NZ784175B2 - Systems and methods for chatbot generation - Google Patents

Systems and methods for chatbot generation Download PDF

Info

Publication number
NZ784175B2
NZ784175B2 NZ784175A NZ78417518A NZ784175B2 NZ 784175 B2 NZ784175 B2 NZ 784175B2 NZ 784175 A NZ784175 A NZ 784175A NZ 78417518 A NZ78417518 A NZ 78417518A NZ 784175 B2 NZ784175 B2 NZ 784175B2
Authority
NZ
New Zealand
Prior art keywords
topic
phrases
specific
dialogue tree
party
Prior art date
Application number
NZ784175A
Other versions
NZ784175A (en
Inventor
Avraham Faizakof
Yochai Konig
Tov Amir Lev
Arnon Mazza
Tamir Tapuhi
Original Assignee
Genesys Cloud S Holdings Ii Llc
Filing date
Publication date
Priority claimed from US15/840,295 external-priority patent/US10498898B2/en
Application filed by Genesys Cloud S Holdings Ii Llc filed Critical Genesys Cloud S Holdings Ii Llc
Publication of NZ784175A publication Critical patent/NZ784175A/en
Publication of NZ784175B2 publication Critical patent/NZ784175B2/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/16—Speech classification or search using artificial neural networks
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5183—Call or contact centers with computer-telephony arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/527—Centralised call answering arrangements not requiring operator intervention

Abstract

method for constructing a deterministic dialogue tree for generating a chatbot: grouping similar phrases of phrases comprising the interactions from the first party of a cluster; for each group of similar phrases: computing a percentage of interaction of the cluster containing at least one phrase from the group of similar phrases; determining whether the percentage exceeds a threshold occurrence rate; and in response to determining that the percentage exceeds the threshold occurrence rate, generating an anchor corresponding to the group of similar phrases; projecting the anchors onto the interactions of the cluster to represent the interactions as sequences of anchors; computing dialogue flows by aligning the sequences of anchors representing the interactions of the clusters; computing the topic-specific dialogue tree from the dialogue flows; and modifying the topic-specific dialogue tree to generate a deterministic dialogue tree.

Claims (12)

1. A method for configuring one or more topic-specific chatbots, using a plurality of transcripts of interactions between a first party and a second party, the method comprising the steps of: grouping, by a processor, similar phrases of phrases comprising the interactions from the first party of a cluster; for each group of similar phrases: computing, by the processor, a percentage of interaction of the cluster containing at least one phrase from the group of similar phrases; determining, by the processor, whether the percentage exceeds a threshold occurrence rate; and in response to determining that the percentage exceeds the threshold occurrence rate, generating, by the processor, an anchor corresponding to the group of similar phrases; projecting, by the processor, the anchors onto the interactions of the cluster to represent the interactions as sequences of anchors; computing, by the processor, dialogue flows by aligning the sequences of anchors representing the interactions of the cluster; computing, by the processor, a topic-specific dialogue tree from the dialogue flows, the topic-specific dialogue tree comprising nodes connected by edges, MARKED-UP COPY wherein, each node of the topic-specific dialogue tree corresponds to an anchor of the anchors, and each edge of the topic-specific dialogue tree connects a first node of the topic-specific dialogue tree to a second node of the topic-specific dialogue tree, and the edge corresponds to a plurality of keyphrases characterizing second party phrases appearing, in the transcripts, in response to first party phrases of the anchor corresponding to the first node and the first party phrases of the anchor corresponding to the second node are in response to the second party phrases of the edge; modifying, by the processor, the topic-specific dialogue tree to generate a deterministic dialogue tree; configuring, by the processor, a topic-specific chatbot in accordance with the deterministic dialogue tree; and outputting, by the processor, the one or more topic-specific chatbots, each of the topic-specific chatbots being configured to generate, automatically, responses to messages regarding the topic of the topic-specific chatbot from the second party in an interaction between the second party and an enterprise.
2. The method of claim 1, further comprising: MARKED-UP COPY displaying, on a user interface, a label of each of the clusters; receiving a command to edit a first label of the labels; and updating the first label of the labels in accordance with the command.
3. The method of claim 1 or 2, wherein the modifying comprises pruning the topic-specific dialogue tree.
4. The method of claim 3, wherein the pruning the topic-specific dialogue tree comprises: identifying nodes of the topic-specific dialogue tree having at least two outgoing edges having overlapping second party phrases, each of the outgoing edges connecting a corresponding first node to a corresponding second node; identifying one edge from among the at least two outgoing edges corresponding to sequences of first party phrases of the second nodes of the at least two outgoing edges most frequently observed in the transcripts of the cluster and identifying the remaining edges among the at least two outgoing edges; and removing the remaining edges from the tropic-specific dialogue tree.
5. The method of claim 3 or 4, wherein the pruning the topic-specific dialogue tree comprises: identifying a first edge and second edge having overlapping second party phrases, the first edge corresponding to sequences of first party phrases most frequently observed in the transcripts of the cluster; and MARKED-UP COPY removing the second edge.
6. The method of any claims 1 to 5, wherein the modifying the topic- specific dialogue tree comprises modifying the phrases characterizing a transition.
7. The method of claim 6, wherein the modifying phrases comprises inserting phrases.
8. The method of claim 6 or 7, wherein the modifying phrases comprises removing phrases.
9. The method of any of claims 1 to 8, wherein the modifying the topic-specific dialogue tree comprises adding a new edge between two nodes.
10. The method of claim 4, wherein the pruning of the topic-specific dialogue tree further comprises: displaying the topic-specific dialogue tree on a user interface; receiving, via the user interface, a command to modify the topic-specific dialogue tree; and updating the topic-specific dialogue tree in accordance with the command.
11. The method of claim 5, wherein the pruning of the topic-specific dialogue tree further comprises: displaying the topic-specific dialogue tree on a user interface; MARKED-UP COPY receiving, via the user interface, a command to modify the topic- specific dialogue tree; and 5 updating the topic-specific dialogue tree in accordance with the command.
12. A system comprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to construct a deterministic dialogue tree for generating a chatbot using a plurality of transcripts of interactions between a first party and a second party, including instructions that cause the processor to: group similar phrases of phrases comprising the interactions from the first party of a cluster; for each group of similar phrases: compute a percentage of interaction of the cluster containing at least one phrase from the group of similar phrases; determine whether the percentage exceeds a threshold occurrence rate; in response to determining that the percentage exceeds the threshold occurrence rate, generating an anchor corresponding to the group of similar phrases; project anchors onto the interactions of the cluster to represent the MARKED-UP COPY interactions as sequences of anchors; compute dialogue flows by aligning the sequences of anchors representing the interactions of the clusters; compute a topic-specific dialogue tree from the dialogue flows, wherein: each node of the topic-specific dialogue tree corresponds to an anchor, and each edge of the topic-specific dialogue tree connects a first node of the topic-specific dialogue tree to a second node of the topic-specific dialogue tree, and the edge corresponds to a plurality of keyphrases characterizing the second party phrases appearing, in the transcripts, in response to the first party phrases of the anchor corresponding to the first node and the first party phrases of the anchor corresponding to the second node are in response to the second party phrases of the edge; and modify the topic-specific dialogue tree to generate a deterministic dialogue tree; configure a topic-specific chatbot in accordance with the deterministic dialogue tree; and output the one or more topic-specific chatbots, each of the topic-specific chatbots being configured to generate, automatically, responses to messages regarding the MARKED-UP COPY topic of the topic-specific chatbot from a customer in an interaction between the customer and an enterprise. Universal Contact | Workbin 1 Server End User 112 118 124 132 122 Agent 1 f\J Device Device Call Routing Stat Reporting Switch/ 108b IMR Controller Server Server Server 136b Media Satewav | Workbin 2 End User Device Agent 2 f\J Device End User 160 156 Device AI Al WFM iXn Multimedia/Social Workbin 3 server Server Media Server Agent 3 j/'Y/ Device 158 170 »»l0oqBlll(1I|1^\yF Web Servers Chatbot recording service Customer Generated Chatbot message response 176 174 m gner ^ User Chatbot input/output interface generation Transcripts of prior extraction chats Start Transcripts from chat interactions -4 Clean and normalize data Normalized transcripts of interactions Cluster interactions by topic Clustered interactions Extract dialogue graph for m 350 I each duster (topic) Dialogue graphs Generate chatbots from dialogue graphs Chatbots End ) FSG. 3 (...Start...) Collection of sentences S Collection of interactions T having content similar to S All available sample transcripts of interactions U t+i Score content word lemmas in T Scored content word lemmas Score n-grams of sentences of S Scored n-grams of S Generate graph G of n-grams based on word mover's distances between n-grams of S and scores Graph G Compute subgraph of G with maximum total node and edge weights subgraph Identify connected components of H subgraph as keyphrases keyphrases o C End ) FSG. 4A Start Select next sentence s from S Sentence s Extract all n-grams of length 1 to N from s Extracted n-grams CO Score all extracted n-grams based on word scores Scored n-grams for sentence s sentences \Ln 5?^ Scored n-grams for sentences in S End") FSG.4B iSJD M I® tx S 8 ' >*^1 ' w 4f + oft Oft oft oft K5S^#S,§J fe> ^ a 8 ^ % %// C 5> d x: X- a oft Oft £ -o~ l% ¦iwf' S lit < <#C ON ^ 1#^ «w s # vv^vv Wf *vs^ S ft- $ ** H XNNNei f*« )««««< <*5 a SUBSTITUTE SHEET (RULE 26) * D:/ // tfiii *='/f S; 'ca tuiy / / /I a S / V' /•••' - 4:f / i .E Vs T3 JO Q £ ™ V / X •>yyyT-’- ii\.. tio ~ — / ssl I" / X v X ; ¦ / .# Xu-" V ;
NZ784175A 2018-12-11 Systems and methods for chatbot generation NZ784175B2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15/840,295 US10498898B2 (en) 2017-12-13 2017-12-13 Systems and methods for chatbot generation
NZ765941A NZ765941A (en) 2017-12-13 2018-12-11 Systems and methods for chatbot generation

Publications (2)

Publication Number Publication Date
NZ784175A NZ784175A (en) 2024-03-22
NZ784175B2 true NZ784175B2 (en) 2024-06-25

Family

ID=

Similar Documents

Publication Publication Date Title
CN111897878B (en) Master-slave data synchronization method and system
EP1292939A4 (en) METHOD AND DEVICE FOR SUMMARIZING PREVIOUS THEMES IN A CONVERSATION CENTER BY A COMMUNICATION CENTER
WO2001040997A1 (en) Method for comparing incoming query with database queries
CN101820398A (en) Instant messenger for dynamically managing messaging group and method thereof
US20170193083A1 (en) Identifying message content related to an event utilizing natural language processing and performing an action pertaining to the event
US20090282114A1 (en) System and method for generating suggested responses to an email
WO2018118546A1 (en) Systems and methods for an emotionally intelligent chat bot
CN101035124A (en) System and method for managing an instant messaging conversation
WO2004025466A3 (en) Distributed computing infrastructure
Jaber et al. Cooking with agents: Designing context-aware voice interaction
Michaud Observations of a new chatbot: Drawing conclusions from early interactions with users
Sood et al. Topic-focused summarization of chat conversations
DE102016102338B4 (en) CONTACT CENTER INTERACTION PREDICTION
CN101834809B (en) Internet instant message communication system
US20200228476A1 (en) System and method for testing of automated contact center customer response systems
CN110417647B (en) Mail processing method, device, computer equipment and storage medium
CN117033590B (en) Information processing and acquiring method, device, equipment and storage medium
NZ784175B2 (en) Systems and methods for chatbot generation
NZ784175A (en) Systems and methods for chatbot generation
CN109062758A (en) A kind of server system delay machine processing method, system, medium and equipment
Shae et al. Efficient internet chat services for help desk agents
WO2024201827A1 (en) Automatic response device, automatic response method, and program
CN115766498A (en) Big data link full link tracking monitoring method and system
US20180096065A1 (en) Media Searching
JP2024003862A (en) Chat system and chat program