US20230396567A1 - Chat bot utilizing metaphors to both relay and obtain information - Google Patents
Chat bot utilizing metaphors to both relay and obtain information Download PDFInfo
- Publication number
- US20230396567A1 US20230396567A1 US18/118,903 US202318118903A US2023396567A1 US 20230396567 A1 US20230396567 A1 US 20230396567A1 US 202318118903 A US202318118903 A US 202318118903A US 2023396567 A1 US2023396567 A1 US 2023396567A1
- Authority
- US
- United States
- Prior art keywords
- user
- updated
- chat
- predetermined value
- metaphor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000004044 response Effects 0.000 claims abstract description 23
- 230000007704 transition Effects 0.000 claims description 20
- 238000013507 mapping Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000000306 recurrent effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 33
- 238000004891 communication Methods 0.000 description 25
- 238000010586 diagram Methods 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004353 relayed correlation spectroscopy Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
Abstract
Techniques to enable a chat bot system to use metaphors during an interaction with a user are provided. Identification information for the user can be received and can be used to determine a customer group assigned to the user. An initial state of a sequence for resolving an issue of the user can be determined, with the sequence for resolving the issue of the user including a final state wherein the issue of the user is resolved. A metaphor can be selected to include in a question based on the determined customer group assigned to the customer and the determined initial state of the sequence for resolving the issue of the customer. The question can request information from the user relating to the issue of the user. The question can be generated to include the selected metaphor and then provided to the user with a prompt to provide a response.
Description
- This application is a continuation of U.S. patent application Ser. No. 16/998,369, filed Aug. 20, 2020, which is a continuation of U.S. patent application Ser. No. 16/270,587, filed Feb. 7, 2019, titled “CHAT BOT UTILIZING METAPHORS TO BOTH RELAY AND OBTAIN INFORMATION”. The contents of the aforementioned application are incorporated herein by reference in their entirety.
- Embodiments described herein generally relate to chat bot systems.
- Conventional chat bot systems can conveniently interact with a user to address an issue of the user. However, many conventional chat bot systems come across as robotic and non-human. Users that interact with these conventional chat bot systems find them unrelatable and difficult to understand at times. As a result, these conventional chat bot systems are often poor at extracting information from a user to effectively address the issue of the user.
- Accordingly, there is a need for a chat bot system that interacts with users more naturally in a more relatable manner to spur a user to more freely and effectively share information with the chat bot system to better address an issue of the user.
-
FIG. 1 illustrates an operating environment. -
FIG. 2 illustrates a first message generated by the chat bot system depicted inFIG. 1 . -
FIG. 3 illustrates a second message generated by the chat bot system depicted inFIG. 1 . -
FIG. 4 illustrates a state diagram representing an interaction between a user and the chat bot system depicted inFIG. 1 . -
FIG. 5 illustrates a table for storing metaphors used by the chat bot system depicted inFIG. 1 . -
FIG. 6 illustrates a first logic flow. -
FIG. 7 illustrates a second logic flow. -
FIG. 8 illustrates a storage medium. -
FIG. 9 illustrates a computing architecture. -
FIG. 10 illustrates a communication architecture. - This disclosure presents various systems, components, and methods related to providing more natural and more efficient chat bot systems. Each of the systems, components, and methods disclosed herein provides one or more advantages over conventional systems, components, and methods.
- Various embodiments include techniques to enable a chat bot system to use metaphors during an interaction with a user to provide and receive information in a more relatable and efficient manner. Identification information for the user can be received and can be used to determine a customer group assigned to the user. An initial state of a sequence for resolving an issue of the user can be determined, with the sequence for resolving the issue of the user including a final state wherein the issue of the user is resolved. A metaphor can be selected to include in a question based on the determined customer group assigned to the customer and the determined initial state of the sequence for resolving the issue of the customer. The question can request information from the user relating to the issue of the user. The question can then be generated to include the selected metaphor and then provided to the user. The user can subsequently be prompted to provide a response. Other embodiments are disclosed and described.
-
FIG. 1 illustrates anoperating environment 100 such as may be representative of various embodiments in which a chat bot utilizing metaphors to interact with a user may be implemented. Theoperating environment 100 can include a user orcustomer 102, afirst device 104, and asecond device 106. In various embodiments, thefirst device 104 can be a local device that can be a handheld device (e.g., held by the user 102). In various embodiments, thesecond device 106 can operate to provide a chat bot system or service. The chat bot service provided by thesecond device 106 can conduct a conversation with theuser 102 via auditory or textual based interactions and can include a voice interaction system. - The first and
second devices second device 106 can be located remote from thefirst device 104. For purposes of illustration and for ease of explanation only, thefirst device 104 will be referred to as a local device and thesecond device 106 will be referred to as a chat bot system with the understanding that thelocal device 104 can be part of thechat bot system 106. - In various embodiments, the
local device 104 can include amicrophone 108, aspeaker 110, adisplay 112, and one ormore input devices 120. In various embodiments, thedisplay 112 can be a touchscreen. Themicrophone 108 can receive audible data or information including spoken or verbalizedspeech 114 of theuser 102. The one ormore input devices 120 can include a keyboard for receiving typed data or information from theuser 102. Thelocal device 104 can be any type of computing device including, for example, a desktop computer, a laptop computer, a tablet, a mobile computing device, a smartphone, a set-top box, a remote (e.g., a television remote), or any other type of device capable of receiving thespeech 114 of theuser 102 or textual data from theuser 102. Thelocal device 104 can include additional components not shown inFIG. 1 . - The
chat bot system 106 can include acontroller component 116 and astorage device 118. Thecontroller component 116 can be implemented in software, hardware, or any combination thereof. Thecontroller component 116 can be a processor and/or can include logic for implementing the techniques and/or features described herein. Thestorage device 118 can be any type of memory storage device. - The
chat bot system 106 can receive thespeech information 114 from theuser 102, can process thespeech information 114 to determine what was spoken by theuser 102, and can respond to theuser 102. Thechat bot system 106 can also receive textual information from theuser 102 provided through thelocal device 104, can process the textual information to determine what was conveyed by the user, and can respond to theuser 102. In various embodiments, thechat bot system 106 can direct thelocal device 104 to provide audible information back to the user 102 (e.g., by way of the speaker 110) and/or visual information (e.g., textual) back to the user 102 (e.g., by way of the display 112). In general, theuser 102 may interact with thechat bot system 106 to request help on an issue such as, for example, any type of customer service issue related to a product or service. - In various embodiments, the
local device 104 can receive and store thespeech 114 of theuser 102 and can provide the stored speech to thechat bot system 106. In various embodiments, thelocal device 104 can receive and store textual information from theuser 102 and can provide the stored textual information to thechat bot system 106. In various embodiments, thelocal device 104 can include its own controller component and storage device (not shown for simplicity) or can include thecontroller component 116 and/or thestorage device 118 as part of the local device 104 (e.g., to form a combinedlocal device 104—chat bot system 106). - In various embodiments, when the
local device 104 and thechat bot system 106 are located remotely from one another, thelocal device 104 and thechat bot system 106 can communicate and/or share any data or information over a communication link. The data can be any type of data including voice data and/or textual data. The communication link can comprise one more computer networks or links. The communication link can include, for example, one or more wireless communication systems that operate according to one or more wireless communication standards or protocols over any frequency band or range. The communication link can include, for example, one or more wired communication systems that operate according to one or more wired communication standards or protocols over any type of wired media. Thelocal device 104 and thechat bot system 106 can communicate according to any computer network protocol including any Internet-related communication protocol to facilitate the sharing of any type of data between thelocal device 104 and thechat bot system 106. - The
