a system comprises one or more processors configured to perform any of the above methods.

[0122] In some embodiments, a non-transitory computer-readable medium stores one or more instructions, which, when executed by one or more processors of a system, cause the system to perform any of the above methods.

[0123] Those skilled in the art will recognize that the systems described herein are representative, and deviations from the explicilty disclosed embodiments are within the scope of the disclosure.

[0124] Although the disclosed embodiments have been fully described with reference to the accompanying drawings, it is to be noted that various changes and modifications will become apparent to those skilled in the art. Such changes and modifications are to be understood as being included within the scope of the disclosed embodiments as defined by the appended claims.

[0125] The terminology used in the description of the various described embodiments herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a”, “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

Claims

CLAIMS1. A method for transmitting results for one or more analysis tasks to a user device, comprising: receiving at a message capture platform a plurality of messages from a plurality of communication applications on a user device; constructing a plurality of embedding representations of the plurality of messages by converting each message of the plurality of messages into one or more embedding representations; providing the embeddings to one or more trained machine-learning models configured to output one or more results for one or more analysis tasks; and transmitting the one or more results for the one or more analysis tasks to the user device.

2. The method of claim 1, wherein: the user device is associated with an organization, and the plurality of communication applications is associated with communication platforms external to the organization.

3. The method of claim 1, wherein: the plurality of communication applications is associated with a plurality of communication platforms, and the message capture platform is configured to receive the plurality of messages via respective devices associated with the plurality of communication platforms.

4. The method of claim 3, wherein the message capture platform comprises a data connector for the receiving the plurality of messages from with the plurality of communication platforms.

5. The method of claim 1, further comprising: receiving, from the user device, one or more statements associated with the one or more analysis tasks; in response to receiving the one or more statements, constructing second embeddings of the one or more statements; andproviding the second embeddings to the one or more trained machine-learning models.

6. The method of claim 1, further comprising displaying, on a display of the user device, results of previous analysis tasks.

7. The method of claim 1, wherein: the user device is associated with an organization, and the one or more results of the one or more analysis tasks comprise an analysis of a user external to the organization.

8. The method of claim 1, wherein the plurality of messages comprises: a text message, an email message, a chat message, an audio message, a video message, or any combination thereof.

9. The method of claim 1, wherein the one or more results comprise one or more of a recommendation and an observation.

10. The method of claim 1, wherein the user device is associated with an organization, the method further comprising: determining whether the plurality of messages meets access control requirements of the organization, wherein the plurality of messages is received in accordance with a determination that the plurality of messages meets the access control requirements.

11. The method of claim 1, wherein: the user device is associated with an organization, and the embeddings are provided to the one or more trained machine-learning models in accordance with a determination that the embeddings meet access control requirements of the organization.

12. The method of claim 1, wherein each embedding of the embeddings is associated with one or more of a corresponding sender identity and corresponding recipient identity.

13. The method of claim 1, further comprising: receiving, from the user device, an input for initiating the one or more analysis tasks, wherein the embeddings are provided to the one or more trained machinelearning models in response to receiving the input.

14. The method of claim 1, wherein the embeddings are provided to the one or more trained machine-learning models in accordance with a determination to initiate the one or more analysis tasks.

15. The method of claim 1, wherein the user device is associated with an organization, the method further comprising: receiving, from the user device, a second plurality of messages from users internal to the organization.

16. A system comprising one or more processors configured to perform a method of any of claims 1-15.

17. A non-transitory computer-readable medium storing one or more instructions, which, when executed by one or more processors of a system, cause the system to perform a method of any of claims 1-15.

Images