CN110688473A - Method for robot to dynamically acquire information - Google Patents
Method for robot to dynamically acquire information Download PDFInfo
- Publication number
- CN110688473A CN110688473A CN201910955647.2A CN201910955647A CN110688473A CN 110688473 A CN110688473 A CN 110688473A CN 201910955647 A CN201910955647 A CN 201910955647A CN 110688473 A CN110688473 A CN 110688473A
- Authority
- CN
- China
- Prior art keywords
- module
- information
- data
- conversation
- robot
- 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
- 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
- G06F16/3343—Query execution using phonetics
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
Abstract
The invention discloses a method for a robot to dynamically acquire information, which solves the problems of poor information timeliness and low safety, and the scheme can dynamically acquire and utilize the information of a called user and feed back the information to a conversation, thereby improving the conversation efficiency of the robot, simultaneously ensuring the timeliness and the safety of the information, analyzing and extracting relevant information through a data processor through a text translated by an identification module according to a specified mode, or inquiring a user information system at necessary moment to obtain the latest information, so that the whole conversation is more intelligent and efficient, and the timeliness and the safety of the user information are ensured. The system comprises a client module, an input module, an identification module, a node setting module, a database, a judgment module, a data processor, a condition judgment module, a network communication module, a data query module, a remote data service module, a language conversion module, an output module, a feedback module and a repeated setting module, wherein the client module is connected with the input module.
Description
Technical Field
The invention relates to the technical field of software, in particular to a method for a robot to dynamically acquire information.
Background
At present, a machine can realize near real-time understanding of human voice language through ASR (real-time speech recognition) and NLP (natural language understanding), AI intelligent communication is carried out in scenes such as customer service and sales, large-scale corpus training is carried out on the human voice language, a recognition model with good recognition quality can be obtained in a specified scene, the robot sends human voice to ASR recognition in real time to obtain a recognition result in a text form, meanwhile, a question-answer knowledge base is searched by combining the input called user information, multiple factors are integrated, or semantic processing is carried out to obtain preset questions and answers, the preset questions and answers are played in an audio form, and the voice communication between a person and the machine is obtained.
Although the existing scheme can support the robot to better utilize personal information of a called user, the information is input into a system in advance, and cannot be changed dynamically according to an actual conversation scene, or some sensitive information cannot be protected, so that the existing scheme cannot be suitable for occasions with high requirements on information timeliness and safety, on the other hand, the robot needs to actively acquire information through conversation context, grasp latest and effective information in the current conversation, and acquire and utilize the latest and effective information, and the existing voice communication scheme of AI and people still needs to be improved in the aspects of information acquisition and utilization, information timeliness, safety and the like.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method for dynamically acquiring information by a robot, which solves the problems of poor information timeliness and low safety, and improves the information acquisition and utilization, and the timeliness and the safety of the information by an AI and human voice communication scheme.
In order to achieve the purpose, the invention is realized by the following technical scheme: a system for dynamically acquiring information by a robot comprises a client module, an input module, an identification module, a node setting module, a database, a judgment module, a data processor, a condition judgment module, a network communication module, a data query module, a remote data service module, a language conversion module, an output module, a feedback module and a repeated setting module, wherein the client module is connected with the input module, the input module is connected with the identification module, the identification module is connected with the node setting module, the node setting module is connected with the database, the node setting module is connected with the judgment module, the judgment module is connected with the data processor, the data processor is connected with the condition judgment module, the data processor is connected with the network communication module, the network communication module is connected with the data query module, and the data query module is connected with the remote data service module, the data query module is connected with the condition judgment module.
Preferably, the data processor is connected with a feedback module, the data query module is connected with a feedback module, the feedback module is connected with an output module, the feedback module is connected with a repeated setting module, the repeated setting module is connected with a judgment module, and the repeated setting module is connected with the output module.
Preferably, the recognition module comprises a voice recognition module and a natural language processing module, and the voice recognition module is connected with the natural language processing module.
Preferably, the data processor comprises a data acquisition module, a data analysis module and a data extraction module, wherein the data acquisition module is connected with the data analysis module, and the data analysis module is connected with the data extraction module.
Preferably, the condition judgment module is connected with the language conversion module, the language conversion module is connected with the output module, and the output module is connected with the client module.
A method for dynamically acquiring information by a robot comprises the following specific steps:
the method comprises the following steps: when the client module initiates voice communication, information is input through the input module, the input module transmits the information to the recognition module, the recognition module recognizes the information through the voice recognition module, and if the information can be recognized, the recognition module transmits the information to the node setting module after recognition.
Step two: if the voice recognition module can not recognize the information, the information is transmitted to the natural language processing module for recognition, and the recognition module transmits the information to the node setting module after recognition.
Step three: the robot can set the current conversation node through the node setting module, transmits the information into a database for matching, feeds the information back to the node setting module after matching is completed, and the node setting module transmits the information to the judging module.
Step four: the judging module judges whether information needs to be acquired or not, the information is transmitted to the data processor after the judgment is finished, and the data acquisition module starts to acquire the information after the data processor receives the data.
Step five: if the information can not be collected, the information is fed back to the output module through the feedback module to carry out the next round of conversation, or the information is fed back to the repeated setting module through the feedback module, the repeated times are set according to the repeated setting module, if the repeated times are reached, the data are transmitted to the output module, the client module acquires the information through the output module to carry out the next round of conversation, and if the repeated times are not reached, the data are transmitted to the judging module to repeat the step four.
Step six: if the information can be collected, after the data collection module finishes collecting, the information is transmitted to the data analysis module to analyze the information in the conversation, after the data analysis module finishes analyzing, the information is transmitted to the data extraction module, the data extraction module starts to extract the information in the conversation, and after the data extraction module finishes extracting, the data processor transmits the extracted information to the condition judgment module.
Step seven: meanwhile, the data processor transmits the extracted information to the data query module through the network communication module, the data query module queries remote data in real time through the remote data service module, if the relevant information cannot be queried, the information is fed back to the output module through the feedback module, and the client module acquires the information through the output module and carries out the next round of conversation or feeds the information back to the repeated setting module through the feedback module.
Step eight: and according to the repetition times set by the repetition setting module, if the repetition times are reached, transmitting the data to the output module, acquiring information by the client module through the output module, carrying out the next round of conversation, and if the repetition times are not reached, transmitting the data to the judging module and repeating the step four.
Step nine: if the relevant information is inquired, the data inquiry module transmits the inquired information to the condition judgment module, and the condition judgment module compares the information inquired by the data inquiry module with the information extracted by the data processor to judge whether the information is matched.
Step ten: after the condition judgment module judges that the information is finished, the information is transmitted to the language conversion module, after the language conversion module receives the information, the information is converted into voice or text according to user requirements and is transmitted to the output module, and the client module acquires the information through the output module and carries out the next round of conversation.
Advantageous effects
The invention provides a method for a robot to dynamically acquire information, which has the following beneficial effects: the method for the robot to dynamically acquire the information can dynamically acquire and utilize the information of the called user and feed the information back to the conversation, so that the conversation efficiency of the robot is improved, the timeliness and the safety of the information are guaranteed, the text translated by the identification module is analyzed and extracted by the data processor according to the specified mode, or the user information system is inquired at any moment to acquire the latest information.
In the conversation process, the robot analyzes and extracts the answer of the called party according to the designated model, extracts the information and stores the information in the conversation for subsequent use, and in the conversation process, the robot can dynamically inquire the called party information in a mode of dynamically inquiring a database, remote data service and the like so as to be used in the conversation process, so that the whole conversation is more intelligent and efficient, and the timeliness and the safety of the user information are guaranteed.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention:
FIG. 2 is a flow chart of FIG. 1 of the present invention.
In the figure: 1. a client module; 2. an input module; 3. an identification module; 4. a node setting module; 5. a database; 6. a judgment module; 7. a data processor; 8. a condition judgment module; 9. a network communication module; 10. a data query module; 11. a remote data service module; 12. a language conversion module; 13. an output module; 14. a feedback module; 15. a repeated setting module; 31. a voice recognition module; 32. a natural language processing module; 71. a data acquisition module; 72. a data analysis module; 73. and a data extraction module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a system for dynamically acquiring information by a robot comprises a client module 1, an input module 2, an identification module 3, a node setting module 4, a database 5, a judgment module 6, a data processor 7, a condition judgment module 8, a network communication module 9, a data query module 10, a remote data service module 11, a language conversion module 12, an output module 13, a feedback module 14 and a repeated setting module 15, wherein the client module 1 is connected with the input module 2, the input module 2 is used for inputting information, the input module 2 is connected with the identification module 3, the identification module 3 is used for identifying information content, the identification module 3 is connected with the node setting module 4, the node setting module 4 is connected with the database 5, the database 5 is used for storing calling data, the node setting module 4 is connected with the judgment module 6, the judgment module 6 judges whether information needs to be acquired or not, the judgment module 6 is connected with the data processor 7, the data processing is carried out, the data processor 7 is connected with the condition judging module 8, the condition judging module 8 carries out data comparison on information inquired by the data inquiring module 10 and information extracted by the data processor 7, whether the information is matched or not is judged, the data processor 7 is connected with the network communication module 9, the network communication module 9 is connected with the data inquiring module 10, the data inquiring module 10 is connected with the remote data service module 11, the data inquiring module 10 carries out real-time inquiry on remote data through the remote data service module 11, and the data inquiring module 10 is connected with the condition judging module 8.
The data processor 7 is connected with the feedback module 14, the data query module 10 is connected with the feedback module 14, the feedback module 14 is connected with the output module 13, the client module 1 acquires information through the output module 13 to carry out the next round of conversation, the feedback module 14 is connected with the repeated setting module 15, multiple rounds of operation are repeated through the set retry times, the repeated setting module 15 is connected with the judgment module 6, and the repeated setting module 15 is connected with the output module 13.
The recognition module 3 includes a speech recognition module 31 and a natural language processing module 32, and the speech recognition module 31 is connected to the natural language processing module 32 for information recognition.
The data processor 7 comprises a data acquisition module 71, a data analysis module 72 and a data extraction module 73, wherein the data acquisition module 71 is connected with the data analysis module 72 and used for analyzing information, and the data analysis module 72 is connected with the data extraction module 73 and used for extracting information data.
The condition judging module 8 is connected with the language converting module 12, the information is converted into voice or text according to the user requirement, the language converting module 12 is connected with the output module 13, and the output module 13 is connected with the client module 1.
A method for dynamically acquiring information by a robot comprises the following specific steps:
the method comprises the following steps: when the client module 1 initiates voice communication, information is input through the input module 2, the input module 2 transmits the information to the recognition module 3, the recognition module 3 recognizes the information through the voice recognition module 31, and if the information can be recognized, the recognition module 3 transmits the information to the node setting module 4 after recognition.
Step two: if the speech recognition module 31 cannot recognize the information, the information is transmitted to the natural language processing module 32 for recognition, and the recognition module 3 transmits the information to the node setting module 4 after recognition.
Step three: the robot can set the current conversation node through the node setting module 4, transmit information into the database 5 for matching, feed back the information to the node setting module 4 after matching is completed, and the node setting module 4 transmits the information to the judging module 6.
Step four: the judging module 6 judges whether information needs to be acquired or not, transmits the information to the data processor 7 after the judgment is finished, and the data acquisition module 71 starts to acquire the information after the data processor 7 receives the data.
Step five: if the information cannot be collected, the information is fed back to the output module 13 through the feedback module 14 to carry out the next round of conversation, or the information is fed back to the repeated setting module 15 through the feedback module 14, the repeated times are set according to the repeated setting module 15, if the repeated times are reached, the data is transmitted to the output module 13, the client module 1 acquires the information through the output module 13 to carry out the next round of conversation, and if the repeated times are not reached, the data is transmitted to the judging module 6 to repeat the step four.
Step six: if the information can be collected, after the data collection module 71 finishes collecting, the information is transmitted to the data analysis module 72 to analyze the information in the conversation, after the data analysis module 72 finishes analyzing, the information is transmitted to the data extraction module 73, the data extraction module 73 starts to extract the information in the conversation, and after the data extraction module 73 finishes extracting, the data processor 7 transmits the extracted information to the condition judgment module 8.
Step seven: meanwhile, the data processor 7 transmits the extracted information to the data query module 10 through the network communication module 9, the data query module 10 queries remote data in real time through the remote data service module 11, if the relevant information cannot be queried, the information is fed back to the output module 13 through the feedback module 14, and the client module 1 acquires the information through the output module 13 and performs the next round of conversation or feeds the information back to the repeated setting module 15 through the feedback module 14.
Step eight: and according to the repetition times set by the repetition setting module 15, if the repetition times are reached, transmitting the data to the output module 13, acquiring information by the client module 1 through the output module 13, carrying out the next round of conversation, and if the repetition times are not reached, transmitting the data to the judging module 6 and repeating the step four.
Step nine: if the relevant information is inquired, the data inquiry module 10 transmits the inquired information to the condition judgment module 8, and the condition judgment module 8 compares the information inquired by the data inquiry module 10 with the information extracted by the data processor 7 to judge whether the information is matched.
Step ten: after the condition judgment module 8 finishes the judgment, the information is transmitted to the language conversion module 12, after the language conversion module 12 receives the information, the information is converted into voice or text according to the user requirement and is transmitted to the output module 13, and the client module 1 acquires the information through the output module 13 to carry out the next round of conversation.
The invention has the beneficial effects that: the method for the robot to dynamically acquire the information can dynamically acquire and utilize the information of the called user and feed the information back to the conversation, so that the conversation efficiency of the robot is improved, the timeliness and the safety of the information are guaranteed, the text translated by the identification module 3 is analyzed and extracted by the data processor 7 according to the specified mode, or the user information system is inquired at any moment to acquire the latest information.
In the conversation process, the robot analyzes and extracts the answer of the called party according to the designated model, extracts the information and stores the information in the conversation for subsequent use, and in the conversation process, the robot can dynamically inquire the called party information in a mode of dynamically inquiring the database 5, the remote data service module 11 and the like so as to be used in the conversation process, so that the whole conversation is more intelligent and efficient, and the timeliness and the safety of the user information are guaranteed.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The utility model provides a system for robot developments obtain information, includes customer module (1), input module (2), identification module (3), node setting module (4), database (5), judge module (6), data processor (7), condition judge module (8), network communication module (9), data query module (10), remote data service module (11), language conversion module (12), output module (13), feedback module (14), repetition setting module (15), its characterized in that: input module (2) is connected in customer module (1), identification module (3) is connected in input module (2), identification module (3) connected node sets up module (4), the node sets up module (4) and connects database (5), judgment module (6) is connected in node setting module (4), data processor (7) is connected in judgment module (6), data processor (7) connection condition judgment module (8), network communication module (9) is connected in data processor (7), network communication module (9) is connected data query module (10), remote data service module (11) is connected in data query module (10), data query module (10) connection condition judgment module (8).
2. The system for robot to dynamically acquire information according to claim 1, wherein: feedback module (14) is connected in data processor (7), feedback module (14) is connected in data inquiry module (10), output module (13) is connected in feedback module (14), repeated setting module (15) is connected in feedback module (14), judge module (6) is connected in repeated setting module (15), output module (13) is connected in repeated setting module (15).
3. The system for robot to dynamically acquire information according to claim 1, wherein: the recognition module (3) comprises a voice recognition module (31) and a natural language processing module (32), and the voice recognition module (31) is connected with the natural language processing module (32).
4. The system for robot to dynamically acquire information according to claim 1, wherein: the data processor (7) comprises a data acquisition module (71), a data analysis module (72) and a data extraction module (73), wherein the data acquisition module (71) is connected with the data analysis module (72), and the data analysis module (72) is connected with the data extraction module (73).
5. The system for robot to dynamically acquire information according to claim 1, wherein: the condition judgment module (8) is connected with the language conversion module (12), the language conversion module (12) is connected with the output module (13), and the output module (13) is connected with the client module (1).
6. A method for dynamically acquiring information by a robot is characterized in that: the method comprises the following specific steps:
the method comprises the following steps: when the client module (1) initiates voice communication, information is input through the input module (2), the input module (2) transmits the information to the recognition module (3), the recognition module (3) recognizes the information through the voice recognition module (31), and if the information can be recognized, the recognition module (3) transmits the information to the node setting module (4).
Step two: if the speech recognition module (31) can not recognize the information, the information is transmitted to the natural language processing module (32) for recognition, and the recognition module (3) transmits the information to the node setting module (4) after recognition.
Step three: the robot can set the current conversation node through the node setting module (4), transmits information into the database (5) for matching, feeds the information back to the node setting module (4) after matching is completed, and the node setting module (4) transmits the information to the judging module (6).
Step four: the judging module (6) judges whether information needs to be acquired or not, after the judgment is finished, the information is transmitted to the data processor (7), and after the data processor (7) receives the data, the data acquisition module (71) starts to acquire the information.
Step five: if the information cannot be collected, the information is fed back to the output module (13) through the feedback module (14) to carry out the next round of conversation, or the information is fed back to the repeated setting module (15) through the feedback module (14), the repeated times are set according to the repeated setting module (15), if the repeated times are reached, the data are transmitted to the output module (13), the client module (1) acquires the information through the output module (13) to carry out the next round of conversation, and if the repeated times are not reached, the data are transmitted to the judging module (6) to repeat the step four.
Step six: if the information can be acquired, after the acquisition of the data acquisition module (71) is finished, the information is transmitted to the data analysis module (72) to analyze the information in the conversation, after the analysis of the data analysis module (72) is finished, the information is transmitted to the data extraction module (73), the data extraction module (73) starts to extract the information in the conversation, and after the extraction of the data extraction module (73) is finished, the data processor (7) transmits the extracted information to the condition judgment module (8).
Step seven: meanwhile, the data processor (7) transmits the extracted information to the data query module (10) through the network communication module (9), the data query module (10) queries remote data in real time through the remote data service module (11), if the relevant information cannot be queried, the information is fed back to the output module (13) through the feedback module (14), the client module (1) acquires the information through the output module (13) and carries out the next round of conversation, or the information is fed back to the repeated setting module (15) through the feedback module (14).
Step eight: and according to the repetition times set by the repetition setting module (15), if the repetition times are reached, transmitting the data to the output module (13), acquiring information by the client module (1) through the output module (13) to perform the next round of conversation, and if the repetition times are not reached, transmitting the data to the judging module (6) to repeat the step four.
Step nine: if the relevant information is inquired, the data inquiry module (10) transmits the inquired information to the condition judgment module (8), and the condition judgment module (8) compares the information inquired by the data inquiry module (10) with the information extracted by the data processor (7) to judge whether the information is matched.
Step ten: after the condition judgment module (8) finishes judgment, the information is transmitted to the language conversion module (12), after the language conversion module (12) receives the information, the information is converted into voice or text according to user requirements and transmitted to the output module (13), the client module (1) acquires the information through the output module (13) and carries out the next round of conversation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955647.2A CN110688473A (en) | 2019-10-09 | 2019-10-09 | Method for robot to dynamically acquire information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910955647.2A CN110688473A (en) | 2019-10-09 | 2019-10-09 | Method for robot to dynamically acquire information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110688473A true CN110688473A (en) | 2020-01-14 |
Family
ID=69111781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910955647.2A Pending CN110688473A (en) | 2019-10-09 | 2019-10-09 | Method for robot to dynamically acquire information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110688473A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967613A (en) * | 2020-08-24 | 2020-11-20 | 浙江百应科技有限公司 | NLP model training, issuing and identifying system |
| WO2021149079A1 (en) * | 2020-01-23 | 2021-07-29 | Rn Chidakashi Technologies Pvt Ltd | System for user initiated generic conversation with an artificially intelligent machine |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708863A (en) * | 2011-03-28 | 2012-10-03 | 德信互动科技（北京）有限公司 | Voice dialogue equipment, system and voice dialogue implementation method |
| CN202634483U (en) * | 2012-05-02 | 2012-12-26 | 杜晓君 | Network-connected robot capable of self-learning and self-growth |
| CN103760984A (en) * | 2014-01-24 | 2014-04-30 | 成都万先自动化科技有限责任公司 | Man-machine conversation system |
| US20180240008A1 (en) * | 2017-02-22 | 2018-08-23 | International Business Machines Corporation | Soft temporal matching in a synonym-sensitive framework for question answering |
| CN109325155A (en) * | 2018-07-25 | 2019-02-12 | 南京瓦尔基里网络科技有限公司 | A kind of novel dialogue state storage method and system |
| CN110111787A (en) * | 2019-04-30 | 2019-08-09 | 华为技术有限公司 | A kind of semanteme analytic method and server |
-
2019
- 2019-10-09 CN CN201910955647.2A patent/CN110688473A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708863A (en) * | 2011-03-28 | 2012-10-03 | 德信互动科技（北京）有限公司 | Voice dialogue equipment, system and voice dialogue implementation method |
| CN202634483U (en) * | 2012-05-02 | 2012-12-26 | 杜晓君 | Network-connected robot capable of self-learning and self-growth |
| CN103760984A (en) * | 2014-01-24 | 2014-04-30 | 成都万先自动化科技有限责任公司 | Man-machine conversation system |
| US20180240008A1 (en) * | 2017-02-22 | 2018-08-23 | International Business Machines Corporation | Soft temporal matching in a synonym-sensitive framework for question answering |
| CN109325155A (en) * | 2018-07-25 | 2019-02-12 | 南京瓦尔基里网络科技有限公司 | A kind of novel dialogue state storage method and system |
| CN110111787A (en) * | 2019-04-30 | 2019-08-09 | 华为技术有限公司 | A kind of semanteme analytic method and server |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021149079A1 (en) * | 2020-01-23 | 2021-07-29 | Rn Chidakashi Technologies Pvt Ltd | System for user initiated generic conversation with an artificially intelligent machine |
| CN111967613A (en) * | 2020-08-24 | 2020-11-20 | 浙江百应科技有限公司 | NLP model training, issuing and identifying system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110266899B (en) | Client intention identification method and customer service system | |
| CN110990544B (en) | Intelligent question-answering platform for legal consultation | |
| CN107862060A (en) | A kind of semantic recognition device for following the trail of target person and recognition methods | |
| CN106354835A (en) | Artificial dialogue auxiliary system based on context semantic understanding | |
| CN111192060A (en) | Electric power IT service-based full-channel self-service response implementation method | |
| CN100349206C (en) | Text-to-speech interchanging device | |
| CN105261356A (en) | Voice recognition system and method | |
| CN105895101A (en) | Speech processing equipment and processing method for power intelligent auxiliary service system | |
| US20170242847A1 (en) | Apparatus and method for translating a meeting speech | |
| CN107239538B (en) | Parallel customer service robot system with self-learning function and self-learning method thereof | |
| CN106649404B (en) | Method and device for creating session scene database | |
| CN110688473A (en) | Method for robot to dynamically acquire information | |
| CN109065052A (en) | A kind of speech robot people | |
| CN101674363A (en) | Mobile equipment and talking method | |
| CN109036416A (en) | simultaneous interpretation method and system, storage medium and electronic device | |
| CN112256854A (en) | Intelligent AI conversation method and device based on AI natural language understanding | |
| CN105160543A (en) | Marketing system of face identification telecommunication service and marketing method | |
| CN110570847A (en) | Man-machine interaction system and method for multi-person scene | |
| CN109325737A (en) | A kind of enterprise intelligent virtual assistant system and its method | |
| CN111405236A (en) | Video conference big data analysis method and system | |
| CN107180629B (en) | Voice acquisition and recognition method and system | |
| CN105656954A (en) | Intelligent community system based on Internet and robot | |
| CN111324719B (en) | Fuzzy recognition system for legal consultation | |
| CN110727772A (en) | Method for realizing dynamic interaction of robot through condition judgment | |
| CN107039041B (en) | Method and voice assistant for voice expansion |
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: 20200114 |