chat bot system 106—either including or not including a portion of thelocal device 104—can receive audio data and/or textual data from theuser 102. The audio data can include thespeech 114 of theuser 102. In various embodiments, the audio data and/or textual data from theuser 102 can relate to an issue of theuser 102. For example, the issue can relate to a customer service issue or question of theuser 102 including issues relating to operation of a device or service. As an example, the audio data and/or textual data of theuser 102 can relate to a question or problem theuser 102 has regarding an internet service provided to theuser 102. Thechat bot system 106 can be a system and/or service provided to theuser 102 for responding to customer service issues of theuser 102 including troubleshooting issues for any product or service provided to theuser 102. - The
chat bot system 106 can operate to conduct a conversation with theuser 102. Thechat bot system 106 can operate to interact with theuser 102 to understand the issue or problem of theuser 102, collect additional information from theuser 102, and to attempt to resolve the issue or problem of theuser 102. To provide a more natural conversational interaction with theuser 102 and to more efficiently discern the issue or problem of theuser 102 as well as resolve the issue or problem of theuser 102 more effectively, thechat bot system 106 can use metaphors to relay information to theuser 102 and to obtain information from theuser 102. In various embodiments, thechat bot system 106 can use a metaphor in place of a predetermined phrase or word or other portion of a menu system to convey and receive information from theuser 102 in a more natural and therefore more efficient manner as disclosed herein. - In various embodiments, the
user 102 can initiate interaction with thechat bot system 106. Theuser 102 can initiate interaction with thechat bot system 106 by engaging thelocal device 104—for example, by textually entering information into thelocal device 104 or speaking to thelocal device 104. Thelocal device 104 can store any received audible or textual information from theuser 102 and can provide the stored data to thechat bot system 106. Thechat bot system 106 can receive the initial information from theuser 102. In various embodiments, thechat bot system 106 can determine that theuser 102 is experiencing an issue that theuser 102 would like help from thechat bot system 106 to resolve. - In various embodiments, to address the issue of the
user 102, thechat bot system 106 can first receive identification information for the user. The identification information can be provided by theuser 102 through a computer interface provided by thelocal device 104. In various embodiments, the identification information can be prestored by thelocal device 104 and/or correlated or related to thelocal device 104. - After the
user 102 is identified, the chat bot system can determine a customer group assigned to theuser 102 based on the received user identification information. Thestorage device 118 of thechat bot system 106 can store an assigned customer group for each possible user that may interact with thechat bot system 106. Information related to each customer group can be stored in thestorage device 118. One or more users can be assigned to a specific customer group. Information regarding each customer group can be stored in thestorage device 118. The customer groups can include users with similar backgrounds, education levels, familiarity or comfort with the device or service to which thechat bot system 106 may relate, and/or other demographic information. - By assigning users to a customer group, including the
user 102, thechat bot system 106 can group related users so that thechat bot system 106 can interact with related users in the same manner. For example, thechat bot system 106 can interact with a first set of users assigned to a first customer group in a first manner while interacting with a second set of users assigned to a second customer group in a second different manner. The manner in which thechat bot system 106 may interact with the customer groups can vary, for instance, by a set of provided menu options, a sequence in which the options are provided, and the use of metaphors used to relay and obtain information. For example, thechat bot system 106 may use certain metaphors with the first customer group and may use different metaphors with the second customer group, with both different sets of metaphors intended to enhance interaction with each customer group (e.g., by more effectively conveying and receiving information from the users). - In various embodiments, the
chat bot system 106 can model interaction with theuser 102 as a sequence of steps or states. In various embodiments, thechat bot system 106 can model the interaction as having an initial state, a final state, and one or more intermediate states. The overall sequence of states can involve determining a problem or issue of theuser 102, collecting additional information from theuser 102 to better understand the issue and/or to guide theuser 102 to a solution, and reaching a state where a satisfactory solution for theuser 102 is obtained. The initial state can be determined based on an initial interaction withuser 102 and can be any state along the modeled sequence. In general, the initial state can represent theuser 102 attempting to covey the issue or problem to thechat bot system 106 or may simply be theuser 102 initializing contact with thechat bot system 106 without stating the issue to be addressed. The final state can represent resolving the issue of theuser 102. The one or more intermediate states can represent states that sequentially advance to the final state through interaction between theuser 102 and thechat bot system 106. - In various embodiments, the
chat bot system 106 can interact with theuser 102 to sequentially advance the resolution of the issue of the user from a determined initial problem state to the final state by collecting information from theuser 102 and/or providing information or instructions to theuser 102. In this way, the resolution of the problem can advance through the one or more intermediate states towards the final state. Information can be collected by thechat bot system 106 by asking theuser 102 questions related to the issue. The questions asked by thechat bot system 106 to theuser 102—for example, for any determined state relating to a sequence for resolving the issue of theuser 102—can be based on a number of inputs including, for example, the issue of theuser 102, the current state of the resolution sequence, and the customer group assigned to theuser 102. - In various embodiments, in order to advance the resolution of the issue for the
user 102, thechat bot system 106 can use one or more metaphors within a question posed to theuser 102 or within any other statement provided to theuser 102. The metaphor can be selected to increase a likelihood of receiving information from theuser 102 that enables thechat bot system 106 to advance to a next state sequentially closer to the final state (i.e., to further advance understanding of the issue and a possible solution). - To this end, in various embodiments, the
chat bot system 106 can generate a question for theuser 102 and can include the selected metaphor within the question. Thechat bot system 106 can provide the generated question for presentation to theuser 102 through thelocal device 104—for example, as audible information conveyed to theuser 102 though thespeaker 110 or as textual information conveyed to the user through thedisplay 112. Theuser 102 can respond to the presented question and can include responsive information. The responsive information can include information that allows thechat bot system 106 to advance to a next state closer to the final state or can fail to include information that allows the chat bot system to advance to the next closer state (e.g., theuser 102 may fail to understand the metaphor and is unable to respond such that the resolution sequence remains in the same or current state). This sequence of interaction can be repeated to sequentially advance the resolution sequence for theuser 102 to the final state. - In various embodiments, the
chat bot system 106 can track and rate the successfulness of using a particular metaphor. For example, each metaphor that can be used by thechat bot system 106 can be associated with a value representing a likelihood that the metaphor will prompt theuser 102 to respond with information that enables thechat bot system 106 to advance the sequence for resolving the issue of theuser 102. In various embodiments, the likelihood value can vary by customer group, the current state of the sequence for resolving the issue, and the particular problem of theuser 102. Thechat bot system 106 can select from any number of stored metaphors. In various embodiments, thechat bot system 106 can select the metaphor having the highest likelihood value associated with it. - If the use of a metaphor results in information that enables the
chat bot system 106 to advance the resolution of the issue of theuser 102, then thechat bot system 106 can store information indicating successful use of the metaphor and/or can increase the stored likelihood value corresponding to the metaphor. If the use of a metaphor does not result in information that enables thechat bot system 106 to advance the resolution of the issue of theuser 102, then thechat bot system 106 can store information indicating the unsuccessful use of the metaphor and/or can decrease the stored likelihood value corresponding to the metaphor. In this manner, thechat bot system 106 can dynamically learn which metaphors are more successful for certain situations (e.g., problem resolution states) and which are less successful for future use. -
FIG. 2 illustrates afirst example message 200 generated by thechat bot system 106 for presentation to theuser 102. Thefirst example message 200 can be generated by thechat bot system 106 for presentation as a textual message or an audible message for theuser 102. Thefirst example message 200 can be provided to theuser 102 through the user interface provided by thelocal device 104. - The
first example message 200 can represent an instance where a question is presented to theuser 102 without the use of a selected metaphor by thechat bot system 106. Many users may find theexample message 200 overly complex and unrelatable. -
FIG. 3 illustrates asecond example message 300 generated by thechat bot system 106 for presentation to theuser 102. Thesecond example message 300 can be generated by thechat bot system 106 for presentation as a textual message or an audible message for theuser 102. Thesecond example message 300 can be provided to theuser 102 through the user interface provided by thelocal device 104. - The
second example message 300 can be presented to theuser 102 in lieu of thefirst example message 200. Thesecond example message 300 can represent an instance where a question is presented to theuser 102 with the use of a selectedmetaphor 302 by thechat bot system 106. By including themetaphor 302 within themessage 300, many users may be more likely to provide more useful information for resolving the issue of theuser 102 as the metaphor is simple and relatable. -
FIG. 4 illustrates a simplified state diagram 400 representing an interaction of thechat bot system 106 and theuser 102. The state diagram 400 can represent different possible states that can occur as thechat bot system 106 interacts with theuser 102 to address the issue of the user. As shown inFIG. 4 , aninitial state 402 can represent the initial state of the interaction between thechat bot system 106 and theuser 102. Theinitial state 402 can represent, for example, when communication between thechat bot system 106 and theuser 102 is first established and prior to theuser 102 stating the problem for which theuser 102 is seeking help. In other embodiments, theuser 102 can state the problem of theuser 102 in theinitial state 402. -
FIG. 4 further illustrates a firstintermediate state 404, a secondintermediate state 406, and afinal state 408, with the understanding that additional intermediate states (not shown inFIG. 4 for simplicity) can be represented between the first and secondintermediate states final state 406. Thefinal state 408 can represent the resolution of the issue of theuser 102. The intermediate states (e.g., the first and secondintermediate states FIG. 4 ) can represent the incremental advancement of the interaction between thechat bot system 106 and theuser 102 towards thefinal state 408. These intermediate states can represent interactions for which thechat bot system 106 attempts to collect or provide information regarding the issue of theuser 102, collect or provide information regarding the status of any service or device related to the issue of theuser 102, or any other step in a sequence of resolving the issue of theuser 102 that incremental advances the interaction to thefinal state 408. - In various embodiments, each step or state shown in the state diagram 400 can represent a state where a certain amount of information related to the issue of the user is obtained by the
chat bot system 106. For example, a state positioned sequentially closer to thefinal state 408 can represent a state where more information related to the issue of theuser 102 is known in comparison to the amount of information known in a state positioned sequentially further from thefinal state 408. The known information can represent any information related to the issue of theuser 102 including, for example, information to understand the problem of theuser 102, information regarding the status of the device or service related to the issue of theuser 102, and/or any other information that when provided to the chat bot system increases a likelihood of reaching thefinal state 408. - Any number of states can be represented in the state diagram 400. Any number of paths can be followed to advance from the
initial state 402 to thefinal state 408, with shorter paths (with fewer total states) representing more efficient problem resolution sequences and longer paths (with more total states) representing less efficient problem resolution sequences. Any number of paths can lead to or from any state. In general, to efficiently resolve the issue of theuser 102, it is desirable for thechat bot system 106 to take the shortest path (e.g., with the fewest intermediate states) from theinitial state 406 to thefinal state 408. Techniques disclosed herein enable thechat bot system 106 to relay and obtain information with theuser 102 using metaphors such that transitions between problem resolution states can be made to advance the sequence of problem resolution toward thefinal state 408. - As shown in
FIG. 4 , from theinitial state 402, the interaction between thechat bot system 106 and theuser 102 can advance to either the firstintermediate state 404 or the secondintermediate state 406. In various embodiments, it may be desirable to advance to the firstintermediate state 404 over the secondintermediate state 406. Accordingly, thechat bot system 106 may attempt to interact with theuser 102—for example, by requesting information from theuser 102—to enable the sequence for resolving the issue of theuser 102 to advance to the firstintermediate state 404. - To do so, in various embodiments, during the
initial state 402 of the interaction, thechat bot system 106 may receive identification information for theuser 102 and may look-up within thestorage device 118 the customer group assigned to theuser 102. A number of options may be provided to thechat bot system 106 during theinitial state 402 of the interaction for advancing to the firstintermediate state 404. For example, a number of questions or information to request can be stored in thestorage device 118 and selected by thechat bot system 106 to provide to theuser 102. In various embodiments, thestorage device 118 may store one or more corresponding metaphors for the different possible interactions thechat bot system 106 can implement. Thechat bot system 106 can select one of the metaphors to use in a question to theuser 102 in an attempt to advance to the firstintermediate state 404. - In various embodiment, the
chat bot system 106 can select the use of a metaphor that has the highest likelihood for advancing to the firstintermediate state 404 based on theuser 102, the customer group assigned to theuser 102, the issue of the user (if known), and/or the determinedinitial state 402. Therefore, in an attempt to advance resolution of the issue of theuser 102 to the firstintermediate state 404, thechat bot system 106 can generate a question for theuser 102 that includes use of the selected metaphor. The generated question including the selected metaphor can then be provided to theuser 102. Theuser 102 can then respond to the question. - If the
user 102 relates well to the use of the selected metaphor in the question, then theuser 102 may respond with information that enables thechat bot system 106 to advance resolution of the issue to the first intermediate state 404 (e.g., the desired information to collect was provided by the user 102). If theuser 102 fails to understand the metaphor or relate to its use, theuser 102 may not respond with information that enables thechat bot system 106 to advance resolution of the issue to the first intermediate state 404 (e.g., theuser 102 may state that they do not understand the posed question). As a result, the sequence for resolution may remain in theinitial state 402. Another attempt by thechat bot system 106 to advance to the firstintermediate state 404 or any other state can then occur. - This process can be repeated as necessary or desired for the
chat bot system 106 to incrementally advance the sequence for resolving the issue of theuser 102 toward thefinal state 408. For any attempt to incrementally advance the sequence for resolving the issue of theuser 102, thechat bot system 106 can determine whether or not to use a metaphor in an audible or textual interaction with theuser 102 along with selecting which metaphor to use. Each determination by thechat bot system 106 can be based on, for example, the customer group of theuser 102 and the current state of the sequence for resolving the issue. - The state diagram 400 can represent a visual depiction of the process undertaken by the
