CN116340482A - Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine - Google Patents
Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine Download PDFInfo
- Publication number
- CN116340482A CN116340482A CN202310192381.7A CN202310192381A CN116340482A CN 116340482 A CN116340482 A CN 116340482A CN 202310192381 A CN202310192381 A CN 202310192381A CN 116340482 A CN116340482 A CN 116340482A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- module
- conversation
- automatic
- speaking
- 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
- 238000004891 communication Methods 0.000 claims abstract description 21
- 230000008451 emotion Effects 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 239000003795 chemical substances by application Substances 0.000 claims description 22
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002996 emotional effect Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000013518 transcription Methods 0.000 claims description 3
- 230000035897 transcription Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 238000011161 development Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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 or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a multi-skill customer service auxiliary product based on enterprise WeChat combined with an NLP engine, which relates to the technical field of enterprise WeChat automatic reply, and collects automatic conversation and answer information of clients to the automatic conversation sent by all agents of each enterprise in an enterprise WeChat system by arranging an enterprise management module; the setting semantic understanding module utilizes NLP technology to understand the real semantic information of the message sent by the client; the voice search module is arranged to search out a proper set of reply voice from a voice library according to the real semantic information of the message sent by the client; the scoring module of the telephone setting operation scores each answering operation according to the feedback condition of the customer on each answering operation; the voice operation recommendation module is arranged to order the searched automatic call answering operation for the real-time information of the clients and then recommend the automatic call answering operation to the seat; the method comprehensively considers the difference of client groups of each company, and avoids the problem that the response telephone operation is too consistent so as to influence the communication emotion of the clients.
Description
Technical Field
The invention belongs to the field of intelligent customer service, relates to an information automatic replying technology, and particularly relates to a multi-skill customer service auxiliary product based on enterprise WeChat combined with an NLP engine.
Background
Along with the increase of the customer flow, due to the uneven distribution of enterprise customer service personnel and personal level, customer service efficiency is low, customer waiting time is long and other reasons, customer flow increase corresponding customer service complaint amount is also increasing, and the development of private domain provides higher service requirements for enterprise customer service personnel.
The existing automatic replies at present mostly adopt unified replies, and the difference of business of each enterprise is not comprehensively considered, and the difference of customer groups is not considered; thereby bringing about the difference of reply attitudes of clients by unified reply; therefore, there is a need for a customer service response auxiliary product that combines the actual situation of each enterprise with the customer's response emotion;
for this reason, a multi-skill customer service auxiliary product based on enterprise WeChat in combination with NLP engine is proposed.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a multi-skill customer service auxiliary product based on an enterprise WeChat combined NLP engine, which is characterized in that independent operation areas are defined for each enterprise in an enterprise WeChat system, and historical communication information of customer service agents and customers in each independent operation area is collected in advance; for each enterprise, according to historical communication information of the enterprise and the distribution condition of enthusiasm of clients for each automatic reply message in communication information of all enterprises, calculating comprehensive weights of the clients of the enterprise on reply emotions of each sentence of automatic replies, and sequencing the automatic reply dialects according to the comprehensive weights; the ordered speaking operation is the recommended order of the speaking operation; the method comprehensively considers the difference of client groups of each company, and avoids the problem that the response telephone operation is too consistent so as to influence the communication emotion of the clients.
