CN110737762A - old people personal information assistant system based on voice interaction - Google Patents
old people personal information assistant system based on voice interaction Download PDFInfo
- Publication number
- CN110737762A CN110737762A CN201910955179.9A CN201910955179A CN110737762A CN 110737762 A CN110737762 A CN 110737762A CN 201910955179 A CN201910955179 A CN 201910955179A CN 110737762 A CN110737762 A CN 110737762A
- Authority
- CN
- China
- Prior art keywords
- service
- services
- personal information
- input
- assistant system
- 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
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
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Abstract
The invention discloses an old people personal information assistant system based on voice interaction, which aims at the complaint of 'too far and too cold' of electronic products and network services, focuses on two specific problems of doctor watching and traveling, naturally interacts with old people through an intelligent sound box, converts input voice into text by calling a voice recognition interface on a network, analyzes input text by calling a natural language processing interface of a third party, understands the intention of the old people, finds out the action corresponding to the intention of the old people and executes related third party services by searching the preset intentions of doctor watching, traveling and the like and an action knowledge base, and provides a solution for the old people to the maximum extent by means of splicing.
Description
Technical Field
The invention belongs to the technical field of software engineering, and particularly relates to old people personal information assistant systems based on voice interaction.
Background
Aging is a great challenge facing China, 24090 thousands of people in 60 years old and over in the population of China in 2017 account for 17.3 percent of the total population, 15831 thousands of people in 65 years old and over account for 11.4 percent of the total population, 2025 is expected, the population over sixty years old reaches 3 hundred million, and becomes an ultra-old country, the aging process of the population of 2040 China reaches the peak.
The popularization of modern society informatization degree, more and more informatization technologies bring great confusion to the life of the old people, such as automatic teller machines, smart televisions, internet, mobile phone payment and the like.
In the report of the 33 rd stage published by the internet association of china, as long as 12 months in 2013, the number of senior citizens in China is slightly increased to 1.9% from 1.8% in 2012, but the share of the elderly population in the whole citizens is still the least, and the elderly population is far away from information life of the modern society.
In the existing products related to the old, the health of the old is more, but the technology and products related to the mental and mental health of the old are few, even if the technology and products related to the mental and mental health of the old are simple to make, most of the website contents of the old tend to be simply repeated, for example, the private old search of Baidu search is performed, although the font of the whole page is enlarged, the navigation is also specific, the search result is still only web site link, and the behavior cannot bring about too great change for most of the old, since the information technology is already part which cannot be divided in life, the old can encounter many obstacles when entering the internet life by using corresponding equipment, the old can ask children for help, but the children cannot be available at any time and cannot solve all problems, so that the development of a special intelligent service system for the old in the aspect demand of the old is necessary.
With the development and progress of internet technology and modern mobile communication technology, more and more internet and mobile applications are applied to cloud computing technology, and cloud computing enables users to utilize massive internet resources and improve device computing power through relatively simple devices by integrating internet resources. At present, due to the popularization of 3G and 4G technologies and WiFi networks, the transmission rate of mobile networks is also increased, and more complex and rich applications can be created through the convergence between mobile cloud services and mobile Web services.
Therefore, facing two scenes of medical treatment and trip of the old people, a man-machine interaction interface is established through a natural interaction mode of voice, a convenient entrance for the old people to enter a network and an information world is provided, the old people are helped to adapt to the information era, electronic products and network services are conveniently and simply used, the life is facilitated, the life quality is improved, and the individual requirements of the old people are met.
Disclosure of Invention
The invention provides old people personal information assistant systems based on voice interaction, aiming at the problem that old people are inconvenient to use electronic products such as mobile phones and the like, focusing on seeing a doctor and going out, the system naturally interacts with the old people through an intelligent sound box, the input voice is converted into a text by calling a voice recognition interface on a network, the text is analyzed through a natural language processing interface of a third party, the intention of the old people is understood, actions corresponding to the intention of the old people are found and related third party services are executed by searching a preset intention and action knowledge base, and therefore means for conveniently and simply using the electronic products and the network services are provided for the old people.
A personal information assistant system for the elderly based on voice interaction, which comprises an input/output module, an intelligent question-answering module and a service combination assembly module, wherein:
the input and output module integrates the functions of voice recognition and voice synthesis;
the intelligent question-answering module comprises five functions of an intention library, natural language understanding, conversation state tracking, conversation strategy and conversation response;
the service combination assembly module is responsible for service execution, service dependency relationship generation and service dynamic assembly;
generating a service dependency relationship, namely generating a service dependency relationship graph according to input and output parameters of the service;
service dynamic assembly means that when specific input is known and specific output is obtained, assembly of the service is realized by traversing the service dependency graph.
, the senior personal information assistant system relies on hardware, a smart speaker, which enables voice input and output.
Further , the speech recognition, speech synthesis, and natural language understanding functions rely on third party open services.
Further , the service dependency in the service dependency graph includes a preamble relation, a successor relation, an association relation, and an interface input relation.
The preamble refers to that the execution of services is a prerequisite for the execution of another services.
The successor relationship indicates that the execution of services is a necessary execution after the execution of another services.
The companion relationship means that the execution of services and the execution of services occur simultaneously.
The interface input relationship means that the input of services requires the output of an additional services.
, the service combination assembly module traverses through the graph in the process of realizing service dynamic assembly, and then judges the satisfaction of input and output conditions to quickly determine the service set of the combination.
And , services such as seeing a doctor, going out and the like related to the service combination and assembly module need to be supported and provided with an open service interface by a third party organization.
, the personal information assistant system for the elderly realizes natural interaction and service execution based on voice for the elderly, can not only inquire single service in a service library, but also realize service assembly, meets user requirements to the maximum extent, and improves user experience.
Compared with the prior art, the system has the following beneficial technical effects:
1. the invention relates to an old people information assistant system based on voice interaction, which naturally interacts with old people through an intelligent sound box and converts input voice into text by calling a voice recognition interface on a network; then, by calling a natural language processing interface of a third party, by establishing a corpus, analyzing an input text, understanding the intention of the old, and providing a convenient entrance for the old in China to enter a network and an information world, the old is helped to adapt to the information era, electronic products and network services are conveniently and simply used, the life quality is improved, the personalized requirements of the old are met, and a solution is provided for solving the problem that the old thinks that electronic products and network products are far and cold.
2. The automatic generation technology of the complicated service requirements of the old people based on the dependency relationship and the action assembly not only can directly search preset intentions such as doctor seeing, trip and the like and a service knowledge base like the prior art, find the action corresponding to the intentions of the old people and execute related third-party services; meanwhile, if the library has no preset service or action, the system supports the service and action based on the library, and adopts an action fast assembly algorithm based on the dependency relations of related preorders, sequencers, accompaniments, interfaces and the like, and provides a solution for the old to the maximum extent through a splicing attempt.
3. Compared with the existing general intelligent sound box and personal information assistant system at home and abroad, the intelligent information assistant applied in specific fields of travel and medical observation of the old people is innovative in that the intelligent information assistant focuses on two specific problems of medical observation and travel, so that answers to the two specific problems of medical observation and travel are more accurate, compared with apple Siri, Tamaoling, Baidu Xiaodu and millet Xiao-ai, the intelligent information assistant can not provide corresponding satisfactory answers for users, and the intelligent information assistant system can provide the corresponding satisfactory answers for the users.
Drawings
Fig. 1 is a schematic diagram of the general architecture of the personal information assistant system for the elderly according to the present invention.
Fig. 2 is a schematic diagram of an implementation framework of the intelligent dialogue module according to the invention.
Fig. 3 is a schematic diagram of an implementation framework of the service assembly module according to the present invention.
FIG. 4 is a schematic diagram of a service dependency generation algorithm of the present invention.
FIG. 5 is a schematic diagram of a service dynamic splicing algorithm of the present invention.
Detailed Description
In order to more specifically describe the present invention, the following detailed description is provided for the technical solution of the present invention with reference to the accompanying drawings and the specific embodiments.
As shown in fig. 1, the system for providing personal information assistance to the elderly based on voice interaction of the present invention comprises three modules:
the input and output module formed by voice recognition and voice synthesis mainly completes the conversion of the voice input of the user into characters and inputs the characters into the intelligent question-answering module, and converts the robot feedback processed by the system from characters into voice, wherein is realized by using the capability of the hardware of the intelligent sound box.
The intelligent question-answering module is used for carrying out semantic understanding on the text input of a user, firstly carrying out field classification according to an intention library, carrying out natural language understanding in the corresponding field, identifying the intention, filling the corresponding word slot, selecting a conversation action according to a conversation strategy and a conversation state, calling the service combination module and generating a conversation response; the intent base defines the capability and comprehension of the system, needs to be trained by the material base, and can be designed by the user.
The problem solving and service assembling module is a background capability library of the system, and firstly, a dependency generation engine can acquire an execution dependency relation table among services through an interface table and an effect table of the services; when the old people call the service, the service combination engine can dynamically combine the services in the service library through the input, the expected output and the expected effect obtained from the dialogue module, call the corresponding service after the service process is completed, and feed back according to the result.
The implementation framework of the intelligent question-answering module is shown in fig. 2, and specifically includes the following steps:
(1) an idea library.
The intention library is designed in advance according to the application scene of the system, and is divided according to different application fields, such as the field of nursing care of the old, wherein the contained intentions comprise appointment registration, inquiry of department information, inquiry of doctor scheduling information and the like, and the field of travel planning, wherein the contained intentions comprise appointment taxi taking, route planning and the like. After the voice input of the user is converted into the text, the domain to which the text input by the user belongs needs to be clarified, and then the intention with finer granularity is determined according to the domain category.
(2) Natural language understanding.
In natural language understanding, there are two types of representations required for the input, meaning sentence level intent classification and the second meaning word level information extraction, such as named entity recognition and filling of keywords (semantic slots) representing the user's semantics.given sentence text input "help me reserve ophthalmology in college hospitals", natural language understanding determines the input's intent as "book register" and maps it into semantic slots, where "college hospital" is the slot value of the < hospital > semantic slot and "ophthalmology" is the slot value of the < department > semantic slot, which are also preset from different domain scenes in the intent graph library.
Intentions are generally named as 'verbs + nouns', such as querying weather, registration of appointments, etc., and intent recognition is used to detect user intent, also known as intent classification, i.e., classifying user utterances into previously defined intent categories based on the domain and intent they relate to.
(3) And tracking conversation states.
Tracking dialog state is the core component for ensuring the robustness of dialog system, and is responsible for maintaining and updating dialog state, and the dialog state is machinesThe data representation that can be processed contains all information that may influence the following decision, such as the output of the NLU module, the characteristics of the user, etc. In particular, dialog state St conversation histories until t time are simplified into data structures for system selection of action information at the next time, the mainstream methods for conversation state tracking comprise manual rules, generative models and discriminant models, and the simplest manual rule mode is adopted.
(4) And (4) conversation strategy.
The module has the main functions of deciding the optimal action to take according to the previous dialogue state (such as providing a result, inquiring specific limiting conditions, clarifying or confirming requirements and the like) so as to most effectively assist a user to complete the task of information or service acquisition, and outputs steps of actions based on the semantic expression input by the user and the current dialogue state.
(5) And (6) responding by a dialog.
The module is responsible for two aspects , namely generating natural language for the selected action in the conversation strategy and feeding back the natural language to a lower module (a speech synthesis or service combination module), and updating the conversation state, when the selected action does not need to be solved, for example, 1 in the above example asks a starting point for a user, such as ' asking where to go from ", 2 confirms the starting point for the user, such as ' asking to go from home ', directly generates natural language and generates speech by the speech synthesis module to feed back to the user, and if the selected action needs to be called, such as ' calling to go from home to the same-kernel hospital for you at once ', the service module needs to be entered, corresponding service is selected, and a solution is generated for the user.
The service execution and assembly part is a task execution part in problem solving, selects and combines services in a system service library according to the intention of a user, and the implementation framework is as shown in figure 3, and the specific steps are as follows.
(1) The intention understanding is that for the intention, relevant corresponding actions (actions) or services are established, and the services can be single services such as weather inquiry, simple services such as whether a number source exists or not, and can also be preset combined or spliced services such as registration, series services including number source inquiry, input information, registration, feedback results and the like.
(2) We propose implementation dependency-based service composition method, which uses relational database to store information of stored services and generates service implementation dependency relationship based on the stored information, and can quickly and flexibly determine service composition path according to user request.
(3) Execution dependencies take into account the service interface (input and output) and capabilities (preconditions and effects); in the method, firstly, the dependency relationship of the service is generated according to the interface and the capability of the service and is filled in a WSRelation table, then according to the requirements (including input, output and function requirements) of a user, a dynamic combination service mode is obtained from the WSRelation table, and a designed database has a table structure as follows: service (WSname, Input, Output, prediction, Effect), Input (i _ id, pid, ws _ id), Output (o.id, pid, ws _ id), prediction (pr _ id, pid, tid, ws _ id), Effect (e _ id, pid, tid _ s, tid _ e, ws _ id), Para (pid, pname, cid), Class (cid, cname), relationship (rid, rname), Axiom (aid, cid _1, cid _2, rid), State (tid, tname), ClassState (cs _ id, cid, sid), StateTranss (sp _ id, tid _1, tid _2), WSname, relationship (as _ s, relationship).
(4) The method for generating the dependency relationship aims at generating a service dependency relationship graph according to input and output parameters of a service, and as shown in FIG. 4, the method comprises the following implementation steps:
①, obtaining a service execution dependency relationship through a service interface, connecting the Output table and the Input table to obtain a new temporary table IO, then judging data in the IO to obtain a matched service pair, and inserting the service pair into the WSRelations;
② obtaining the dependency relationship by the Precondition and result of the service, connecting the Effect and Precondition to obtain the temporary table;
③ acquiring matched service pairs from the data in the history table, and inserting the service pairs into the WSRelations;
④ dependency relations can be divided into a preamble relation, a subsequent relation, an accompanying relation, an interface input relation and the like according to types, the relations can be automatically obtained or can be manually specified, the preamble relation refers to that the execution of services is a prerequisite for the execution of another services, the subsequent relation refers to that the execution of services is inevitable after the execution of another services, the accompanying relation refers to that the execution of services and the execution of another services occur simultaneously, and the interface input relation refers to that the input of services needs the output of another services.
(5) The method for generating the dependency relationship can connect the associated services into service network graphs, and when specific input is known and specific output is obtained, the assembly of the services can be realized by traversing the graphs, as shown in fig. 5, the realization steps are as follows:
① inquiring the WSRelation table by user input and input inquiry to obtain paths, if no path exists, the program is terminated;
② input parameters of the scan path;
③ output parameters of the scan path;
④ determining whether the user's output parameters are all included in the output parameters of the path;
⑤ if not, return to ①;
⑥ checks if the input parameters can fully trigger all services on the path;
⑦ if all services can be triggered, the path is an alternative service assembly, if not, return to ①.
The foregoing description of the embodiments is provided to enable one of ordinary skill in the art to make and use the invention, and it is to be understood that other modifications of the embodiments, and the application of the principles of set forth herein, may be readily made by those skilled in the art without the use of inventive faculty.
Claims (8)
1, old people personal information assistant system based on voice interaction, which is characterized in that it comprises input and output module, intelligent question answering module and service combination assembling module, wherein:
the input and output module integrates the functions of voice recognition and voice synthesis;
the intelligent question-answering module comprises five functions of an intention library, natural language understanding, conversation state tracking, conversation strategy and conversation response;
the service combination assembly module is responsible for service execution, service dependency relationship generation and service dynamic assembly;
generating a service dependency relationship, namely generating a service dependency relationship graph according to input and output parameters of the service;
service dynamic assembly means that when specific input is known and specific output is obtained, assembly of the service is realized by traversing the service dependency graph.
2. An elderly personal information assistant system according to claim 1, wherein: the personal information assistant system for the elderly relies on hardware, namely a smart speaker, which enables input and output of speech.
3. An elderly personal information assistant system according to claim 1, wherein: the speech recognition, speech synthesis and natural language understanding functions rely on third party open services.
4. An elderly personal information assistant system according to claim 1, wherein: the service dependency relationship in the service dependency relationship graph comprises a preamble relationship, a subsequent relationship, an accompanying relationship and an interface input relationship.
5. The personal information assistant system for elderly people as claimed in claim 4, wherein the preamble relation means that the execution of services is a prerequisite for the execution of another services, the subsequent relation means that the execution of services is a necessary execution after the execution of another services, the companion relation means that the execution of services and the execution of another services occur simultaneously, and the interface input relation means that the input of services requires the output of another services.
6. An elderly personal information assistant system according to claim 1, wherein: the service combination assembly module is traversed through a graph in the process of realizing dynamic assembly of the service, and then the satisfaction of input and output conditions is judged so as to quickly determine the service set of the combination.
7. An elderly personal information assistant system according to claim 1, wherein: services such as seeing a doctor, going out and the like related to the service combination assembly module need to be supported and provided with an open service interface by a third party organization.
8. An elderly personal information assistant system according to claim 1, wherein: the personal information assistant system for the old people realizes natural interaction and service execution based on voice for the old people, can not only inquire single service in a service library, but also realize service assembly, meets user requirements to the maximum extent, and improves user experience.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955179.9A CN110737762A (en) | 2019-10-09 | 2019-10-09 | old people personal information assistant system based on voice interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955179.9A CN110737762A (en) | 2019-10-09 | 2019-10-09 | old people personal information assistant system based on voice interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110737762A true CN110737762A (en) | 2020-01-31 |
Family
ID=69269892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910955179.9A Pending CN110737762A (en) | 2019-10-09 | 2019-10-09 | old people personal information assistant system based on voice interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110737762A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199498A (en) * | 2020-09-27 | 2021-01-08 | 中国建设银行股份有限公司 | Man-machine conversation method, device, medium and electronic equipment for endowment service |
| CN114373260A (en) * | 2022-01-20 | 2022-04-19 | 上海市共进通信技术有限公司 | Method for realizing registration reservation processing based on home gateway, home gateway system, device, processor and storage medium thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7421393B1 (en) * | 2004-03-01 | 2008-09-02 | At&T Corp. | System for developing a dialog manager using modular spoken-dialog components |
| CN101465749A (en) * | 2008-12-29 | 2009-06-24 | 武汉大学 | Method for building interlocution service based on Web Service combination |
| CN105808200A (en) * | 2010-01-18 | 2016-07-27 | 苹果公司 | Intelligent automated assistant |
| CN107103005A (en) * | 2016-02-23 | 2017-08-29 | 阿里巴巴集团控股有限公司 | The collection method and device of question and answer language material |
| CN108536852A (en) * | 2018-04-16 | 2018-09-14 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer readable storage medium |
| CN109002510A (en) * | 2018-06-29 | 2018-12-14 | 北京百度网讯科技有限公司 | A kind of dialog process method, apparatus, equipment and medium |
| CN109614474A (en) * | 2018-06-05 | 2019-04-12 | 安徽省泰岳祥升软件有限公司 | Process configuration unit, method and the intelligent robot interactive system of more wheel sessions |
| CN110110059A (en) * | 2019-05-20 | 2019-08-09 | 挂号网（杭州）科技有限公司 | A kind of medical conversational system intention assessment classification method based on deep learning |
| CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
-
2019
- 2019-10-09 CN CN201910955179.9A patent/CN110737762A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7421393B1 (en) * | 2004-03-01 | 2008-09-02 | At&T Corp. | System for developing a dialog manager using modular spoken-dialog components |
| CN101465749A (en) * | 2008-12-29 | 2009-06-24 | 武汉大学 | Method for building interlocution service based on Web Service combination |
| CN105808200A (en) * | 2010-01-18 | 2016-07-27 | 苹果公司 | Intelligent automated assistant |
| CN107103005A (en) * | 2016-02-23 | 2017-08-29 | 阿里巴巴集团控股有限公司 | The collection method and device of question and answer language material |
| CN108536852A (en) * | 2018-04-16 | 2018-09-14 | 上海智臻智能网络科技股份有限公司 | Question and answer exchange method and device, computer equipment and computer readable storage medium |
| CN109614474A (en) * | 2018-06-05 | 2019-04-12 | 安徽省泰岳祥升软件有限公司 | Process configuration unit, method and the intelligent robot interactive system of more wheel sessions |
| CN109002510A (en) * | 2018-06-29 | 2018-12-14 | 北京百度网讯科技有限公司 | A kind of dialog process method, apparatus, equipment and medium |
| CN110110059A (en) * | 2019-05-20 | 2019-08-09 | 挂号网（杭州）科技有限公司 | A kind of medical conversational system intention assessment classification method based on deep learning |
| CN110209791A (en) * | 2019-06-12 | 2019-09-06 | 百融云创科技股份有限公司 | It is a kind of to take turns dialogue intelligent speech interactive system and device more |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112199498A (en) * | 2020-09-27 | 2021-01-08 | 中国建设银行股份有限公司 | Man-machine conversation method, device, medium and electronic equipment for endowment service |
| CN114373260A (en) * | 2022-01-20 | 2022-04-19 | 上海市共进通信技术有限公司 | Method for realizing registration reservation processing based on home gateway, home gateway system, device, processor and storage medium thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11727941B2 (en) | Managing dialog data providers | |
| CN109271498B (en) | Natural language interaction method and system for virtual robot | |
| JP6686226B2 (en) | Call the appropriate agent automation assistant | |
| US9666185B2 (en) | Automatic data-driven dialog discovery system | |
| US7647228B2 (en) | Method and apparatus for speech processing incorporating user intent | |
| EP1557824A1 (en) | System and method to disambiguate user's intention in a spoken dialog system | |
| JP2020503620A (en) | Context-Aware Human-Computer Dialogue | |
| US20060235694A1 (en) | Integrating conversational speech into Web browsers | |
| US20120296638A1 (en) | Method and system for quickly recognizing and responding to user intents and questions from natural language input using intelligent hierarchical processing and personalized adaptive semantic interface | |
| JPH08106298A (en) | Device and method for conversation processing | |
| KR20220000046A (en) | System and method for manufacturing conversational intelligence service providing chatbot | |
| CN110737762A (en) | old people personal information assistant system based on voice interaction | |
| CN114760387A (en) | Method and device for managing maintenance | |
| KR20200092455A (en) | Server, method and computer program for predicting intention of user | |
| Meliones et al. | DALÍ: A digital assistant for the elderly and visually impaired using Alexa speech interaction and TV display | |
| KR20200119035A (en) | Dialogue system, electronic apparatus and method for controlling the dialogue system | |
| Larsson et al. | Domain-specific and general syntax and semantics in the talkamatic dialogue manager | |
| Potamianos et al. | Information seeking spoken dialogue systems—part II: Multimodal dialogue | |
| TWI639997B (en) | Dialog understanding method based on probabilistic rule | |
| Belenko et al. | Design, implementation and usage of modern voice assistants | |
| Griol et al. | From VoiceXML to multimodal mobile Apps: development of practical conversational interfaces | |
| Barnwal et al. | ARIVA: Artificial Intelligence Enabled Voice Assistance System using Natural Language Processing | |
| Loutas et al. | Facilitating the Semantic Discovery of eGovernment Services: The SemanticGov Portal | |
| Cabrera Paraiso et al. | A voice-enabled assistant in a multi-agent system for e-government services | |
| US20230048077A1 (en) | Mobile intelligent outside sales assistant |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |