Bot Monitoring
Patent Information
- Application Number
- JP2023516792
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2020-09-15
- Filing Date
- 2021-09-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2041-09-15
Smart Images

Figure 0007581496000001 
Figure 0007581496000002 
Figure 0007581496000003
Abstract
Description
[Technical field]
[0001]
[0001] This patent application claims the benefit of priority to U.S. Provisional Patent Application No. 63 / 078,718, entitled "Bot Monitoring," filed September 15, 2020, the disclosure of which is incorporated herein by reference.
[0002]
[0002] The present disclosure relates generally to bot operation and training, and more specifically, techniques are provided for monitoring bot operation and training. [Background technology]
[0003]
[0003] Currently available bots can operate from models. Although the models can be updated over time, bot errors, failures, or other operational failures may nevertheless occur. Thus, businesses may employ human agents to take over from such bot failures in order to meet customer needs and expectations. However, requiring human agents to take over various tasks may be very time consuming, and bots may continue to fail until at some point the models are updated. Thus, there is a need in the art for improved methods and systems for monitoring bot operation and training. Summary of the Invention
[0004]
[0004] The term "embodiment" and similar terms are intended to broadly refer to all of the subject matter of this disclosure and the following claims. Statements containing these terms should be understood not to limit the subject matter described herein or to limit the meaning or scope of the following claims. The embodiments of the disclosure encompassed herein are defined by the following claims, not this summary. This summary is a high-level overview of various aspects of the disclosure and introduces some of the concepts that are further described in the Detailed Description section below. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used separately to determine the scope of the claimed subject matter. The subject matter should be understood by reference to the entire specification of this disclosure, any or all drawings, and appropriate portions of each claim. Certain embodiments of the disclosure include computer-implemented methods. The method may include storing in a memory a set of monitoring criteria including a threshold level of confidence, monitoring one or more messages in a conversation between the bot and a user of the client device, detecting that a bot prediction associated with the conversation does not meet the threshold level of confidence, requesting input from an agent device providing classification input regarding the conversation, routing the conversation to one or more endpoint devices according to the classification input, updating a learning model based on the classification input, and providing for use of the updated learning model by the bot to make a next bot prediction.
[0005] Certain embodiments of the present disclosure include a system that may include one or more data processors and a non-transitory computer-readable storage medium that includes instructions that, when executed on the one or more data processors, cause the one or more data processors to perform the methods described above and herein.
[0006]
[0006] Certain embodiments of the present disclosure include a computer program product tangibly embodied in a non-transitory machine-readable storage medium, comprising instructions configured to cause a data processing apparatus to perform the methods described above and herein. [Brief description of the drawings]
[0007]
[0007] The present disclosure is described in conjunction with the accompanying drawings. [Figure 1]
[0008] FIG. 1 shows a block diagram of one embodiment of a network interaction system. [Diagram 2]
[0009] FIG. 2 shows a block diagram of another embodiment of a network interaction system. [Figure 3A]
[0010] FIG. 3A illustrates a block diagram of another embodiment of a network interaction system including a connection management system. [Figure 3B] FIG. 3B illustrates a block diagram of another embodiment of a network interaction system including a connection management system. [Figure 3C] FIG. 3C illustrates a block diagram of another embodiment of a network interaction system including a connection management system. [Figure 4]
[0011] FIG. 4 shows a protocol stack mapping representation of the operation of the connection components. [Diagram 5]
[0012] FIG. 5 illustrates a multi-device communication exchange system according to an embodiment. [Figure 6]
[0013] FIG. 6 illustrates a block diagram of one embodiment of a connection management system. [Figure 7]
[0014] FIG. 7 illustrates a block diagram of a network environment for dynamically switching between a bot and a terminal device during a communication session. [Figure 8]
[0015] FIG. 8 illustrates a block diagram representing a network environment for dynamically selecting an endpoint across a multiple channel environment. [Figure 9]
[0016] FIG. 9 illustrates a block diagram representing a network environment for enhancing endpoint selection using machine learning techniques. [Figure 10]
[0017] FIG. 10 illustrates an example process for monitoring bot behavior and training. [Figure 11]
[0018] FIG. 11 shows a block diagram representing a network environment in which a system for monitoring bot behavior and training may be implemented. [Figure 12-1]
[0019] FIG. 12-1 illustrates an example interface for monitoring bot behavior and training. [Figure 12-2] FIG. 12-2 illustrates an example interface for monitoring bot behavior and training.
[0008]
[0020] In the accompanying drawings, similar components and / or features may have the same reference label. Furthermore, various components of the same type may be distinguished by following the reference label with a dash and a second label that distinguishes between the similar components. If only a first reference label is used in this specification, the description is applicable to any one of the similar components having the same first reference label, regardless of the second reference label. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009]
[0021] The following description provides only preferred examples of embodiments and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the following description of preferred examples of embodiments provides those skilled in the art with an enabling description for implementing the preferred examples of embodiments. It is understood that various changes may be made in the arrangement and function of elements without departing from the spirit and scope as set forth in the appended claims.
[0010]
[0022] 1 illustrates a block diagram of an embodiment of a network interaction system 100 that implements and supports certain embodiments and features described herein. Certain embodiments relate to establishing a connection channel between a network device 105, which may be operated by a user 110, and a terminal device 115, which may be operated by an agent 120. In certain embodiments, the network interaction system 100 may include a client device 130 associated with a client 125.
[0011]
[0023] In certain embodiments, the user 110 can be an individual browsing a website or accessing an online service provided by a remote server 140. The client 125 can be an entity that provides, operates, or runs a website or online service, or can be an individual employed or assigned by such an entity to perform tasks available to the client 125 as described herein. The agent 120 can be an individual, such as a support agent tasked with providing support or information regarding the website or online service to the user 110. Of a large number of agents, a subset of agents may be appropriate for providing support or information to a particular client 125. The agent 120 may or may not be affiliated with the client 125. Each agent can be associated with one or more clients 125. In some non-limiting examples, the user 110 can be an individual shopping at an online store from a personal computing device, the client 125 can be a business that sells products online, and the agent 120 can be a representative employed by the business. In various embodiments, the user 110, the client 125, and the agent 120 may be other individuals or entities.
[0012]
[0024] While Fig. 1 shows only a single network device 105, terminal device 115, and client device 130, the interaction system 100 may include a plurality or large number (e.g., tens, hundreds, or thousands) of each of one or more of these types of devices. Similarly, while Fig. 1 shows only a single user 110, agent 120, and client 125, the interaction system 100 may include a plurality or large number of each of one or more of such entities. Thus, it may be necessary to determine which terminal device should be selected to communicate with a given network device. To further complicate matters, a remote server 140 may also be configured to receive and respond to selected network device communications.
[0013]
[0025] The connection management system 150 can facilitate strategic routing of communications. A communication can include a message having a content (e.g., defined based on input from an entity, such as typed or spoken input). A communication can also include additional data, such as data about the sending device (e.g., IP address, account identifier, device type, and / or operating system), destination address, client identifier, identifier or online history data of a web page or web page element (e.g., a web page or web page element that is being visited when the communication is generated or is otherwise associated with the communication), time (e.g., time and / or date), and / or destination address. Other information can also be included in the communication. In some cases, the connection management system 150 routes the entire communication to another device. In some cases, the connection management system 150 modifies the communication or generates a new communication (e.g., based on the original communication). The new or revised communication may include at least some (or all) of the message (or a processed version thereof), additional data (e.g., relating to the sending device, web page or online history, and / or time), and / or other data identified by connection management system 150 (e.g., account data associated with a particular account identifier or device). The new or revised communication may include other information as well.
[0014]
[0026] Part of the strategic routing facilitation can include establishing, updating, and using one or more connection channels between the network device 105 and one or more terminal devices 115. For example, upon receiving a communication from the network device 105, the connection management system 150 can first estimate which client (if any) the communication corresponds to. Upon identifying the client, the connection management system 150 can identify the terminal device 115 associated with the client for communication with the network device 105. In some cases, the identification can include evaluating the respective profiles of a plurality of agents (or experts or delegates), each agent (e.g., agent 120) in the plurality of agents being associated with a terminal device (e.g., terminal device 115). The evaluation can relate to content in the message of the network device. The identification of the terminal device 115 can include, for example, techniques described in U.S. Application Serial No. 12 / 725,799, filed March 17, 2010, which is incorporated by reference in its entirety for all purposes.
[0015]
[0027] In some cases, the connection management system 150 can determine whether any connection channel has been established between the network device 105 and a terminal device associated with the client (or remote server 140), and if so, whether such a channel should be used to exchange a series of communications including that communication.
[0016]
[0028] Upon selecting a terminal device 115 for communicating with the network device 105, the connection management system 150 can establish a connection channel between the network device 105 and the terminal device 115. In some instances, the connection management system 150 can send a message to the selected terminal device 115. The message may request acceptance of a proposed assignment for communicating with the network device 105 or may identify that such an assignment has been generated. The message may include information about the network device 105 (e.g., IP address, device type, and / or operating system), information about the associated user 110 (e.g., language spoken, duration of interacting with the client, skill level, sentiment, and / or topic preferences), the received communication, code (e.g., clickable hyperlinks) for generating and sending a communication to the network device 105, and / or instructions for generating and sending a communication to the network device 105.
[0017]
[0029] In one instance, communications between network devices 105 and terminal devices 115 can be routed through connection management system 150. Such configuration may enable connection management system 150 to monitor communication exchanges and detect problems (e.g., as defined based on rules), such as unresponsiveness or extended latency of any device. Additionally, such configuration may facilitate selective or complete storage of communications, which may be used later, for example, to assess the quality of the communication exchange and / or to support learning to update or generate routing rules to promote specific post-communication targets.
[0018]
[0030] In some embodiments, connection management system 150 can monitor communication exchanges in real time and perform automated actions (e.g., rule-based actions) based on the live communication. For example, when connection management system 150 determines that a communication is related to a particular item (e.g., a product), connection management system 150 may automatically send an additional message to terminal device 115 that includes additional information about the item (e.g., a quantity of the item available, links to support documents related to the item, or other information about the item or similar items).
[0019]
[0031] In one instance, a designated terminal device 115 may communicate with the network device 105 without relaying the communications through the connection management system 150. One or both of the devices 105, 115 may (or may not) report certain communication metrics or content to the connection management system 150 to facilitate communication monitoring and / or data storage.
[0020]
[0032] As described above, the connection management system 150 may route the selected communication to the remote server 140. The remote server 140 may be configured to provide information in a predetermined manner. For example, the remote server 140 may access one or more defined text passages, audio recordings, and / or files for transmission in response to the communication. The remote server 140 may select a particular text passage, recording, or file based on, for example, an analysis (e.g., a semantic analysis or mapping analysis) of the received communication.
[0021]
[0033] Routing and / or other decisions or processes performed in the connection management system 150 may be performed based on data and / or rules defined or provided at least in part by one or more client devices 130. For example, the client device 130 may send a communication identifying agent prioritization, terminal device type, and / or topic / skill matching. As another example, the client device 130 may identify one or more weights to apply to various variables potentially affecting the routing decision (e.g., language compatibility, expected response time, device type and capabilities, and / or load balancing of terminal devices). It will be appreciated that which terminal devices and / or agents should be associated with a client may be dynamic. Communications from the client device 130 and / or terminal device 115 may provide information indicating that a given terminal device and / or agent should be added or removed as associated with the client. For example, the client device 130 may send a communication having an IP address and an indication as to whether a terminal device having that address should be added to or removed from a list identifying terminal devices associated with the client.
[0022]
[0034] Each communication (e.g., between devices, between devices and the connection management system 150, between the remote server 140 and the connection management system 150, or between the remote server 140 and devices) can take place over one or more networks 170. Any combination of open or closed networks can be included in the one or more networks 170. Examples of suitable networks include the Internet, a personal area network, a local area network (LAN), a wide area network (WAN), or a wireless local area network (WLAN). Other networks may be suitable as well. The one or more networks 170 can be fully embedded within or can include an intranet, an extranet, or combinations thereof. In some cases, a network in the one or more networks 170 includes a short-range communication channel, such as a Bluetooth® or Bluetooth Low Energy channel. In one embodiment, communication between two or more systems and / or devices can be achieved by a secure communication protocol, such as Secure Sockets Layer (SSL) or Transport Layer Security (TLS). Additionally, the data and / or transaction details may be encrypted based on any convenient, known, or future developed methodology, such as, but not limited to, Data Encryption Standard (DES), Triple DES, Rivest-Shamir-Adleman Cipher (RSA), Blowfish Cipher, Advanced Encryption Standard (AES), CAST-128, CAST-256, Decorrelated Fast Cipher (DFC), Tiny Encryption Algorithm (TEA), eXtended TEA (XTEA), Corrected Block TEA (XXTEA), and / or RC5.
[0023]
[0035] The network devices 105, the terminal devices 115, and / or the client devices 130 may include, for example, portable electronic devices (e.g., a smartphone, a tablet, a laptop computer, or a smart wearable device) or non-portable electronic devices (e.g., one or more desktop computers, smart appliances, servers, and / or processors). The connection management system 150 may be housed separately from the network devices, the terminals, and the client devices, or may be part of one or more such devices (e.g., via the installation of an application on the device). The remote server 140 may be housed separately from each device and the connection management system 150, and / or may be part of another device or system. While each device, server, and system in FIG. 1 is shown as a single device, it will be understood that multiple devices may be used instead. For example, a set of network devices may be used to transmit various communications from a single user, or the remote server 140 may include a server stack.
[0024]
[0036] Software agents or applications may be installed and / or executable on the illustrated devices, systems, or servers. In one instance, the software agents or applications are configured to enable the various illustrated elements to operate in a complementary manner. For example, a software agent on a device can be configured to collect and send data regarding device usage to a separate connection management system, and a software application on the separate connection management system can be configured to receive and process this data.
[0025]
[0037] Figure 2 shows a block diagram of another embodiment of a network interaction system 200. In general, Figure 2 illustrates various components configured and arranged to enable a network device 205 to communicate with one or more terminal devices 215. The depicted example includes nine terminal devices 215 included in three local area networks 235.
[0026]
[0038] In some instances, communications from network device 205 include destination data (e.g., a destination IP address) that indicates, at least partially or completely, which end device should receive the communication. Network interaction system 200 can include one or more internetwork connectivity components 240 and / or one or more intranetwork connectivity components 255 that can process the destination data and facilitate appropriate routing.
[0027]
[0039] Each internetwork connectivity component 245 can be connected to multiple networks 235 and can have multiple network cards installed (e.g., each card connected to a different network). For example, an internetwork connectivity component 245 can be connected to a wide area network 270 (e.g., the Internet) and one or more local area networks 235. In the depicted example, in order for a communication to be sent from network device 205 to any of the terminal devices, in the depicted system, the communication must be processed by multiple internetwork connectivity components 245.
[0028]
[0040] When internetwork connectivity component 245 receives a communication (or a set of packets corresponding to a communication), it can determine at least a portion of a route for passing the communication to a network associated with a destination. The route can be determined, for example, using a routing table (e.g., stored in a router), which can include one or more routes that are predefined, generated based on an incoming message (e.g., from another router or from another device), or learned.
[0029]
[0041] Examples of internetwork connectivity components 245 include routers 260 and gateways 265. Internetwork connectivity components 245 (e.g., gateways 265) may be configured to translate between network systems or protocols. For example, gateways 265 may facilitate communication between Transmission Control Protocol / Internet Protocol (TCP / IP) devices and Internetwork Packet Switching / Sequenced Packet Switching (IPX / SPX) devices.
[0030]
[0042] Upon receiving a communication at the local area network 235, further routing may still need to be performed. Such intra-network routing may be performed via an intra-network connectivity component 255, such as a switch 280 or a hub 285. Each intra-network connectivity component 255 may be connected (e.g., wirelessly or wired, such as via an Ethernet cable) to multiple end devices 215. The hub 285 may be configured to repeat all received communications for each device to which it is connected. Each end device may then evaluate each communication to determine whether the end device is a destination device or whether the communication should be ignored. The switch 280 may be configured to selectively direct communications only to destination end devices.
[0031]
[0043] In some instances, the local area network 235 can be divided into multiple segments, each of which can be associated with independent firewalls, security rules, and network protocols. An intra-network connectivity component 255 can be provided in each of one, more than one, or all of the segments to facilitate intra-segment routing. A bridge 280 can be configured to route communications across the segments 275.
[0032]
[0044] To properly route communications across or within a network, various components analyze destination data in the communications. For example, such data may indicate which network the communication should be routed to, which device within the network the communication should be routed to, or which communication an end device should process (or ignore). However, in some cases, it is not immediately clear which end devices (or even which networks) should participate in a communication from a network device.
[0033]
[0045] To illustrate, a set of terminal devices may be configured to provide similar types of response communications. Thus, it may be expected that queries in communications from a network device may be responded to in a similar manner regardless of which network device the communication is routed to. While this assumption may be true at a high level, various details relating to the terminal devices may result in certain routings being advantageous compared to others. For example, terminal devices in a set may differ from one another with respect to (for example) which communication channels are supported, geographic and / or network proximity to the network devices, and / or characteristics of associated agents (e.g., knowledge base, experience, language used, availability, general personality or sentiment, etc.). Thus, selective routing may facilitate faster responses that respond more accurately and / or completely to the network device's communications. One issue is that static routing that maps network devices to terminal devices may not be able to account for variations in communication topics, channel types, agent availability, etc.
[0034]
[0046] 3A-3C show block diagrams of other embodiments of network interaction systems 300a-c including a connection management system. Each of the depicted systems 300a-c shows only two local area networks 235 for simplicity, but it may be understood that the embodiments can be expanded to increase the number of local area networks. Each of the systems 300a-c includes a connection management system 350 that can identify which terminal devices should communicate with the network device 205, establish and manage (e.g., maintain or close) connection channels, determine whether and when to reroute communications in an exchange, etc. Thus, the connection management system 350 can be configured to dynamically and in real time evaluate communications, agent availability, terminal device or agent capabilities, etc. to affect routing decisions.
[0035]
[0047] In FIG. 3A , a connection management system 350 is associated with each of the network device 205 and the remote server 340 (e.g., connection management system 350a is associated with the network device 205 and connection management system 350b is associated with the remote server 340). For example, the connection management system 350a and / or the connection management system 350b can be installed or stored as an application on each of the network device 205 and the remote server 340, respectively. Execution of the application can facilitate communication between the network device 205 and the remote server 340, for example, to identify the terminal device 215 selected to participate in a communication exchange with the network device 205. The identification can be based on one or more factors disclosed herein (e.g., availability, matching between the topic / level of detail of the communication and the knowledge base of an agent or terminal device, expected latency, availability of channel type, etc.).
[0036]
[0048] The client device 330 can provide client data that indicates how routing decisions should be made. For example, such data can include indications regarding how certain characteristics should be weighted or matched, or constraints or biases (e.g., related to load balancing or expected response latency). The client data can also include specifications regarding when a communication channel should be established (or closed) or when a communication should be re-routed to a different network device. The client data can be used to define various client-specific rules, such as rules for communication routing, etc.
[0037]
[0049] The connection management system 350b running on the remote server 340 may monitor various metrics related to the terminal device (e.g., related to a given client), such as which communication channels are supported, geographic and / or network proximity to the network device, latency and / or stability of communications with the terminal device, the type of terminal device, the capabilities of the terminal device, whether the terminal device (or agent) has previously communicated with a given network device (or user), and / or characteristics of the associated agent (e.g., knowledge base, experience, language used, availability, general personality or sentiment, etc.). Thus, the connection management system 350b may be able to make routing choices based on the metrics to promote faster responses that respond more accurately and / or completely to the network device's communications.
[0038]
[0050] In the example depicted in FIG. 3A, communication exchanges between network device 205 and remote server 340 can facilitate early identification of a destination address. Network device 205 may then use the destination address to direct subsequent communications. For example, network device 205 may send an initial communication to remote server 340 (e.g., via one or more internetwork connections and wide area networks), which may identify one or more corresponding clients. Remote server 340 may then identify a set of end devices associated with the one or more corresponding clients and collect metrics for those end devices. The metrics can be evaluated (e.g., by remote server 340) to select end devices to engage in the communication exchange, and information related to the end devices (e.g., IP addresses) can be sent to network device 205. In some embodiments, remote server 340 may continuously or periodically collect and evaluate metrics for various end devices and store the evaluation results in a data store. In such an embodiment, upon identifying a set of terminal devices associated with one or more corresponding clients, the remote server 340 can access the stored evaluation results from the data store and select the terminal devices to engage in a communication exchange based on the stored evaluation results.
[0039]
[0051] In FIG. 3B, the connection management system 350 can be configured to act as a relay and / or a destination address. Thus, for example, a set of network devices 205 may send communications that each identify the connection management system 350 as a destination. The connection management system 350 can receive each communication and can concurrently monitor a set of terminal devices (e.g., to generate metrics for each terminal device). Based on the monitoring and rules, the connection management system 350 can identify a terminal device 215 to which it may relay each communication. Depending on the embodiment, the terminal device's communications may similarly be directed to a consistent destination (e.g., in the connection management system 350) for further relaying, or the terminal device may initiate communication directly with the corresponding network device. These embodiments can facilitate efficient routing and thorough communication monitoring.
[0040]
[0052] The embodiment depicted in Figure 3C is similar to that of Figure 3B, however, in some embodiments, the connection management system 350 is directly connected to intra-network components (e.g., terminal devices, intra-network connections, or otherwise).
[0041]
[0053] It will be appreciated that many variations of Figures 3A-3C are contemplated. For example, connection management system 350 may be associated with a connectivity component (e.g., internetwork connectivity component 245 or intranetwork connectivity component 255) such that an application corresponding to connection management system 350 (or a portion thereof) is installed on the component. The application may execute, for example, independently or by communicating with one or more similar or complementary applications (e.g., running on one or more other components, network devices, or remote servers).
[0042]
[0054] Figure 4 shows a representation of a protocol stack mapping 400 of the operations of the connectivity components. More specifically, Figure 4 identifies the layers of operations in the Open Systems Interaction (OSI) model that correspond to the various connectivity components.
[0043]
[0055] The OSI model can include multiple logical layers 402-414. These layers are arranged in an ordered stack such that layers 402-412 each service a higher level and layers 404-414 are each serviced by a lower layer. The OSI model includes a physical layer 402. The physical layer 402 can define the physical communication of parameters (e.g., electrical, optical, or electromagnetic). The physical layer 402 also defines connection management protocols, such as protocols for establishing and closing connections. The physical layer 402 can further define flow control protocols and transmission modes.
[0044]
[0056] The link layer 404 can manage inter-node communication. The link layer 404 can detect and correct errors (e.g., transmission errors in the physical layer 402) and manage access permissions. The link layer 404 can include a medium access control (MAC) layer and a logical link control (LLC) layer.
[0045]
[0057] The network layer 406 can coordinate the transfer of data (eg, of variable length) across nodes within the same network (eg, as datagrams). The network layer 406 can translate logical network addresses into physical machine addresses.
[0046]
[0058] The transport layer 408 can manage the quality of transmission and reception. The transport layer 408 can provide a protocol for transferring data, such as Transmission Control Protocol (TCP). The transport layer 408 can perform segmentation / desegmentation of data packets for transmission, and can detect and handle transmission errors that occur in layers 402-406. The session layer 410 can initiate, maintain, and terminate connections between local and remote applications. Sessions may be used as part of remote procedure interactions. The presentation layer 412 can encrypt, decrypt, and format data based on data types known to be accepted by the application layer or the network layer.
[0047]
[0059] The application layer 414 can interact with software applications that control or manage communications. Through such applications, the application layer 414 can identify (for example) the destination, the status or availability of local resources, and / or the content or formatting of the communication. The various layers 402-414 can perform other functions as available and applicable.
[0048]
[0060] The intra-network connectivity components 422, 424 are shown operating at the physical layer 402 and the link layer 404. More specifically, hubs can operate at the physical layer so that operations can be controlled with respect to receiving and transmitting communications. Hubs have little or no ability to operate at a higher level because they do not have the ability to address communications or filter data. Switches, on the other hand, can operate at the link layer 404 because they are able to filter communication frames based on addresses (e.g., MAC addresses).
[0049]
[0061] Internetwork connectivity components 426, 428, on the other hand, are shown operating at a higher level (e.g., layers 406-414). For example, a router can filter communication data packets based on address (e.g., IP address). A router can forward packets to a particular port based on the address to direct the packet to the appropriate network. Gateways operate at the network layer and above and can perform similar filtering and steering, as well as further translation of data (e.g., across protocols or architectures).
[0050]
[0062] The connection management system 450 can interact with and / or operate on one, more, all, or any of the various layers in various embodiments. For example, the connection management system 450 can interact with a hub to dynamically adjust which end devices the hub communicates with. As another example, the connection management system 450 can communicate with a bridge, switch, router, or gateway to influence which end device the component selects as a destination (e.g., MAC, logical, or physical) address. As a further example, the connection management system 450 can monitor, control, or direct the segmentation of data packets on the transport layer 408, the session duration on the session layer 410, and / or the encryption and / or compression on the presentation layer 412. In some embodiments, connection management system 450 can interact with various layers by exchanging communications with (e.g., sending commands to) equipment operating at a particular layer (e.g., a switch operating at link layer 404), by routing or modifying existing communications (e.g., between a network device and an end device) in a particular manner, and / or by generating new communications containing particular information (e.g., a new destination address) based on existing communications. Thus, connection management system 450 can affect communication routing and channel establishment (or maintenance or termination) through interactions with various devices and / or through affecting operation at various protocol stack layers.
[0051]
[0063] 5 illustrates a multi-device communication switching system 500 according to one embodiment. The system 500 includes a network device 505 configured to communicate with various types of terminal devices over various types of communication channels.
[0052]
[0064] In the depicted case, a network device 505 can transmit a communication over a cellular network (e.g., via a base station 510). The communication can be routed to an operating network 515. The operating network 515 can include a connection management system 520 that receives the communication and identifies which terminal device should respond to the communication. Such a determination can depend on identifying a client to which the communication pertains (e.g., based on content analysis or user input indicating the client) and determining one or more metrics for each of one or more terminal devices associated with the client. For example, in FIG. 5, each cluster of terminal devices 530a-c can correspond to a different client. The terminal devices may be geographically co-located or distributed. The metrics may be determined based on stored or learned data and / or real-time monitoring (e.g., based on availability).
[0053]
[0065] The connection management system 520 can communicate with various terminal devices via one or more routers 525 or other internetwork or intranetwork connection components. The connection management system 520 may collect, analyze, and / or store data from or relating to communications, terminal device operations, client rules, and / or user-related actions (e.g., online activity) in one or more data stores. Such data may affect communication routing.
[0054]
[0066] In particular, various other devices may also be used to affect communication routing and / or processing. For example, in the depicted example, the connection management system 520 is also connected to a web server 540. Thus, the connection management system 520 may retrieve data of interest, such as technical product details, etc.
[0055]
[0067] Network device 505 may also be connected to web servers, including, for example, web server 545. In some cases, communications with such servers are provided with an initial option to initiate a communication exchange with connection management system 520. For example, network device 505 may detect that a communication opportunity is available while visiting a particular web page, and such an option may be presented.
[0056]
[0068] One or more elements of the communication system 500 can also be connected to a social networking server 550. The social networking server 550 can aggregate data received from various user devices. Thus, for example, the connection management system 520 may be able to infer general (or user-specific) behavior of a given user or class of users.
[0057]
[0069] FIG. 6 illustrates a block diagram of an embodiment of the connection management system 600. A message receiver interface 605 can receive a message. In some cases, the message can be received as part of a communication sent by a source device (e.g., housed separately from the connection management system 600 or housed in the same housing), such as, for example, a network device or a terminal device. In some cases, the communication can be part of a series of communications or communication exchanges, which can include a series of messages or message exchanges being routed between two devices (e.g., a network device and a terminal device). This message or communication exchange can be part of and / or define an interaction between the devices. The communication channel or operating channel can include one or more protocols (e.g., a routing protocol, a task assignment protocol, and / or an addressing protocol) used to facilitate the routing and communication exchanges between the devices.
[0058]
[0070] In some cases, the message may include a message generated based on input received at a local or remote user interface. For example, the message may include a message generated based on a button or key press or a recorded audio signal. In one case, the message includes an automatically generated message, such as one generated upon detecting that a network device is presenting a particular app page or web page or providing a particular input command (e.g., a key sequence). The message may include an instruction or request, such as one to initiate a communication exchange.
[0059]
[0071] In some cases, the message may include or be associated with an identifier of the client. For example, the message may explicitly identify the client (or a device associated with the client), the message may include or be associated with a web page or app page associated with the client, the message may include or be associated with a destination address associated with the client, or the message may include or be associated with an identification of an item (e.g., a product) or service associated with the client. As an example, the network device may present an app page for a particular client, which may provide an option to send a communication to an agent. Upon receiving user input corresponding to the message, a communication may be generated to include the message and an identifier of the particular client.
[0060]
[0072] The processing engine 610 may process received communications and / or messages. Processing may include, for example, extracting one or more particular data elements (e.g., a message, a client identifier, a network device identifier, an account identifier, etc.). Processing may include formatting or converting the communication type (e.g., to be compatible with a particular device type, operating system, communication channel type, protocol, and / or network).
[0061]
[0073] A message assessment engine 615 may assess a message (e.g., extracted or received). The assessment may include, for example, identifying one or more categories or tags for the message. Examples of types of categories or tags may include (for example) topic, sentiment, complexity, and urgency. The difference between categorizing and tagging a message is that a tag can be open, while a category can be limited (e.g., according to a predefined set of category options). A topic may include, for example, a technical issue, a use question, or a request. A category or tag may be determined based on, for example, a semantic analysis of the message (e.g., by identifying keywords, sentence structure, repeated words, punctuation characters, and / or non-article words), user input (e.g., with one or more categories selected), and / or message-related statistics (e.g., typing speed and / or response latency).
[0062]
[0074] In some cases, the message assessment engine 615 can determine metrics for the message. The metrics can include, for example, the number of characters, the number of words, the number of capital letters, the number of words in all capital letters, or the number of instances of a particular character or punctuation mark (e.g., an exclamation point, a question mark, and / or a period). The metrics can include ratios such as the percentage of sentences that end with an exclamation point (or a question mark), the percentage of words in all capital letters, etc.
[0063]
[0075] The message assessment engine 615 can store messages, message metrics, and / or message statistics in the message data store 620. Each message can also be stored in association with other data (e.g., metadata), such as data identifying a corresponding source device, destination device, network device, terminal device, client, one or more categories, one or more stages, and / or message-related statistics. Various components of the connection management system 600 (e.g., the message assessment engine 615 and / or the interaction management engine 625) can query the message data store 620 to retrieve query response messages, message metrics, and / or message statistics.
[0064]
[0076] The interaction management engine 625 can determine to which device a communication should be routed and how the receiving and transmitting devices should communicate. Each of these decisions can depend, for example, on whether a particular network device (or any network device associated with a particular user) has previously communicated with a terminal device in the set of terminal devices (e.g., any terminal device associated with the connection management system 600 or any terminal device associated with one or more particular clients).
[0065]
[0077] In some instances, when a network device (or other network devices associated with the same user or profile) has previously communicated with a given terminal device, communication routing may generally be biased toward the same terminal device. Other factors that may affect routing may include, for example, whether the terminal device (or corresponding agent) is available and / or the expected response latency of the terminal device. Such factors may be considered in absolute terms or relative to similar metrics corresponding to other terminal devices. It may be shown how such factors should be assessed and weighted to determine whether a rerouting rule (e.g., client-specific or general rule) foregoes agent consistency.
[0066]
[0078] When a network device (or other network devices associated with the same user or account) has not previously communicated with a given terminal device, the selection of the terminal device can be performed based on factors such as, for example, the extent to which the knowledge bases of various agents correspond to the topic of communication, the availability of various agents at a given time and / or on a channel type, the type and / or capabilities of the terminal device (e.g., associated with the client), etc. In one instance, the rules can identify how to determine sub-parameters for one or more factors such as these and the weight to assign to each parameter. By combining (e.g., summing) the weighted sub-parameters, a parameter for each agent can be determined. The selection of the terminal device can then be made by comparing the parameters of the terminal devices.
[0067]
[0079] With regard to determining how the devices should communicate, the interaction management engine 625 can determine whether the terminal device should respond to the communication via (e.g.) an SMS message, a voice call, a video communication, etc. The communication type can be selected based on, for example, a communication type priority list (e.g., defined at least in part by a client or user), the type of communication previously received from the network device (e.g., to promote consistency), the complexity of the received message, the capabilities of the network device, and / or the availability of one or more terminal devices. Clearly, some communication types will result in real-time communication (e.g., where fast message responses are expected), while others may result in asynchronous communication (e.g., where delays (e.g., minutes or hours) between messages are tolerable).
[0068]
[0080] Additionally, the interaction management engine 625 can determine whether a continuous channel between two devices should be established, used, or terminated. The continuous channel can be structured to facilitate routing of future communications from the network device to a specified end device. This bias can even persist across a message series. In some instances, a representation of the continuous channel (e.g., identifying the agent) can be included in the presentation to be presented on the network device. In this way, the user can understand that communications should be routed consistently to promote efficiency.
[0069]
[0081] In one instance, parameters may be generated using one or more factors and rules (e.g., including weights for each of the one or more factors) described herein to determine connection parameters corresponding to a given network device and terminal device. The parameters may relate to an overall match or a match specific to a given communication or communication sequence. Thus, for example, the parameters may reflect the degree to which a given terminal device is predicted to be suitable to respond to a network device communication. In some instances, parameter analysis may be used to identify each of the terminal devices to which a given communication should be routed and whether to establish, use, or terminate a connection channel. When parameter analysis is used to address both routing and channel decisions, the parameters associated with each decision may be determined in the same, similar, or different manners.
[0070]
[0082] Thus, it will be appreciated that different factors may be considered depending on, for example, whether the parameters are for predicting the strength of a long-term match or for responding to a particular message query. For example, in the former case, overall schedule and time-of-day considerations may be important, whereas in the latter case, immediate availability may be weighted more highly. One parameter may be determined for a single network device / terminal device combination, or multiple parameters may be determined, each parameter characterizing a match between a given network device and a different terminal device.
[0071]
[0083] As an example, a set of three terminal devices associated with a client may be evaluated for potential communication routing. A parameter for each may be generated that is related to a match for a particular communication. Each of the first two terminal devices may have previously communicated with the network device that sent the communication. The input from the network device may indicate positive feedback associated with the interaction in the communication with the first device. Thus, the past interaction subparameters (calculated according to the rules) for the first, second, and third devices may be 10, 5, and 0, respectively. (An input of negative feedback may result in a negative subparameter). It may be determined that only the third terminal device is available. The second terminal device may be expected to be available for a response within 15 minutes, while the first terminal device will not be available for a response until the next day. Thus, the fast response subparameters for the first, second, and third devices may be 1, 3, and 10. Finally, the degree to which the agents (associated with the terminal devices) are familiar with the topic in the communication may be estimated. It may be determined that the agent associated with the third terminal device is more knowledgeable than the agents associated with the other two devices, with sub-parameters of 3, 4, and 9. In this example, the rule does not include a weighting or normalization parameter (although in other cases the rule may include one), with parameters of 14, 11, and 19. Thus, the rule may indicate that the message should be routed to the device with the highest parameter, i.e., the third terminal device. If routing to a particular terminal device fails, the message may be routed to the device with the next highest parameter, and so on.
[0072]
[0084] The parameters may be compared to one or more absolute or relative thresholds. For example, to select a terminal device to which a communication can be routed, parameters for a set of terminal devices can be compared to one another to identify high parameters. As another example, a parameter (e.g., high parameter) can be compared to one or more absolute thresholds to determine whether to establish a continuous channel with a terminal device. The overall threshold for establishing a continuous channel may be (but need not be) higher than the threshold for consistently routing a communication in a given series of messages. This difference between the overall threshold and the threshold for determining whether to consistently route a communication may be because strong agreement is important in the context of continuous channels, given the extended usefulness of the channel. In some embodiments, the overall threshold for using a continuous channel may be (but need not be) lower than the threshold for consistently routing a communication in a given series of messages and / or for establishing a continuous channel.
[0073]
[0085] The interaction management engine 625 can interact with the account engine 630 in various contexts. For example, the account engine 630 may look up a network device or terminal device identifier in the account data store 635 to identify an account corresponding to the device. Additionally, the account engine 630 can maintain data regarding previous communication exchanges (e.g., number of times, other devices involved, channel type, resolution stage, topic, and / or associated client identifier), data regarding connected channels (e.g., indicating - for each of one or more clients - whether any channels exist, the terminal device associated with each channel, the establishment time, frequency of use, date of last use, any channel constraints and / or types of communication supported), data regarding user or agent preferences or constraints (e.g., related to terminal device selection, response latency, terminal device consistency, agent expertise, and / or communication type preferences or constraints), and / or data regarding user or agent characteristics (e.g., age, language used or preferred, geographic location, interests, etc.).
[0074]
[0086] Additionally, the interaction management engine 625 can inform the account engine 630 of various connection channel actions so that the account data store 635 can be updated to reflect current channel data. For example, upon establishing a channel, the interaction management engine 625 can inform the account engine 630 of the establishment and identify one or more of the network device, the terminal device, the account, and the client. The account engine 635 can then inform the user of the existence of the channel so that the user is aware of the agent consistency being utilized (in some cases).
[0075]
[0087] The interaction management engine 625 can further interact with a client mapping engine 640, which can map the communication to one or more clients (and / or associated brands). In some cases, the communication received from the network device itself includes an identifier corresponding to the client (e.g., an identifier for the client, web page, or app page). The identifier can be included as part of the message (e.g., which the client mapping engine 640 may detect) or can be included as other data in the message-containing communication. The client mapping engine 640 can then look up the identifier in a client data store 645 to retrieve additional data regarding the client and / or the client's identifier.
[0076]
[0088] In some cases, the message may not specifically address any client. For example, the message may include a general query. The client mapping engine 640 may, for example, perform a semantic analysis on the message to identify one or more keywords and identify one or more clients associated with the keywords. In some cases, a single client is identified. In some cases, multiple clients are identified. The identification of each client may then be presented via the network device so that a user can select (e.g., via an associated terminal device) a client with which to communicate.
[0077]
[0089] The client data store 645 may include an identification of one or more terminal devices (and / or agents) associated with a client. The terminal routing engine 650 may retrieve or collect data relating to each of one, more than one, or all such terminal devices (and / or agents) to affect routing decisions. For example, the terminal routing engine 650 may maintain a terminal data store 655, which may store information such as the device type, operating system, communication type capabilities, installed application accessories, geographic location, and / or identifier (e.g., IP address) of the terminal device. Some information may be dynamically updated. For example, information indicating whether a terminal device is available may be dynamically updated based on (for example) communications from the terminal device (e.g., identifying whether the device is asleep, turned off / on, inactive / active, or identifying whether an input has been received within a period of time), communication routing (e.g., indicating whether the terminal device is involved in or assigned to a part of a communication exchange), or communications from a network device or terminal device indicating that a communication exchange has ended or started.
[0078]
[0090] It will be appreciated that in various contexts, being engaged in one or more communication exchanges does not necessarily indicate that the terminal device is unavailable to engage in another communication exchange. Various factors, such as communication type (e.g., message), client-identified or user-identified target response time, and / or system load (e.g., general or user-related), may affect how many exchanges a terminal device may be involved in.
[0079]
[0091] When the interaction management engine 625 identifies a terminal device to be involved in a communication exchange or connection channel, it can notify the terminal routing engine 650, which may retrieve any relevant data about the terminal device from a terminal data store 655, such as the destination (e.g., IP) address, device type, protocol, etc. The processing engine 610 can then modify the message-inclusive communication (in some cases) to have a particular format, conform to a particular protocol, etc., or generate a new communication (containing the message). In some cases, the new or modified message may include additional data, such as account data corresponding to the network device, a message chronicle, and / or client data.
[0080]
[0092] The message transmitter interface 660 can then transmit the communication to a terminal device. The transmission may include, for example, a wired or wireless transmission to a device contained in a separate housing. The terminal device may include a terminal device in the same or a different network (e.g., a local area network) as the connection management system 600. Thus, transmitting the communication to a terminal device may include transmitting the communication to an inter- or intra-network connection component.
[0081]
[0093] Systems and methods are provided for dynamically switching between a bot and a terminal device (e.g., operated by a live user) during a communication session with a network device (e.g., operated by a user). In some implementations, the bot can be configured to communicate autonomously with the network device. Additionally, the bot can be configured for specific capabilities. Examples of capabilities include updating database records, providing updates to a user, providing additional data about the user to an agent, determining the intent of the user and routing the user to a destination system based on the intent, predicting or suggesting responses to an agent communicating with the user, escalating the communication session to include one or more additional bots or agents, and other suitable capabilities. In some implementations, while the bot is communicating with a network device (e.g., operated by a user) during a communication session (e.g., using a chat-enabled interface), a communication server can automatically and dynamically determine to switch the bot to a terminal device. For example, a bot may communicate with a user regarding a particular task (e.g., updating a database record associated with the user), while a terminal device may communicate with a user regarding more difficult tasks (e.g., communicating using a communication channel to resolve a technical issue).
[0082]
[0094] In some implementations, determining whether to switch between the bot and the terminal device during a communication session can be based on an analysis of one or more characteristics of messages in the communication session. Additionally, dynamic sentiment parameters can be generated to represent the sentiment of a message, a conversation, an entity, an agent, etc. For example, if the dynamic sentiment parameters indicate that a user is dissatisfied with the bot, the system can automatically switch the bot to the terminal device so that a live agent can communicate with the user. See U.S. Serial No. 15 / 171,525, filed June 2, 2016, the disclosure of which is incorporated herein by reference in its entirety for all purposes. In some examples, determining whether to switch between the bot and the terminal device can be performed without a prompt from the user. The determination may be performed automatically in the communication server based on any number of factors, including characteristics of the current message in a communication session (e.g., a chat), characteristics of previous messages sent by the user in previous communication sessions, a trajectory of characteristics (e.g., sentiment) across multiple messages in a conversation, or additional information associated with the user (e.g., profile information, preference information, and other suitable information associated with the user).
[0083]
[0095] FIG. 7 illustrates a block diagram of a network environment for dynamically switching between a bot and a terminal device during a communication session. In some implementations, the network environment 700 can include a network device 705, a communication server 710, a terminal device 715, and a bot 720. The communication server 710 can be a server with one or more processors with at least one storage device and can be configured to perform the methods and techniques described herein. For example, the communication server 710 can manage a communication session between a network device (e.g., operated by a user) and a terminal device (e.g., operated by an agent). The communication server 710 can establish a communication channel between the network device 705 and the terminal device 715 such that the network device 705 and the terminal device 715 can communicate with each other during the communication session. The communication session can facilitate the exchange of one or more messages between the network device 705 and the terminal device 715. The present disclosure is not limited to the exchange of messages during the communication session. Other forms of communication can be facilitated by the communication session, for example, video communication (eg, a video feed) and audio communication (eg, a voice over IP connection).
[0084]
[0096] In some implementations, the communication server 710 can establish a communication channel between the network device 705 and a bot 720. The bot 720 can be code configured to autonomously communicate with the network device 705 when executed. For example, the bot 720 can be a bot for automatically generating messages to initiate a conversation with a user associated with the network device 705 and / or automatically responding to messages from the network device 705. Additionally, the communication server 710 can be associated with the platform. Clients (e.g., systems external to the platform) can use the platform to deploy bots in their internal communication systems. In some examples, clients can use their own bots in the platform, which allows the clients to implement the methods and techniques described herein in their internal communication systems.
[0085]
[0097] In some implementations, bots can be defined by one or more sources. For example, data store 730 can store code representing bots defined (e.g., written or coded) by clients of the communication server. For example, clients that have defined their own bots can load the bots into the communication server 710. Bots defined by clients can be stored in client bot data store 730. Data store 740 can store code representing bots defined by third party systems. For example, third party systems can include independent software vendors. Data store 750 can store code representing bots defined by entities associated with the communication server 710. For example, bots coded by entities can be loaded into or accessible by the communication server 710 such that the bots can be executed and communicate autonomously with users. In some implementations, the communication server 710 can access bots stored in data store 730, data store 740, and / or data store 750 using cloud network 760. The cloud network 760 may be any network, including an open network such as the Internet, a personal area network, a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a wireless local area network (WLAN), a private network such as an intranet, an extranet, or other backbone.
[0086]
[0098] Additionally, the terminal device 715 can be operated by an agent. The terminal device 715 can be any portable (e.g., mobile phone, tablet, laptop) or non-portable device (e.g., electronic kiosk, desktop computer, etc.). In some instances, the agent can access a website using a browser running on the terminal device 715. For example, the website can include a console or platform running on the browser of the terminal device 715. The agent can log into the platform using the browser. One or more login credentials (e.g., username, password, etc.) can be used to authenticate the agent's identity before allowing the agent to gain access to the console or a web application contained within the console. An example of a console can include a platform including one or more APIs (application programming interfaces), a dashboard including one or more functions, a web-hosted application running on a web browser capable of establishing or participating in a communication session (without the need to download a plug-in), and other suitable interfaces. Additionally, the console can include one or more web applications or functions that can be executed. The web application or function can run in a browser, on the communication server 710, a local server, a remote server, or other suitable computing device. For example, the web application, native application, or function can enable an agent to communicate with a user and to view communications between a user and one or more bots.
[0087]
[0099] In some implementations, the communication server 710 can be configured to dynamically switch between the bot 720 and the terminal device 715 during a particular communication session. For example, the communication server 710 can facilitate a communication session between the network device 705 and the bot 720. The bot 720 can be configured to autonomously communicate with the network device 705 by exchanging one or more messages with the network device 705 during the communication session. The communication server 710 can dynamically determine whether to switch the bot 720 to the terminal device 715 (or vice versa, as the case may be) so that a live agent can communicate with the network device 705 on behalf of the bot 720. In some implementations, the switching can be performed without prompting from the network device 705 or the terminal device 715. For example, the switching can be based on a message parameter (e.g., a score representing the sentiment of the message or a series of messages) of a message exchanged between the network device 705 and the bot 720 without prompting the network device 705 to request the terminal device.
[0088]
[0100] In some implementations, the communication server 710 can determine to automatically switch between the bot 720 and the terminal device 715 based on characteristics of messages exchanged between the bot 720 and the network device 705. In some cases, analyzing the text of the message to determine characteristics (e.g., message parameters) can include analyzing textual or non-textual attributes related to the message. For example, the communication server 710 can extract one or more lines of text included in the message from the network device 705. The communication server 710 can identify whether the one or more lines of text include an anchor. Examples of anchors include columns of text related to polarity (e.g., emotion or intent, the word "irritated" corresponding to a negative polarity or an irritated polarity, the word "happy" corresponding to a positive polarity, etc.). For example, the term "argument" may be negative to one client, but neutral or positive to a second client. In some cases, the anchors can be dynamically determined using supervised machine learning techniques. For example, one or more clustering algorithms can be run on the stored messages to find patterns within the stored messages. The clustered messages can be further filtered and evaluated to determine anchors. Additionally, one or more words near the identified anchors can be parsed for amplifiers. An example of an amplifier is a term that increases or decreases the strength related to the polarity of the anchor, such as "very," "not much," "kind of," etc. The characteristics can include, for example, typing speed, the number of special characters used in the message (e.g., exclamation marks, question marks, etc.), semantic analysis of the message (e.g., by identifying keywords, sentence structure, repeated words, punctuation characters, and / or words that are not articles), user input (e.g., with one or more categories selected), and / or message-related statistics (e.g., response latency).
[0089]
[0101] As a non-limiting example, the message parameter can be a numeric value indicating a high intensity of negative polarity (e.g., a message parameter of 20 on a scale of 0-100, with lower numbers indicating negative polarity and higher numbers indicating positive polarity). An algorithm can be used to calculate the message parameter. For example, the algorithm may be based on supervised machine learning techniques. In a further example, if the term "hey" is close to the anchor "don't like" (e.g., as in the sentence "I don't like... kinda"), the term "hey" may be identified as an amplifier term indicating a medium intensity of negative polarity. In this case, the message parameter can be generated based on the identification of a medium intensity of negative polarity. As a non-limiting example, the message parameter can be a numeric value indicating a medium intensity of negative polarity (e.g., a message parameter of 40 as opposed to a message parameter of 20). In some instances, the message parameter can be used to determine which secondary cue should store the communication.
[0090]
[0102] In some implementations, the message characteristic may be a sentiment associated with the message. A message parameter may represent the sentiment of the message. For example, if the sentiment of the message is joy, the message parameter may be one value or range of values, while if the sentiment of the message is anger, the message parameter may be another value or range of values. The decision of whether to switch between the bot and the terminal device may be based on the message parameter, which is continuously and automatically updated with each new message received at the communication server 710.
[0091]
[0103] In some implementations, the communications server 710 may recommend or predict responses to messages received from the network device 705. For example, the communications server 710 may include a message recommendation system that can use machine learning models to evaluate messages received from the network device 705 and recommend responses to those received messages. The message recommendation system can display on the terminal device 715 a set of recommended messages to assist an agent in communication with the network device 705.
[0092]
[0104] 8 shows a block diagram depicting a network environment 800 for dynamically selecting an endpoint across multiple communication channels. In some implementations, the network environment 800 may include a network device 805, a terminal device 810, and a communication server 820. The network device 805 may be similar to the network device 705 and therefore will not be described here for the sake of brevity. The terminal device 810 may be similar to the terminal device 715 and therefore will not be described here for the sake of brevity. The communication server 820 may be similar to the communication server 710 and therefore will not be described here for the sake of brevity.
[0093]
[0105] The communication server 820 may establish or facilitate the establishment of a communication channel between the network device 805 and the terminal device 810. As illustrated in FIG. 8, the communication server 820 may establish a communication channel C 840, which allows the network device 805 and the terminal device 810 to exchange one or more messages. As non-limiting examples, the communication channel C 840 may be a web chat feature of a website, the communication channel B 835 may be a chat application running on a mobile device (e.g., a smartphone), and the communication channel A 830 may be a Voice Over Internet Protocol (VOIP) audio channel that allows an agent to communicate with a user.
[0094]
[0106] The communication server 820 may configure the bot 825 to communicate autonomously with the network device 805. In some implementations, the bot 825 may access and execute one or more protocols that enable the bot 825 to communicate with the network device 805 using the communication channel C 840. Continuing with the non-limiting example above, the bot 825 may access and execute a protocol for communicating through a web chat feature of a website. In this example, the protocol may include coding language specific to the web chat feature for exchanging messages using the web chat feature. The protocol, when executed, may include code that converts messages entered by an agent at the terminal device 810 (e.g., text strings or other content) into structured content (e.g., content separated into separate data fields) and maps the structured content to elements of the web chat feature of the website. When input is received at the terminal device 810 (e.g., by an agent), the bot 825 can translate the structured content into elements of the web chat feature to enable the messages to be communicated using the web chat feature.
[0095]
[0107] In some implementations, the bot 825 can also be configured to communicate with the network device 805 using a communication channel B 835. The communication channel B 835 can be a different communication channel than the communication channel C 840. Additionally, the communication channel B 835 may require different elements to facilitate communication than those required for the communication channel C 840. The bot 825 can be configured to translate structured content into elements of the communication channel B 835. Continuing with the non-limiting example described above, the communication channel B 835 may be an in-app chat feature of a native application running on the smartphone. One or more elements may be required to facilitate communication using the communication channel B 835. For example, FACEBOOK MESSENGER may be a native application running on the smartphone. In this example, one or more elements of the FACEBOOK MESSENGER may be templates specific to FACEBOOK MESSENGER that are required to facilitate communication using FACEBOOK MESSENGER. The protocol that enables the bot 825 to communicate using communication channel B835 may map structured content to templates in the FACEBOOK MESSENGER native application to send the structured content as messages within the FACEBOOK MESSENGER application.
[0096]
[0108] In some examples, a mobile application (e.g., a mobile native application) may include executable code (stored on the mobile device or on one or more external servers) that can be executed using an operating system of a network device (e.g., a smartphone). In some examples, a mobile application may include a hybrid mobile application that is composed of native user interface (UI) components (generated and stored on the mobile device) but is written in an interpreted language (e.g., using a web-based coding language). The present disclosure is not limited to mobile native or hybrid applications, and thus any type of mobile application may be used in the methods described herein.
[0097]
[0109] In some implementations, the bot 825 can also be configured to communicate with the network device 805 using communication channel A 830. Communication channel A 835 can be a different communication channel than communication channel C 840 and communication channel B 835. Furthermore, communication channel A 830 may require different elements to facilitate communication than those required for communication channel C 840 and communication channel B 835. The bot 825 can be configured to translate structured content into elements of communication channel A 830. Continuing with the non-limiting example described above, communication channel A 830 may be a VOIP audio communication link between the network device 805 and the terminal device 810. One or more elements may be required to facilitate communication using communication channel A 830. The protocol may include a mapping of structured content to elements associated with communication channel A 830.
[0098]
[0110] In some implementations, the communication server 820 may be configured to dynamically, autonomously, and / or automatically transfer the communication session between different communication channels so that the bot 825 can continue to communicate with the network device 805 regardless of the communication channel. For example, the network device 805 may be communicating with the terminal device 810 using a first communication channel 845 (i.e., communication channel C 840). The network device 805 may send a message indicating that a user operating the network device 805 intends to change the communication channel currently being used for the communication session. For example, the network device 805 may indicate that the second communication channel 850 is a target communication channel for continuing the communication session with the terminal device 810. The bot 825 may automatically detect an indication that the communication channel should be changed from the first communication channel 845 to the second communication channel 850. For example, the bot 825 may continuously evaluate messages exchanged during the communication session to detect that the communication channel should be changed. Upon detecting an indication that the communication channel should be changed, the communication server may identify a user identifier associated with the network device 805. For example, the user data database 815 may store user identifiers for various users. The user identifier may be a string of text and / or numbers that uniquely identifies the network device. If, at any given time, the communication server 820 determines that the same user identifier is associated with two active communication channels, the communication server 820 may recognize that the network device is requesting to continue the communication session but change communication channels.
[0099]
[0111] The communication server 820 may be configured to support continuity between different communication channels. For example, the target communication channel (e.g., the second communication channel 850) can be automatically used by the bot 825 to continue the communication session with the network device 805, albeit using the second communication channel 850 instead of the first communication channel 845. In some implementations, the bot 825 may automatically send a message to the network device 805 using the second communication channel 850. Sending the message to the network device 805 may indicate to the network device 805 that the transfer of the communication channel is complete. In some implementations, the communication server 820 may automatically detect that the communication channel has changed from the first communication channel 845 to the second communication channel 850. For example, the communication server 820 may recognize a user identifier associated with the network device 805 when the network device 805 is communicating with the bot 825 using the first communication channel 845. If the network device 805 begins using the second communication channel 850 (e.g., without indicating an intent to change communication channels during a communication session), the communication server 820 can automatically detect that a user identifier for the network device 805 is currently associated with two active communication channels (e.g., the first communication channel 845 and the second communication channel 850). The communication server 820 can detect that the first communication channel 845 is associated with a recent history of messages (e.g., messages sent or exchanged within the last five minutes) and that the second communication channel 850 is not associated with a recent history of messages (e.g., within the last few minutes). As a result, the communication server 820 can determine that the network device 805 is requesting to transfer the communication session from the first communication channel 845 to the second communication channel 850.The communication server 820 can perform the transfer by accessing a protocol associated with the second communication channel 850 and executing the bot 825 using the accessed protocol to enable the bot 825 or the terminal device 810 to communicate with the network device 805 using the second communication channel 850 instead of using the first communication channel 845.
[0100]
[0112] In some implementations, one or more machine learning techniques can be used to identify patterns in the network device 805's use of communication channels. For example, the use of communication channels by the network device 805 can be tracked and recorded (and stored as historical data). Machine learning techniques can be applied to the historical data to identify which communication channel the network device 805 is most likely to use when communicating with a particular entity (e.g., a bot, an enterprise, an end device, an agent, etc.). When initiating communication from the end device 810 (or a bot 825 or any other end device) to the network device 805, the communication server 820 can establish the type of communication channel that the network device 805 is most likely to use (based on the results of the machine learning techniques). As the network device 805 begins to use different communication channels more frequently, the communication server 820 can identify this changing trend and initiate a communication session using the most used or most frequently used communication channel.
[0101]
[0113] 9 shows a block diagram illustrating a network environment 900 for improving endpoint selection using machine learning techniques. The network environment 900 may include a network device 905 (operated by a user), a communication server 910, a bot 915, and a terminal device 920. The communication server 910 can facilitate the establishment of a communication channel that allows the network device 905 and at least one bot 915 and the terminal device 920 to communicate.
[0102]
[0114] The communication server 910 may include an intelligent routing system 925, a message recommendation system 930, and a message data store 935. Each of the intelligent routing system 925 and the message recommendation system 930 may include one or more computing devices having a processor and memory to execute instructions to perform certain operations. In some implementations, the intelligent routing system 925 may be a bot configured to intelligently route communications received from the network devices to appropriate destinations. The intelligent routing system 925 may include one or more processors configured to execute code that causes one or more machine learning or artificial intelligence techniques to intelligently route messages. In some implementations, the intelligent routing system 925 can execute one or more machine learning techniques to train a model to predict a destination associated with a message received from the network device 905.
[0103]
[0115] As a non-limiting example, the intelligent routing system 925 may receive messages from the network device 905 through a communication channel established or facilitated by the communication server 910 (e.g., a native application configured to enable users to communicate with each other across various devices). The intelligent routing system 925 may evaluate the incoming message according to certain embodiments described above. For example, the intelligent routing system 925 may use a trained machine learning model to evaluate the content (e.g., text, audio clips, images, emoticons, or other suitable content) included in the received message. The content of the message can be input to the machine learning model to generate a predicted destination (e.g., a particular terminal device or bot). The machine learning model may be trained continuously based on a feedback signal 940 received from the network device 905. In some implementations, the intelligent routing system 925 may request an acknowledgement from the network device 905 for the predicted destination. As a non-limiting example, the intelligent routing system 925 may evaluate the message using machine learning techniques, and the results of the evaluation may include a prediction that the bot 915 is a destination for the message. To confirm, the intelligent routing system 925 may automatically request a feedback signal 940. For example, the feedback signal 940 may include a request for the network device 905 to acknowledge whether the bot 915 is the correct destination for the message (e.g., "Is tech support the correct destination?").If the network device 905 sends an acknowledgment that the bot 915 is the correct destination (e.g., the destination intended by the user operating the network device 905), the intelligent routing system 925 may train a machine learning model to predict that future messages containing identical or similar content to the received message (e.g., a similarity threshold, such as a 10 percent difference in content) should be routed to the bot 915. However, if the intelligent routing system 925 receives a feedback signal 940 indicating that the bot 915 was not the correct or intended destination for the received message, but rather the terminal device 920 was, the intelligent routing system 925 can train the machine learning model such that future messages containing identical or similar content to the received message will be routed to the terminal device 920 (instead of the bot 915). In some implementations, the intelligent routing system 925 may not immediately update or train the machine learning model to route future messages to the terminal device 920; rather, the intelligent routing system 925 may wait until a threshold number of incorrect routings to the bot 915 before routing all future messages having the exact same or similar content as the received message to the terminal device 920. As a non-limiting example, the intelligent routing system 925 may begin routing future messages (that were predicted to be routed to the bot 915) to the terminal device 920 instead of the bot 915 after five instances in which a network device has sent a feedback signal indicating that the bot 915 is not the correct or intended destination.
[0104]
[0116] In some embodiments, the intelligent routing system 925 may select where to route a given message based on received bids for processing a particular request in the message. The intelligent routing system 925 may broadcast intent to different services to determine who wants to bid to process the request. The bidding parties may respond with their confidence in successfully processing the request and a plan to perform the processing of the request. The intelligent routing system 925 may evaluate all responses from the bidding parties and determine which bidding party to use for a given message based on machine learning policies.
[0105]
[0117] The message data store 935 may store some or all (e.g., not all) messages previously received from one or more network devices. Additionally, the message data store 935 may also store some or all messages sent by a terminal device or a bot during a previous communication session with a network device. The message data store 935 may also store some or all messages sent by a network device to a bot during a communication session. Additionally, the message data store 935 may store some or all messages sent by a bot to a network device during a communication session. In some implementations, the message data store 935 may be a database of all messages processed by (e.g., sent by or received at) the communication server 910.
[0106]
[0118] The message recommendation system 930 may analyze a database of messages stored in the message data store 935. In some implementations, the message recommendation system 930 may use one or more machine learning or artificial intelligence algorithms to evaluate the messages stored in the message data store 935. For example, the message recommendation system 930 may run one or more clustering algorithms, such as K-means clustering, means-shift clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering, Expectation-Maximization (EM) clustering using Gaussian Mixture Models (GMM), and other suitable machine learning algorithms, on the database of messages stored in the message data store 935. In some implementations, a recurrent neural network (RNN) or a convolutional neural network (CNN) may be used to predict a response message to assist the agent. In some implementations, the message recommendation system 930 may use support vector machines (SVM), supervised, semi-supervised, ensemble techniques, or unsupervised machine learning techniques to evaluate all previous messages with the goal of predicting a response to an incoming message received from a network device during a communication session. For example, the message recommendation system 930 may evaluate the content of a message received from a network device (or a message received at the communication server 910 from a bot or terminal device) and compare the results of the evaluation to one or more clusters of previous messages stored in the message data store 935. Once the clusters are identified, the message recommendation system 930 can identify the most relevant response message based on a confidence threshold.For example, an incoming message (e.g., received at the communication server 910 from the network device 905) may correspond to a technical issue based on the content of the incoming message. The message recommendation system 930 may identify that the incoming message corresponds to a technical issue based on an evaluation (e.g., a text evaluation) of the content of the incoming message. The message recommendation system 930 may access the message data store 935 to identify a cluster of messages related to the technical issue. The message recommendation system 930 may select one or more response messages in the cluster of messages based on a confidence threshold. As a non-limiting example, a confidence algorithm may be performed to generate a confidence score. The confidence score may be a percentage value where the lower the percentage, the less likely the response is a good prediction for the incoming message and the higher the percentage, the more likely the response is a good prediction for the incoming message. The minimum confidence threshold may be defined as a measure of certainty or credibility associated with each discovered pattern. Further, an example of a confidence algorithm may be an a priori algorithm, a similarity algorithm indicating the similarity between two data sets, and other suitable confidence algorithms.
[0107]
[0119] FIG. 10 illustrates an exemplary process for monitoring and training bot behavior. In the illustrated method, certain criteria may be defined and stored in memory. Such criteria may be applicable to a conversation conducted between a bot (or a set of bots) and a customer. When a conversation is identified as not meeting the criteria, the conversation is escalated to an agent device associated with a human agent. For example, the bot may make a prediction regarding a particular intent of the customer (e.g., to purchase or return a particular product, need to update an address, password, or other user information). The agent may review the conversation and provide input that may classify or reclassify the conversation. The conversation may be returned to the bot for continued execution taking into account the classification input. Additionally, the classification input may be used to update a learning model associated with the bot, and such updated learning model may be used to execute subsequent conversations.
[0108]
[0120] In step 1005, a set of monitoring criteria may be stored in memory, including a threshold level of trust. Such stored criteria may define factors (and levels thereof) that may be measured and considered in making a decision to escalate an ongoing conversation with a bot. The set of monitoring criteria may, for example, specify one or more conditions that are used to determine a threshold level of trust. The specified conditions may be detected, counted, measured, or otherwise evaluated within a conversation and compared to the threshold level of trust. Different aspects of a message or set of messages within a conversation may be evaluated against the stored criteria. In some embodiments, different sets of criteria may apply to different bots, departments, geographic locations, and systems. Such criteria may also be customized to a particular business entity or industry.
[0109]
[0121] In step 1010, one or more messages in a conversation between the bot and the user of the client device may be monitored and evaluated against the set of monitoring criteria stored in step 1005. Such monitoring may be performed for a particular bot, a particular group of bots, a particular department, or the entire system. The specification of what to monitor may be customized for different entities or businesses, or for sets of associated agents. For example, messages associated with a new type of bot may be specified for monitoring.
[0110]
[0122] In step 1015, the monitored messages may be further passed to predict one or more intents regarding a particular need of the customer. For example, a conversation queue may indicate intents related to product information, purchasing, and updating user information. Such intents may drive bot coordination of the conversation and results, for example, in routing the conversation to bots tasked with providing product information, processing purchase orders, and handling updated user information, respectively.
[0111]
[0123] Each prediction regarding the user intent may be scored (confidence score) based on the stored criteria, and the score may be compared to a threshold level of confidence. In some examples, one or more of the bot predictions regarding the user intent may meet at least the set threshold level of confidence, and the bot may proceed to conduct the conversation in a manner that meets the customer's needs without requiring intervention. In step 1020, the predicted intent for a particular conversation may not meet at least the threshold level of confidence. For example, a particular intent prediction by a bot may not meet the threshold level of confidence when the confidence score assigned to that intent prediction is compared to the threshold level of confidence and found to not meet the threshold level of confidence.
[0112]
[0124] In step 1025, the request for input may be sent to the agent device, which may respond by providing classification input regarding the conversation. When a conversation is flagged as failing to fully meet the threshold level of confidence, such failure may indicate to the agent that the conversation may need to be escalated in order to maintain a certain level of customer satisfaction. Thus, agent intervention may be requested. Rather than completely handing over the task of conducting the identified conversation to the agent, the request may specifically request input regarding the particular intent prediction that does not meet the threshold level of confidence (e.g., from among one or more other identified intent predictions that do not meet the threshold level of confidence). In an exemplary embodiment, the request may present at least a portion of the conversation associated with the particular intent prediction that did not meet the threshold level of confidence. Some embodiments may further present a set of options associated with the request for input. Such options may be associated with different types of bots (or other parameters of the conversation that are required to improve the intent prediction).
[0113]
[0125] In step 1030, input from the agent device can be provided to the bot, which can use such input to classify and route the conversation to one or more endpoint devices (e.g., other bots or agents). Such classification and routing may be the same as or different from the identified predictions that did not meet a threshold level of confidence. If the classification input enables a better intent prediction regarding purchase intent, for example, the conversation may be handed off to a bot designed to take purchase orders. In some examples, the routing and handoff of the conversation to one or more endpoints may occur in real-time as the conversation is ongoing. For example, the bot can continue to ask follow-up questions regarding one or more potential intents even when the conversation is escalated to an agent device.
[0114]
[0126] In step 1035, it may be determined whether any new annotations are ready to be added to the learning model associated with the bot, and if not, the method may return to step 1010 and continue to monitor further conversations. If there are annotations ready to be added to the learning model, the method may proceed to step 1040. In addition to satisfactorily facilitating bot behavior related to the current conversation, the classification input from the agent device may also be stored and tracked in the learning model for use by the same bot, bots of the same type, and / or other system bots in future conversations. Such classification input may function, for example, like an annotation to the conversation. In some examples, the learning model may be updated based on a single annotated conversation, or based on multiple conversations annotated in the same or similar manner according to the same or similar classification input.
[0115]
[0127] In step 1040, the new classification input may be added to the learning model for use in future conversations. For example, a bot having a future similar conversation may no longer make predictions that do not meet the threshold level of confidence. In this way, future similar conversations are therefore not escalated to the agent device. Instead, the bot may use the learning model (immediately updated based on the classification input from the agent device) in real time when conducting the next conversation to arrive at an intent prediction (e.g., following the intent prediction or routing decision of step 1030). Such intent prediction may further be assigned a classification score that meets at least the threshold level of confidence.
[0116]
[0128] 11 shows a block diagram representing a network environment in which a system for monitoring bot behavior and training may be implemented. As shown, the network environment may be categorized by operations associated with customer devices 1105, bot interaction management 1110, bot intent recognition 1115, bot monitoring 1120, and agent devices 1125, respectively. Thus, conversations may involve and be routed between multiple different devices and systems based on real-time analysis of incoming communications.
[0117]
[0129] Bot dialogue management operations may include functions involving communicating with the customer via any mode known in the art, including phone, text (e.g., SMS, MMS, instant message), graphics, etc. Such dialogue management operations may include greeting the customer, asking questions or providing prompts for specific customer information, and generating responses to the customer. Response generation may be based on learning models for dialogue management or based on inputs (e.g., from agent devices) related to dialogue management and classification. Data regarding the conversation may be tracked continuously in real time and stored in conjunction with historical data. Historical and real-time data may also be incorporated into the learning model, which is dynamically updated to take into account the historical and real-time data. Such updates to the learning model may further result in dynamic adjustments to predictions and recommendations made for similar conversations over time. Different learning models may also be customized to different entities (e.g., companies, brands) operating the bot, different customers, and categories thereof.
[0118]
[0130] Intent recognition operations may include text classification, dialogue annotation for intent recognition, and training of intent-related models. Alternatively, a customer may be prompted for such information to initiate a conversation, interaction with predefined contexts (e.g., buttons, drop-down menus), or natural language communication. As discussed above, such information may be provided through a variety of different types of communication channels. Regardless of the channel, such customer input may be parsed, analyzed, and used to perform operations related to bot dialogue management 1110, intent recognition 1115, and bot monitoring 1120 in real time.
[0119]
[0131] In step 1130, the customer device 1105 may initiate a conversation within the communication system. The customer device 1105 may initiate a conversation through any of the channels described above. Such initiation may be explicit (e.g., requesting or selecting an option) or implicit (e.g., repeated searching, extended browsing). Based on the initiation, a communication session may be established between the customer device 1105 and the chatbot (e.g., the chatbot dialogue management system 1110).
[0120]
[0132] In step 1135, the chatbot dialogue management system 1110 may respond to the initiation of the conversation or establishment of the communication session by sending a greeting or other prompt to the customer device. In some implementations, the communication session may be associated with a graphical user interface in which the customer at the customer device 1105 may make selections (e.g., button clicks from a drop-down menu) or interact with predefined content in step 1140. The chatbot dialogue management system 1110 may respond to such selections or interactions based on predefined dialogue management rules and policies.
[0121]
[0133] In some examples, a customer 1105 at a customer device may input a natural language communication, such as at step 1150. The chatbot intent recognition system 1115 may then, at step 1155, classify the natural language communication according to one or more learning models. Such learning models may include both historical and real-time data regarding multiple different conversations. The data may include data regarding the particular customer, any chatbots or agents involved, operating entities, keywords and phrases, actual messages exchanged, routing decisions, conversation outcomes, and other contextual data.
[0122]
[0134] In step 1160, it is determined whether the confidence score associated with the classification meets a specified criterion or threshold. If so, the method proceeds to step 1165 where the chatbot dialogue management system 1110 can respond to the natural language communication based on the classification. If the confidence score associated with the classification does not meet the specified criterion or threshold, the method proceeds to step 1170 where it is determined whether the chatbot dialogue management system 1110 currently involved in the conversation is capable of serving the user text. If the chatbot dialogue management system 1110 currently involved in the conversation is not capable of serving the user text, the method proceeds to step 1180 where the conversation is routed to another bot or agent.
[0123]
[0135] Once it is determined that the chatbot dialogue management system 1110 currently engaged in the conversation is indeed capable of serving the user text, the method may proceed to step 1175, where a live agent using an agent device 1125 is queried in real-time regarding the classification of the natural language communication entered by the customer at the customer device 1105. Thus, in situations where the natural language communication cannot be categorized by the chatbot intent recognition system 1115 with a certain level of confidence (e.g., 80%, 90%), the natural language communication (and associated contextual data) may be provided to the agent device 1125 for real-time classification.
[0124]
[0136] The classification provided by the live agent of the agent device 1125 may be provided to the chatbot dialogue management system 1110 as the method returns to step 1165 for the continued conversation. In addition, the classification provided by the live agent of the agent device 1125 may also be added to a database for storage in step 1185. The classification from the live agent of the agent device 1125 may also be used to update one or more learning models in real time such that other ongoing conversations involving similar natural language communications may be classified with a higher level of confidence than before the update.
[0125]
[0137] In some implementations, a live agent at the agent device 1125 may also provide annotations to the natural language communication or other conversational data. Such annotations may provide further context and supplemental information to understand the intent.
[0126]
[0138] In step 1190, it may be determined whether there were any new annotations associated with the classification. If there are no new annotations, the method may end. If there are any new annotations associated with the classification, the method may proceed to step 1195, where the annotations are added to the data used for intent recognition and classification of natural language communications. Then, in step 1199, any learning models that rely on such data may be retrained in real time based on the classification and associated annotations.
[0127]
[0139] Bot monitoring operations may include the operations described with respect to FIG. 11, including evaluating confidence scores, comparing confidence scores to specified thresholds, and adding new classification inputs and new annotations to the learning model database. Bot monitoring may further operate with input from a human agent, which may include text classification, which may be used directly or indirectly to provide routing instructions for the current conversation. Furthermore, such input may be used to update the learning model and database, such that the same classification inputs may not be required from a human agent for future conversations conducted by the bot.
[0128]
[0140] 12 illustrates an example interface for monitoring bot behavior and training. Such an interface may be presented on an agent device in response to a request from a bot. As shown, such an interface may include several parts: a list 1210 of different conversations (e.g., associated with bot escalations), a detailed view 1220 of one particular conversation that may be shown (with routing options) within the agent monitoring graphical user interface, detailed information 1230 regarding a particular campaign (e.g., business) associated with the conversation, and an overview GUI 1240.
[0129]
[0141] A list of different conversations 1210 may be routed to the agent device 1125 based on the current natural language communication having a classification that did not meet a certain criterion or threshold. Additionally, as illustrated in the agent monitoring GUI 1220 portion of the interface, the natural language communication may be presented with a set of different options (e.g., corresponding to different classifications). The options may be selectable to classify the natural language communication in real-time, as the classification is provided to the chatbot dialogue management system 1110 so that it can formulate a response based on the classification and thus continue the conversation. Contextual data 1230 may also be provided to the interface so that the agent at the agent device 1125 can reference the contextual data 1230 when making the classification. Such contextual data may include data about a particular campaign, data about a particular conversation, or personal data about the customer.
[0130]
[0142] When a human agent selects one of the options presented in the agent monitoring GUI 1220, such option can then be used to classify the intent prediction associated with the conversation. The overview GUI 1240 portion of the interface can be used to input annotations associated with the classification. The conversation can be returned to the bot to act according to the selected option for the intent prediction. In addition, such selections can be analyzed in the context of similar conversations and used to update relevant learning models used by the bot in future conversations. Meanwhile, the classifications and annotations can be used to refine learning models for message classification and intent recognition. Such learning models can be applied to ongoing and future conversations, which can then result in different classifications and confidence levels for such classifications.
[0131]
[0143] The disclosed systems and methods for bot monitoring can be implemented using a computing server. An exemplary computing server can 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 sets of code, software, scripts, etc. The components of the computer server can be coupled to each other via a bus or through 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 code stored in the memory. One or more of the user device or computer, the provider server or servers, or the suspended database update server may include components of a computing server or variations of such servers.
[0132]
[0144] The present disclosure contemplates a computer server taking any suitable physical form, including, but not limited to, a point-of-sale server ("POS"). By way of example and not limitation, a computer server may be an embedded computer server, a server-on-chip (SOC), a single-board computer server (SBC) (e.g., a computer-on-module (COM) or server-on-module (SOM) etc.), a desktop computer server, a laptop or notebook computer server, an interactive kiosk, a mainframe, a mesh of computer servers, a mobile phone, a personal digital assistant (PDA), a server, or a combination of two or more of these. Where appropriate, a computer server may include one or more computer servers; may be single or distributed; may span multiple locations; may span multiple machines; and / or may reside in a cloud that may include one or more cloud components in one or more networks. Where appropriate, one or more computer servers may perform one or more steps of one or more methods described or illustrated herein without substantial spatial or temporal limitations. By way of example, and not limitation, one or more computer servers may perform one or more steps of one or more methods described or illustrated herein in real time or in batch mode. One or more computer servers may, where appropriate, perform one or more steps of one or more methods described or illustrated herein at different times or in different locations.
[0133]
[0145] 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 terms "machine-readable (storage) medium" or "computer-readable (storage) medium" include any type of device that can be accessed by a processor.
[0134]
[0146] The memory may be coupled to the processor, for example, by a bus. The memory may include, by way of example and not limitation, random access memory (RAM), such as dynamic RAM (DRAM) and static RAM (SRAM). The memory may be local, remote, or distributed.
[0135]
[0147] The bus may also couple the processor to non-volatile memory and drive units. Non-volatile memory is often a magnetic floppy disk or hard disk, a magneto-optical disk, an optical disk, a CD-ROM, a read-only memory (ROM) such as an EPROM or EEPROM, a magnetic or optical card, or another form of storage for large amounts of data. Part of this data is often written to the memory during the execution of software in the computer by a direct memory access process. The non-volatile storage may be local, remote, or distributed. The non-volatile memory is optional since a server may be created with all applicable data available in the memory. A typical computer server usually includes at least a processor, a memory, and a device (e.g., a bus) that couples the memory to the processor.
[0136]
[0148] The software can be stored in a non-volatile memory and / or a drive unit. In fact, for large programs, it may not even be possible to store the entire program in memory. It should be understood, however, that in order to execute the software, it is moved, if necessary, to a computer-readable location suitable for processing, and for purposes of illustration, that location is referred to herein as memory. Even when the software is moved to memory for execution, the processor can utilize hardware registers to store values associated with the software, and ideally a local cache, which serves to speed up execution. As used herein, a software program is assumed to be stored in any known or convenient location (from non-volatile storage to hardware registers) when the software program is referred to as being "embodied in a computer-readable medium." A processor is considered to be "configured to execute a program" when at least one value associated with the program is stored in a register readable by the processor.
[0137]
[0149] The bus may also couple the processor to a network interface device. The interface may include one or more of a modem or a network interface. It will be appreciated that the modem or network interface may be considered to be part of the computer server. The interface may include an analog modem, an integrated services digital network (ISDN0 modem, a cable modem, a token ring interface, a satellite transmission interface (e.g., "Direct PC"), or other interface for coupling the computer server to other computer servers. The interface may include one or more input and / or output (I / O) devices. The I / O devices may include, by way of example and not limitation, 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. The display device may include, by way of example and not limitation, a cathode ray tube (CRT), a liquid crystal display (LCD), or any other applicable known or convenient display device.
[0138]
[0150] In operation, computer servers may be controlled by operating server software, including file management servers, such as disk operating servers. One example of operating server software with associated file management server software is the family of operating servers known as Windows® from Microsoft Corporation of Redmond, Washington, and their associated file management servers. Another example of operating server software with associated file management server software is the Linux® operating server and its associated file management servers. The file management servers may be stored in non-volatile memory and / or drive units, and may have a processor perform various operations required by the operating server to input and output data and store data in the memory, including storing files in the non-volatile memory and / or drive units.
[0139]
[0151] Some portions of the detailed descriptions may be presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of operations leading to a desired result. The operations require physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, or otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.
[0140]
[0152] It should be noted, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. As will be apparent from the discussion below, unless specifically stated otherwise, throughout this application, discussions utilizing terms such as "processing," or "computing," or "calculating," or "determining," or "displaying," or "generating," or the like, are understood to refer to the actions and processing of a computer server or similar electronic computing device that manipulates and converts data represented as physical (electronic) quantities in the computer server's registers and memory into other data similarly represented as physical quantities in the computer server's memory or registers, or other such information storage, transmission, or display device.
[0141]
[0153] The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose servers may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform some of the example methods. The required structure for a variety of these servers will appear from the description that follows. In addition, the techniques are not described with reference to any particular programming language, and thus the various examples may be implemented using a variety of programming languages.
[0142]
[0154] In various implementations, a server may operate as a stand-alone device or may be connected (e.g., networked) to other servers. In a networked deployment, a server may operate in a server or client-server capacity in a client-server network environment, or as a peer server in a peer-to-peer (or distributed) network environment.
[0143]
[0155] A server 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 telephone, a web appliance, a network router, switch or bridge, or any server capable of executing (sequentially or otherwise) a set of instructions that specify actions to be taken by that server.
[0144]
[0156] Although the machine-readable medium or machine-readable storage medium is shown as being a single medium by way of example, the terms "machine-readable medium" and "machine-readable storage medium" should be interpreted to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more sets of instructions. The terms "machine-readable medium" and "machine-readable storage medium" should also be interpreted to include any medium capable of storing, encoding, or carrying a set of instructions for execution by a server, causing the server to perform any one or more of the methodologies or modules disclosed herein.
[0145]
[0157] In general, the routines executed to realize an implementation of the present disclosure may be realized as part of an operating system or a specific application, component, program, object, module, or sequence of instructions referred to as a "computer program." A computer program is typically stored at various times in various memory and storage devices within a computer, and includes one or more instructions that, when read and executed by one or more processing units or processors within the computer, cause the computer to perform operations to implement elements including various aspects of the present disclosure.
[0146]
[0158] Moreover, while the examples are described in the context of fully functional computers and computer servers, those skilled in the art will appreciate that the various examples may be distributed as program objects in a variety of forms, and that the present disclosure applies equally regardless of the particular type of machine-readable or computer-readable medium used to actually effect the distribution.
[0147]
[0159] Further 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 and other removable disks, hard disk drives, optical disks (e.g., Compact Disk Read Only Memory (CD ROM), Digital Versatile Disk (DVD), etc.), and transmission type media such as digital and analog communications links, among others.
[0148]
[0160] In some circumstances, an operation of a memory device, such as a change in state from a binary 1 to a binary 0 or vice versa, may comprise a transformation, such as, for example, a physical transformation. In certain types of memory devices, such a physical transformation may comprise a physical transformation of an article to a different state or thing. For example, but not by way of limitation, for some types of memory devices, a change in state may involve the accumulation and storage of an electric charge or the release of a stored electric charge. Similarly, in other memory devices, a change in state may comprise a physical change or transformation in magnetic orientation, or a physical change or transformation in 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 in state from a binary 1 to a binary 0 or vice versa in a memory device may comprise a transformation, such as a physical transformation. Rather, the foregoing is intended as an illustrative example.
[0149]
[0161] Storage media may typically be non-transitory or may include non-transitory devices. In this context, non-transitory storage media may include devices that are tangible, meaning that the device has a concrete, tangible physical form, although the device can change its physical state. Thus, for example, non-transitory refers to a device that remains tangible despite this change in state.
[0150]
[0162] The above description and drawings are illustrative and should not be construed as limiting the subject matter to the precise form disclosed. Those skilled in the art will appreciate that many modifications and variations are possible in light of the above disclosure. Numerous specific details have been described in order to provide a thorough understanding of the present disclosure. However, in certain instances, well-known or conventional details have not been described in order to avoid obscuring the description.
[0151]
[0163] As used herein, the terms "connected," "coupled," or any variation thereof, when applied to a module of a server, means any direct or indirect connection or coupling between two or more elements, and the coupling of connections between the elements may be physical, logical, or any combination thereof. In addition, the terms "herein," "above," "below," and terms of similar import, when used in this application, shall refer to this application as a whole and not to any particular portions of this application. Where the context permits, terms in the above Detailed Description using singular or plural numbers may also include plural or singular numbers, respectively. The term "or" in reference to a list of two or more items covers all of the following interpretations of that term: any of the items in the list, all of the items in the list, or any combination of the items in the list.
[0152]
[0164] Those skilled in the art will appreciate that the disclosed subject matter may be embodied in other forms and manners not set forth below. It will be understood that the use of related terminology, if any, such as first, second, top and bottom, and the like, is only used to distinguish one entity or action from another, without necessarily requiring or implying any such actual relationship or order between such entities or actions.
[0153]
[0165] Although processes or blocks are presented in a given order, alternative implementations may perform routines having steps or use servers having blocks in a different order, and some processes or blocks may be deleted, moved, added, sub-divided, substituted, combined, and / or modified to provide alternative or sub-combinations. Each of these processes or blocks may be implemented in a variety of different ways. Also, while processes or blocks are at times shown as being performed sequentially, these processes or blocks may instead be performed in parallel or at different times. Additionally, any specific numbers referenced herein are examples only, and alternative implementations may employ different values or ranges.
[0154]
[0166] The teachings of the disclosure provided herein may be applied to other servers, not necessarily those described above. Elements and operations of the various examples described above may be combined to provide further examples.
[0155]
[0167] Any of the above patents and applications and other references, including any that may be listed in accompanying application papers, are incorporated herein by reference. Aspects of the present disclosure can be modified, if necessary, to employ the servers, functionality, and concepts of the various references described above to provide still further examples of the present disclosure.
[0156]
[0168] These and other modifications can be made to the present disclosure in light of the above detailed description. Although the above description illustrates certain examples and describes the best mode contemplated, no matter how detailed the above may be in the text, the present teachings can be implemented in many ways. The details of the server may vary widely in their implementation details while still being encompassed by the subject matter disclosed herein. As also noted above, it should be noted that a particular term used when describing a particular feature or aspect of the present invention should not be taken to imply that the term is redefined herein to be limited to any particular characteristic, feature, or aspect of the present disclosure with which the term is associated. In general, the terms used in the following claims should not be construed to limit the disclosure to the particular implementations disclosed herein, unless the detailed description section above explicitly defines such terms. Thus, the actual scope of the present disclosure encompasses not only the disclosed implementations, but also all equivalent ways of practicing or implementing the present disclosure under the scope of the claims.
[0157]
[0169] Although some aspects of the disclosure are presented below in some claim form, the inventors contemplate various aspects of the disclosure in any number of claim forms. Any claim intended to be treated under 35 U.S.C. 112(f) will begin with the phrase "means 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 disclosure.
[0158]
[0170] The terms used in this specification generally have their ordinary meaning in the art in the specific context in which each term is used within the context of this disclosure. Some terms used to describe this disclosure are explained above or elsewhere in this specification to provide additional guidance to practitioners regarding the description of this disclosure. For convenience, some terms may be highlighted, for example, by using capitalization, italics, and / or quotation marks. The use of highlighting has no effect on the scope and meaning of a term, and the scope and meaning of a term is the same in the same context whether it is highlighted or not. It will be understood that the same element can be described in more than one way.
[0159]
[0171] Thus, alternative wording and synonyms may be used for any one or more of the terms described herein, and no special importance is placed on whether a term is recited or explained herein. Synonyms for some terms are provided. The recitation of one or more synonyms does not exclude the use of other synonyms. The use of examples anywhere in this specification, including examples of any term described herein, is merely illustrative and is not intended to further limit the scope and meaning of the disclosure or any exemplified term. Similarly, the disclosure is not limited to the various examples provided herein.
[0160]
[0172] Without intending to further limit the scope of the present disclosure, examples of instruments, devices, methods and their related results according to the examples of the present disclosure are given below. Please note that titles or subtitles may be used in the examples for the convenience of the reader, and in any case, this should not limit the scope of the present disclosure. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure pertains. In case of conflict, this document, including definitions, shall control.
[0161]
[0173] Some portions of this specification describe examples in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations are commonly used by those skilled in the data processing arts to effectively convey the substance of their work to others skilled in the art. These operations, while described functionally, computationally, or logically, will be understood to be implemented by computer programs or equivalent electrical circuits, microcode, or the like. Further, it has proven convenient at times to refer to these configurations of operations as modules, without loss of generality. The described operations and their associated modules may be embodied in software, firmware, hardware, or any combination thereof.
[0162]
[0174] Any of the 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, a software module is implemented in a computer program object comprising a computer readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the steps, operations, or processes described.
[0163]
[0175] Examples may also relate to an apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes and / or may comprise a general-purpose computing device selectively activated or reconfigured by a computer program stored in the computer. Such computer programs may be stored in a non-transitory, tangible computer-readable storage medium, which may be coupled to a computer server bus, or in any type of medium suitable for storing electronic instructions. Additionally, any computing server referred to herein may include a single processor or may be an architecture employing a multiple processor design to increase computing power.
[0164]
[0176] Examples may also relate to objects produced by the computing processes described herein. Such objects may comprise information resulting from 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.
[0165]
[0177] The language used herein has been selected primarily for ease of reading and instructional purposes, and not to specifically delineate or limit the subject matter. Accordingly, the scope of the disclosure is intended to be limited not by this detailed description, but by any claims issued on an application based hereon. Accordingly, the disclosure of the examples is intended to be illustrative, but not limiting, of the scope of the subject matter described in the following claims.
[0166]
[0178] Specific details have been provided in the above description to provide a thorough understanding of various implementations of the servers and components for the context connection server. However, it should be understood by those skilled in the art that the above-described implementations may be practiced without these specific details. For example, circuits, servers, networks, processes, and other components may be shown as components in block diagram form so as not to obscure the embodiments with unnecessary detail. In other examples, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail so as to avoid obscuring the embodiments.
[0167]
[0179] It should also be noted that the individual implementations may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe operations as a sequential process, many of the operations may be performed in parallel or simultaneously. Additionally, the order of operations may be rearranged. A process terminates when its operations are completed, but may have additional steps not included in the drawings. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination may correspond to the call of the function or a return of the function to the main function.
[0168]
[0180] The client devices, network devices, and other devices may be computing servers that include, among other things, one or more integrated circuits, input devices, output devices, data storage devices, and / or network interfaces. The integrated circuits may include, for example, one or more processors, volatile memory, and / or non-volatile memory, among other things. The input devices 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 devices may include, for example, a display screen, a speaker, a haptic feedback server, a printer, and / or other types of output devices. The data storage devices, such as a hard drive or flash memory, may enable the computing device to temporarily or permanently store data. The network interfaces, such as wireless or wired interfaces, may enable the computing device to communicate with a network.
[0169]
[0181] Examples of computing devices include desktop computers, laptop computers, server computers, handheld computers, tablets, smartphones, personal digital assistants, digital home assistants, as well as machines and equipment in which computing devices are embedded.
[0170]
[0182] 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 transporting instructions and / or data. Computer-readable media may also include non-transitory media that can store data and do not include carrier waves and / or transitory electronic signals propagating wirelessly or over wired connections. Examples of non-transitory media may include, but are not limited to, magnetic 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 store code and / or machine-executable instructions, which may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, or the like.
[0171]
[0183] Additionally, the various examples described above may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented by software, firmware, middleware, or microcode, the program code or code segments (e.g., computer program product) to perform the necessary tasks may be stored in a computer-readable or machine-readable medium (e.g., a medium for storing program code or code segments). A processor implemented in an integrated circuit may perform the necessary tasks.
[0172]
[0184] When a component is described as being "configured to" perform a certain operation, such configuration may be achieved, for example, by designing electronic circuitry or other hardware to perform the operation, by programming programmable electronic circuitry (e.g., a microprocessor or other suitable electronic circuitry) to perform the operation, or any combination thereof.
[0173]
[0185] The various example logic blocks, modules, circuits, and algorithm steps described in connection with the implementations disclosed herein may be implemented as electronic hardware, computer software, firmware, or a combination thereof. To clearly illustrate this interchangeability of hardware and software, the various example components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall server. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
[0174]
[0186] The techniques described herein may also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques may be implemented in any of a variety of devices, such as a general purpose computer, a wireless communication device handset, or an integrated circuit device having multiple uses, including applications in wireless communication device handsets and other devices. Any features described as modules or components may be implemented together in an integrated logic device, or separately as discrete but interoperable logic devices. If implemented in software, the techniques may be realized at least in part by a computer-readable data storage medium comprising program code including instructions that, when executed, perform one or more of the methods described above. The computer-readable data storage medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may comprise a memory or data storage medium such as random access memory (RAM), such as synchronous dynamic random access memory (SDRAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), FLASH memory, magnetic or optical data storage media, and the like. The present technology may additionally or alternatively be embodied at least in part by a computer-readable communications medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computer, such as a propagated signal or wave.
[0175]
[0187] The program code may 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 circuits or discrete logic circuits. Such a processor may be configured to perform any of the techniques described in this disclosure. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Thus, as used herein, the term "processor" may refer to any of the foregoing structures, any combination of the foregoing structures, or any other structure or device suitable for implementing the techniques described herein. Additionally, in some aspects, the functionality described herein may be provided within dedicated software or hardware modules configured for implementation of a suspended database update server.
[0176]
[0188] The foregoing detailed description of the technology has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the technology to the precise form disclosed. Many modifications and variations are possible in light of the above teachings. The described embodiments were chosen 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.
[0177]
[0189] Thus, while specific embodiments of the present invention have been described, other embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results. The invention as described in the claims of the original application is set forth below. [C1] 1. A computer-implemented method, comprising: storing a set of supervision criteria in a memory, the set of supervision criteria including a threshold level of confidence; monitoring one or more messages in a conversation between the bot and a user of the client device; Detecting that a bot prediction associated with the conversation does not meet the threshold level of confidence; requesting input from an agent device, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction. [C2] Detecting that the bot prediction does not meet the threshold level of confidence includes: assigning a confidence score to the bot prediction; and comparing the assigned confidence score to a threshold level of confidence. [C3] The computer-implemented method of claim 1, wherein the routing of the conversation to the one or more endpoints occurs in real time. [C4] The computer-implemented method of C1, further comprising annotating the messages in the conversation based on the classification input. [C5] The computer-implemented method of C4, wherein the learning model is updated based on the annotated messages. [C6] The computer-implemented method of C1, wherein routing the conversation includes providing the classification input to the bot, the classification corresponding to a prediction that is different from the bot prediction. [C7] The computer-implemented method of C6, wherein the bot routes the conversation by using the different prediction corresponding to the classification input in place of the bot prediction that did not meet the threshold level of confidence. [C8] Routing subsequent conversations is making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; and routing the subsequent conversation to the one or more endpoints based on the prediction. [C9] The computer-implemented method of C1, wherein requesting the input includes presenting the prediction within a set of prediction options to an agent device. [C10] The computer-implemented method of C1, wherein updating the learning model is further based on one or more other conversations associated with other classification inputs that correspond to the classification input. [C11] The computer-implemented method of C1, wherein the classification input further includes one or more selections of content from the messages in the conversation. [C12] The computer-implemented method of C1, wherein the set of supervision criteria further specifies one or more conditions, and further comprising setting the threshold level of trust based on a condition of the conversation that corresponds to the condition specified by the supervision criteria. [C13] 1. A system comprising: a memory for storing a set of confidence criteria in said memory, said set of confidence criteria including a threshold level of confidence; a communications interface for receiving data over a communications network, said received data relating to one or more messages in a monitored conversation between the bot and a user of a client device; one or more processors; one or more non-transitory machine-readable storage media comprising instructions executable by the one or more processors to perform operations, the operations including: Detecting that a bot prediction associated with the conversation does not meet the threshold level of confidence; requesting input from an agent device regarding the conversation, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction. [C14] The processor, assigning a confidence score to the bot prediction; and comparing the assigned confidence score to the threshold level of confidence. Detecting when the bot prediction does not meet the threshold level of confidence. [C15] The system of C13, wherein the processor routes the conversation to the one or more endpoints in real time. [C16] The system of C13, further comprising instructions executable by the processor to annotate the messages in the conversation based on the classification input. [C17] The system of C16, wherein the learning model is updated based on annotated messages. [C18] The system of C13, wherein the processor routes the conversation by providing the classification input to the bot, the classification corresponding to a prediction that is different from the bot prediction. [C19] The system of C18, wherein the bot routes the conversation by using the different prediction corresponding to the classification input instead of the bot prediction that did not meet the threshold level of confidence. [C20] The processor, making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; and routing the subsequent conversation to the one or more endpoints based on the prediction. [C21] The system of C13, wherein the processor requests the input by presenting the prediction in a set of prediction options to the agent device. [C22] The system of C13, wherein the processor updates the learning model further based on one or more other conversations associated with other classification inputs that correspond to the classification input. [C23] The system of C13, wherein the classification input further includes one or more selections of content from the messages in the conversation. [C24] The system of C13, wherein the set of supervision criteria further specifies one or more conditions and further comprises executable instructions to set the threshold level of trust based on conditions of the conversation that correspond to the conditions specified by the supervision criteria. [C25] A non-transitory machine-readable storage medium containing instructions that, when executed by one or more processors, cause the one or more processors to: storing a set of confidence criteria in a memory, the set of confidence criteria including a threshold level of confidence; monitoring one or more messages in a conversation between the bot and a user of the client device; Detecting that a bot prediction associated with the conversation does not meet the threshold level of confidence; requesting input from an agent device regarding the conversation, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction. [C26] Detecting that the bot prediction does not meet the threshold level of confidence includes: assigning a confidence score to the bot prediction; and comparing the assigned confidence score to a threshold level of confidence. [C27] 20. The non-transitory machine-readable storage medium of claim 19, wherein the routing of the conversation to the one or more endpoints occurs in real time. [C28] The non-transitory machine-readable storage medium of C25, further comprising executable instructions to annotate the messages in the conversation based on the classification input. [C29] The non-transitory machine-readable storage medium of C28, wherein the learning model is updated based on the annotated messages. [C30] The non-transitory machine-readable storage medium of C25, wherein routing the conversation includes providing the classification input to the bot, the classification corresponding to a prediction that is different from the bot prediction. [C31] The non-transitory machine-readable storage medium of C30, wherein the bot routes the conversation by using the different prediction corresponding to the classification input instead of the bot prediction that failed to meet the threshold level of trust. [C32] Routing subsequent conversations is making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; and routing the subsequent conversation to the one or more endpoints based on the prediction. [C33] The non-transitory machine-readable storage medium of C25, wherein requesting the input includes presenting the prediction within a set of prediction options to the agent device. [C34] The non-transitory machine-readable storage medium of C25, wherein updating the learning model is further based on one or more other conversations associated with other classification inputs that correspond to the classification input. [C35] The non-transitory machine-readable storage medium of C25, wherein the classification input further includes one or more selections of content from the messages in the conversation. [C36] The non-transitory machine-readable storage medium of C25, wherein the set of supervision criteria further specifies one or more conditions, and further comprising setting the threshold level of trust based on conditions of the conversation that correspond to the conditions specified by the supervision criteria.
Claims
1. 1. A computer-implemented method, comprising: storing a set of supervision criteria in a memory, the set of supervision criteria including a threshold level of confidence; monitoring one or more messages in a conversation between the bot and a user of the client device; Detecting that a bot prediction of the user's intent associated with the conversation does not meet the threshold level of confidence; and requesting input from an agent device, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction.
2. Detecting that the bot prediction does not meet the threshold level of confidence includes: assigning a confidence score to the bot prediction; and comparing the assigned confidence score to a threshold level of confidence.
3. The computer-implemented method of claim 1 , wherein the routing of the conversation to the one or more endpoints occurs in real-time.
4. The computer-implemented method of claim 1 , further comprising annotating the messages in the conversation based on the classification input.
5. The computer-implemented method of claim 4 , wherein the learning model is updated based on annotated messages.
6. 2. The computer-implemented method of claim 1, wherein routing the conversation includes providing the classification input to the bot, the classification corresponding to a prediction that is different from the bot prediction.
7. 7. The computer-implemented method of claim 6, wherein the bot routes the conversation by using the different predictions corresponding to the classification inputs in place of the bot predictions that did not meet the threshold level of confidence.
8. Routing subsequent conversations is making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; and routing the subsequent conversation to the one or more endpoints based on the prediction.
9. The computer-implemented method of claim 1 , wherein the requesting the input comprises presenting the bot predictions in a set of prediction options to an agent device.
10. The computer-implemented method of claim 1 , wherein updating the learning model is further based on one or more other conversations associated with other classification inputs that correspond to the classification input.
11. The computer-implemented method of claim 1 , wherein the categorization input further comprises one or more selections of content from the messages in the conversation.
12. 2. The computer-implemented method of claim 1, wherein the set of supervision criteria further specifies one or more conditions, and further comprising setting the threshold level of confidence based on a condition of the conversation that corresponds to the condition specified by the supervision criteria.
13. 1. A system comprising: a memory for storing a set of confidence criteria in said memory, said set of confidence criteria including a threshold level of confidence; a communications interface for receiving data over a communications network, said received data relating to one or more messages in a monitored conversation between the bot and a user of a client device; one or more processors; one or more non-transitory machine-readable storage media comprising instructions executable by the one or more processors to perform operations, the operations including: Detecting that a bot prediction of the user's intent associated with the conversation does not meet the threshold level of confidence; and requesting input from an agent device regarding the conversation, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction.
14. The processor, assigning a confidence score to the bot prediction; and comparing the assigned confidence score to the threshold level of confidence. The system of claim 13 , further comprising: detecting when the bot prediction does not meet the threshold level of confidence.
15. The system of claim 13 , wherein the processor routes the conversation to the one or more endpoints in real time.
16. The system of claim 13 , further comprising instructions executable by the processor to annotate the messages in the conversation based on the classification input.
17. The system of claim 16 , wherein the learning model is updated based on annotated messages.
18. 14. The system of claim 13, wherein the processor routes the conversation by providing the classification input to the bot, the classification corresponding to a prediction different from the bot prediction.
19. 20. The system of claim 18, wherein the bot routes the conversation by using the different prediction corresponding to the classification input in place of the bot prediction that did not meet the threshold level of confidence.
20. The processor, making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; 14. The system of claim 13, further comprising: routing the subsequent conversation to the one or more endpoints based on the prediction.
21. The system of claim 13 , wherein a processor requests the input by presenting the bot predictions in a set of prediction options to the agent device.
22. The system of claim 13 , wherein the processor updates the learning model further based on one or more other conversations associated with other classification inputs that correspond to the classification input.
23. The system of claim 13 , wherein the categorization input further comprises one or more selections of content from the messages in the conversation.
24. 14. The system of claim 13, wherein the set of supervisory criteria further specifies one or more conditions and further comprises executable instructions to set the threshold level of trust based on a condition of the conversation that corresponds to the condition specified by the supervisory criteria.
25. 1. A non-transitory machine-readable storage medium containing instructions that, when executed by one or more processors, cause the one or more processors to: storing a set of confidence criteria in a memory, the set of confidence criteria including a threshold level of confidence; monitoring one or more messages in a conversation between the bot and a user of the client device; Detecting that a bot prediction of the user's intent associated with the conversation does not meet the threshold level of confidence; and requesting input from an agent device regarding the conversation, the agent device providing classification input regarding the conversation; routing the conversation to one or more endpoint devices in accordance with the classification input; and updating a learning model based on the classification input, wherein the bot uses the updated learning model to make a next bot prediction.
26. Detecting that the bot prediction does not meet the threshold level of confidence includes: assigning a confidence score to the bot prediction; and comparing the assigned confidence score to a threshold level of confidence.
27. 26. The non-transitory machine-readable storage medium of claim 25, wherein the routing of the conversation to the one or more endpoints occurs in real time.
28. 26. The non-transitory machine-readable storage medium of claim 25, further comprising instructions executable to annotate the messages in the conversation based on the classification input.
29. 30. The non-transitory machine-readable storage medium of claim 28, wherein the learning model is updated based on annotated messages.
30. 26. The non-transitory machine-readable storage medium of claim 25, wherein routing the conversation includes providing the classification input to the bot, the classification corresponding to a prediction that is different from the bot prediction.
31. 31. The non-transitory machine-readable storage medium of claim 30, wherein the bot routes the conversation by using the different prediction corresponding to the classification input in place of the bot prediction that failed to meet the threshold level of confidence.
32. Routing subsequent conversations is making the next prediction based on the updated learned model, the prediction meeting the threshold level of confidence; and routing the subsequent conversation to the one or more endpoints based on the prediction.
33. 26. The non-transitory machine-readable storage medium of claim 25, wherein the requesting the input includes presenting the bot predictions in a set of prediction options to the agent device.
34. 26. The non-transitory machine-readable storage medium of claim 25, wherein updating the learning model is further based on one or more other conversations associated with other classification inputs that correspond to the classification input.
35. 26. The non-transitory machine-readable storage medium of claim 25, wherein the classification input further comprises one or more selections of content from the messages in the conversation.
36. 26. The non-transitory machine-readable storage medium of claim 25, wherein the set of supervision criteria further specifies one or more conditions, and further comprising setting the threshold level of trust based on a condition of the conversation that corresponds to the condition specified by the supervision criteria.
Citation Information
Patent Citations
Dynamic response prediction for improved bot task processing
US20180322403A1
Automatic BOT creation based on scripts
WO2020102571A1
Dynamic text message processing implementing endpoint communication channel selection
WO2020172326A1
Intent-driven contact center
WO2020176353A1