chat bot system 106 to resolve the issue of theuser 102. In various embodiment, the state diagram 400 can represent a model for the process that can be undertaken by thechat bot system 106 to resolve the issue of theuser 102. Accordingly, the state diagram 400 can be a model having states stored in thestorage device 118. Further, the state diagram 400 can vary for each customer or customer group. In various embodiments, the state diagram 400 can be implemented or can represent a Hidden Markov Model (HMM). -
FIG. 5 illustrates a table 500 that can be stored in thestorage device 118 and maintained by thechat bot system 106. The table 500 can be used as a reference for storing candidate metaphors for use during an interaction between thechat bot system 106 and theuser 102. The table 500 is shown with headings of different types of information stored in the table 500 and values for the headings are not shown for simplicity.FIG. 5 can show a portion of the table 500 for simplicity. - As shown in
FIG. 5 , the table 500 can organize information relating to acurrent state 502 of the interaction between thechat bot system 106 and theuser 102. For each possiblecurrent state 502 provided in the table 500, a next state 504 (e.g., a desired next state) of the interaction between thechat bot system 106 and theuser 102 can be listed. For eachcurrent state 502 and next state 504 pair, one or more candidate metaphors can be stored. As shown inFIG. 5 , afirst metaphor 506 is shown and an nth metaphor 508 is shown, with the nth metaphor 508 indicating than n different metaphors (where n is an integer) are listed for a specificcurrent state 502 and next state 504 pair. - As further shown in
FIG. 5 , each metaphor is associated with a value. For example, thefirst metaphor 506 is associated with avalue 510 and the nth metaphor 508 is associated with a value 512. Thevalue 510 can represent a likelihood that thefirst metaphor 506, when used in a message to theuser 102, will result in theuser 102 providing responsive information that enables thechat bot system 106 to advance resolution of the issue of theuser 102 to the next state 504. Similarly, the value 512 can represent a likelihood that the nth metaphor 508, when used in a message to theuser 102, will result in theuser 102 providing responsive information that enables thechat bot system 106 to advance the resolution of the issue of theuser 102 to the next state 504. In various embodiments, thechat bot system 106 can select the metaphor having the highest corresponding likelihood value. - In various embodiments, the table 500 can be maintained across all customer groups. In various embodiments, the table 500 can be maintained for a specific customer group with other tables maintained for other corresponding customer groups. The
chat bot system 106 can adjust the storedvalues 510 and 512 based on the successful or unsuccessful use of the metaphors in an attempt to advance to any next state 504. For example, if thefirst metaphor 506 is used in a message to theuser 102 but is unsuccessful in extracting desired information from theuser 102 in a response that enables advancement to the next state 504, then thechat bot system 106 can reduce or decrease the storedvalue 510. Alternatively, if thefirst metaphor 506 is used in a message to theuser 102 and is successful in extracting desired information from theuser 102 in a response that enables advancement to the next state 504, then thechat bot system 106 can increase the storedvalue 510. In this manner, the table 500 can be dynamically updated based on usage of the stored metaphors and then applied to other customers within a particular customer group. - In various embodiments, the table 500 can store a plurality of metaphors for each possible state transition and separate tables can be established for each customer group. The metaphors can include any alternative words or phrases (e.g., pseudonyms or synonyms) used in replace of other words or phrases. The metaphors can be used to map between a conventional word or phrasing and the selected metaphor. In this way, conventional keywords, terms, or phrases of a menu system can be translated to a specific metaphor. The metaphors can vary for each customer group or can be stored in different manners between tables for each customer group with different likelihood values.
- In various embodiments, metaphors stored in the table 500 can be selected based on a statistical analysis of the possible metaphors—for example, by selecting metaphors having the highest likelihood of advancing to a next desired problem resolution state that is sequentially closer to the
final state 408. In various embodiments, a machine learning model such as a recurrent neural network (RNN) can be used to develop a bank of stored metaphors that can be used and tested for receptiveness by theuser 102. - In various embodiments, metaphor data—for example, metaphor data stored in the table 500 or otherwise maintained and stored for use in any embodiment disclosed herein—can be maintained in one or more relational lists. For example, a list can be maintained that relates common words or phrases to one or more metaphors that can be used in lieu of the common words or phrases. The common words or phrases can be information or options stored as part of a menu system such that predetermined alternative metaphors can be mapped to portions of the menu system. In this way, metaphors can be maintained and retrieved for use as an alternative to certain menu words, phrases, options, or questions, for example. As disclosed herein, the relational mapping for the metaphor data can be constructed prior to implementation of the
chat bot system 106, during implementation of the chat bot system 106 (e.g., built and modified during implementation), or can be purchased or otherwise acquired for use with thechat bot system 106. Further, relational mapping for the metaphor data can be developed through machine learning as disclosed herein. In a similar manner, mapping from metaphor data from a user to related common words or phrases (e.g., as they may relate to a menu system) can also be implemented. As an example of either type of mapping, search lists can be constructed and reviewed to translate a common word, phrase, or question to a metaphor, or vice versa. -
FIG. 6 illustrates an example of alogic flow 600 that may be representative of a chat bot system that uses metaphors during an interaction with a user. For example, thelogic flow 600 may be representative of operations that may be performed in various embodiments by thechat bot system 106 in the operatingenvironment 100 ofFIG. 1 . - At 602, the
chat bot system 106 can receive identification information for a customer oruser 102 through a user interface of a computing device. The computing device can be thelocal device 104. In various embodiments, thelocal device 104 can be associated with a specific customer such that thelocal device 104 can inform thechat bot system 106 as to the identity of thecustomer 102 operating thelocal device 104. In various embodiments, thelocal device 104 can store identification information for thecustomer 102 that is provided to thechat bot system 106. In various embodiments, thecustomer 102 can provide identification information through a user interface provided by thelocal device 104. - At 604, the
chat bot system 106 can determine a customer group assigned to thecustomer 102. Data indicating the customer group assigned thecustomer 102 can be stored in thestorage device 118. Thechat bot system 106 can determine the customer group assigned to thecustomer 102 based on the on the received identification information for the customer. - At 606, the
chat bot system 106 can determine an initial state of a sequence for resolving an issue of the customer. In various embodiments, thecustomer 102 can initiate an interaction with thechat bot system 106 to request resolution of a problem or issue. A process for resolving the problem or issue can be viewed or represented as a sequence of steps or states, with a final state of the sequence representing resolution of the issue. The initial state can be an introductory state of interaction where thecustomer 102 simply engages thechat bot system 106. In various embodiments, the initial state can represent a state where certain information related to theuser 102 issue or problem is relayed by theuser 102. By determining the initial state, thechat bot system 106 can then determine a next state within the sequence for resolving the issue that thechat bot system 106 may decide to advance to if possible and based on interaction with theuser 102. - At 608, the
chat bot system 106 can select a metaphor stored in the storage device to include in a question that is to be provided to theuser 102. The metaphor can be selected based on the determined customer group assigned to thecustomer 102 and the determined initial state of the sequence for resolving the issue of thecustomer 102. The question can be generated to request information from thecustomer 102 relating to the issue of thecustomer 102. In various embodiments, in lieu of a question, the chat bot system can generate a statement that includes the metaphor. - At 610, the chat bot system can generate the question (or statement) with the question including the selected metaphor. The generated question can be prepared for transmission to the
user 102. - At 612, the generated question (or statement) that includes the selected metaphor can be provided to the
customer 102 by thechat bot system 106. The generated question can be provided to theuser 102 through thelocal device 104. In various embodiments, the generated question can be provided to theuser 102 as a textual message through thedisplay 112 of thelocal device 104. In various embodiments, the generated question can be provided to theuser 102 as an auditory message through thespeaker 110 of thelocal device 104. At 612, theuser 102 can also be prompted to respond to the provided question. Theuser 102 can then subsequently respond to the generated question—either audibly or textually—to further interaction between theuser 102 and thechat bot system 106. -
FIG. 7 illustrates an example of alogic flow 700 that may be representative of a chat bot system obtaining information from a user. For example, thelogic flow 700 may be representative of operations that may be performed in various embodiments by thechat bot system 106 in the operatingenvironment 100 ofFIG. 1 . - At 702, the
chat bot system 106 can receive a response to a question provided to the user 102 (e.g., the question provided at 612 of logic flow 600). The response can be provided by theuser 102 through the user interface provided by thelocal device 104. In various embodiments, the response can be provided as a textual message or as an auditory message. - At 704, the
chat bot system 106 can review and process the received response. Thechat bot system 106 can determine if the received response includes responsive information to advance the sequence for resolving the issue of thecustomer 102—for example, from a previously determined initial state to a next state, where the next state is sequentially closer to a final state of the sequence for resolving the issue of the customer. - At 706, if it is determined that the response from the
user 102 includes sufficient responsive information, then thechat bot system 106 can increase a stored value associated with a metaphor that was selected to be included in the question provided to theuser 102 to which theuser 102 responded. The stored value associated with the selected metaphor can represent a likelihood that the selected metaphor will cause the response of theuser 102 to include responsive information for advancing the sequence for resolving the issue of thecustomer 102 from the determined initial state to the next state. - At 708, if it is determined that the response from the
user 102 does not include sufficient responsive information, then thechat bot system 106 can decrease the stored value associated with the metaphor that was selected to be included in the question provided to theuser 102 to which theuser 102 responded. -
FIG. 8 illustrates astorage medium 800.Storage medium 800 may represent an implementation of thestorage device 118. Thestorage medium 800 can comprise any non-transitory computer-readable storage medium or machine-readable storage medium. In various embodiments, thestorage medium 800 can comprise a physical article of manufacture. In various embodiments,storage medium 800 can store computer-executable instructions, such as computer-executable instructions to implement one or more of logic flows or operations described herein, such as thelogic flow 600 ofFIG. 6 and/or thelogic flow 700 ofFIG. 7 . In various embodiments,storage medium 800 can store computer-executable instructions, such as computer-executable instructions to implement any of the features or functions of any of the components described inFIG. 1 . Examples of a computer-readable storage medium or machine-readable storage medium can include any tangible media capable of storing electronic data. Examples of computer-executable instructions can include any type of computer readable code. -
FIG. 9 illustrates acomputing architecture 900 that can implement various embodiments described herein. In various embodiments, thecomputing architecture 900 can comprise or be implemented as part of an electronic device. In various embodiments, thecomputing architecture 900 can represent an implementation of thelocal device 104 and/or thechat bot system 106. In various embodiments, thecomputing architecture 900 can represent an implementation of thechat bot 106 for interacting with theuser 102 - The
computing architecture 900 can include various common computing elements, such as one or more processors, multi-core processors, co-processors, memory units, chipsets, controllers, peripherals, interfaces, oscillators, timing devices, video cards, audio cards, multimedia input/output (I/O) components, power supplies, and so forth. - As shown in
FIG. 9 , thecomputing architecture 900 can comprise acomputer 902 having aprocessing unit 904, asystem memory 906 and asystem bus 908. Theprocessing unit 904 can be any of various commercially available processors or can be a specially designed processor. - The
system bus 908 provides an interface for system components including, but not limited to, an interface between thesystem memory 906 and theprocessing unit 904. Thesystem bus 908 can be any of several types of bus structure that may further interconnect to a memory bus (with or without a memory controller), a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. - The
system memory 906 can include any type of computer-readable storage media including any type of volatile and non-volatile memory. Thecomputer 902 can include any type of computer-readable storage media including an internal (or external) hard disk drive (HDD) 914. In various embodiments, thecomputer 902 can include any other type of disk drive such as, for example, a magnetic floppy disk and/or an optical disk drive. TheHDD 914 can be connected to thesystem bus 908 by aHDD interface 924. - In various embodiments, any number of program modules can be stored in the drives and
memory units 906 and/or 914 such as, for example, anoperating system 930, one ormore application programs 932,other program modules 934, andprogram data 936. - A user can enter commands and information into the
computer 902 through one or more wired/wireless input devices such as, for example, akeyboard 938 and a pointing device, such as amouse 940. These and other input devices can be connected to theprocessing unit 904 through aninput device interface 942 that is coupled to thesystem bus 908. Amonitor 944 or other type of display device can also be connected to thesystem bus 908 via an interface, such as avideo adaptor 946. Themonitor 944 may be internal or external to thecomputer 902. - The
computer 902 may operate in a networked environment using logical connections via wired and/or wireless communications to one or more remote computers, such as aremote computer 948. Theremote computer 948 can be a workstation, a server computer, a router, a personal computer, portable computer, microprocessor-based entertainment appliance, a smartphone, a tablet, a peer device or other common network node, and typically includes many or all of the elements described relative to thecomputer 902. The logical connections depicted include wired and/or wireless connectivity tonetworks 952 such as, for example, a local area network (LAN) and/or larger networks, for example, a wide area network (WAN).Networks 952 can provide connectivity to a global communications network such as, for example, the Internet. Anetwork adapter 956 can facilitate wired and/or wireless communications to thenetworks 952. Thecomputer 902 is operable to communicate over any known wired or wireless communication technology, standard, or protocol according to any known computer networking technology, standard, or protocol. -
FIG. 10 illustrates a block diagram of acommunication architecture 1000. Thecommunication architecture 1000 can implement various embodiments described herein. As shown inFIG. 10 , thecommunication architecture 1000 comprises one ormore clients 1002 andservers 1004. Theclient 1002 can represent an implementation of thelocal device 104 and/or use of thelocal device 104 to interact with thechat bot system 106. One of theservers 1004 can represent an implementation of thechat bot system 106 and/or operation of thechat bot system 106 to interact with theuser 102 as described herein. - The
client 1002 and theserver 1004 can be operatively connected to aclient data store 1008 and aserver data store 1010, respectively, that can be employed to store information local to therespective client 1002 andserver 1004. In various embodiments, theserver 1004 can implement one or more of logic flows or operations described herein and/or any of the functions and features described in relation to chatbot system 106. - The
client 1002 and theserver 1004 can communicate data or other information between each other using acommunication framework 1006. Thecommunications framework 1006 can implement any known communications technique or protocol. Thecommunications framework 1006 can be implemented as a packet-switched network (e.g., public networks such as the Internet, private networks such as an enterprise intranet, and so forth), a circuit-switched network (e.g., the public switched telephone network), or a combination of a packet-switched network and a circuit-switched network (with suitable gateways and translators), or any combination thereof. Thecommunications framework 1006 can operate over any communication media according to any networking technology including any wired or wireless communications standard or protocol, or any combination thereof. - The following set of examples pertain to further embodiments.
- Example 1 is an apparatus comprising a storage device and logic, at least a portion of the logic implemented in circuitry coupled to the storage device, the logic to receive identification information for a customer through a user interface of a computing device, determine a customer group assigned to the customer and stored in the storage device based on the received identification information for the customer, determine an initial state of a sequence for resolving an issue of the customer, the sequence for resolving the issue of the customer including a final state wherein the issue of the customer is resolved, select a metaphor stored in the storage device to include in a question based on the determined customer group assigned to the customer and the determined initial state of the sequence for resolving the issue of the customer, the question requesting information from the customer relating to the issue of the customer, generate the question, the question to include the selected metaphor, and provide the question including the selected metaphor to the customer and prompt the customer to respond to the provided question, the question provided through at least one of an electronic audio device and a display of the computing device.
- Example 2 is an extension of Example 1 or any other example disclosed herein, the logic to receive a response to the provided question from the customer and to determine if the received response includes responsive information to advance the sequence for resolving the issue of the customer from the determined initial state to a next state, the next state sequentially closer to the final state of the sequence for resolving the issue of the customer.
- Example 3 is an extension of Example 2 or any other example disclosed herein, the logic to increase a value associated with the selected metaphor when the received response includes responsive information to advance the sequence for resolving the issue of the customer from the determined initial state to the next state, the value representing a likelihood of the selected metaphor for advancing the sequence for resolving the issue of the customer from the determined initial state to the next state.
- Example 4 is an extension of Example 3 or any other example disclosed herein, the logic to decrease the value associated with the selected metaphor when the received response does not include responsive information to advance the sequence for resolving the issue of the customer from the determined initial state to the next state.
- Example 5 is an extension of Example 4 or any other example disclosed herein, the logic to select the metaphor from a plurality of candidate metaphors, each candidate metaphor assigned a value representing a likelihood of the candidate metaphor for advancing the sequence for resolving the issue of the customer from the determined initial state to the next state.
- Example 6 is an extension of Example 5 or any other example disclosed herein, the selected metaphor having a highest assigned value of the plurality of candidate metaphors.
- Example 7 is an extension of Example 1 or any other example disclosed herein, the logic to assign the customer to the customer group based on at least one of demographic information of the customer, an education level of the customer, and a prior interaction with the customer.
- Example 8 is an extension of Example 1 or any other example disclosed herein, the logic to present the question to the customer in a textual message on the display of the computing device.
- Example 9 is an extension of Example 1 or any other example disclosed herein, the logic to present the question to the customer in an auditory message through the electronic audio device.
- Example 10 is a method comprising receiving identification information for a customer, determining a customer group assigned to the customer based on the received identification information for the customer, determining an initial state of a sequence for resolving an issue of the customer, the sequence for resolving the issue of the customer including a final state wherein the issue of the customer is resolved, determining a metaphor to include in a question based on the determined customer group assigned to the customer and the determined initial state of the sequence for resolving the issue of the customer, the question requesting information from the customer relating to the issue of the customer, generating the question, the question to include the selected metaphor, providing the question including the selected metaphor to the customer, and requesting the customer to respond to the presented question.
- Example 11 is an extension of Example 10 or any other example disclosed herein,
- further comprising receiving a response from the customer to the provided question.
- Example 12 is an extension of Example 11 or any other example disclosed herein, further comprising determining if the received response includes responsive information to advance the sequence for resolving the issue of the customer from the determined initial state to a next state, the next state sequentially closer to the final state of the sequence for resolving the issue of the customer.
- Example 13 is an extension of Example 12 or any other example disclosed herein, further comprising increasing a stored value corresponding to the selected metaphor when the received response includes the responsive information, the stored value representing a likelihood of the selected metaphor for advancing the sequence for resolving the issue of the customer from the determined initial state to the next state.
- Example 14 is an extension of Example 13 or any other example disclosed herein, further comprising decreasing the stored value when the received response does not include the responsive information.
- Example 15 is an extension of Example 10 or any other example disclosed herein, further comprising determining the metaphor from a plurality of candidate metaphors, each candidate metaphor assigned a value representing a likelihood of the candidate metaphor for advancing the sequence for resolving the issue of the customer from the determined initial state to the next state.
- Example 16 is an extension of Example 15 or any other example disclosed herein, the determined metaphor having a highest assigned value of the plurality of candidate metaphors.
- Example 17 is at least one non-transitory computer-readable medium comprising a set of instructions that, in response to being executed on a computing device, cause the computing device to receive identification information for a customer, determine a customer group assigned to the customer based on the received identification information for the customer, determine an initial state of a sequence for resolving an issue of the customer, the sequence for resolving the issue of the customer including a final state wherein the issue of the customer is resolved, select a metaphor to include in a question based on the determined customer group assigned to the customer and the determined initial state of the sequence for resolving the issue of the customer, the question requesting information from the customer relating to the issue of the customer, generate the question, the question to include the selected metaphor, and provide the question including the selected metaphor to the customer and prompt the customer to respond to the presented question.
- Example 18 is an extension of Example 17 or any other example disclosed herein, the computing device to select the metaphor from a set of candidate metaphors, each candidate metaphor corresponding to a stored value representing a likelihood for advancing the sequence for resolving the issue of the customer to a next state sequentially closer to the final state, the selected metaphor having the largest stored value of the set of candidate metaphors.
- Example 19 is an extension of Example 17 or any other example disclosed herein, the computing device to present the question to the customer in a textual message.
- Example 20 is an extension of Example 17 or any other example disclosed herein, the computing device to present the question to the customer in an auditory message.
- Various embodiments described herein may comprise one or more elements. An element may comprise any structure arranged to perform certain operations. Each element may be implemented as hardware, software, or any combination thereof. Any reference to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrases “in one embodiment,” “in some embodiments,” and “in various embodiments” in various places in the specification are not necessarily all referring to the same embodiment.
- In various instances, for simplicity, well-known operations, components, and circuits have not been described in detail so as not to obscure the embodiments. It can be appreciated that the specific structural and functional details disclosed herein may be representative and do not necessarily limit the scope of the embodiments.
- Certain embodiments of the present invention were described above. It is, however, expressly noted that the present invention is not limited to those embodiments, but rather the intention is that additions and modifications to what was expressly described herein are also included within the scope of the invention. Moreover, it is to be understood that the features of the various embodiments described herein were not mutually exclusive and can exist in various combinations and permutations, even if such combinations or permutations were not made express herein, without departing from the spirit and scope of the invention. In fact, variations, modifications, and other implementations of what was described herein will occur to those of ordinary skill in the art without departing from the spirit and the scope of the invention. As such, the invention is not to be defined only by the preceding illustrative description.
Claims (21)
1. (canceled)
2. A computer implemented method, comprising:
generating, using at least one processor, a plurality of metaphors, one or more metaphors in the plurality of metaphors being selectable in response to at least one input in a plurality of inputs received from a chat-bot interface, the generating including
associating each metaphor in the plurality of metaphors with a transition in a plurality of transitions between two or more states in a plurality of states, each state in the plurality of states being associated with a chat-bot interface state of the chat-bot interface, and
assigning a corresponding predetermined value in a plurality of predetermined values to each metaphor, each predetermined value in the plurality of predetermined values being indicative of a likelihood of a corresponding transition from at least one state to at least another state in the plurality of states;
receiving, using the least one processor, an input in the plurality of inputs from the chat-bot interface;
selecting, using the at least one processor, at least one metaphor in the plurality of metaphors responsive to the received input;
updating, using the at least one processor, at least one of: at least one predetermined value associated with the selected at least one metaphor, a likelihood of corresponding transition associated with the at least one predetermined value, and any combination thereof; and
storing, using the at least one processor, an updated plurality of metaphors including at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof.
3. The method according to claim 2 , further comprising transitioning the chat-bot interface from at least one chat-bot interface state to at least another chat-bot interface state based on at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof.
4. The method according to claim 2 , wherein the updating includes increasing the at least one predetermined value associated with the selected at least one metaphor upon the input from the chat-bot interface being a positive input.
5. The method according to claim 2 , wherein the updating includes decreasing the at least one predetermined value associated with the selected at least one metaphor upon the input from the chat-bot interface being a negative input.
6. The method according to claim 2 , wherein the plurality of inputs from the chat-bot interface includes at least one of the following: an audio format input, a textual format input, and any combination thereof.
7. The method according to claim 2 , wherein at least one metaphor in the plurality of metaphors is configured to be mapped to at least a portion of the received input using at least one stored mapping.
8. The method according to claim 7 , further comprising
updating the stored mapping based on at least one of: the updated plurality of metaphors including at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof; and
generating, based on the updating of the stored mapping, an updated mapping and storing the updated mapping.
9. The method according to claim 7 , wherein the stored mapping is generated using one or more search lists generated based on a translation of one or more inputs in the plurality of inputs from the chat-bot interface to the one or more metaphors.
10. The method according to claim 2 , wherein the one or more metaphors are generated using one or more recurrent neural networks.
11. A system, comprising:
at least one processor; and
at least one non-transitory storage media storing instructions, that when executed by the at least one processor, cause the at least one processor to perform operations including
selecting at least one metaphor in a plurality of metaphors responsive to an input received from a chat-bot interface; and
updating at least one of: at least one predetermined value associated with the selected at least one metaphor, a likelihood of a transition from at least one state to at least another state in a plurality of states, the transition being associated with the at least one predetermined value, and any combination thereof, wherein each state in the plurality of states being associated with a chat-bot interface state of the chat-bot interface.
12. The system according to claim 11 , wherein the operations further comprise storing an updated plurality of metaphors including at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof.
13. The system according to claim 11 , wherein the operations further comprise generating the plurality of metaphors by
associating each metaphor in the plurality of metaphors with one or more transitions in the plurality of transitions between two or more states in the plurality of states; and
assigning a corresponding predetermined value in a plurality of predetermined values to each metaphor, each predetermined value in the plurality of predetermined values being indicative of a likelihood of a corresponding transition from the at least one state to the at least another state in the plurality of states.
14. The system according to claim 11 , wherein the operations further comprise transitioning the chat-bot interface from at least one chat-bot interface state to at least another chat-bot interface state based on at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof.
15. The system according to claim 11 , wherein the updating includes increasing the at least one predetermined value associated with the selected at least one metaphor upon the input from the chat-bot interface being a positive input.
16. The system according to claim 11 , wherein the updating includes decreasing the at least one predetermined value associated with the selected at least one metaphor upon the input from the chat-bot interface being a negative input.
17. The system according to claim 11 , wherein the plurality of inputs from the chat-bot interface includes at least one of the following: an audio format input, a textual format input, and any combination thereof.
18. The system according to claim 11 , wherein at least one metaphor in the plurality of metaphors is configured to be mapped to at least a portion of the received input using at least one stored mapping;
wherein the operations further comprise
updating the stored mapping based on at least one of: the updated plurality of metaphors including at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof; and
generating, based on the updating of the stored mapping, an updated mapping and storing the updated mapping.
19. The system according to claim 18 , wherein the operations further comprise
generating the stored mapping using one or more search lists generated based on a translation of one or more inputs in the plurality of inputs from the chat-bot interface to one or more metaphors.
20. The system according to claim 11 , wherein one or more metaphors are generated using one or more recurrent neural networks.
21. A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
updating at least one of: at least one predetermined value associated with at least one metaphor in response to an input received via a chat-bot interface, a likelihood of a transition from at least one state to at least another state in a plurality of states, the transition being associated with the at least one predetermined value, and any combination thereof, wherein each state in the plurality of states being associated with a chat-bot interface state of the chat-bot interface; and
storing an updated plurality of metaphors including at least one of: the updated at least one predetermined value, the updated likelihood of corresponding transition associated with the updated at least one predetermined value, and any combination thereof.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18/118,903 US20230396567A1 (en) | 2019-02-07 | 2023-03-08 | Chat bot utilizing metaphors to both relay and obtain information |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/270,587 US10785171B2 (en) | 2019-02-07 | 2019-02-07 | Chat bot utilizing metaphors to both relay and obtain information |
US16/998,369 US11621929B2 (en) | 2019-02-07 | 2020-08-20 | Chat bot utilizing metaphors to both relay and obtain information |
US18/118,903 US20230396567A1 (en) | 2019-02-07 | 2023-03-08 | Chat bot utilizing metaphors to both relay and obtain information |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/998,369 Continuation US11621929B2 (en) | 2019-02-07 | 2020-08-20 | Chat bot utilizing metaphors to both relay and obtain information |
Publications (1)
Publication Number | Publication Date |
---|---|
US20230396567A1 true US20230396567A1 (en) | 2023-12-07 |
Family
ID=71945574
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/270,587 Active US10785171B2 (en) | 2019-02-07 | 2019-02-07 | Chat bot utilizing metaphors to both relay and obtain information |
US16/998,369 Active 2039-03-23 US11621929B2 (en) | 2019-02-07 | 2020-08-20 | Chat bot utilizing metaphors to both relay and obtain information |
US18/118,903 Pending US20230396567A1 (en) | 2019-02-07 | 2023-03-08 | Chat bot utilizing metaphors to both relay and obtain information |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/270,587 Active US10785171B2 (en) | 2019-02-07 | 2019-02-07 | Chat bot utilizing metaphors to both relay and obtain information |
US16/998,369 Active 2039-03-23 US11621929B2 (en) | 2019-02-07 | 2020-08-20 | Chat bot utilizing metaphors to both relay and obtain information |
Country Status (1)
Country | Link |
---|---|
US (3) | US10785171B2 (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11544080B2 (en) * | 2019-10-25 | 2023-01-03 | Micro Focus Llc | Adaptive user interface based on device context as well as user context |
JP7423277B2 (en) * | 2019-11-28 | 2024-01-29 | キヤノン株式会社 | Server system and program that suppresses printing proposal inquiries |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180181855A1 (en) * | 2016-12-27 | 2018-06-28 | Microsoft Technology Licensing, Llc | Systems and methods for a mathematical chat bot |
US20190073994A1 (en) * | 2017-09-05 | 2019-03-07 | Microsoft Technology Licensing, Llc | Self-correcting computer based name entity pronunciations for speech recognition and synthesis |
US10923113B1 (en) * | 2018-04-13 | 2021-02-16 | Amazon Technologies, Inc. | Speechlet recommendation based on updating a confidence value |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6484136B1 (en) | 1999-10-21 | 2002-11-19 | International Business Machines Corporation | Language model adaptation via network of similar users |
US6442519B1 (en) | 1999-11-10 | 2002-08-27 | International Business Machines Corp. | Speaker model adaptation via network of similar users |
GB0107772D0 (en) * | 2001-03-28 | 2001-05-16 | Hewlett Packard Co | Improvements relating to data delivery |
US20030120493A1 (en) | 2001-12-21 | 2003-06-26 | Gupta Sunil K. | Method and system for updating and customizing recognition vocabulary |
US20030191639A1 (en) | 2002-04-05 | 2003-10-09 | Sam Mazza | Dynamic and adaptive selection of vocabulary and acoustic models based on a call context for speech recognition |
US8428934B2 (en) * | 2010-01-25 | 2013-04-23 | Holovisions LLC | Prose style morphing |
WO2005034086A1 (en) | 2003-10-03 | 2005-04-14 | Asahi Kasei Kabushiki Kaisha | Data processing device and data processing device control program |
US8200495B2 (en) | 2005-02-04 | 2012-06-12 | Vocollect, Inc. | Methods and systems for considering information about an expected response when performing speech recognition |
US20090171665A1 (en) | 2007-12-28 | 2009-07-02 | Garmin Ltd. | Method and apparatus for creating and modifying navigation voice syntax |
US9043407B1 (en) | 2009-06-12 | 2015-05-26 | Avaya Inc. | Interactive user interface to communication-enabled business process platforms method and apparatus |
US8818926B2 (en) | 2009-09-29 | 2014-08-26 | Richard Scot Wallace | Method for personalizing chat bots |
US9043205B2 (en) | 2012-06-21 | 2015-05-26 | Google Inc. | Dynamic language model |
US10373212B2 (en) * | 2013-03-14 | 2019-08-06 | Facebook, Inc. | Methods for linking images in social feeds to branded content |
US20140365068A1 (en) | 2013-06-06 | 2014-12-11 | Melvin Burns | Personalized Voice User Interface System and Method |
KR102386863B1 (en) | 2015-09-09 | 2022-04-13 | 삼성전자주식회사 | User-based language model generating apparatus, method and voice recognition apparatus |
US10049663B2 (en) | 2016-06-08 | 2018-08-14 | Apple, Inc. | Intelligent automated assistant for media exploration |
US10418026B2 (en) * | 2016-07-15 | 2019-09-17 | Comcast Cable Communications, Llc | Dynamic language and command recognition |
US20180060088A1 (en) | 2016-08-31 | 2018-03-01 | Microsoft Technology Licensing, Llc | Group Interactions |
KR20180070970A (en) | 2016-12-19 | 2018-06-27 | 삼성전자주식회사 | Method and Apparatus for Voice Recognition |
KR102338990B1 (en) | 2017-01-23 | 2021-12-14 | 현대자동차주식회사 | Dialogue processing apparatus, vehicle having the same and dialogue processing method |
US20180293221A1 (en) | 2017-02-14 | 2018-10-11 | Microsoft Technology Licensing, Llc | Speech parsing with intelligent assistant |
US10977319B2 (en) * | 2017-07-10 | 2021-04-13 | Ebay Inc. | Expandable service architecture with configurable dialogue manager |
-
2019
- 2019-02-07 US US16/270,587 patent/US10785171B2/en active Active
-
2020
- 2020-08-20 US US16/998,369 patent/US11621929B2/en active Active
-
2023
- 2023-03-08 US US18/118,903 patent/US20230396567A1/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180181855A1 (en) * | 2016-12-27 | 2018-06-28 | Microsoft Technology Licensing, Llc | Systems and methods for a mathematical chat bot |
US20190073994A1 (en) * | 2017-09-05 | 2019-03-07 | Microsoft Technology Licensing, Llc | Self-correcting computer based name entity pronunciations for speech recognition and synthesis |
US10923113B1 (en) * | 2018-04-13 | 2021-02-16 | Amazon Technologies, Inc. | Speechlet recommendation based on updating a confidence value |
Also Published As
Publication number | Publication date |
---|---|
US20200382453A1 (en) | 2020-12-03 |
US10785171B2 (en) | 2020-09-22 |
US20200259767A1 (en) | 2020-08-13 |
US11621929B2 (en) | 2023-04-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230396567A1 (en) | Chat bot utilizing metaphors to both relay and obtain information | |
JP6751122B2 (en) | Page control method and apparatus | |
US11061700B2 (en) | Virtual assistants using state-based artificial intelligence | |
US10210865B2 (en) | Method and apparatus for inputting information | |
US11748512B2 (en) | Protecting client personal data from customer service agents | |
US10395641B2 (en) | Modifying a language conversation model | |
US11170173B2 (en) | Analyzing chat transcript data by classifying utterances into products, intents and clusters | |
US8954314B2 (en) | Providing translation alternatives on mobile devices by usage of mechanic signals | |
US20230022004A1 (en) | Dynamic vocabulary customization in automated voice systems | |
US20180114527A1 (en) | Methods and systems for virtual agents | |
US20210058844A1 (en) | Handoff Between Bot and Human | |
KR20190074508A (en) | Method for crowdsourcing data of chat model for chatbot | |
WO2022206307A1 (en) | Method for electronic messaging using image based noisy content | |
US11893354B2 (en) | System and method for improving chatbot training dataset | |
US11847416B2 (en) | Systems and methods for converting an input content item based on contexts | |
US11776537B1 (en) | Natural language processing system for context-specific applier interface | |
US11941641B2 (en) | Method and system to manage technical support sessions using historical technical support sessions | |
US11809471B2 (en) | Method and system for implementing a pre-check mechanism in a technical support session | |
US11595527B2 (en) | Dynamic routing for communication systems | |
US20230122631A1 (en) | Global technical support infrastructure with regional data compliance | |
US20230121453A1 (en) | Method and system for generating a question path graph for technical support | |
US20230118212A1 (en) | Method and system for augmenting a question path graph for technical support | |
US20230118749A1 (en) | Global technical support infrastructure | |
CN116384360A (en) | Task processing method, device, electronic equipment and computer readable storage medium | |
CN115221933A (en) | Vertical arbitration full-link processing system and method based on natural language processing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: CAPITAL ONE SERVICES, LLC, VIRGINIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:WALTERS, AUSTIN GRANT;ABAD, FARDIN ABDI TAGHI;GOODSITT, JEREMY EDWARD;AND OTHERS;REEL/FRAME:064241/0203 Effective date: 20190205 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |