System and method for intent messaging

Abstract

The disclosed embodiments provide a framework to help customers obtain relevant responses from brands and other users to intents communicated by these customers. In response to obtaining an intent, an intent messaging service identifies one or more users to whom the intent can be provided to solicit responses to the intent. The one or more users are selected based on characteristics of the intent. The intent messaging service evaluates responses to the intent from one or more users to identify relevant responses that can be presented to the customer. The intent messaging service provides relevant responses to the intent to the customer, and the customer can determine which users to interact with to process the intent.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 033,529, filed on June 2, 2020, the disclosure of which is incorporated herein by reference. Technical Field

[0003] The present invention generally relates to systems and methods for facilitating messaging between customers and brands. More specifically, a technology is provided to deploy a framework to help customers obtain relevant responses from brands and other users to the intent conveyed by these customers. Summary of the invention

[0004] The disclosed embodiments provide a framework for an intent processing system that allows customers to interact with brands and other users to obtain relevant responses to these intents. According to some embodiments, a computer-implemented method is provided. The computer-implemented method includes obtaining an intent. The intent corresponds to a request to be processed. In addition, the intent is associated with a customer. The computer-implemented method also includes identifying one or more users to whom the intent is to be provided. The one or more users are identified based on a set of characteristics of the intent. The computer-implemented method also includes providing the intent. The intent is provided to the one or more users to solicit a response to the intent. The computer-implemented method also includes obtaining a set of responses to the intent. The computer-implemented method also includes evaluating the set of responses to identify relevant responses to the intent. Discarding irrelevant responses in the set of responses. The computer-implemented method also includes providing the relevant responses so that the relevant responses are presented to the customer in response to the intent.

[0005] In one example, a system includes: one or more processors and a memory including instructions, which, due to being executed by the one or more processors, cause the system to perform the method described herein. In another example, a non-transitory computer-readable storage medium stores executable instructions on the non-transitory computer-readable storage medium, which, due to being executed by one or more processors of a computer system, cause the computer system to perform the method described herein.

[0006] This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used alone to determine the scope of the claimed subject matter. The subject matter should be understood by reference to appropriate portions of the entire specification of this patent application, any or all drawings, and each claim.

[0007] The above and other features and examples will be described in more detail below in the following description, claims and accompanying drawings.

[0008] Various embodiments of the present invention are discussed in detail below. Although specific implementations are discussed, it should be understood that this is for illustrative purposes only. Those skilled in the relevant art will recognize that other components and configurations can be used without departing from the spirit and scope of the present invention. Therefore, the following description and drawings are illustrative and should not be construed as restrictive. Many specific details are described to provide a thorough understanding of the present invention. However, in some cases, well-known or conventional details are not described to avoid obscuring the specification. Reference to an embodiment or an embodiment of the present invention may refer to the same embodiment or any embodiment; and, such reference means at least one embodiment in the embodiment.

[0009] Reference to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. The phrase "in one embodiment" appearing in various places in this specification is not necessarily all referring to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive of other embodiments. In addition, various features are described that may be possessed by some embodiments and not by other embodiments.

[0010] The terms used in this specification generally have their ordinary meanings in the art in the context of the present invention and in the specific contexts in which each term is used. Alternative language and synonyms may be used for any one or more of the terms discussed herein, and whether or not a term is elaborated or discussed herein should not have a special meaning. In some cases, synonyms for certain terms are provided. The recording of one or more synonyms does not exclude the use of other synonyms. The examples used anywhere in this specification (including examples of any term discussed herein) are only illustrative and are not intended to further limit the scope and meaning of the present invention or any example term. Similarly, the present invention is not limited to the various embodiments provided in this specification.

[0011] It is not intended to limit the scope of the present invention, and the examples of the instrument, device, method and the related results thereof according to the embodiments of the present invention are given below. It should be noted that, for the convenience of the reader, a title or subtitle can be used in the example, which should not limit the scope of the present invention in any way. Unless otherwise defined, the technical terms and scientific terms used herein have the meanings commonly understood by those of ordinary skill in the art to which the present invention belongs. In the case of contradiction, the present application document including the definition shall prevail.

[0012] Additional features and advantages of the present invention will be set forth in the following description and will be apparent to some extent from the description or may be learned from the practice of the principles disclosed herein. The features and advantages of the present invention may be realized and obtained by the instruments and combinations particularly pointed out in the appended claims. These and other features of the present invention may become more fully apparent from the following description and the appended claims or may be understood from the practice of the principles set forth herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention is described in conjunction with the accompanying drawings:

[0014] Figure 1 An illustrative example of an environment in which an intent messaging service obtains intents from a client and presents responses to the intents by brands and other users to the client in accordance with at least one embodiment is shown;

[0015] Figure 2 An illustrative example of an environment in which an intent messaging service identifies brands and other users to solicit responses to a customer-submitted intent in accordance with at least one embodiment is shown;

[0016] Figure 3 An illustrative example of an environment in which a customer generates an intent through a user interface to solicit responses from brands and other users of an intent messaging service in accordance with at least one embodiment is shown;

[0017] Figure 4 An illustrative example of an environment for providing a status to a customer regarding a customer-submitted intent through a user interface in accordance with at least one embodiment is shown;

[0018] Figure 5 An illustrative example of an environment in which a customer introduces another user or brand into an existing conversation based on a response to the customer's intent through a user interface in accordance with at least one embodiment is shown;

[0019] Figure 6 An illustrative example of an environment in which a customer initiates a communication channel with a brand through a user interface to engage in a conversation with the brand regarding an intent in accordance with at least one embodiment is shown;

[0020] Figure 7 An illustrative example of an environment in which a customer provides a response to another customer's intent through a user interface in accordance with at least one embodiment is shown;

[0021] Figure 8 An illustrative example of a process for obtaining intent and providing that intent to other users and brands in accordance with at least one embodiment is shown;

[0022] Fig. 9An illustrative example of a process for evaluating responses to offers from brands and other users to identify relevant responses that can be presented to a customer in response to an intent in accordance with at least one embodiment is shown; and

[0023] Fig.10 Illustrative examples of environments in which various embodiments may be implemented are shown.

[0024] In the drawings, similar components and / or features may have the same reference number. In addition, various components of the same type may be distinguished by following the reference number with a dash and a second reference that distinguishes between similar components. If only the first reference number is used in the specification, the description applies to any of the similar components having the same first reference number, regardless of the second reference number. DETAILED DESCRIPTION

[0025] The following description only provides preferred examples of (one or more) embodiments, and is not intended to limit the scope, applicability or configuration of the present invention. On the contrary, the description of the preferred examples of (one or more) embodiments that follow will provide an enabling description of the preferred examples for implementing the embodiments to those skilled in the art. It should be understood that various changes may be made to the functions and arrangements of the elements without departing from the spirit and scope as set forth in the appended claims.

[0026] Figure 1 An illustrative example of an environment 100 in which an intent messaging service 102 obtains intents from a customer 108 and presents the customer with responses to the intents from brands 112 and other users 114 according to at least one embodiment. An intent may correspond to a problem that a customer wishes to resolve. Examples of intents may include, for example, a topic, sentiment, complexity, and urgency. Topics may include, but are not limited to, topics, products, services, technical issues, usage issues, complaints, refund requests, or purchase requests, etc. For example, intent may be determined based on semantic analysis of a message (e.g., by identifying keywords, sentence structure, repeated words, punctuation, and / or non-articles), user input (e.g., one or more categories have been selected), and / or statistical information associated with the message (e.g., typing speed and / or response latency).

[0027] In the environment 100, a customer 108 sends a request to an intent processing system 104 of an intent messaging service 102 through an intent messaging application implemented on a computing device 110 to obtain one or more responses to the request from one or more brands 112 and / or other users 114 associated with the intent messaging service 102. The other users 114 may include members of the intent messaging service 102 community, who may also interact with the brands 112 to obtain responses to their intents, and who may have experience with various topics, goods, services, or other areas that may be associated with intents. The intent messaging application implemented on the computing device 110 may be provided by the intent messaging service 102 to allow customers (e.g., the customer 108) to interact with brands 112 and other users 114 (e.g., a user community using the intent messaging service 102) that are associated with the intent messaging service 102 and may provide goods and services to the customer. The intent messaging service 102 may provide a platform for customers and brands to connect in order to provide suggestions and recommendations about intents submitted by these customers.

[0028] In response to obtaining a request from a customer 108, the intent processing system 104 can evaluate the request to extract the intent expressed by the customer 108, which can be used to identify brands 112 and other users 114 that can provide relevant responses to the customer's request. In one embodiment, the intent processing system 104 uses a machine learning model to process the request in order to identify and extract intent from the request. The machine learning model can be used to perform semantic analysis of the request (e.g., by identifying keywords, sentence structures, repeated words, punctuation marks, and / or non-articles) to identify the intent expressed in the request. The machine learning model used by the intent processing system 104 can be dynamically trained using supervised learning techniques. For example, an input request and a data set of known intents included in the input request can be selected to train the machine learning model. In some implementations, the known intents used to train the machine learning model may include characteristics of these intents. The machine learning model can be evaluated to determine whether the machine learning model is extracting the expected intent from each request based on the input sample request provided to the machine learning model. Based on the evaluation, the machine learning model can be modified to increase the likelihood that the machine learning model generates the desired result. The machine learning model can also be dynamically trained by soliciting feedback from clients, including client 108, on the extracted intents obtained from submitted requests. For example, before submitting the extracted intents to identify one or more brands 112 or other users 114 from which responses to the intents are solicited, the extracted intents can be presented to client 108 to determine whether the extracted intents correspond to the requests submitted by client 108. Thus, the responses from client 108 can be used to train the machine learning model based on its accuracy in identifying intents from requests.

[0029] The intent processing system 104 can provide the extracted intent to the intent matching system 106 of the intent messaging service 102. The intent matching system 106 can be implemented on a computing system or other system (e.g., a server, a virtual machine instance, etc.) of the intent messaging service 102. Alternatively, the intent matching system 106 can be implemented as an application or other process executed on the computing system of the intent messaging service 102. In one embodiment, in response to obtaining a new intent from the intent processing system 104, the intent matching system 106 uses the new intent and information about different brands 112 and other users associated with the intent messaging service 102 as input to a machine learning model to identify one or more brands 112 and / or other users 114 that may provide relevant responses to the intent. The information about the different brands 112 and other users 114 may include historical data corresponding to responses submitted by the different brands 112 and other users 114 to previously provided intents. The historical data may indicate the performance of the brand or other user in providing relevant responses to different intents submitted to the brand or other user, information about any previous interactions between the brand / other user and the customer 108, customer feedback (if any) related to the customer's interaction with the brand or other user, etc. In addition, the information about the brand or other user may specify the types of intents that the brand or other user may have expertise in responding to. For example, the information may indicate what goods and services the brand offers, what goods or services the user has used, or any other information that can be used to identify whether a solution to a particular intent involves those goods and services.

[0030] The machine learning model used by the intent matching system 106 can be dynamically trained using sample intents and sample outputs corresponding to the characteristics of the brands 112 and other users 114, which can be used to identify the brands 112 and other users 114 to which the intent is to be provided. In addition, the machine learning model can be dynamically trained using feedback from different brands 112 and other users 114 that receive the intent. This feedback can be used to determine whether the machine learning model is selecting brands 112 and other users 114 that can respond to the intent with a relevant response or are otherwise associated with the characteristics of the intent. This feedback can also be used to train the machine learning model used by the intent matching system 106. Therefore, as the intent matching system 106 obtains feedback from different brands 112 and other users 114 for a large number of intents submitted to these different brands 112 and other users 114, the machine learning model can be dynamically trained in real time. Alternatively, the machine learning model can be periodically trained based on feedback obtained from the brands 112 and other users 114.

[0031] The output of the machine learning model used by the intent matching system 106 may include identifiers corresponding to one or more brands 112 and / or other users 114 to which the new intent is to be provided, so as to solicit responses from each of the one or more brands 112 and / or other users 114. The new intent may be assigned a unique identifier so that the responses obtained from the one or more brands 112 and / or other users 114 can be associated with the specific intent by reference to the unique identifier. In one embodiment, the intent matching system 106 updates the user interface of the intent messaging application used by each brand 112 or other user 114 to indicate the solicitation of responses to the specific intent. For example, through the user interface, the intent matching system 106 can present the new intent and the option for responding to the intent to the agent associated with the brand 112 or other user 114. The agent associated with the brand 112 or other user 114 can respond to the intent, reject / ignore the intent, or provide the intent matching system 106 with an indication that the intent is not related to the brand 112 or other user through the user interface. Actions performed by agents associated with brands 112 or other users 114 may be used to further dynamically train the machine learning model used by the intent matching system 106 to select brands 112 and other users to respond to intents. For example, if an agent associated with a brand indicates that the provided intent is not relevant to the brand, the intent matching system may use this feedback to train the machine learning model to not provide irrelevant intents to the brand.

[0032] In one embodiment, a brand 112 (e.g., an agent associated with the brand assigned to interact with the intent messaging service 102) or other user 114 that receives an intent is limited to a single response to the intent. For example, when an agent associated with a brand 112 or other user 114 submits a response to an intent to the intent processing system 104, the intent messaging application used by the agent associated with the brand 112 or other user 114 can disable the ability to submit additional responses to the intent until the customer 108 has indicated that he or she wishes to be further engaged with the brand 112 or other user 114 regarding the intent. This can prevent the brand 112 or other user 114 from overwhelming (e.g., "spamming") the customer 108 with responses to the intent. In addition, if the customer 108 declines to be engaged with the brand 112 or other user 114, the customer 108 can be exempt from additional responses from the brand 112 or other user 114.

[0033] If an agent associated with a brand 112 or other user 114 submits an intent response for a customer 108 to the intent processing system 104, the intent processing system 104 may evaluate the intent response to determine whether the intent response is relevant to the intent submitted by the customer 108. In one embodiment, the intent processing system 104 uses a classification algorithm or other machine learning model to classify the intent response as relevant to the intent or irrelevant to the intent. The classification algorithm or other machine learning model used by the intent processing system 104 can be dynamically trained using supervised learning techniques. For example, input intents, known relevant responses, known irrelevant responses, and classified data sets can be selected to train the classification algorithm or other machine learning model. In some examples, the input intent can be obtained from an administrator of the intent messaging service, an intent messaging service customer, or other sources associated with the intent messaging service. In some implementations, the known relevant responses and irrelevant responses used to train the classification algorithm or other machine learning model used by the intent processing system include responses generated by the entity that generated the sample intent. In addition, feedback from customers (including customers 108) can be used to train the classification algorithm or other machine learning model used to classify the intent response as relevant or irrelevant. For example, if a response classified as relevant to an intent is provided to a client 108, the client 108 may provide feedback indicating whether the response is indeed relevant to the intent. This feedback may be used to strengthen the model (e.g., a response classified as relevant is considered relevant by the client) or to update the model (e.g., a response classified as relevant is considered not relevant by the client). As clients of the intent messaging service 102 provide this feedback to the intent messaging service 102, the classification algorithm or other machine learning model may be dynamically updated in real time.

[0034] The intent processing system 104, using the classification algorithm or machine learning model described above, can discard any responses that are classified as irrelevant to the intent. In one embodiment, if the intent processing system 104 determines that the brand 112 or other user has provided an irrelevant response to the intent, the intent processing system 104 updates the profile of the brand 112 or other user to indicate that it has provided an irrelevant response to the intent. This can reduce the likelihood that the brand 112 or other user 114 is selected by the intent matching system 106 to respond to similar intents. In some cases, this feedback can also be used to dynamically train the machine learning model used by the intent matching system 106 to further reduce the likelihood that the brand 112 or other user 114 is solicited to provide a response to similar intents. If the brand 112 or other user 114 is deemed to have provided irrelevant responses on a consistent basis, other remedial actions can be performed, such as disassociating or removing the brand 112 or other user from the intent messaging service 102.

[0035] If the intent processing system 104 determines that a relevant response to the intent has been obtained, the intent processing system 104 can provide the response to the customer 108 through the intent messaging application operating on the computing device 110. This can cause the intent response to be displayed on the user interface of the computing device 110. Through the user interface, the customer 108 can evaluate the intent response and determine whether to further engage with the brand 112 or other user 114, thank the brand 112 or other user or express gratitude for the response of the brand 112 or other user, or ignore the intent response. In addition, the customer 108 can provide feedback to the intent processing system 104 regarding the quality of the intent response. This feedback can be used to further dynamically train the machine learning model used by the intent matching system 106, which is used to identify the brand 112 and other users 114 to which the intent is provided to solicit a response to the intent.

[0036] In one embodiment, if the customer 108 determines that he or she wants to communicate further with the brand 112 or other user 114 regarding the intent submitted by the customer 108, the intent messaging service 102 establishes a communication channel between the customer 108 and the brand 112 or other user 114, through which the customer 108 and the brand 112 or other user 114 can exchange messages or other content. As described above, when the brand 112 or other user 114 submits a response to the intent, the intent messaging application used by the brand 112 or other user 114 can prohibit the brand 112 or other user 114 from submitting additional responses. However, if the customer 108 indicates that he or she wishes to have a conversation with the brand 112 or other user 114 regarding the intent, the intent messaging service 102 can send instructions or other instructions to the intent messaging application to enable the brand 112 or other user 114 to submit additional responses to the customer 108 using the intent messaging application. Furthermore, the intent messaging service 102 may provide additional information about the customer 108 (eg, customer name, customer address, customer image, customer contact information, etc.) to the brand 112 or other users.

[0037] Figure 2An illustrative example of an environment 200 in which an intent messaging service 202 identifies brands 220 and other users 222 to solicit responses to an intent submitted by a customer 218 according to at least one embodiment is shown. In the environment 200, the intent messaging service 202 obtains a request from a customer 218 to solicit responses from one or more brands 220 and / or other users 222 regarding a particular intent. For example, the customer 218 can generate a request using an intent messaging application installed on a computing device used by the customer 218 or accessed by the customer 218 using a computing device (e.g., through a website, etc.), and indicates in the request the intent for which the customer 218 is seeking a relevant response. The intent can be, for example, a subject, a sentiment, a complexity, and / or an urgency. The subject can include, but is not limited to, a topic, a product, a service, a technical issue, a usage problem, a complaint, a refund request, or a purchase request, etc.

[0038] The client 218 may send its request and corresponding intent to the client messaging system 206 of the intent processing system 204 through the intent messaging application. The client messaging system 206 may be implemented on the computing system of the intent messaging service 202 or as an application executed by the computing system of the intent processing system 204. The client messaging system 206 may facilitate communications between the client 218 and the intent messaging service 202 and any brands 220 and / or other users 222 associated with the intent messaging service 202. For example, the client messaging system 206 may establish a communication channel with any brand 220 or other user 222 with whom the client 218 has chosen to engage in a conversation about a particular intent through the intent messaging application. In addition, the client messaging system 206 may be used to update the user interface of the intent messaging application based on the provided intent and the response obtained from the intent messaging service 202 to identify the brand 220 and other user 222 from which the intent response is solicited for a particular intent.

[0039] In response to obtaining a request and a corresponding intent from a client 218, the client messaging system 206 can send the request and the corresponding intent to an intent extraction engine 208 of the intent processing system 204 to extract the intent from the request. The intent extraction engine 208 can be implemented as a computer system that processes incoming requests from clients 218 using a machine learning model to identify the intent expressed in the request. For example, the machine learning model can be used to perform semantic analysis of the request (e.g., by identifying keywords, sentence structure, repeated words, punctuation, and / or non-articles) to identify the intent expressed in the request. For example, the intent can also be determined based on user input (e.g., one or more categories have been selected); and / or statistical information related to the message (e.g., typing speed and / or response delay).

[0040] The machine learning model used by the intent extraction engine 208 may be trained using supervised learning techniques. For example, input requests and a data set of known intents included in the input requests may be selected to train the machine learning model implemented by the intent extraction engine 208. In some examples, the input requests may be obtained from an administrator of the intent messaging service 202, a customer of the intent messaging service 202, or other sources associated with the intent messaging service 202. In some implementations, the known intents used to train the machine learning model used by the intent extraction engine 208 may include characteristics of those intents provided by the entity that generated the sample requests. The machine learning model may be evaluated to determine whether the machine learning model is extracting the expected intent from each request based on the input sample requests provided to the machine learning model. Based on the evaluation, the machine learning model may be modified (e.g., one or more parameters or variables may be updated) to increase the likelihood that the machine learning model generates a desired result (e.g., an expected intent).

[0041] In one embodiment, the intent extraction engine 208 evaluates the request from the customer 208 to determine whether additional information is needed in order to extract or otherwise supplement the intent from the request, thereby allowing the identification of brands 220 and / or other users 222 that can provide relevant responses to the intent. For example, the intent extraction engine 208 can determine that the customer's geographic location and the time frame for the intent to be resolved are required. The intent extraction engine 208 can send a request to the customer messaging system 206 to solicit the additional information from the customer 218. In one embodiment, the customer messaging system 206 uses natural language processing (NLP) or other artificial intelligence to solicit the requested information from the customer 208. For example, using NLP or other artificial intelligence, the customer messaging system 206 can ask the customer 218 to provide their location, the time frame for the intent to be resolved, which users or brands the customer 218 wants to solicit responses from, etc. The responses provided by the customer 218 can be provided to the intent extraction engine 208, and the intent extraction engine 208 can use these responses and the provided request from the customer 218 to extract the intent and supplement the intent with the additional information provided by the customer 218. The intent may be used by the intent matching system 210 to identify brands 220 and / or other users 222 that may be solicited to obtain a response to the intent.

[0042] The intent extraction engine 208 may provide the intent extracted from the request submitted by the customer 218 to the intent machine learning modeling engine 212 of the intent matching system 210. The intent machine learning modeling engine 212 may be implemented on a computing system of the intent matching system 210, or as an application or process executed on a computing system of the intent matching system 210. In one embodiment, the intent machine learning modeling engine 212 implements a machine learning model that is configured to identify brands 220 and / or other users 222 to which intents may be provided to solicit responses to the intents. The machine learning model implemented by the intent machine learning modeling engine 212 may use a brand database 214 and a user database 216 maintained by the intent matching system 210 and the intent of the customer as inputs to the machine learning model to identify brands 220 and / or users 222 that may provide relevant responses to the intents. The brand database 214 and the user database 216 may include profiles of each of the brands 220 and the users 222, respectively, which may be associated with the intent messaging service 202. Each profile may indicate the user's or brand's experience in responding to a particular intent or intent category, as well as the user's or brand's interest in potential topics or intent categories. In addition, each profile may indicate feedback about the user's or brand's responses to previously provided intents. The feedback may specify whether the responses provided for a particular intent were relevant, useful, or otherwise appreciated by the corresponding customer.

[0043] The user database 216 may also include profiles of customers 218. The profiles of customers 218 may indicate any customer preferences for particular brands 220 or other users 222. For example, the profiles of customers 218 may specify which brands 220 or other users 222 the customer 218 has interacted with to resolve previously provided intents. In addition, for each of these interactions, the profile may include feedback from the customer 218. The feedback may indicate whether the interaction with a particular brand or other user is relevant to the corresponding intent, whether it was useful in processing the corresponding intent, or whether it contributed to a positive experience with the brand or other user. The intent machine learning modeling engine 212 may also use this information to identify which brands 220 and / or other users 222 to solicit to obtain responses to the intent.

[0044] The machine learning model used by the intent machine learning modeling engine 212 can be trained using sample intents and sample outputs corresponding to characteristics of brands 220 and other users 222, which can be used to identify brands 220 and other users 222 to whom intents are to be provided. In addition, the machine learning model can be trained using feedback from different brands 220 and other users 222 that receive intents. This feedback can be used to determine whether the machine learning model is selecting brands 220 and other users 222 that can respond to intents with relevant responses or are otherwise associated with the characteristics of intents. For example, if a brand that provides interior design services obtains intents that are not related to interior design, the brand can provide feedback indicating that the intent provided is not related to the brand. This feedback can be used to further train the machine learning model used by the intent machine learning modeling engine 212.

[0045] The output generated by the machine learning model implemented by the intent machine learning modeling engine 212 may include an identifier corresponding to a brand 220 and / or other user 222 to which the intent may be provided to solicit a response from the brand 220 and / or other user 222. Based on the output, the intent machine learning modeling engine 212 may send the intent to the identified brand 220 and / or other user 222. For example, the intent machine learning model engine 212 may update the user interface of the intent messaging application for each of the identified brands 220 and / or other users 222 to present the intent. The intent may be assigned a unique identifier so that responses to the intent from the brand 220 and / or other user 222 may be associated with the intent via the unique identifier. A brand or other user receiving the intent through the intent messaging application may respond to the intent and submit the response to the intent processing system 204, which may evaluate the response to determine whether the response is relevant to the intent.

[0046] In one embodiment, the intent is provided anonymously to the identified brand 220 and / or other user 222. For example, the intent machine learning modeling engine 212 can remove any identifying information of the customer 218 (e.g., customer name, customer address, customer contact information, etc.) when providing the intent to the identified brand 210 and / or other user 222. However, in addition to the intent, the intent machine learning modeling engine 212 can provide other information that may be useful to the brand or other user when preparing a response to the intent. For example, the approximate location of the customer 218 (e.g., city, state, etc.) can be provided for the intent. The approximate location can be used to determine whether the brand or other user can provide a response to the intent, which response can indicate the ability to help the customer 218 at the approximate location (e.g., the brand can open a store within the approximate location, the user can provide goods and services at the approximate location, etc.).

[0047] In one embodiment, once a brand or other user submits a response to an intent, the intent messaging service 202 can disable the ability of the brand or other user to provide additional responses to the intent through the intent messaging application. This prevents the brand or other user from potentially flooding the customer 218 with responses to a particular intent. A conversation with the customer 218 can be established through the intent messaging application based on a request from the customer 218 to initiate a communication channel with a particular brand 220 or other user 222.

[0048] In one embodiment, the intent processing system 204, in response to obtaining an intent response from a brand or other user, uses a classification algorithm or other machine learning model to evaluate the intent response to classify the intent response as relevant to the intent or not relevant to the intent. Any response classified as not relevant to the intent may be discarded by the intent processing system 204. Responses classified as relevant to the intent may be presented to the customer 218 by the customer messaging system 206 through an intent messaging application implemented on the customer's computing device. In addition, the intent response may provide the customer 218 with options to invite the brand or other user who submitted the intent response to engage in a conversation about the intent, thank the brand or other user for its intent response, ignore the intent response from the brand or other user, ignore future responses from the brand or other user in the future (e.g., block the brand or other user), and the like. If the customer 218 chooses to engage in a conversation with the brand or other user based on the provided intent response, the customer messaging system 206 may establish a communication channel between the customer 218 and the brand or other user to allow the customer 218 to engage in a conversation with the brand or other user using their respective intent messaging applications. In one embodiment, the customer messaging system 206 provides the brand or other user with customer information (e.g., name, image, address, contact information, etc.) after the communication channel is established. In addition, the customer messaging system 206 re-enables the brand or other user to send messages or responses to the customer 218 through the newly established communication channel.

[0049] The intent processing system 204 can evaluate responses to the intent from the brand 220 and / or other users 222 to determine their relevance to the intent of the customer 218 .

[0050] Figure 3An illustrative example of an environment 300 is shown in which a customer 306 generates an intent through a user interface 310 to solicit responses from brands and other users 305 of an intent messaging service 302 in accordance with at least one embodiment. In the environment 300, the customer 306 generates a new intent through an intent messaging application operating on a computing device 308, which can be submitted to the intent messaging service 302 to solicit one or more responses from brands 304 and other users 305 associated with the intent messaging service 302. For example, the customer 306 can use the intent messaging application through the user interface 310 to define a request or intent for which the customer 306 is seeking responses from brands 304 and other users 305 associated with the intent messaging application 302.

[0051] like Figure 3 As shown, the customer 306 may be presented with the option of providing a title for his request or intent, and the option of defining the request or intent, through the user interface 310. For example, the customer 306 may provide "Interior Design Advice" as the title of his request or intent, which serves as a solicitation by the customer 306 for suggestions of interior designers who may serve the customer 306. In addition, through the user interface 310, the customer 306 may define the parameters of the request or intent (e.g., "I am looking for a good interior designer"). The intent messaging service 302 may use this information to extract the intent of the customer 306 and identify one or more brands 304 and other users 305 from which to solicit responses to the intent submitted by the customer 306.

[0052] In one embodiment, the intent messaging service 302 may use natural language processing or other artificial intelligence to query the customer 306 for additional information that may be used to supplement the intent and allow for customized identification of brands 304 and other users 305 that may provide relevant responses to the intent. For example, the intent messaging service 302 may query the customer 306 to identify the customer's location, whether other users can help the customer fulfill their intent, the time frame for resolution of the intent, etc. The responses provided by the customer 306 to the intent messaging service 302 may be used to further narrow the selection of brands 304 and other users 305 from which responses to the intent may be solicited.

[0053] In one embodiment, the intent messaging application may present to the customer 306, via the user interface 310, a list of contacts or other participants that may be added to a conversation associated with the submitted intent. For example, the intent messaging application may obtain a list of contacts from the customer's computing device 308, which list may be presented via the user interface 310. Alternatively, the intent messaging application may obtain a list of contacts associated with the customer 306 that also use the intent messaging service 302 from the intent messaging service 302. This list of contacts from the intent messaging service 302 may include users that the customer 306 has designated as "friends" or that can otherwise communicate directly with the customer 306 via the intent messaging service 302.

[0054] In one embodiment, through the user interface 310, the intent messaging service 302 can further provide suggestions of brands 304 and / or other users 305 from which responses to the submitted intent can be solicited. For example, based on the intent messaging service 302's evaluation of the intent, the intent messaging service 302 can suggest one or more brands 304 or other users 305 that may provide relevant responses to the submitted intent. The intent messaging service 302 can present the one or more brands 304 or other users 305 to allow the customer 306 to select which brands 304 or other users 305 will receive the intent to solicit responses to the intent. Based on the customer's selection, the intent messaging service 302 can solicit responses to the intent from the selected brands and / or other users.

[0055] Figure 4An illustrative example of an environment for providing a status of an intent submitted by a customer 406 to a customer 406 through a user interface 410 according to at least one embodiment is shown. In the environment 400, in response to submitting a new intent to an intent messaging service 402 to solicit responses to the intent from one or more brands 404 and other users 405, the intent messaging service 402 may evaluate the intent and the profiles of different brands and users associated with the intent messaging service 402 to identify a subset of brands 404 and other users 405 that may be solicited to provide responses to the intent. In one embodiment, the intent messaging service 402 uses a machine learning model implemented by an intent matching system to identify brands 404 and other users 405 that may provide relevant responses to the intent submitted by the customer 406. The machine learning model may use a brand database and a user database maintained by the intent matching system, as well as the customer's intent, as inputs to the machine learning model to identify brands and / or users that may provide relevant responses to the intent. The brand database and the user database may include profiles of each of the brands and users, respectively, which may be associated with the intent messaging service 402. Each profile may indicate the user's or brand's experience in responding to a particular intent or category of intent, as well as the user's or brand's interest in the underlying topic or classification of intent. In addition, each profile may indicate feedback regarding the user's or brand's response to a previously provided intent. The feedback may specify whether the response provided in response to the intent was relevant, useful, or otherwise appreciated by the corresponding customer.

[0056] In response to obtaining an intent from client 406, intent messaging service 402 can update user interface 410 to provide a new dialog window for the provided intent. The name or title of the dialog window presented through user interface 410 can correspond to the name or title of the request submitted by client 406 to intent messaging service 402 through user interface 410. In addition, through user interface 410 and within the dialog window for the intent, intent messaging service 402 can provide a processing status regarding the client-provided intent. For example, Figure 4 As shown, the intent messaging service 402 may indicate that the intent has been shared by the community of the intent messaging service (e.g., brands 404 and other users 405 that were solicited to provide responses to the intent). In addition, the intent messaging service 402 may indicate through the user interface 410 that any reviewed responses from brands 404 and / or other users 405 may be presented to the customer 406 within a conversation window associated with the intent submitted by the customer 406.

[0057] In one embodiment, the client 406 may introduce one or more other contacts into the conversation window to enable communication between the client 406 and the one or more contacts within the conversation window. For example, the client 406 may select one or more contacts from a list of available contacts, and the client 406 may invite the one or more contacts to participate in a conversation related to the submitted intent. The list of available contacts may be maintained by the intent messaging service 402 and may be provided to the client 406 by an intent messaging application operating on the computing device 408. Alternatively, the list of available contacts may be maintained on the computing device 406. If the client 406 selects one or more contacts from the list, the intent messaging service 402 may obtain contact information for each of the one or more contacts and send a notification to each of the one or more contacts to invite the one or more contacts to participate in a conversation with the client 406 about the intent. If the contact list is maintained on the computing device 408, the intent messaging application may obtain contact information from the computing device 408 and provide the contact information to the intent messaging service 402 to provide notifications about the conversation to the contacts. In one embodiment, the notification may include a uniform resource identifier (URI) or other network address of the conversation. The contact can access the conversation by using a URI or other network address provided by the intent messaging service 402.

[0058] When responses to the intent are obtained from the brands 404 and other users 405 to which the intent is provided for response, the intent messaging service 402 can determine these responses to determine whether these responses are relevant to the intent submitted by the customer 406 and respond to it. In one embodiment, the intent messaging service 402 uses a classification algorithm or other machine learning model to classify the responses to the intent as relevant to the intent or not relevant to the intent. Responses classified as not relevant to the intent are discarded by the intent messaging service 402 and are not presented to the customer 406 through the user interface 410. However, any response classified as relevant to the intent submitted by the customer 406 can be presented to the customer 406 through the user interface 410. For example, the intent messaging service 402 can send relevant (e.g., reviewed) responses to the intent messaging application on the customer's computing device 408 so that the intent messaging application updates the conversation window associated with the intent to present the obtained responses. The customer 406 can select any of the obtained responses to the intent to initiate a conversation with the brand 404 or other user 405 that provided the selected response. The conversation may be presented within a conversation window through which the customer 406 may communicate with the brand 404 or other users 405 .

[0059] Figure 5An illustrative example of an environment in which a customer 506 introduces another user 504 or brand into an existing conversation based on a response to an intent of the customer 506 through a user interface 510 according to at least one embodiment is shown. In the environment 500, a customer 506 is presented with a reviewed response of another user 504 to an intent submitted by the customer 506 to an intent messaging service 502 through a user interface 510 of an intent messaging application operating on a computing device 508 of the customer 506. As described above, intents can be provided to select brands and other users based on one or more factors. For example, the intent of the customer 506 can be presented to the other user 504 because the other user 504 has experience responding to similar intents and / or submitting similar intents to the intent messaging service 502. In addition, the intent can be presented to the other user because the other user 504 is interested in the subject matter of the intent submitted to the intent messaging service 502. In one embodiment, the intent is presented to other users 504 as a result of a determination generated using a machine learning model, which can use the intent and brand and user profiles from various databases as input to generate an output that includes identifiers of the selected brand and user to whom the intent is to be provided.

[0060] The intent messaging service 502 can evaluate the responses of brands and other users 504 to the intent to determine whether the responses are relevant to the specific intent. For example, the intent messaging service 502 can use a classification algorithm or other machine learning model to evaluate the responses to the intent to classify each response as relevant to the intent or not relevant to the intent. Any response classified as not relevant to the intent can be discarded by the intent messaging service 502. Responses classified as relevant to the intent can be presented to the customer 506 through the user interface 510. In addition, each response can be provided for the customer 506 to invite other users 504 to participate in the conversation about the intent, thank other users 504 for their response, ignore the response from other users 504, ignore future responses from other users 504 (e.g., block other users 504), etc.

[0061] In one embodiment, the customer 506 can have a conversation with one or more of his or her contacts through the user interface 510 while waiting for a response to the intent submitted by the customer 506 to the intent messaging service 502. For example, the intent messaging application can present the customer 506 with a user interface 510 that is specific to the intent submitted by the customer 506 to the intent messaging service 502. Through the user interface 510, the customer 506 can receive relevant responses from other users 504 and brands to whom the intent messaging service 504 provided the intent. In addition, through the user interface 510, the customer 506 can invite any known contacts to participate in the conversation about the intent. For example, using the intent messaging application provided by the intent messaging service 502, the customer 506 can select one or more contacts to add to the conversation related to the intent submitted by the customer 506 to the intent messaging service 502. The one or more contacts can also be customers of the intent messaging service 502, and therefore can also use the intent messaging application to access the intent messaging service 502 and interact with the customer 506, other users 504, and brands.

[0062] In one embodiment, the customer 506 may additionally or alternatively select contacts that are not associated with the intent messaging service 502. For example, the customer 506 may select one or more contacts from a set of contacts maintained on the computing device 508. The intent messaging application may use the contact information of the selected contacts to send notifications to these selected contacts, indicating that these contacts have been invited to participate in a conversation with the customer 506 about a specific intent. The notification may include a uniform resource identifier (URI) to the intent messaging service 502 or other links from which these contacts can obtain access to the intent messaging application required for the conversation. While waiting for responses from other users 504 and brands, the customer 506 can talk to any invited contacts through the user interface 510. These contacts can also use the intent messaging application provided by the intent messaging service 502 on their respective computing devices, or through other messaging applications that can interact with the intent messaging service 502, to allow communication between the customer 506 and their contacts.

[0063] When the reviewed response to the intent is presented to the customer 506 via the user interface 510, any other participants participating in the conversation with the customer 506 and associated with the intent may also view the response. This may allow these other participants to provide their own feedback on the reviewed response. For example, Figure 5As shown, a reviewed response provided by another user 504 to the intent messaging service 502 may be presented to a participant in a conversation between the customer 506 and any selected contacts for a particular intent for presentation to the customer 506 via the user interface 510. Other participants in the conversation with the customer 506 for the particular intent may provide comments or suggestions to the customer 506 regarding the responses obtained from the other users 504.

[0064] Customer 506 can introduce other users 504 or brands that provide responses to the intent to customer 506 into an existing conversation related to the intent through user interface 510. For example, Figure 5 As shown, the response from another user 504 may be provided with the option for the client 506 to invite the other user 504 to participate in the existing conversation between the client 506 and other contacts about the intent, to thank the other user 504 for the response, to ignore the response from the other user 504, to ignore future responses from the other user 504 (e.g., to block the other user 504), etc. If the client 506 invites the other user 504 to participate in the conversation about the intent, the intent messaging application operating on the computing device 508 may send a request to the intent messaging service 502 to allow the other user 504 to interact with the client 506 and any other contacts participating in the conversation related to the intent. In response to the request, the intent messaging service 502 may send additional client information to the other user 504. The additional client information may include the client's name, address, contact information, picture, etc. In addition, the intent messaging service 502 may allow the other user 504 to interact with the client 506 and any other participants in the conversation about the intent.

[0065] Figure 6 An illustrative example of an environment 600 is shown in which a customer 606 initiates a communication channel with a brand 604 through a user interface 610 to engage in a conversation with the brand 604 about an intent according to at least one embodiment. In the environment 600, an intent messaging service 602 can provide a vetted response to an intent submitted by the customer 606 to the intent messaging service 602 through the user interface 610 of an intent messaging application operating on the customer's computing device 608. Figure 6As shown, the reviewed response may include the name of the brand 604 that submitted the response to the intent. As described above, the intent messaging service 602 may evaluate responses from brands 604 and other users to determine whether the responses are relevant to a particular intent. For example, the intent messaging service 602 may use a classification algorithm or other machine learning model to evaluate responses to the intent to classify each response as relevant to the intent or not relevant to the intent. Any response classified as not relevant to the intent may be discarded by the intent messaging service 602. Responses classified as relevant to the intent may be presented to the customer 606 via the user interface 610. In addition, each response may be provided for the customer 606 to invite the brand 604 to participate in a conversation about the intent, thank the brand 604 for its response, ignore the response from the brand 604, ignore future responses from the brand 604 (e.g., block the brand 604), etc.

[0066] Through the user interface 610, the customer 606 can invite the brand 604 to participate in a conversation with the response provided by the brand 604 to the intent submitted by the customer 606 to the intent messaging service 602. For example, through the user interface 610, the customer 606 can select an option to invite the brand 604 to participate in a conversation with the customer 606. If the customer 606 selects this option, the intent messaging application on the customer's computing device 608 can send a request to the intent messaging service 602 to initiate a communication channel between the customer 606 and the brand 604. In response to the request, the intent messaging service 602 can send additional customer information to the brand 604. The additional customer information can include the customer's name, address, contact information, pictures, etc. In addition, the intent messaging service 602 can allow the brand 604 to interact with the customer 606 through the communication channel established between the customer 606 and the brand 604.

[0067] Once the communication channel between customer 606 and brand 604 is established, customer 606 can send messages to brand 604 through user interface 610. For example, Figure 6 As shown, customer 606 may greet brand 604 in response to brand 604's vetted response and provide additional details about its intent that may be responsive to the vetted response from brand 604. This response from customer 606 may be sent to brand 604 via a communication channel established by intent messaging service 602. This may result in the response being presented to brand 604 via a user interface of an intent messaging application used by an agent or other user associated with brand 604. Brand 604 may provide additional responses that may be presented to customer 606 via user interface 610. Thus, via intent messaging service 602, customer 606 and brand 604 may communicate about a particular intent of customer 606 to potentially identify a solution to that intent.

[0068] Figure 7 An illustrative example of an environment 700 in which a customer 706 provides a response to another customer's intent through a user interface 710 according to at least one embodiment is shown. In the environment 700, the intent messaging service 702 can select the customer 706 to solicit a response to an intent submitted by another user 704 of the intent messaging service 704. As described above, in response to obtaining a request from a user, the intent messaging service 702 can extract the intent from the request and identify one or more brands and other users who may have relevant experience with the intent and may provide relevant responses to the intent. For example, the intent messaging service 702 can use a machine learning model through an intent matching system to identify one or more brands and other users to whom the intent will be provided in order to solicit a response to the intent that can be presented to the user who submitted the request. The machine learning model can use the intent and the brand and user profiles from the corresponding database as input to generate an output that includes an identifier of the selected brand and user to which the intent is to be provided.

[0069] like Figure 7 As shown, the intent messaging service 702 selects a customer 706 to obtain an intent from another user 704 in order to solicit a response to the intent from the customer 706. The intent messaging service 702 may select the customer 706 based on one or more factors. For example, the customer 706 may have previous experience with a specific intent from other users 704. As an illustrative example, if the other user 704 expresses an intent to identify a location where pet food can be ordered quickly, the intent messaging service 702 may determine that the customer 706 has previous experience in obtaining pet food from different brands or locations. This previous experience may be expressed to the intent messaging service 702 by a previous intent submitted by the customer 706 to the intent messaging service 702, by a response provided to other users 704 of the intent messaging service 702, or by other expressions provided by the customer 706 to the intent messaging service 702 (e.g., the customer has expressed an interest in pets, the customer has interacted with brands related to pets and pet care, etc.).

[0070] The intent messaging service 702 may update the user interface 710 of the intent messaging application installed on the client's computing device 708 to provide the intent of the other user 704. For example, a new dialog window including the intent of the other user may be presented to the client 706 through the user interface 710. The intent may be presented without any identifying information of the other user 704 who submitted the intent. In some cases, the intent may be provided together with other information that may be used for the client 706 to provide a response to the intent. For example, the intent may be presented together with the geographic location information of the other user 704, the time range for addressing the intent, etc. through the user interface 710. The client 706 may use the additional information to adjust its response to the intent. For example, if the intent is used to identify a location where the other user 704 can quickly obtain pet food, the intent may be provided together with the geographic location of the other user 704. The client 706 may use the additional information to identify a pet food location near a specified geographic location. Therefore, the additional information may be useful to the client 706 to allow the client 706 to prepare a relevant response to the intent.

[0071] Client 706 may submit a response to the intent via user interface 710. Figure 7 As shown, customer 706 has indicated the names of brands that other users 704 can use to handle the intent. In addition, customer 706 can provide other information that may be useful to other users 704. For example, if customer 706 decides to use a specified brand, customer 706 can indicate his or her own experience with the specified brand, which may be useful to other users 704. Through user interface 710, customer 706 can additionally provide digital images, voice recordings, video recordings, or other media that may be useful to other users 704 in response to the intent.

[0072] The intent messaging service 702 may obtain an intent response submitted by a customer 706 from a computing device 708 through a user interface 710. In response to obtaining the intent response from the customer 706, the intent messaging service 702 may evaluate the intent response to determine whether the intent response is relevant to the intent submitted by other users 704. For example, the intent messaging service 702 may use a classification algorithm or other machine learning model to classify the intent response submitted by the customer 706 as relevant or irrelevant to the intent. The classification algorithm or other machine learning model may be trained using supervised learning techniques. For example, an input intent, a known relevant response, a known irrelevant response, and a classified data set may be selected to train the classification algorithm or other machine learning model. In some examples, the input intent may be obtained from an administrator of the intent messaging service, a customer of the intent messaging service, or other sources associated with the intent messaging service. In some implementations, the known relevant responses and irrelevant responses used to train the classification algorithm or other machine learning model used by the intent processing system include responses generated by the entity that generated the sample intent.

[0073] If the intent messaging service 702 determines that the response provided by the customer 706 to the intent is relevant to the intent, the intent messaging service 702 can provide the response to the other user 704. The other user 704 can evaluate the response from the customer 706 and determine whether to further engage in a conversation with the customer 706 through the intent messaging service 702. If so, the intent messaging service 702 can update the user interface 710 of the customer 706 to provide the customer 706 with identification information of the other user 704. In addition, the intent messaging service 702 can establish a communication channel between the customer 706 and the other user 704 to allow the customer 706 to engage in a conversation with the other user 704 using their respective intent messaging applications.

[0074] Figure 8 An illustrative example of a process 800 for obtaining an intent and providing the intent to other users and brands according to at least one embodiment is shown. Process 800 can be performed by an intent messaging service, which can use an intent processing system to extract intent from a request generated by a customer, and use an intent matching system to identify one or more brands and other users to whom the intent can be provided in order to solicit responses to the intent from the one or more brands and other users. For example, in response to a request to obtain a response from a customer through an intent messaging application, the intent messaging service can obtain the customer's intent and identify brands and other users that can provide responses to the intent. The customer can use these responses to determine which brands and users to communicate with to obtain a solution to its request.

[0075] At step 802, the intent messaging service obtains a request for creating an intent. For example, using an intent messaging application provided by the intent messaging service and installed on the client's computing device, the client can generate a request to solicit one or more responses from different brands or other users within the user network of the intent messaging service. In the request, the client can specify a name for the request and provide a request associated with the provided name. The request may include an intent that can be used to identify brands and other users that may be able to provide relevant responses to the client's request. Examples of intents may include, for example, subject matter, sentiment, complexity, and urgency. Subject matter may include, but is not limited to, topics, products, services, technical issues, usage issues, complaints, refund requests, or purchase requests, etc. For example, the intent may be determined based on a semantic analysis of the message (e.g., by identifying keywords, sentence structure, repeated words, punctuation, and / or non-articles), user input (e.g., one or more categories have been selected), and / or statistical information related to the message (e.g., typing speed and / or response delay).

[0076] In response to the request from the client, the intent messaging service maintains the client's new intent at step 804. For example, the intent messaging service may extract the intent from the request, which may be used to identify brands and users that may respond to the request with relevant information or responses that may be useful to the client. In addition, the intent messaging service may associate the intent with a unique identifier that may be used to track the intent and any responses obtained to the intent. This may help the intent messaging service identify responses to the intent from various brands or users to whom the intent is to be provided, and provide relevant responses from those brands or users to the client.

[0077] At step 806, the intent messaging service determines whether additional information is needed from the customer that can be used to identify which brands and users can be selected to solicit responses to the intent. For example, the intent messaging service can evaluate the request and intent to determine whether additional information is useful for identifying a set of brands and users that can provide relevant responses to the customer's intent. The additional information can include the customer's geographic location, a time frame for resolving the request, any customer preferences for specific brands and / or users, and the like.

[0078] If the intent messaging service determines that additional information is needed to supplement the request and intent provided by the customer, then in step 808, the intent messaging service may solicit the additional information from the customer associated with the intent. For example, the intent messaging service may ask the customer various questions related to the customer's intent through the intent messaging application using natural language processing (NLP) or other artificial intelligence algorithms to solicit the additional information. For example, if the customer has submitted a request for a proposal from an interior design company, the intent messaging service may ask the customer where they live, the time frame for completing the new interior design project, the budget for the new interior design project, various aspects of the interior design project, and other questions related to the customer's interior design query. In response to these additional questions from the intent messaging service, the customer may provide additional information, which may be used to supplement the intent and identify brands and other users that may provide relevant responses to the customer's intent.

[0079] At step 810, the intent messaging service identifies brands and / or other users that are relevant to the customer's intent (e.g., may provide relevant responses) and are associated with the intent messaging service. In one embodiment, the intent messaging service uses an intent machine learning modeling engine through an intent matching system to identify one or more brands and / or other users to whom the intent is to be provided, so as to solicit responses from the one or more brands and / or other users. The intent machine learning modeling engine may use a brand database and a user database maintained by the intent matching system, and the customer's intent as inputs to a machine learning model to identify brands and / or users that may provide relevant responses to the intent. The brand database and the user database may include profiles for each of the brand and the user, respectively, which may be associated with the intent messaging service. Each profile may indicate the user's or brand's experience in responding to a particular intent or category of intent, and the user's or brand's interest in the underlying theme or classification of the intent (e.g., interior design, etc.). In addition, each profile may indicate feedback about the user's or brand's response to a previously provided intent. The feedback may specify whether the response provided in response to the intent is relevant, useful, or otherwise appreciated by the corresponding customer.

[0080] The machine learning model used by the intent machine learning modeling engine can be trained using sample intents and sample outputs corresponding to characteristics of brands and other users, which can be used to identify brands and other users to whom intents are to be provided. In addition, the machine learning model can be trained using feedback from different brands and other users that receive intents. This feedback can be used to determine whether the machine learning model is selecting brands and other users that can respond to intents with relevant responses or are otherwise associated with the characteristics of the intent. For example, if a brand that provides interior design services obtains intents that are not related to interior design, the brand can provide feedback indicating that the intent provided is not relevant to the brand. This feedback can be used to further train the machine learning model used by the intent matching system.

[0081] At step 812, based on the output generated by the intent machine learning modeling engine, the intent messaging service suggests other users and / or brands from which to solicit responses to the customer's intent. For example, the intent messaging service may provide, via the intent messaging application, a list of brands and / or other users identified by the intent machine learning modeling engine as likely to provide relevant responses to the customer's intent. Using the intent messaging application, the customer may select a subset of other users and brands to whom the customer's intent is to be provided to solicit responses.

[0082] Based on the customer's selection, in step 814, the intent messaging service sends the customer's intent to other users and / or brands selected by the customer. In one embodiment, if the customer does not select a brand and / or user to whom to provide his intent, the intent messaging service may, by default, send the customer's intent to other users and / or brands identified by the intent machine learning modeling engine. In some cases, the intent messaging service may select a subset of other users and / or brands by default based on a relevance threshold. For example, each brand and other user may be scored based on the likelihood that each brand and other user will provide a relevant response to the customer's intent. The score may be calculated by the intent machine learning modeling engine based on the brand's or user's historical interest in the subject of the customer's intent, the brand's or user's historical experience in responding to similar intents, and the like.

[0083] Fig. 9An illustrative example of a process 900 for evaluating proposed responses from brands and other users to identify relevant responses that can be presented to a customer in response to an intent is shown in accordance with at least one embodiment. Process 900 can be performed by an intent messaging service, which can use an intent processing system to evaluate responses to an intent from different brands and users to which an intent is presented to determine whether the responses are relevant to the intent and can be presented to the customer. In one embodiment, the intent processing system implements a machine learning model that is used to evaluate responses from different brands and users to identify a subset of responses that can be presented to the customer in response to the customer's intent.

[0084] In step 902, the intent processing system obtains one or more proposed responses to the customer intent from the brand and other users to which the customer intent is provided for response. As described above, the intent matching system of the intent matching service can identify one or more brands and other users that can provide relevant responses to the customer intent submitted by the customer of the intent messaging service. For example, the intent matching system can query the brand database and the user database to respectively identify brands and users that may be interested in the intent, have experience in responding to similar intents, or may otherwise provide relevant responses to the intent. In one embodiment, the intent matching system uses a machine learning model to identify brands and other users that may provide relevant responses to the customer intent. The machine learning model can be trained using sample intents and sample outputs corresponding to the characteristics of the brand and other users, which can be used to identify brands and other users to whom the intent is to be provided. In addition, the machine learning model can be trained using feedback from different brands and other users who receive the intent. The feedback can be used to determine whether the machine learning model is selecting brands and other users that can respond to the intent with a relevant response or are otherwise associated with the characteristics of the intent. For example, if a brand that provides interior design services obtains an intent that is not related to interior design, the brand can provide feedback indicating that the provided intent is not relevant to the brand. This feedback can be used to further train the machine learning model used by the intent matching system.

[0085] In step 904, the intent processing system evaluates responses to proposals provided by one or more brands and other users to determine the relevance of the proposed responses to the customer intent. For example, the intent processing system may use a classification algorithm or other machine learning model to evaluate the responses and classify the responses as relevant to the intent or irrelevant to the intent. The classification algorithm or other machine learning model may be trained using supervised learning techniques. For example, an input intent, known relevant responses, known irrelevant responses, and a classified data set may be selected to train the classification algorithm or other machine learning model. In some examples, the input intent may be obtained from an administrator of the intent messaging service, a customer of the intent messaging service, or other source associated with the intent messaging service. In some implementations, the known relevant responses and irrelevant responses used to train the classification algorithm or other machine learning model used by the intent processing system include responses generated by the entity that generated the sample intent.

[0086] In some examples, the resulting classifications of known relevant responses and irrelevant responses to sample intents are evaluated to determine failures or errors that can be used to train a classification algorithm or other machine learning model. For example, if a classification algorithm or other machine learning model classifies a relevant response to a sample intent as an irrelevant response or classifies an irrelevant response to a sample intent as a relevant response, the parameters of the classification algorithm or other machine learning model can be adjusted based on the failures resulting from the misclassification of the response to the sample intent. These parameters may include weights and biases of the classification algorithm or other machine learning model used by the intent processing system.

[0087] In one embodiment, a classification algorithm or other machine learning model is also trained to identify characteristics or other features of a response, as well as characteristics or other features of the intent for which the response was generated. These characteristics or features can be used to classify the response as being relevant or irrelevant to the intent. For example, if the intent includes one or more characteristics corresponding to an interior design request, the classification algorithm or other machine learning model can evaluate the response to determine whether the response includes one or more characteristics that also correspond to an interior design. Based on the similarity between these characteristics, the classification algorithm or other machine learning model can determine a relevance score, which can correspond to a relevant response if the relevance score exceeds a relevance threshold. Therefore, using a classification algorithm or other machine learning model, the intent processing system can evaluate responses and classify responses as being relevant or irrelevant to a particular intent.

[0088] In step 906, the intent processing system discards any responses from brands and other users that are not related to the customer's intent. As described above, the intent processing system can use a classification algorithm or other machine learning model to classify each response obtained from a brand or other user for a specific intent. If the classification algorithm or other machine learning model determines that the response does not meet the relevance threshold, the classification algorithm or other machine learning model can classify the response as being irrelevant to the intent. Therefore, the intent processing system can obtain any responses classified as being irrelevant to the customer's intent and discard these responses. In one embodiment, if a brand or other user is identified as having provided an irrelevant response, the intent processing system can provide information about the brand or other user and the customer intent for which the brand or other user is determined to have provided an irrelevant response to the intent matching system. The intent matching system can use this information to further train its machine learning model, which is used to identify brands and other users that can be selected to solicit responses to specific intents. This can result in brands or other users that provide irrelevant responses being less likely to be selected by the intent matching system to provide responses to intents similar to the customer's intent (for which the brand or other user provided an irrelevant response).

[0089] At step 908, the intent processing system provides the customer with relevant responses obtained from one or more brands and other users to allow the customer to interact with these brands and other customers through the intent messaging application. For example, the intent processing system can send relevant responses to the intent messaging application, which can cause the intent messaging application to update the GUI to present available responses to the customer through the customer's computing device. Through the GUI, the customer can determine whether to initiate a conversation with the brand or other user that provides the relevant response. If the customer does not want to initiate a conversation with the brand or other user that provides a response that is considered relevant by the intent processing system, the customer can send a notification to the brand or other user through the intent messaging service to thank the brand or other user for the response. Additionally or alternatively, the customer can submit feedback on the obtained response. For example, the customer can indicate whether the provided response is relevant to the intent submitted by the customer. The intent processing system can use the feedback to further train a classification algorithm or other machine learning model for identifying relevant responses to a given intent. If the customer chooses to initiate a conversation with a brand or other user, the intent messaging service can open a communication channel between the customer and a specific brand or other user. This allows the brand or other user to interact with the customer through the communication channel.

[0090] Fig.10A computing system architecture 1000 is shown according to some implementations, which includes various components that communicate electrically with each other using a connection 1006 such as a bus. The example system architecture 1000 includes a processing unit (CPU or processor) 1004 and a system connection 1006 that couples various system components including a system memory 1020 (e.g., ROM 1018 and RAM 1016) to the processor 1004. The system architecture 1000 may include a cache 1002 of high-speed memory that is directly connected to the processor 1004, in close proximity to the processor 1004, or integrated as part of the processor 1004. The system architecture 1000 may copy data from the memory 1020 and / or storage device 1008 to the cache 1002 for quick access by the processor 1004. In this way, the cache can provide a performance boost, avoiding delays in the processor 1004 while waiting for data. These and other modules may control or be configured to control the processor 1004 to perform various actions.

[0091] Other system memories 1020 may also be used. Memory 1020 may include a number of different types of memory with different performance characteristics. Processor 1004 may include any general purpose processor and hardware or software services, such as service 1 1010, service 2 1012, and service 3 1014 stored in storage device 1008, which are configured to control processor 1004, as well as special purpose processors where software instructions are incorporated into the actual processor design. Processor 1004 may be a completely independent computing system containing multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0092] To enable a user to interact with the computing system architecture 1000, the input device 1022 may represent any number of input mechanisms, such as a microphone for speech, a touch-sensitive screen for gesture or graphic input, a keyboard, a mouse, motion input, speech, and the like. The output device 1024 may also be one or more of a variety of output mechanisms known to those skilled in the art. In some cases, a multimodal system may enable a user to provide multiple types of input to communicate with the computing system architecture 1000. The communication interface 1026 may manage and control user input and system output in general. There is no limitation on operation on any particular hardware arrangement, so as hardware or firmware arrangements evolve, the basic features herein may be easily replaced with improved hardware or firmware arrangements.

[0093] The storage device 1008 is a non-volatile memory and may be a hard disk or other type of computer-readable medium that can store data accessible by a computer, such as a magnetic tape cartridge, a flash memory card, a solid-state memory device, a digital versatile disk, a cassette, RAM 1016, ROM 1018, and a mixture thereof.

[0094] The storage device 1008 may include services 1010, 1012, 1014 for controlling the processor 1004. Other hardware or software modules are contemplated. The storage device 1008 may be connected to the system connection 1006. In one aspect, a hardware module that performs a particular function may include a software component stored in a computer-readable medium connected to the required hardware components to perform the function, such as the processor 1004, the connection 1006, the output device 1024, etc.

[0095] The disclosed method can be performed using a computing system. An example computing system may include a processor (e.g., a central processing unit), a memory, a non-volatile memory, and an interface device. The memory may store data and / or one or more code sets, software, scripts, etc. The components of the computer system may be connected together via a bus or by some other known or convenient device. The processor may be configured to perform all or part of the methods described herein, for example, by executing a code stored in the memory. One or more of a user device or computer, a provider server or system, or a suspension database update system may include components of a computing system or a variant of such a system.

[0096] The present invention contemplates computer systems in any suitable physical form, including but not limited to point of sale systems ("POS"). By way of example and not limitation, the computer system may be an embedded computer system, a system on a chip (SOC), a single board computer system (SBC) (such as, for example, a computer on module (COM) or a system on module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive self-service terminal (kiosk), a mainframe, a computer system grid, a mobile phone, a personal digital assistant (PDA), a server, or a combination of two or more of the above. Where appropriate, the computer system may: include one or more computer systems; be unified or distributed; span multiple locations; span multiple machines; and / 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 may perform one or more steps of one or more methods described or shown herein substantially without spatial or temporal limitations. By way of example and not limitation, one or more computer systems may perform one or more steps of one or more methods described or shown herein in real time or in batch mode. Where appropriate, one or more computer systems may perform one or more steps of one or more methods described or shown herein at different times or at different locations.

[0097] The processor may be, for example, a conventional microprocessor such as an Intel Pentium microprocessor or a Motorola Power PC microprocessor. Those skilled in the relevant art will recognize that the term "machine-readable (storage) medium" or "computer-readable (storage) medium" includes any type of device accessible by a processor.

[0098] The memory may be coupled to the processor via, for example, a bus. By way of example and not limitation, the memory may include random access memory (RAM), such as dynamic RAM (DRAM) and static RAM (SRAM). The memory may be local, remote, or distributed.

[0099] The bus can also couple the processor to nonvolatile memory and drive units. Nonvolatile memory is typically a magnetic floppy or hard disk, a magneto-optical disk, an optical disk, a read-only memory (ROM) (such as a CD-ROM, EPROM, or EEPROM), a magnetic or optical card, or another form of storage device for large amounts of data. Some of this data is typically written to the memory by a direct memory access process during software execution in the computer. The nonvolatile storage device can be local, remote, or distributed. Nonvolatile memory is optional because a system can be created using all applicable data available in the memory. A typical computer system will typically include at least a processor, a memory, and a device (e.g., a bus) that couples the memory to the processor.

[0100] The software can be stored in a non-volatile memory and / or a drive unit. In fact, for large programs, the entire program may not even be stored in a memory. However, it should be understood that for the software to be run, if necessary, it can be moved to a computer-readable location suitable for processing, and for illustrative purposes, this location is referred to as a memory in this article. Even when the software is moved to the memory for execution, the processor can use hardware registers to store the values ​​associated with the software and use a local cache that is ideally used to accelerate execution. As used herein, when a software program is referred to as "implemented in a computer-readable medium", the software program is assumed to be stored in any known or convenient location (from a non-volatile storage device to a hardware register). When at least one value associated with a program is stored in a register that can be read by a processor, the processor is considered to be "configured to execute a program".

[0101] The bus can also connect the processor to a network interface device. The interface can include one or more of a modem or a network interface. It can be understood that a modem or a network interface can be considered as part of a computer system. The interface can include an analog modem, an integrated services digital network (ISDN) modem, a cable modem, a token ring interface, a satellite transmission interface (e.g., "direct PC"), or other interfaces for connecting a computer system to other computer systems. The interface can include one or more input and / or output (I / O) devices. By way of example and not limitation, the I / O device can include a keyboard, a mouse or other pointing device, a disk drive, a printer, a scanner, and other input and / or output devices (including a display device). By way of example and not limitation, the display device can include a cathode ray tube (CRT), a liquid crystal display (LCD), or some other applicable known or convenient display device.

[0102] In operation, a computer system may be controlled by operating system software that includes a file management system, such as a disk operating system. An example of operating system software with associated file management system software is the Microsoft Windows operating system from Microsoft Corporation of Redmond, Washington, known as Microsoft Windows. Another example of operating system software with its associated file management system software is Linux TM An operating system and its associated file management system. The file management system may be stored in the non-volatile memory and / or the drive unit and may cause the processor to perform various actions required by the operating system to input and output data and store data in the memory, including storing files on the non-volatile memory and / or the drive unit.

[0103] Some parts of the specific embodiments can be presented in terms of algorithms and symbolic representations of the operations on the data bits in the computer memory. These algorithmic descriptions and representations are the means used by those skilled in the art of data processing to most effectively convey the essence of their work to other technicians in the field. Algorithms are here and are generally conceived as self-consistent sequences of operations that lead to desired results. Operations are those that require physical manipulation of physical quantities. Usually, although not necessarily, these physical quantities take the form of electrical or magnetic signals that can be stored, transferred, combined, compared, and otherwise manipulated. It has been confirmed that it is sometimes convenient to refer to these signals as bits, values, elements, symbols, characters, items, numbers, etc., mainly for commonly used reasons.

[0104] It should be remembered, however, that all of these terms and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless expressly stated in a manner significantly different from the following discussion, it should be understood that throughout the specification, discussions using terms such as "processing" or "computing" or "calculating" or "determining" or "displaying" or "generating" refer to the actions and processes of a computer system or similar electronic computing device that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system's memories or registers or other such information storage, transmission or display devices.

[0105] The algorithms and displays presented herein are not inherently related to any particular computer or other device. Various general purpose systems can be used together with the programs taught herein, or it can be confirmed that it is convenient to build more specialized devices to perform some of the examples. According to the following description, the required structure for various of these systems will appear. In addition, the technology is not described with reference to any specific programming language, so various examples can be implemented using various programming languages.

[0106] In various implementations, the system can operate as a standalone device or can be connected (e.g., networked) to other systems. In a networked deployment, the system can operate as a server or client system in a client-server network environment, or as a peer system in a peer-to-peer (or distributed) network environment.

[0107] The system may be a server computer, a client computer, a personal computer (PC), a tablet PC, a laptop computer, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, an iPhone, a Blackberry, a processor, a phone, a network device, a network router, a switch or bridge, or any system capable of executing a set of instructions (sequentially or otherwise) that specify actions to be taken by the system.

[0108] Although the machine-readable medium or machine-readable storage medium is shown as a single medium as an example, the terms "machine-readable medium" and "machine-readable storage medium" should be understood to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) storing one or more sets of instructions. The terms "machine-readable medium" and "machine-readable storage medium" should also be understood to include any medium that can store, encode, or carry a set of instructions for execution by a system and cause the system to perform any one or more methods or modules disclosed herein.

[0109] Typically, the routines executed to implement the implementation of the present invention may be implemented as part of an operating system or a dedicated application, component, program, object, module, or sequence of instructions referred to as a "computer program." A computer program typically includes one or more instructions that are placed in various memories and storage devices in a computer at different times, and when the instructions are read and executed by one or more processing units or processors in the computer, cause the computer to operate to perform elements related to various aspects of the present invention.

[0110] Furthermore, although the examples have been described in the context of fully functional computers and computer systems, those skilled in the art will appreciate that the various examples can be distributed as program objects in a variety of forms and that the present invention is equally applicable regardless of the specific type of machine or computer readable media actually used to implement the distribution.

[0111] Other examples of machine-readable storage media, machine-readable media, or computer-readable (storage) media include, but are not limited to: recordable-type media, such as volatile and non-volatile memory devices, floppy disks and other removable disks, hard drives, optical disks (e.g., compact disk read-only memory (CD ROM), digital versatile disk (DVD), etc.), etc.; and transmission-type media, such as digital and analog communication links.

[0112] In some cases, the operation of a memory device (such as a change of state from binary 1 to binary 0 or vice versa) may include, for example, a transformation (such as a physical transformation). With certain types of memory devices, such physical transformations may include a physical transformation of an item to a different state or thing. For example, but not by way of limitation, for certain types of memory devices, the change of state may involve the accumulation and storage of charge or the release of stored charge. Similarly, in other memory devices, the change of state may include a physical change or transformation of magnetic orientation or a physical change or transformation of molecular structure, such as from crystalline to amorphous or vice versa. The foregoing is not intended to be an exhaustive list of all examples in which a change of state from binary 1 to binary 0 (or vice versa) in a memory device may include a transformation (such as a physical transformation). Rather, the foregoing is intended as an illustrative example.

[0113] Storage media may generally be or may include non-transitory devices. In this case, non-transitory storage media may include tangible devices, meaning that the device has a specific physical form, but the physical state of the device may change. Thus, for example, non-transitory refers to a device that remains tangible despite changes in state.

[0114] The above description and accompanying drawings are illustrative and should not be construed as limiting the subject matter to the exact form disclosed. It will be appreciated by those skilled in the relevant art that many modifications and variations are possible in view of the above disclosure. Many specific details are described to provide a thorough understanding of the present invention. However, in some cases, well-known or conventional details are not described to avoid obscuring the description.

[0115] As used herein, the term "connection", "coupling", or any variation thereof, when applied to a module of a system, means any connection or coupling between two or more elements, directly or indirectly; the coupling or coupling between elements may be physical, logical, or any combination thereof. In addition, the words "herein", "above", "below", and words of similar meaning, when used in this application, should refer to the application as a whole, rather than any particular part of the application. When the context permits, the words used in the singular or plural in the above specific implementation section may also include the plural or singular, respectively. In a list of two or more items, the word "or" covers all the following interpretations of the word: any one of the items in the list, all the items in the list, or any combination of the items in the list.

[0116] Those skilled in the art will appreciate that the disclosed subject matter may be implemented in other forms and manners not shown below. It should be understood that the use of relational terms (if any, such as first, second, top and bottom, etc.) is only used to distinguish one entity or action from another entity or action, and does not necessarily require or imply any such actual relationship or order between these entities or actions.

[0117] Although the process or square frame is presented in a given order, alternative implementations can perform routines with steps in different orders or adopt systems with square frames in different orders, and some processes or square frames can be deleted, moved, added, subdivided, replaced, combined and / or modified to provide alternative combinations or sub-combinations. Each of these processes or square frames can be implemented in various different ways. In addition, although the process or square frame is sometimes shown as serial execution, these processes or square frames can also be executed in parallel or can be executed at different times. In addition, any specific numbers mentioned herein are only examples: alternative implementations can adopt different values ​​or ranges.

[0118] The teachings of the invention provided herein may be applied to other systems, not necessarily the system described above.The elements and actions of the various examples described above may be combined to provide further examples.

[0119] Any patents and applications and other references mentioned above (including any references that may be listed in the attached submission documents) are incorporated herein by reference. If necessary, aspects of the present invention can be modified to adopt the systems, functions and concepts of the above-mentioned various references to provide other further examples of the present invention.

[0120] These and other changes can be made to the present invention according to the above specific embodiments. Although the above description describes specific examples, and describes the expected best mode, no matter how detailed the text of the above content is presented, teaching can be practiced in many ways. The details of the system can be changed considerably in its implementation details, but are still included by the subject matter disclosed herein. As mentioned above, the specific terms used when describing certain features or aspects of the present invention should not be regarded as implying that the term is redefined in this article to limit to any specific characteristics, features or aspects of the present invention associated with the term. Generally, the terms used in the attached claims should not be interpreted as limiting the present invention to the specific implementation disclosed in the specification, unless the above specific implementation part clearly defines these terms. Therefore, the actual scope of the present invention not only includes the disclosed implementation, but also includes all equivalents of practicing or realizing the present invention according to the claims.

[0121] Although certain aspects of the invention are presented in certain claim forms, the inventors contemplate the various aspects of the invention in any number of claim forms. Any claim intended to be addressed under 35 U.S.C. §112(f) will begin with the phrase "for . . . ." Accordingly, the applicants reserve the right to add additional claims after filing this application to pursue such additional claim forms for other aspects of the invention.

[0122] Within the context of the present invention, the terms used in this specification generally have their ordinary meaning in the art and in the specific context in which each term is used. Specific terms used to describe the present invention are discussed above or elsewhere in the specification to provide practitioners with additional guidance on the description of the present invention. For convenience, certain terms may be highlighted, for example, using capitalization, italics, and / or quotation marks. The use of highlighting will not have any effect on the scope and meaning of the terms; in the same context, whether or not a term is highlighted, the scope and meaning of the term are the same. It can be understood that the same element can be described in more than one way.

[0123] Therefore, any one or more of the terms discussed herein may use alternative language and synonyms, but no special meaning is given to the terms based on whether they are exhaustively or discussed herein. Synonyms for certain terms are provided. The recording of one or more synonyms does not exclude the use of other synonyms. Examples used anywhere in this specification including examples of any term discussed herein are merely illustrative and are not intended to further limit the scope and meaning of the present invention or any exemplary term. Similarly, the present invention is not limited to the individual examples given in this specification.

[0124] The following provides examples of equipment, devices, methods and related results according to the examples of the present invention, but it is not intended to further limit the scope of the present invention. It should be noted that, for the convenience of the reader, titles or subtitles can be used in the examples, but the scope of the present invention is not limited in any way. Unless otherwise defined, all technical terms and scientific terms used herein have the same meaning as those of ordinary skill in the art to which the present invention belongs. In the event of a conflict, the present invention will be determined by including the definition herein.

[0125] Some parts of this specification sheet describe examples of algorithms and symbolic representations that operate on information. These algorithmic descriptions and representations are usually used by technical personnel in the field of data processing to effectively convey their work essence to other technical personnel in the field. When these operations are described functionally, computationally, or logically, these operations are understood to be implemented by computer programs or equivalent circuits, microcodes, etc. In addition, it has also been confirmed that it is sometimes convenient to refer to the arrangement of these operations as modules without losing versatility. The described operations and their associated modules can be embodied in software, firmware, hardware, or any combination thereof.

[0126] Any steps, operations, or processes described herein may be performed or implemented using one or more hardware or software modules alone or in combination with other devices. In some examples, the software modules are implemented using a computer program object including a computer-readable medium containing computer program code that can be executed by a computer processor to perform any or all of the steps, operations, or processes described.

[0127] Examples may also relate to apparatus for performing the operations described herein. The apparatus may be specially constructed for the desired purpose, and / or the apparatus may include a general-purpose computing device selectively activated or reconfigured by a computer program stored in a computer. Such a computer program may be stored in a non-transitory, tangible computer-readable storage medium or any type of medium suitable for storing electronic instructions, which may be connected to a computer system bus. In addition, any computing system mentioned in this specification may include a single processor or may be an architecture that uses a multi-processor design to increase computing power.

[0128] Examples may also relate to objects formed by the computing processes described herein. The objects may include information generated by the computing processes, where the information is stored on a non-transitory, tangible computer-readable storage medium and may include any implementation of a computer program object or other data combination described herein.

[0129] The language used in this specification has been selected primarily for readability and instructional purposes, and not to describe or constrain the subject matter. Therefore, it is not intended that the scope of the invention be limited by the detailed description, but rather by any claims issued based on this application. Therefore, the disclosure of the examples is intended to be illustrative, not limiting, of the scope of the subject matter, which is set forth in the appended claims.

[0130] Specific details are given in the above description to provide a thorough understanding of various implementations of systems and components for contextual connection systems. However, it should be understood by those of ordinary skill in the art that the above implementations can be practiced without these specific details. For example, circuits, systems, networks, processes, and other components can be shown as components in block diagram form to avoid obscuring the implementation in unnecessary details. In other cases, well-known circuits, processes, algorithms, structures, and techniques can be shown without unnecessary details to avoid obscuring the implementation.

[0131] In addition, it should be noted that various implementations can be described as processes, which are depicted as flow charts, job diagrams, data flow diagrams, structure diagrams, or block diagrams. Although flow charts can describe operations as sequential processes, many operations can be performed in parallel or simultaneously. In addition, the order of operations can be rearranged. When the operations of a process are completed, the process will terminate, but may have additional steps not included in the figure. A process can correspond to a method, function, program, subroutine, subprogram, etc. When a process corresponds to a function, its termination may correspond to the function returning to the calling function or main function.

[0132] Client devices, network devices, and other devices can be computing systems that include one or more integrated circuits, input devices, output devices, data storage devices, and / or network interfaces, etc. The integrated circuit may include, for example, one or more processors, volatile memory, and / or non-volatile memory, etc. The input device may include, for example, a keyboard, a mouse, a keypad, a touch interface, a microphone, a camera, and / or other types of input devices. The output device may include, for example, a display screen, a speaker, a tactile feedback system, a printer, and / or other types of output devices. Data storage devices such as hard drives or flash memory may enable computing devices to store data temporarily or permanently. Network interfaces such as wireless or wired interfaces may enable computing devices to communicate with a network. Examples of computing devices include desktop computers, laptop computers, server computers, handheld computers, tablet computers, smart phones, personal digital assistants, digital home assistants, and machines and devices that have been incorporated into computing devices.

[0133] The term "computer-readable medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other media capable of storing, containing, or carrying (one or more) instructions and / or data. Computer-readable media may include non-transitory media in which data may be stored, and does not include carrier waves and / or temporary electrical signals propagated wirelessly or via a wired connection. Examples of non-transitory media may include, but are not limited to, disks or tapes, optical storage media such as compact disks (CDs) or digital versatile disks (DVDs), flash memory, memory, or memory devices. Computer-readable media may have codes and / or machine-executable instructions stored thereon, which may represent any combination of processes, functions, subroutines, programs, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. A code segment may be associated with another code segment or hardware circuit by passing and / or receiving information, data, independent variables, parameters, or storage content. Information, independent variables, parameters, data, etc. may be delivered, forwarded, or transmitted by any appropriate means including memory sharing, message passing, token passing, network transmission, etc.

[0134] The various examples discussed above may also be implemented by hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. When implemented in software, firmware, middleware, or microcode, the program code or code segments (e.g., computer program products) that perform the necessary tasks may be stored in a computer-readable or machine-readable storage medium (e.g., a medium for storing program code or code segments). The processor(s) implemented in an integrated circuit may perform the necessary tasks.

[0135] When a component is described as being “configured to” perform certain operations, such configuration may be accomplished, for example, by designing an electronic circuit or other hardware to perform the operation, by programming a programmable electronic circuit (e.g., a microprocessor, or other suitable electronic circuit) to perform the operation, or any combination thereof.

[0136] The various illustrative logic blocks, modules, circuits and algorithmic steps described in conjunction with the implementation disclosed herein can be implemented as electronic hardware, computer software, firmware or a combination thereof. In order to clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been generally described above in terms of their functions. Whether this function is implemented as hardware or software depends on specific applications and the design constraints to the entire system. The technician can implement the described functions in different ways for each specific application, but this implementation decision should not be interpreted as causing deviations from the scope of the present invention.

[0137] The technology described herein can also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such technology can be implemented in any of a variety of devices, such as a general-purpose computer, a wireless communication device mobile phone, or an integrated circuit device with multiple uses, including applications in wireless communication devices and other devices. Any features described as modules or components can be implemented together in an integrated logic device, or implemented separately as a discrete but interoperable logic device. If implemented in software, the technology can be implemented at least in part by a computer-readable data storage medium including a program code, the program code including instructions, which, when executed, execute one or more of the above methods. The computer-readable data storage medium can form a part of a computer program product, which can include packaging materials. The computer-readable medium can include a memory or a data storage medium, such as a random access memory (RAM) (e.g., a synchronous dynamic random access memory (SDRAM)), a read-only memory (ROM), a non-volatile random access memory (NVRAM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic or optical data storage medium, etc. Additionally or alternatively, these techniques may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and which can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.

[0138] The program code can be executed by a processor, which may include one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Such a processor can be configured to perform any of the techniques described in the present invention. A general-purpose processor can be a microprocessor; however, in an alternative, the processor can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP core, or any other such configuration. Therefore, the term "processor" used herein may refer to any of the aforementioned structures, any combination of the aforementioned structures, or any other structure or device suitable for implementing the techniques described herein. In addition, in some aspects, the functions described herein may be provided in a dedicated software module or hardware module configured to implement a system for pausing database updates.

[0139] The foregoing detailed description of the technology has been presented for purposes of illustration and description. This detailed description is not exhaustive, nor is it intended to limit the technology to the exact form disclosed. Many modifications and variations are possible in light of the above teachings. The described embodiments were selected in order to best explain the principles of the technology, its practical application, and to enable others skilled in the art to utilize the technology in various embodiments and with various modifications suitable for the particular use contemplated. It is intended that the scope of the technology be defined by the claims.

Claims

1. A computer-implemented method comprising: obtaining an intent, wherein the intent corresponds to a request to be processed and the intent is associated with a client; identifying one or more users to be provided with the intent, wherein the one or more users are identified based on a set of characteristics of the intent; providing the intent, wherein the intent is provided to the one or more users to solicit a response to the intent; obtaining a set of responses to the intent; sending an instruction, wherein when the instruction is received at an application implemented by the one or more users, the application prohibits the creation of a new response; evaluating the set of responses to identify relevant responses to the intent, wherein irrelevant responses in the set of responses are discarded; and The relevant response is provided such that the relevant response is presented to the client in response to the intent.

2. The computer-implemented method of claim 1 , further comprising: receiving another request to initiate a communication channel with a user, wherein the another request is associated with the intent and a response of the user to the intent; and The communication channel is established to allow the user to send a communication responsive to the intent through the communication channel.

3. The computer-implemented method of claim 1, wherein: The set of responses is evaluated using a classification model, wherein the classification model is trained using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.

4. The computer-implemented method of claim 1, wherein: The one or more users are identified using a machine learning model, wherein the machine learning model is trained using sample intents and sample outputs corresponding to characteristics of the one or more users.

5. The computer-implemented method of claim 1 , further comprising using natural language processing to solicit information associated with the intent, wherein: The information associated with the intent is used to extract the intent from the request.

6. The computer-implemented method of claim 1, wherein: The intent is extracted from the request based on a semantic analysis of the request.

7. The computer-implemented method of claim 1, wherein: The set of characteristics of the intent is obtained in response to a query for additional information associated with the intent.

8. A system comprising: one or more processors; as well as a memory storing instructions that, when executed by the one or more processors, cause the system to: obtaining an intent, wherein the intent corresponds to a request to be processed and the intent is associated with a client; identifying one or more users to be provided with the intent, wherein the one or more users are identified based on a set of characteristics of the intent; providing the intent, wherein the intent is provided to the one or more users to solicit a response to the intent; obtaining a set of responses to the intent; sending an instruction, wherein when the instruction is received at an application implemented by the one or more users, the application prohibits the creation of a new response; evaluating the set of responses to identify relevant responses to the intent, wherein irrelevant responses in the set of responses are discarded; and The relevant response is provided such that the relevant response is presented to the client in response to the intent.

9. The system of claim 8, wherein: The relevant responses are identified using a classification model, wherein the classification model is trained using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.

10. The system of claim 8, wherein: The set of characteristics of the intent is obtained in response to a query for additional information associated with the intent.

11. The system of claim 8, wherein: The instructions also cause the system to: obtaining another request to establish a communication channel between the first computing system of the client and the second computing system of the user, wherein the another request is obtained in response to determining that a response from the user satisfies the intent; and The communication channel is established in response to the other request.

12. The system of claim 8, wherein: The one or more users are identified using a machine learning model, wherein the machine learning model is trained using sample intents and sample outputs corresponding to characteristics of the one or more users.

13. The system of claim 8, wherein: The instructions further cause the system to solicit information associated with the intent using natural language processing, wherein the information associated with the intent is used to extract the intent from the request.

14. The system of claim 8, wherein: The instructions also cause the system to perform a semantic analysis of the request to extract the intent from the request.

15. A non-transitory computer-readable storage medium having executable instructions stored thereon, wherein the executable instructions, when executed by one or more processors of a computer system, cause the computer system to: Get the intent, where The intent corresponds to a request to be processed, and the intent is associated with a client; identifying one or more users to be provided with the intent, wherein the one or more users are identified based on a set of characteristics of the intent; providing the intent, wherein the intent is provided to the one or more users to solicit a response to the intent; obtaining a set of responses to the intent; sending an instruction, wherein when the instruction is received at an application implemented by the one or more users, the application prohibits the creation of a new response; evaluating the set of responses to identify relevant responses to the intent, wherein irrelevant responses in the set of responses are discarded; and The relevant response is provided such that the relevant response is presented to the client in response to the intent.

16. The non-transitory computer-readable storage medium of claim 15, wherein: The executable instructions further cause the computer system to: obtaining another request to establish a communication channel between a first computing device of the client and a second computing device of a user providing an associated response; as well as The communication channel is established between the first computing device of the customer and the second computing device of the user, so that the customer and the user interact with each other regarding the intent through the communication channel.

17. The non-transitory computer-readable storage medium of claim 15, wherein: The executable instructions further cause the computer system to perform a semantic analysis of the request to obtain the intent.

18. The non-transitory computer-readable storage medium of claim 15, wherein: The one or more users are identified using a machine learning model, wherein the machine learning model is trained using sample intents and sample outputs corresponding to characteristics of the one or more users.

19. The non-transitory computer-readable storage medium of claim 15, wherein: The executable instructions also cause the computer system to evaluate the set of responses using a classification model, wherein the classification model is trained using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.

20. The non-transitory computer-readable storage medium of claim 15, wherein: The set of characteristics of the intent is obtained in response to a query for additional information associated with the intent.

21. The non-transitory computer-readable storage medium of claim 15, wherein: The executable instructions further cause the computer system to solicit information associated with the intent using natural language processing, wherein the information associated with the intent is used to extract the intent from the request.

Images