CN113190663A - Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment - Google Patents
Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment Download PDFInfo
- Publication number
- CN113190663A CN113190663A CN202110436377.1A CN202110436377A CN113190663A CN 113190663 A CN113190663 A CN 113190663A CN 202110436377 A CN202110436377 A CN 202110436377A CN 113190663 A CN113190663 A CN 113190663A
- Authority
- CN
- China
- Prior art keywords
- information
- thinking
- scene
- library
- entering
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000003993 interaction Effects 0.000 title claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 37
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 239000002131 composite material Substances 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 2
- 239000000178 monomer Substances 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000013277 forecasting method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000012850 discrimination method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The intelligent interaction method applied to the water conservancy scene comprises the following steps: s10: acquiring voice information; s20: entering a semantic parsing-information scene flow, which specifically comprises the following steps: s21: extracting key words in the voice information; s22: classifying the keywords and entering a corresponding information scene library; s30: entering an information scene-thinking scheme flow, which comprises the following specific steps: s31: analyzing the keywords entering the information scene library, entering a corresponding composite thinking scheme library according to the analysis result, and inquiring a matched single thinking scheme library in the composite thinking scheme library; s32: entering a corresponding single thinking scheme library, analyzing the single thinking scheme, and acquiring corresponding data according to a unit analyzed by a knowledge graph and a data network; s33: entering a corresponding thinking method library, acquiring a calculation method interface, and outputting a calculation result; s40: and entering a thinking scheme-information scene flow, returning the calculation result to the information scene, calling a corresponding thinking method, and outputting scene result information.
Description
Technical Field
The invention belongs to the field of intelligent interaction of water conservancy scenes, and particularly relates to an intelligent interaction method and device, a storage medium and computer equipment applied to a water conservancy scene.
Background
At present, the water conservancy scene intelligent platform is more and more extensive and intelligent in use, but the interactive mode of present water conservancy scene intelligent platform is still very traditional, like figure click interaction etc. lacks intelligent water conservancy scene voice interaction platform, and the interactive mode is rigid, is difficult to carry out semantic recognition.
Therefore, aiming at some problems existing in the prior art, the water conservancy scene interaction method is further researched and improved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent interaction method, an intelligent interaction device, a storage medium and computer equipment applied to a water conservancy scene, which are different from the traditional voice question-answer method: a question invokes a mode of an interface. According to the method, through the construction of a generalized information scene library, a composite thinking scheme library, a thinking method library and the like, a generalized water conservancy intelligent question-answering machine thinking flow is designed, the free combination of various water conservancy question-answering machines can be realized only by adding information scenes, and the intelligent capability of the machine for answering complex problems and professional problems is improved.
In order to solve the above technical problems, the present invention is solved by the following technical solutions.
The intelligent interaction method applied to the water conservancy scene comprises the following steps: s10: acquiring voice information; s20: entering a semantic parsing-information scene flow, which specifically comprises the following steps: s21: extracting key words in the voice information; s22: classifying the keywords and entering a corresponding information scene library; s30: entering an information scene-thinking scheme flow, which comprises the following specific steps: s31: analyzing the keywords entering the information scene library, entering a corresponding composite thinking scheme library according to the analysis result, and inquiring a matched single thinking scheme library in the composite thinking scheme library; s32: entering a corresponding single thinking scheme library, analyzing the single thinking scheme, and acquiring corresponding data according to a knowledge graph and a data network; s33: entering a corresponding thinking method library, acquiring a calculation method interface, and outputting a calculation result; s40: and entering a thinking scheme-information scene flow, returning the calculation result to the information scene, calling a corresponding thinking method, and outputting scene result information.
The intelligent interaction method is specially used for water conservancy scenes, and due to the fact that in water conservancy scene interaction, the directivity of information keywords in sentences is strong, simple and clear, the keywords in voice information are extracted and respectively matched into corresponding information scene libraries, then the thinking scheme libraries are searched and analyzed in the information scene libraries, and finally data are output. The system can realize free combination of various water conservancy questions and answers, and can remarkably improve the intelligent capability of the machine for answering complex questions and professional questions.
Preferably, in step S10, the voice information is a direct or indirect human voice.
Preferably, in step S20, the keywords in the speech information include: a time attribute keyword, an object attribute keyword, an event attribute keyword, a place attribute keyword. The time attribute key may be a specific date, a future time period, etc. The object attribute keywords can be specific reservoir names, river channel names, lake names and the like. The event attribute keywords can be rainfall, water level, reservoir flood-holding, risk early warning and the like. The location attribute keyword may be a specific location name.
Preferably, in step S20, the information scene library includes a future risk early warning scene of the reservoir; in step S30, the compound thinking plan library includes reservoir risk early warning analysis, and the single thinking plan library includes forecast rainfall analysis and reservoir rainfall analysis.
Preferably, in step S30, the acquired data includes: forecasting one or more of rainfall, flood control high water level, water collection area, runoff coefficient, actual measurement water level, real-time water level and real-time storage capacity.
Preferably, in step S30, the data acquisition means includes: knowledge graphs, data networks; the knowledge graph comprises an entity relation table (such as the connection relation of a reservoir and a rainfall forecasting mechanism) and an entity attribute table (such as information of ID, reservoir name, characteristic parameters and the like); the data network includes a big data warehouse (e.g., an information retrieval library including reservoir basic information, real-time water and rain conditions, a storage capacity curve, etc.).
Preferably, in step S30, the thinking plan library includes a forecast rainfall calculation method, a reservoir rainfall tolerance calculation method, a reservoir risk discrimination method, and the like.
The intelligent interaction device applied to the water conservancy scene comprises an input module, a processing module and an output module; the input module is a voice input device and is used for acquiring voice information; the processing module is used for executing the intelligent interaction method; the output module is a screen and/or a loudspeaker and is used for outputting image information and/or sound information.
A readable storage medium having executable instructions thereon that, when executed, cause a computer to perform the intelligent interaction method of the present application.
A computer device comprising one or more processors, memory, and one or more programs, wherein: the one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the intelligent interaction method of the present application.
Compared with the prior art, the invention has the following beneficial effects: the intelligent interaction method, the intelligent interaction device, the storage medium and the computer equipment applied to the water conservancy scene are provided, the universal water conservancy intelligent question-answering machine thinking flow is designed through the construction of a universal information scene library, a composite thinking scheme library, a thinking method library and the like, the free combination of various water conservancy question-answering machines can be realized only through increasing the information scene, and the intelligent capability of the machine for answering complex questions and professional questions is improved.
Drawings
Fig. 1 is a flowchart of intelligent interaction in an embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
The application provides an intelligent interaction method applied to a water conservancy scene, which comprises the following steps: s10: acquiring voice information; s20: entering a semantic parsing-information scene flow, which specifically comprises the following steps: s21: extracting key words in the voice information; s22: classifying the keywords and entering a corresponding information scene library; s30: entering an information scene-thinking scheme flow, which comprises the following specific steps: s31: analyzing the keywords entering the information scene library, entering a corresponding composite thinking scheme library according to the analysis result, and inquiring a matched single thinking scheme library in the composite thinking scheme library; s32: entering a corresponding single thinking scheme library, analyzing the single thinking scheme, and acquiring corresponding data according to a unit analyzed by a knowledge graph and a data network; s33: entering a corresponding thinking method library, acquiring a calculation method interface, and outputting a calculation result; s40: and the output data enters a thinking scheme-information scene flow, the calculation result is returned to the information scene, the corresponding thinking method is called, and the scene result information is output.
Specifically, in the present application, in step S10, the voice information is a direct or indirect voice. In step S20, the keywords in the speech information include: one or more of a time attribute keyword, an object attribute keyword, an event attribute keyword, a location attribute keyword. In the step S20, the information scene library comprises a future risk early warning scene of the reservoir; in step S30, the compound thinking plan library includes reservoir risk early warning analysis, and the single thinking plan library includes forecast rainfall analysis and reservoir rainfall analysis. In step S30, the acquired data includes: forecasting one or more of rainfall, flood control high water level, water collection area, runoff coefficient, real-time water level and real-time storage capacity. In step S30, the data acquisition path includes: knowledge graphs, data networks; the knowledge graph comprises an entity relation table and an entity attribute table; the data network includes a big data warehouse. In step S30, the thinking plan library includes a forecast rainfall calculation method, a reservoir rainfall bearable calculation method, a reservoir risk discrimination method, and the like. In addition, the application also relates to an intelligent interaction device applied to the water conservancy scene, and the device comprises an input module, a processing module and an output module; the input module is a voice input device and is used for acquiring voice information; the processing module is used for executing the intelligent interaction method; the output module is a screen and/or a loudspeaker and is used for outputting image information and/or sound information.
The present application also relates to a readable storage medium having executable instructions thereon that, when executed, cause a computer to perform the intelligent interaction method of the present application.
The present application also relates to a computer device comprising one or more processors, memory, and one or more programs, wherein: the one or more programs are stored in the memory and configured to be executed by the one or more processors to perform the intelligent interaction method of the present application.
The following is a specific example of the present application.
Voice information: XX risk status of reservoir in the future 12 hours.
The voice information can be a voice directly spoken by a user or a sound made by software through a loudspeaker.
The operational flow is analyzed as follows.
Enter into the flow of' semantic analysis-information scene
Step 1: semantic parsing, time: for 12 hours in the future, subjects were analyzed: XX reservoir, analysis events: a risk status; time-to-data time constraints: current time +12 hours
Step 2: and scene identification, entering an information scene library, and identifying the information scene as a future risk early warning scene of the reservoir according to keywords of future, reservoir and risk state.
Step 3: the scheme corresponds to that the corresponding thinking scheme in the 'future reservoir risk early warning scene' is 'reservoir risk early warning analysis'.
Enter into the process of' information scene-thinking scheme
Step 4: the scheme analysis and the reservoir risk early warning analysis are combined schemes, the combined scheme enters a rechecking thinking scheme library, and related monomer schemes are inquired to be rainfall forecast analysis and reservoir rainfall bearable analysis.
Step 5: running a monomer scheme, "forecast rainfall analysis" and "analysis of rainfall capacity bearable of reservoir".
(1) Rainfall forecast analysis monomer scheme flow (need to be associated with other entities):
step 01: entering a monomer thinking scheme library, and analyzing a rainfall forecast monomer scheme:
analysis of the object: XX reservoir, data time constraint: current time +12h, query data: forecasting rainfall, and associating the relationship: surface rainfall forecast, associated entity: forecasting mechanism, thinking method: the rainfall forecasting method comprises the following steps: rainfall, network number (e.g., SJWL0008), query constraints: reservoir number, hours, forecasting mechanism, look-up table name (e.g., R _ fortast).
Step 02: acquiring input data of a rainfall forecasting method (acquiring the input data by entering a data network through a knowledge graph);
entering a knowledge graph library: inquiring a relation table of 'surface rainfall forecast' and searching a forecasting mechanism for surface rainfall forecast of the XX reservoir;
entering a data network: matching the query data and the field names corresponding to the query constraint conditions according to the data network dictionary table;
entering a database table: the corresponding field (e.g., porcastR) is queried from the table (e.g., R _ fork) according to query constraints (e.g., id, hour, obj).
Step 03: the operation calculation of the rainfall forecasting method comprises the following steps:
entering a thinking method library, and acquiring an interface address, an input field, a request mode and the like corresponding to the forecast rainfall analysis.
Inputting the data obtained by query, forecasting rainfall (such as porcastR) for calculation, and outputting the rainfall of the XX reservoir in the future 12 hours.
(2) And the rainfall bearable analysis monomer scheme flow (no other entity needs to be associated):
step 01: entering a monomer thinking scheme library, and analyzing the rainfall bearable monomer scheme of the reservoir:
analysis of the object: XX reservoir, data time constraint: current time +12h, query data: flood control high water level, water collection area, runoff coefficient; actually measuring the water level; water level, reservoir capacity, association relation: none, associated entity: none, thinking method: a rainfall bearable analysis method for a reservoir. Outputting data: the rainfall network number can be borne (such as SJWL 0001; SJWL 0002; SJWL0003), and the query constraint conditions are as follows: numbering the reservoirs; reservoir number, current time; reservoir number, look-up table name (e.g. I _ Res; ST _ RSVR _ R; HT _ ZVARL _ B)
Step 02: acquiring input data of a reservoir rainfall bearable analysis method (acquiring the input data by entering a data network through a knowledge graph);
entering a data network: matching field names of data to be inquired according to the data network dictionary table;
and acquiring the address, the user name, the password and the database of the server where the data is located.
Entering a database table: according to query constraints (e.g., resID); looking up the corresponding fields (e.g., resFHz, ctrS) from the table (e.g., I _ Res); according to query constraints (e.g., stcd, tm); querying a corresponding field (e.g., rz) from a table (e.g., ST _ RSVR _ R); according to query constraints (e.g., STCD); the corresponding field (e.g., RZ, W) is looked up from the table (e.g., HT _ ZVARL _ B).
Step 03: the operation calculation of the reservoir rainfall bearable analysis method comprises the following steps:
firstly, entering a thinking method library to obtain a corresponding interface address, an input field, a request mode and the like corresponding to the rainfall analysis bearable of the reservoir,
② inputting the inquired data to prevent flood high water level (such as resFHz), water collecting area (such as ctrS), runoff coefficient (such as ctrS), real-time water level (such as RZ), water level storage capacity curve (such as RZ, W)
And thirdly, calculating and outputting 'rainfall capacity bearable' of the XX reservoir.
Enter into the process of thinking scheme-information scene
Step 6: entering an information scene library, wherein the query information scene is a 'future risk early warning scene of the reservoir', the corresponding information discrimination interface is a 'reservoir risk discrimination interface', and the data needing to be input into the interface is the rainfall bearable and the rainfall capacity of the reservoir
Step 7: entering a thinking method library, inquiring interface addresses, input fields, request modes and the like according to the future risk early warning scene of the reservoir
Step 8: and (3) information discrimination: calling a 'reservoir risk judgment interface' to judge information; inputting the rainfall (such as AffRain) of the data reservoir, the rainfall (such as PreRain), and outputting the data: XX reservoir "risk classification" 12 hours into the future.
The scene analysis table corresponding to the above embodiment is as follows.
(1) Information scene library
(2) Composite thinking scheme library
(3) Single body thinking scheme library
(4) Knowledge map library
(5) Data network table
(6) Thinking method library
| Thinking method | Computing interface addresses | Input field | Name of method | Request mode |
| Analysis method for rainfall bearable of reservoir | ||||
| Rainfall forecasting method | ||||
| Reservoir risk discrimination interface |
In the attached drawings, fig. 1 shows an intelligent interaction flow chart, and as can be seen from fig. 1, in the method in the application, all modules and steps are connected smoothly, through the construction of a generalized information scene library, a composite thinking scheme library, a thinking method library and the like, a generalized water conservancy intelligent question-answering machine thinking flow is designed, and the free combination of various water conservancy question-answering machines can be realized only by adding information scenes, so that the intelligent capability of the machine for answering complex questions and professional questions is improved.
As described above, the intelligent interaction method in the present application has the advantages that: different from the traditional voice question answering, a question calls an interface mode, a generalized information scene library, a thought scheme library, a thought method library and the like are constructed, a generalized water conservancy intelligent question answering machine thought flow is designed, free combination of various water conservancy question answering can be realized only by increasing information scenes, and the intelligent capability of the machine for answering complex questions and professional questions is improved. The method comprises the following specific steps:
1. water conservancy intelligence question-answering information scene construction and identification
The water conservancy intelligent question and answer information scene is used for concrete analysis of 'what' to ask, key information of water conservancy business scenes such as scene names, analysis objects, analysis events, information discrimination mechanisms, output information and the like is stored in a database table form, and different information scenes are classified around water conservancy management business to form an information scene library. And the method is used for carrying out scene recognition on the keywords analyzed by the semantics and associating a thinking scheme corresponding to the problem.
2. Water conservancy intelligent question-answering thinking scheme flow design
The water conservancy intelligent question-answer thinking scheme is used for concrete analysis of how to answer, key information of the water conservancy thinking scheme such as entity association, association relation and thinking method is stored in a database table form, the association entity is inquired through a knowledge graph library, input data is obtained through a data network, a calculation method calling mode is obtained through a thinking method library, and finally the output of a result is realized by using a circulation process of finding an object, searching data and adjusting a method.
3. Water conservancy intelligent question-answering composite thinking flow design
Aiming at the relatively complex water conservancy question and answer needing step-by-step calculation, a minimum calculation unit is constructed to serve as a single thinking scheme, a composite thinking scheme is designed to store information such as analysis flow, output data and the like of the single thinking scheme, different composite thinking schemes can call the same single thinking scheme so as to avoid repeatedly constructing the same calculation interface, and step-by-step calculation and result output are rapidly realized.
The scope of the present invention includes, but is not limited to, the above embodiments, and the present invention is defined by the appended claims, and any alterations, modifications, and improvements that may occur to those skilled in the art are all within the scope of the present invention.
Claims (10)
1. The intelligent interaction method applied to the water conservancy scene is characterized by comprising the following steps of:
s10: acquiring voice information;
s20: entering a semantic parsing-information scene flow, which specifically comprises the following steps:
s21: extracting key words in the voice information;
s22: classifying the keywords and entering a corresponding information scene library;
s30: entering an information scene-thinking scheme flow, which comprises the following specific steps:
s31: analyzing the keywords entering the information scene library, entering a corresponding composite thinking scheme library according to the analysis result, and inquiring a matched single thinking scheme library in the composite thinking scheme library;
s32: entering a corresponding single thinking scheme library, analyzing the single thinking scheme, and acquiring corresponding data according to a knowledge graph and a data network;
s33: entering a corresponding thinking method library, acquiring a calculation method interface, and outputting a calculation result;
s40: and entering a thinking scheme-information scene flow, returning the calculation result to the information scene, calling a corresponding thinking method, and outputting scene result information.
2. The intelligent interaction method applied to water conservancy scenes as claimed in claim 1, wherein in the step S10, the voice information is direct or indirect human voice.
3. The intelligent interaction method applied to water conservancy scenes as claimed in claim 1, wherein in step S20, the keywords in the voice message include: a time attribute keyword, an object attribute keyword, an event attribute keyword, a place attribute keyword.
4. The intelligent interaction method applied to water conservancy scenes as claimed in claim 1, wherein in the step S20, the information scene library comprises a future risk early warning scene of the reservoir; in step S30, the compound thinking plan library includes reservoir risk early warning analysis, and the single thinking plan library includes forecast rainfall analysis and reservoir rainfall analysis.
5. The intelligent interaction method applied to water conservancy scenes as claimed in claim 4, wherein in the step S30, the acquired data comprises: forecasting one or more of rainfall, flood control high water level, water collection area, runoff coefficient, actual measurement water level, real-time water level and real-time storage capacity.
6. The intelligent interaction method applied to water conservancy scenes as claimed in claim 4, wherein in the step S30, the data acquisition path comprises: knowledge graphs, data networks;
the knowledge graph comprises an entity relation table and an entity attribute table;
the data network includes a big data warehouse.
7. The intelligent interaction method applied to water conservancy scenes as claimed in claim 4, wherein in the step S30, the thinking scheme library comprises a forecast rainfall calculation method, a reservoir rainfall tolerance calculation method and a reservoir risk judgment method.
8. The intelligent interaction device applied to the water conservancy scene is characterized by comprising an input module, a processing module and an output module;
the input module is a voice input device and is used for acquiring voice information;
the processing module is used for executing the intelligent interaction method in any one of claims 1 to 7;
the output module is a screen and/or a loudspeaker and is used for outputting image information and/or sound information.
9. A readable storage medium having executable instructions thereon, which when executed, cause a computer to perform the intelligent interaction method of any one of claims 1 to 7.
10. A computer device comprising one or more processors, memory, and one or more programs, wherein: the one or more programs stored in the memory and configured to be executed by the one or more processors to perform the intelligent interaction method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436377.1A CN113190663A (en) | 2021-04-22 | 2021-04-22 | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110436377.1A CN113190663A (en) | 2021-04-22 | 2021-04-22 | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113190663A true CN113190663A (en) | 2021-07-30 |
Family
ID=76978349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110436377.1A Pending CN113190663A (en) | 2021-04-22 | 2021-04-22 | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113190663A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117235219A (en) * | 2023-09-15 | 2023-12-15 | 宁波市水利水电规划设计研究院有限公司 | Reservoir knowledge intelligent question-answering system based on flood prevention demands |
| CN117389659A (en) * | 2023-09-06 | 2024-01-12 | 苏州数设科技有限公司 | Method library management method and device for industrial software |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961780A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | A kind of man-machine interaction method, device, server and storage medium |
| CN110211577A (en) * | 2019-07-19 | 2019-09-06 | 宁波方太厨具有限公司 | Terminal device and its voice interactive method |
| CN110955764A (en) * | 2019-11-19 | 2020-04-03 | 百度在线网络技术（北京）有限公司 | Scene knowledge graph generation method, man-machine conversation method and related equipment |
| CN111008532A (en) * | 2019-12-12 | 2020-04-14 | 广州小鹏汽车科技有限公司 | Voice interaction method, vehicle and computer-readable storage medium |
| CN111625658A (en) * | 2020-07-28 | 2020-09-04 | 杭州翔毅科技有限公司 | Voice interaction method, device and equipment based on knowledge graph and storage medium |
-
2021
- 2021-04-22 CN CN202110436377.1A patent/CN113190663A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961780A (en) * | 2017-12-22 | 2019-07-02 | 深圳市优必选科技有限公司 | A kind of man-machine interaction method, device, server and storage medium |
| CN110211577A (en) * | 2019-07-19 | 2019-09-06 | 宁波方太厨具有限公司 | Terminal device and its voice interactive method |
| CN110955764A (en) * | 2019-11-19 | 2020-04-03 | 百度在线网络技术（北京）有限公司 | Scene knowledge graph generation method, man-machine conversation method and related equipment |
| CN111008532A (en) * | 2019-12-12 | 2020-04-14 | 广州小鹏汽车科技有限公司 | Voice interaction method, vehicle and computer-readable storage medium |
| CN111625658A (en) * | 2020-07-28 | 2020-09-04 | 杭州翔毅科技有限公司 | Voice interaction method, device and equipment based on knowledge graph and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117389659A (en) * | 2023-09-06 | 2024-01-12 | 苏州数设科技有限公司 | Method library management method and device for industrial software |
| CN117235219A (en) * | 2023-09-15 | 2023-12-15 | 宁波市水利水电规划设计研究院有限公司 | Reservoir knowledge intelligent question-answering system based on flood prevention demands |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110362660B (en) | Electronic product quality automatic detection method based on knowledge graph | |
| CN108345690B (en) | Intelligent question and answer method and system | |
| CN107341215B (en) | Multi-source vertical knowledge graph classification integration query system based on distributed computing platform | |
| WO2019200752A1 (en) | Semantic understanding-based point of interest query method, device and computing apparatus | |
| CN110222045B (en) | Data report acquisition method and device, computer equipment and storage medium | |
| CN111859969B (en) | Data analysis method and device, electronic equipment and storage medium | |
| CN111291161A (en) | Legal case knowledge graph query method, device, equipment and storage medium | |
| CN111651447B (en) | Intelligent construction life-span data processing, analyzing and controlling system | |
| CN109522312A (en) | A kind of data processing method, device, server and storage medium | |
| CN113190663A (en) | Intelligent interaction method and device applied to water conservancy scene, storage medium and computer equipment | |
| CN111552813A (en) | Power knowledge graph construction method based on power grid full-service data | |
| CN113641833B (en) | Service demand matching method and device | |
| CN117370493A (en) | Intelligent interaction method and device for system based on large language model | |
| CN109739992A (en) | A kind of method and terminal obtaining related information | |
| US10866944B2 (en) | Reconciled data storage system | |
| CN114328681A (en) | Data conversion method and device, electronic equipment and storage medium | |
| CN113610626A (en) | Bank credit risk identification knowledge graph construction method and device, computer equipment and computer readable storage medium | |
| CN115952770B (en) | Data standardization processing method and device, electronic equipment and storage medium | |
| CN117217933A (en) | Data multidimensional analysis method and device for insurance industry | |
| CN117112767A (en) | Question and answer result generation method, commercial query big model training method and device | |
| CN115438995B (en) | Business processing method and equipment for clothing customization enterprise based on knowledge graph | |
| CN106055702B (en) | Internet-oriented data service unified description method | |
| CN109829048A (en) | Electronic device, interview householder method and computer readable storage medium | |
| CN112416754B (en) | Model evaluation method, terminal, system and storage medium | |
| KR20190052980A (en) | Device and method of processing recruitment information |
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 |
Application publication date: 20210730 |
|
| RJ01 | Rejection of invention patent application after publication |