To achieve the above objective, an embodiment according to a first aspect of the present invention provides a multi-skill customer service auxiliary product based on an enterprise WeChat in combination with an NLP engine, which includes an enterprise WeChat communication module, an enterprise management module, a semantic understanding module, a speaking search module, a speaking scoring module, and a speaking recommendation module; wherein, each module is connected by an electric and/or wireless network mode;
the enterprise WeChat communication module is mainly used for enabling a user to communicate with a seat through enterprise WeChat;
the enterprise WeChat communication module synchronizes dialogue messages between agents and clients on enterprise WeChats in real time by opening a session archiving function of the enterprise WeChats, and pushes messages to an agent assistant interface in real time, and the information replied by the agents is pushed to enterprise WeChat processing; acquiring chat dialogue content and related information association based on an official API provided by enterprise WeChat; the enterprise WeChat communication module sends the acquired chat dialogue content and related information to the semantic understanding module;
the enterprise management module is mainly used for independently managing each enterprise message in the enterprise WeChat system;
the enterprise management module defines an independent operation area for each enterprise in the enterprise WeChat system; collecting automatic conversation and answer information of clients to the automatic conversation sent by all agents of each enterprise in an independent operation area of the enterprise; the automatic conversation sent by a seat and the answer information of a customer to the automatic conversation are called an automatic conversation;
the enterprise management module sends all automatic conversations occurring in each enterprise independent operation area to the speaking scoring module; and labeling the name of each enterprise for the automatic dialogue of each enterprise;
the enterprise management module collects all automatic dialogs of all enterprises and sends all automatic dialogs to the speaking scoring module;
the semantic understanding module is mainly used for understanding the semantics of the message sent by the client by utilizing an NLP technology;
in a preferred embodiment, the semantic understanding module includes ASR transcription of speech, photo OCR recognition and text NLP semantic understanding tools;
for the audio message sent by the client, transferring the audio message into a text by calling an ASR engine, and generating real semantic information of the client voice by calling an NLP semantic understanding engine;
for text messages sent by clients, generating real semantic information of client voices by calling an NLP semantic understanding engine;
the semantic understanding module sends the real semantic information of the client to the speaking search module;
the telephone operation searching module is mainly used for searching out a proper set of reply telephone operation from a telephone operation library according to the real semantic information of a message sent by a client;
the speaking search module downloads various speaking sets of reply client information used by the enterprise seat from the Internet; it is to be understood that each piece of speaking information in the speaking collection comprises client information and a corresponding answer speaking;
for the message sent by the client in real time, the speaking search module selects all the speaking technologies with the semantic information similar to that of the real-time message from the speaking operation set; the judging mode of the similarity of the semantic information is as follows: calculating the similarity between the real-time information of the client and the semantic feature vector of the client information of each conversation in the conversation collection, and presetting a similarity threshold according to actual experience; when the similarity is larger than a similarity threshold, judging that the real-time information of the client is similar to the semantic information of the client information of the speaking operation;
the speaking search module sends the searched semantically similar speaking collection to the speaking recommendation module;
the telephone scoring module is mainly used for scoring each answering operation according to feedback conditions of clients on each answering operation for each enterprise;
the scoring module for scoring each answer comprises the following steps:
step S1: for each enterprise, acquiring automatic dialogue data of the enterprise from the automatic dialogue data sent by the enterprise management module;
step S2: classifying each enterprise dialogue data according to the automatic replied conversation content; marking each auto-answer type as w;
step S3: analyzing emotion attributes of each automatic reply by a client by using sentence emotion analysis technology; the emotional attributes include positive, neutral, and negative;
step S4: for the automatic replying conversation type w, counting the proportion of positive feedback of clients in the enterprise conversation data; marking the enterprise as c, and marking the positive feedback proportion of the automatic replying speaking type w in the enterprise c as Pwc;
step S5: for the automatic replying conversation type w, counting the proportion of positive feedback of clients in all conversation data; marking the positive feedback proportion of the automatic replying conversation type w in all conversation data as Pw;
step S6: each enterprise respectively sets weight coefficients a and b for Pwc and Pw according to actual experience; and calculates the comprehensive weight Qwc of the automatic replying speaking type w; the calculation formula of the comprehensive weight is qwc=a×pwc+b×pw;
the speaking skill scoring module sends the comprehensive weight Qwc of each enterprise to the speaking skill recommending module;
the conversation recommending module is mainly used for sequencing the searched automatic answer conversations for the real-time information of the clients and recommending the automatic answer conversations to the agents;
the method for ordering the automatic call replying by the call recommending module comprises the following steps: for the agents of each enterprise c, sequencing the conversation sets received from the conversation searching module according to the comprehensive weight of each answer conversation in the conversation sets from large to small; and recommending the sequenced conversation collection to the seat in sequence.
Compared with the prior art, the invention has the beneficial effects that:
in the enterprise WeChat system, an independent operation area is defined for each enterprise, and historical communication information of customer service agents and customers in each independent operation area is collected in advance; for each enterprise, according to historical communication information of the enterprise and the distribution condition of enthusiasm of clients for each automatic reply message in communication information of all enterprises, calculating comprehensive weights of the clients of the enterprise on reply emotions of each sentence of automatic replies, and sequencing the automatic reply dialects according to the comprehensive weights; the ordered speaking operation is the recommended order of the speaking operation; the method comprehensively considers the difference of client groups of each company, and avoids the problem that the response telephone operation is too consistent so as to influence the communication emotion of the clients.
Drawings
Fig. 1 is a schematic diagram of the present invention.
Description of the embodiments
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the multi-skill customer service auxiliary product based on the combination of enterprise WeChat and NLP engine comprises an enterprise WeChat communication module, an enterprise management module, a semantic understanding module, a speaking search module, a speaking scoring module and a speaking recommendation module; wherein, each module is connected by an electric and/or wireless network mode;
with the increase of the customer flow, due to the uneven distribution of enterprise customer service personnel and personal level, customer service efficiency is low, customer waiting time is long and other reasons, customer flow increase corresponding customer service complaint amount is also increased, and the development of private domain brings higher service requirements to enterprise customer service personnel;
the enterprise WeChat communication module is mainly used for enabling a user to communicate with a seat through enterprise WeChat;
in a preferred embodiment, the enterprise WeChat communication module synchronizes dialogue messages between agents and clients on enterprise WeChat in real time by opening a session archiving function of the enterprise WeChat, and pushes the messages to an agent assistant interface in real time, and the information replied by the agents is pushed to enterprise WeChat processing; acquiring chat dialogue content and related information association based on an official API provided by enterprise WeChat; preferably, the related information is a plurality of pieces of information above each piece of information; the enterprise WeChat communication module sends the acquired chat dialogue content and related information to the semantic understanding module;
the enterprise management module is mainly used for independently managing each enterprise message in the enterprise WeChat system;
it can be understood that the number of customer service agents of each enterprise is generally more than 1, and the number of customer service agents of each enterprise is different according to different services;
in a preferred embodiment, the enterprise management module defines an independent operation area for each enterprise in the enterprise WeChat system; collecting automatic conversation and answer information of clients to the automatic conversation sent by all agents of each enterprise in an independent operation area of the enterprise; the automatic conversation sent by a seat and the answer information of a customer to the automatic conversation are called an automatic conversation;
the enterprise management module sends all automatic conversations occurring in each enterprise independent operation area to the speaking scoring module; and labeling the name of each enterprise for the automatic dialogue of each enterprise;
further, the enterprise management module collects all automatic dialogs of all enterprises and sends all automatic dialogs to the speaking scoring module;
the semantic understanding module is mainly used for understanding the semantics of the message sent by the client by utilizing an NLP technology;
in a preferred embodiment, the semantic understanding module includes ASR transcription of speech, photo OCR recognition and text NLP semantic understanding tools;
for the audio message sent by the client, transferring the audio message into a text by calling an ASR engine, and generating real semantic information of the client voice by calling an NLP semantic understanding engine;
for text messages sent by clients, generating real semantic information of client voices by calling an NLP semantic understanding engine; preferably, the real semantic information is in the form of semantic feature vectors of context information of each message of the client;
the semantic understanding module sends the real semantic information of the client to the speaking search module;
the telephone operation searching module is mainly used for searching out a proper set of reply telephone operation from a telephone operation library according to the real semantic information of a message sent by a client;
in a preferred embodiment, the speaking search module downloads a speaking collection of various reply client information used by the enterprise agents from the internet; it is to be understood that each piece of speaking information in the speaking collection comprises client information and a corresponding answer speaking;
for the message sent by the client in real time, the speaking search module selects all the speaking technologies with the semantic information similar to that of the real-time message from the speaking operation set; the judging mode of the similarity of the semantic information is as follows: calculating the similarity between the real-time information of the client and the semantic feature vector of the client information of each conversation in the conversation collection, and presetting a similarity threshold according to actual experience; when the similarity is larger than a similarity threshold, judging that the real-time information of the client is similar to the semantic information of the client information of the speaking operation;
the speaking search module sends the searched semantically similar speaking collection to the speaking recommendation module;
the telephone scoring module is mainly used for scoring each answering operation according to feedback conditions of clients on each answering operation for each enterprise;
in a preferred embodiment, the scoring module scores each answer phone comprising the steps of:
step S1: for each enterprise, acquiring automatic dialogue data of the enterprise from the automatic dialogue data sent by the enterprise management module;
step S2: classifying each enterprise dialogue data according to the automatic replied conversation content; marking each auto-answer type as w;
step S3: analyzing emotion attributes of each automatic reply by a client by using sentence emotion analysis technology; the emotional attributes include positive, neutral, and negative;
step S4: for the automatic replying conversation type w, counting the proportion of positive feedback of clients in the enterprise conversation data; marking the enterprise as c, and marking the positive feedback proportion of the automatic replying speaking type w in the enterprise c as Pwc;
step S5: for the automatic replying conversation type w, counting the proportion of positive feedback of clients in all conversation data; marking the positive feedback proportion of the automatic replying conversation type w in all conversation data as Pw;
step S6: each enterprise respectively sets weight coefficients a and b for Pwc and Pw according to actual experience; and calculates the comprehensive weight Qwc of the automatic replying speaking type w; the calculation formula of the comprehensive weight is qwc=a×pwc+b×pw;
the speaking skill scoring module sends the comprehensive weight Qwc of each enterprise to the speaking skill recommending module;
the conversation recommending module is mainly used for sequencing the searched automatic answer conversations for the real-time information of the clients and recommending the automatic answer conversations to the agents;
in a preferred embodiment, the speaking recommendation module ranks the automatic reply utterances in the following manner: for the agents of each enterprise c, sequencing the conversation sets received from the conversation searching module according to the comprehensive weight of each answer conversation in the conversation sets from large to small; and recommending the sequenced conversation collection to the seat in sequence.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine is characterized by comprising an enterprise WeChat communication module, an enterprise management module, a semantic understanding module, a speaking operation searching module, a speaking operation scoring module and a speaking operation recommending module; wherein, each module is connected by an electric and/or wireless network mode;
the enterprise WeChat communication module is used for being responsible for communication between a user and a seat through enterprise WeChat; the acquired chat dialogue content and related information are sent to a semantic understanding module;
the enterprise management module is used for independently managing each enterprise message in the enterprise WeChat system; the automatic conversation sent by a seat and the answer information of a customer to the automatic conversation are called an automatic conversation; the enterprise management module sends all automatic conversations occurring in each enterprise independent operation area to the speaking scoring module; and labeling the name of each enterprise for the automatic dialogue of each enterprise;
the enterprise management module collects all automatic dialogs of all enterprises and sends all automatic dialogs to the speaking scoring module;
the semantic understanding module is used for understanding real semantic information of a message sent by a client by utilizing an NLP technology; the real semantic information of the client is sent to a speaking search module;
the telephone operation searching module is used for searching out a proper set of reply telephone operation from a telephone operation library according to the real semantic information of the message sent by the client; sending the searched semantic similar conversation collection to a conversation recommendation module;
the telephone scoring module is used for scoring each answering operation according to the feedback condition of the client on each answering operation for each enterprise; the speaking skill scoring module sends the comprehensive weight Qwc of each enterprise to the speaking skill recommending module;
the conversation recommending module is used for sequencing the searched automatic answer conversations for the real-time information of the clients and recommending the automatic answer conversations to the agents.
2. The multi-skill customer service auxiliary product based on the enterprise WeChat combined with the NLP engine according to claim 1, wherein the enterprise WeChat communication module synchronizes dialogue messages of agents and clients on the enterprise WeChat in real time, and acquires chat dialogue content and related information association based on an official API provided by the enterprise WeChat.
3. The enterprise WeChat in combination with NLP engine based multi-skill customer service assistance product of claim 1, wherein the enterprise management module defines an independent operating area for each enterprise in an enterprise WeChat system;
in the independent operation area of each enterprise, collecting the automatic conversation and the answer information of the customer to the automatic conversation sent by all the agents of the enterprise.
4. The enterprise WeChat in combination with NLP engine based multi-skill customer service assistance product of claim 1, wherein the semantic understanding module comprises ASR transcription of speech, photo OCR recognition, and text NLP semantic understanding tools.
5. The multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine according to claim 1, wherein the speaking search module downloads speaking sets of various reply customer information used by enterprise agents from the Internet; for the message sent by the client in real time, the speaking search module selects all the speaking technologies with the semantic information similar to that of the real-time message from the speaking operation set.
6. The multi-skill customer service auxiliary product based on the enterprise WeChat combined NLP engine of claim 5, wherein the semantic information similarity judging mode is as follows: calculating the similarity between the real-time information of the client and the semantic feature vector of the client information of each conversation in the conversation collection, and presetting a similarity threshold according to actual experience; when the similarity is larger than the similarity threshold, judging that the real-time information of the client is similar to the semantic information of the client information of the conversation.
7. The multi-skill customer service assistance product based on enterprise WeChat in combination with NLP engine of claim 1, wherein the scoring module is mainly used for scoring each answering operation for each enterprise according to feedback condition of clients to each answering operation;
the scoring module for scoring each answer comprises the following steps:
for each enterprise, acquiring automatic dialogue data of the enterprise from the automatic dialogue data sent by the enterprise management module;
classifying each enterprise dialogue data according to the automatic replied conversation content; marking each auto-answer type as w;
analyzing emotion attributes of each automatic reply by a client by using sentence emotion analysis technology; the emotional attributes include positive, neutral, and negative;
for the automatic replying conversation type w, counting the proportion of positive feedback of clients in the enterprise conversation data; marking the enterprise as c, and marking the positive feedback proportion of the automatic replying speaking type w in the enterprise c as Pwc;
for the automatic replying conversation type w, counting the proportion of positive feedback of clients in all conversation data; marking the positive feedback proportion of the automatic replying conversation type w in all conversation data as Pw;
each enterprise respectively sets weight coefficients a and b for Pwc and Pw according to actual experience; and calculates the comprehensive weight Qwc of the automatic replying speaking type w; the calculation formula of the comprehensive weight is qwc=a×pwc+b×pw.
8. The multi-skill customer service assistance product based on enterprise WeChat in combination with NLP engine of claim 1, wherein the way the phone recommendation module ranks auto-answer phones is: for the agents of each enterprise c, sequencing the conversation sets received from the conversation searching module according to the comprehensive weight of each answer conversation in the conversation sets from large to small; and recommending the sequenced conversation collection to the seat in sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310192381.7A CN116340482A (en) | 2023-03-02 | 2023-03-02 | Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310192381.7A CN116340482A (en) | 2023-03-02 | 2023-03-02 | Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116340482A true CN116340482A (en) | 2023-06-27 |
Family
ID=86879936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310192381.7A Pending CN116340482A (en) | 2023-03-02 | 2023-03-02 | Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116340482A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117221447A (en) * | 2023-08-10 | 2023-12-12 | 国网浙江省电力有限公司杭州供电公司 | Online telephone communication auxiliary support system based on AI technology |
| CN117221447B (en) * | 2023-08-10 | 2024-05-14 | 国网浙江省电力有限公司杭州供电公司 | Online telephone communication auxiliary support system based on AI technology |
-
2023
- 2023-03-02 CN CN202310192381.7A patent/CN116340482A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117221447A (en) * | 2023-08-10 | 2023-12-12 | 国网浙江省电力有限公司杭州供电公司 | Online telephone communication auxiliary support system based on AI technology |
| CN117221447B (en) * | 2023-08-10 | 2024-05-14 | 国网浙江省电力有限公司杭州供电公司 | Online telephone communication auxiliary support system based on AI technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11706339B2 (en) | System and method for communication analysis for use with agent assist within a cloud-based contact center | |
| CN109672786B (en) | Incoming call answering method and device | |
| CN109949805B (en) | Intelligent collection urging robot based on intention recognition and finite state automaton and collection urging method | |
| US20210136207A1 (en) | Methods and systems for seamless outbound cold calls using virtual agents | |
| US20210136205A1 (en) | Methods and systems of virtual agent real-time recommendation, suggestion and advertisement | |
| US7933399B2 (en) | System and method for utilizing virtual agents in an interactive voice response application | |
| US20210134284A1 (en) | Methods and systems for personalized virtual agents to learn from customers | |
| US20210134283A1 (en) | Methods and systems of virtual agent real-time recommendation, suggestion and advertisement | |
| US20210133765A1 (en) | Methods and systems for socially aware virtual agents | |
| CN101662549B (en) | Customer evaluation system and customer evaluation method based on voice | |
| US20210136204A1 (en) | Virtual agents within a cloud-based contact center | |
| US20210136206A1 (en) | Virtual agents within a cloud-based contact center | |
| CN112885348A (en) | AI-combined intelligent voice electric marketing method | |
| US20210136195A1 (en) | Methods and systems for virtual agent to understand and detect spammers, fraud calls, and auto dialers | |
| US20210136208A1 (en) | Methods and systems for virtual agent to understand and detect spammers, fraud calls, and auto dialers | |
| CN113645124B (en) | System and method for pushing social platform information through intelligent voice interaction platform | |
| WO2021135317A1 (en) | Method and system for making call on the basis of order | |
| CN110705926A (en) | Method, device and system for acquiring logistics object distribution information | |
| CN111212189A (en) | Intelligent outbound system based on mobile phone terminal | |
| CN116340482A (en) | Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine | |
| CN113645364B (en) | Intelligent voice outbound method for power dispatching | |
| US20210133533A1 (en) | Methods and systems for seamless outbound cold calls using virtual agents | |
| US20210133764A1 (en) | Methods and systems for virtual agents to check caller identity via multi channels | |
| CN112185383A (en) | Processing method and system for customer service return visit | |
| CN112333341A (en) | Intelligent voice robot system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |