CN110472113B - Intelligent interaction engine optimization method, device and equipment - Google Patents
Intelligent interaction engine optimization method, device and equipment Download PDFInfo
- Publication number
- CN110472113B CN110472113B CN201910706655.3A CN201910706655A CN110472113B CN 110472113 B CN110472113 B CN 110472113B CN 201910706655 A CN201910706655 A CN 201910706655A CN 110472113 B CN110472113 B CN 110472113B
- Authority
- CN
- China
- Prior art keywords
- interaction
- interaction engine
- module
- engine
- slot position
- 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.)
- Active
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 229
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 title claims description 20
- 238000012545 processing Methods 0.000 claims abstract description 14
- 230000002452 interceptive effect Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 101001049829 Homo sapiens Potassium channel subfamily K member 5 Proteins 0.000 description 3
- 102100023202 Potassium channel subfamily K member 5 Human genes 0.000 description 3
- 101001049835 Homo sapiens Potassium channel subfamily K member 3 Proteins 0.000 description 2
- 102100023207 Potassium channel subfamily K member 3 Human genes 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- COCAUCFPFHUGAA-MGNBDDOMSA-N n-[3-[(1s,7s)-5-amino-4-thia-6-azabicyclo[5.1.0]oct-5-en-7-yl]-4-fluorophenyl]-5-chloropyridine-2-carboxamide Chemical compound C=1C=C(F)C([C@@]23N=C(SCC[C@@H]2C3)N)=CC=1NC(=O)C1=CC=C(Cl)C=N1 COCAUCFPFHUGAA-MGNBDDOMSA-N 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Robotics (AREA)
- Information Transfer Between Computers (AREA)
- Machine Translation (AREA)
Abstract
The embodiment of the invention discloses an intelligent interaction platform training method which is characterized by comprising the following steps: acquiring a first interaction engine shared by a third party; extracting a first element in the first interaction engine and first data information associated with the first element; acquiring a second element matched with the first element in a second interaction engine; and filling the first data information into a second element in a second interaction engine. The implementation of the embodiment of the invention can effectively optimize the interaction engine in the intelligent interaction platform, establish more optimized intelligent interaction control, improve the task processing capacity of the intelligent interaction platform, improve the user experience and obtain beneficial effects.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to an intelligent interaction engine optimization method, device and equipment and a computer readable storage medium.
Background
With the development and popularization of computer technology, intelligent technologies such as human-computer interaction provide convenient and fast services in various aspects of people's life. Human-Computer Interaction (HCI) technology refers to a technology for realizing Human-Computer Interaction in an efficient manner through Computer input and output devices. The man-machine interaction technology comprises the steps that a machine provides a large amount of relevant information and prompt requests for people through an output or display device, and a person inputs the relevant information into the machine through an input device, answers questions and prompts and the like. The current human-computer interaction mode based on the rapid development of artificial intelligence is continuously developed.
The current man-machine interaction service is usually an interaction engine of an intelligent interaction platform created by a developer, and the function is relatively limited. How to effectively optimize an interaction engine in an intelligent interaction platform, establish more optimized intelligent interaction control, improve the task processing capacity of the intelligent interaction platform and improve the user experience is a problem which needs to be solved urgently at present.
Disclosure of Invention
The embodiment of the invention provides a scene-based input method, a scene-based input device, a scene-based input equipment and a computer-readable storage medium, which can be used for solving the problems in the related art.
In one aspect, an embodiment of the present invention provides an intelligent interaction engine optimization method, where the method includes:
103, acquiring a second element matched with the first element in a second interaction engine;
and 104, filling the first data information into a second element in a second interaction engine.
Preferably, the first and second electrodes are formed of a metal,
the first element comprises a first slot position;
the second element comprises a second slot position;
the first data information associated with the first element comprises first key knowledge data associated with a first slot;
the first interaction engine and the second interaction engine have the same task attributes. .
Preferably, the step 101 further comprises
Acquiring one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform;
or alternatively
And one or more interaction engines shared in the network platform are captured through network searching.
Preferably, the step 103 further comprises
Judging whether a slot position matched with the first slot position exists in a second interaction engine; and if not, creating a second slot position matched with the first slot position.
Preferably, the step 104 further comprises
The second slot position is provided with a plurality of candidate positions;
and filling the candidate bits according to the priority level of the first key knowledge data.
Preferably, the download amount and/or the recommendation value of the first interaction engine are obtained, and the priority level of the first key knowledge data associated with the first slot in the first interaction engine is determined according to the download amount and/or the recommendation value.
Preferably, the plurality of key knowledge data filled in the second slot are screened, and the error data are deleted.
Preferably, the method further comprises step 105
Judging whether a third slot position which is not filled exists in the second interaction engine;
and if so, feeding back slot data missing information to the third party.
On the other hand, an embodiment of the present invention provides an intelligent interaction engine optimization apparatus, where the apparatus includes:
the interaction engine acquisition module is used for acquiring a first interaction engine shared by a third party;
the extraction module is used for extracting a first element in the first interaction engine and first data information associated with the first element;
the matching module is used for acquiring a second element matched with the first element in a second interaction engine;
and the filling module is used for filling the first data information into a second element in the second interaction engine.
Preferably, the first element comprises a first slot;
the second element comprises a second slot position;
the first data information associated with the first element comprises first key knowledge data associated with a first slot;
the first interaction engine and the second interaction engine have the same task attributes.
Preferably, the interaction engine acquisition module is further used for
Acquiring one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform;
or
And one or more interaction engines shared in the network platform are captured through network searching.
Preferably, the apparatus further creates a module;
the matching module is further used for judging whether a slot position matched with the first slot position exists in a second interaction engine; and if not, the creating module creates a second slot position matched with the first slot position.
Preferably, the second slot has a plurality of candidate bits;
the filling module is further configured to fill the first key knowledge data into the plurality of candidate bits according to the priority of the first key knowledge data.
Preferably, the apparatus further comprises a priority determination module
The priority determining module is used for acquiring the download quantity and/or the recommendation value of the first interaction engine, and determining the priority level of the first key knowledge data associated with the first slot position in the first interaction engine according to the download quantity and/or the recommendation value.
Preferably, the apparatus further includes a screening module configured to screen the plurality of key knowledge data filled in the second slot to delete the error data.
Preferably, the apparatus further comprises a feedback module
The matching module is further used for judging whether a third slot position which is not filled exists in the second interaction engine;
and if so, the feedback module feeds back the slot missing information to the third party.
On the other hand, the embodiment of the invention provides terminal equipment comprising the intelligent interaction engine optimization device.
In another aspect, an embodiment of the present invention provides a computer device, which includes a processor and a memory, where the memory stores a computer program that is executable on the processor, and the computer program implements the foregoing method when executed by the processor.
In another aspect, the present invention provides a computer-readable storage medium, in which a computer program that can be run on a processor is stored, and when being executed, the computer program implements the foregoing method.
The implementation of the embodiment of the invention can effectively optimize the existing interaction engine of the intelligent interaction platform, establish more optimized intelligent interaction control, improve the processing capacity of the intelligent interaction platform, improve the user experience and obtain beneficial effects.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of an intelligent interaction platform provided in an embodiment of the present specification.
Fig. 2 is a schematic flowchart of an intelligent interaction engine optimization method provided in an embodiment of the present specification.
Fig. 3 is a structure of an intelligent interaction engine optimization device provided in an embodiment of the present specification.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The embodiments and specific features of the embodiments of the present invention are detailed descriptions of technical solutions of the embodiments of the present invention, and are not limited to technical solutions of the present invention, and the technical features of the embodiments and the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic diagram of an intelligent interaction platform of the present invention, which mainly includes: a human-computer interaction interface 101, a processing module 102, a database 103 and the like. Wherein the processing module comprises a plurality of interaction engines 112, the interaction engines 112 may comprise a semantic understanding module 201, a dialog management and control module 202, a dialog generation module 203, a command execution module 204. The processing module 102 is connected to the human-computer interface 101, and can receive data input by a user through the human-computer interface 101 and output interactive data to the user through the human-computer interface, that is, on one hand, the human-computer interface 101 can receive dialogue data fed back to the user through the processing module 102 and on the other hand, can receive command execution process and result data fed back by the processing module 102. For the intelligent voice interaction platform, the processing module 102 may further include: a voice recognition module 210 and a voice output module 211. The speech recognition module 210 and the speech output module 211 may also be configured in the interaction engine 112. Further, the interaction engine 112 may be a single interaction engine or may be comprised of one or more interaction sub-engines.
One key point of the optimization of the interaction engine in the intelligent interaction platform is to improve the processing capacity of the interaction engine, enhance the understanding of the interaction engine on semantics, improve the efficiency of dialogue interaction and improve the task execution accuracy; these all need to understand the user's intention accurately, and through slot position and slot position analysis in the enrichment interaction engine, improve the control and management of interaction engine to the interaction.
Example one
Referring to fig. 2, fig. 2 is a flowchart illustrating an intelligent interaction engine optimization method according to an embodiment of the present invention, where the method includes, but is not limited to:
103, acquiring a second element matched with the first element in a second interaction engine;
and 104, filling the first data information into a second element in a second interaction engine.
Specifically, the first element comprises a first slot position;
the second element comprises a second slot position;
the first data information associated with the first element comprises first key knowledge data associated with a first slot;
the first interaction engine and the second interaction engine have the same task attributes.
The intelligent interaction platform can open an interface to a user, so that the user can create own tasks through the open interface, and an interaction engine based on the tasks is generated by packaging the tasks created and completed by the user. And simultaneously, the user can also directly upload the packaged interaction engine which accords with the platform format by using the interface which is opened to the user.
Specifically, the step 101 further includes acquiring one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform; for example, a plurality of users upload an interaction engine1, an interaction engine2, … … and an interaction engine n based on the same task on the intelligent interaction platform. In step 101, based on the task attribute of the interaction engine to be optimized, an interaction engine shared by a third party and conforming to the same task can be first found on the intelligent interaction platform, so that the interaction engine initially developed in the intelligent interaction platform and based on the task can be subsequently optimized by using the interaction engines.
Or the first interaction engine for obtaining the third-party share in step 101 may further obtain one or more interaction engines shared in the network platform through network search and crawling. For example, in some public resource sharing platforms, there are interaction engines where users voluntarily share and provide communication downloads; the interaction engines can be captured by utilizing network search, and the interaction engines based on the task initially developed in the intelligent interaction platform can be optimized by utilizing the interaction engines subsequently.
Specifically, the step 103 further includes determining whether a slot matching the first slot exists in a second interaction engine; and if not, creating a second slot position matched with the first slot position. Because all necessary slot positions cannot be exhausted during initial design, at the moment, the aim of learning can be fulfilled by extracting the information of the relevant slot positions in the interaction engine shared by a plurality of third parties, and the slot positions lacking by the interaction engine are optimized and updated so as to further perfect the design of the interaction engine.
Specifically, the step 104 further includes that the second slot has a plurality of candidate bits; and filling the candidate bits according to the priority level of the first key knowledge data.
As in the previous example, a plurality of users 1,2, … …, n all upload the interaction engine1, the interaction engine2, … …, and the interaction engine n based on the same task on the intelligent interaction platform. When the user intelligent interaction platform shares, a related interaction engine information list can be created, and the following table shows that:
| user ID | Interaction engine identification | Attribute | Download volume | Recommended value |
| UE1 | ENGINE1 | TASK1 | 79 | 8.1 |
| UE2 | ENGINE2 | TASK1 | 67 | 6.7 |
| UE3 | ENGINE3 | TASK2 | 116 | 9.2 |
| …… | …… | …… | ||
| UEn | ENGINEn | TASKm | 94 | 8.9 |
Wherein m is 1,2,3 … based on the same task attribute TASKm; there may be multiple interaction ENGINEs uploaded by multiple users, such as UE1, UE2, UE4, such as ENGINE1, ENGINE2, ENGINE 4; extracting key knowledge data corresponding to slot positions and slot positions in the ENGINE1, ENGINE2 and ENGINE 4 through a step 102; the key knowledge data filled in the same slot position in the interaction engine shared by a plurality of users and associated with the slot position can be different. Thus, a slot may be set to have multiple candidate bits to which multiple key knowledge data is populated. For the user of the interaction engine, diversified selections can be provided for the user through the key knowledge data of a plurality of candidate positions in the slot position. For multiple possible choices, in order to better provide the user experience, the priority ranking of the multiple pieces of key knowledge data may be performed, and the 1 st to nth candidate bits are sequentially filled according to the priority ranking from high to low, specifically, for example, the key knowledge data with the highest priority ranking is filled into the first candidate bit.
Specifically, the downloading amount and/or the recommended value of the first interaction engine are obtained, and the priority level of the first key knowledge data associated with the first slot in the first interaction engine is determined according to the downloading amount and/or the recommended value. For example, the download amount and recommendation value of each interactive ENGINE are counted through the interactive ENGINE information list, the priority level of the key knowledge data extracted from the interactive ENGINE is set by how much the download amount is, or the priority level of the key knowledge data extracted from the interactive ENGINE is set by the level of the evaluation value, or the value weight of the interactive ENGINE is calculated by combining the download amount and the recommendation value, and the priority level of the key knowledge data extracted from the interactive ENGINE is set by the level of the value weight, for example, for the same TASK attribute TASK2, it is known that the value weight of the ENGINE3 created by the UE3 is the highest by calculation, and thus the slot extracted from the ENGINE3 and the priority level of the key knowledge data associated with the slot are the highest.
Further, erroneous data may also exist in the interaction engine shared by multiple users, and at this time, the data needs to be analyzed to remove obviously erroneous data; the method can be realized by the following steps:
and screening a plurality of key knowledge data filled in the second slot position, and deleting error data.
Specifically, for the same slot in the same task, for example, the slot description information is the same slot for transfer, the key knowledge data filled in the slot in the shared ENGINE1 by the user 1 is station a; the key knowledge data that the user 2 fills in the slot in the shared ENGINE2 is the B site; the key knowledge data that user 5 fills in the slot in his shared entry 5 is the C site. The station A and the station B belong to optional transfer stations of two transfer lines, and the station C is not a transfer station and may be error data which is key knowledge data filled in the slot position due to the fact that a user fills in errors. In order to avoid providing error information to the user when the interaction engine is subsequently used, the filled multiple pieces of key knowledge data need to be screened, the error data is found, and the error data is removed, so that the use experience of the optimized interaction engine is guaranteed.
Further, the method may further include step 105, determining whether a third slot that is not filled exists in the second interaction engine; and if so, feeding back slot data missing information to the third party.
For example, when a user shares an interaction engine, the intelligent interaction platform counts the related information of the shared user. When the interactive engine optimization is executed and the slot position designed in the interactive engine is found not to obtain the fillable key knowledge data from other interactive engines with the same task, the sharing user corresponding to the interactive engine can be searched in the interactive engine information list, slot position data missing information is fed back to the user to request the response of the user, and if the user responds to the feedback request and carries available key knowledge data, the key knowledge data can be filled in the corresponding slot position in a supplementing manner.
Example two
Based on the same concept as the message pushing method in the foregoing embodiment, the embodiment of the present invention further provides an intelligent interaction engine optimization device, which may be independent of the intelligent interaction platform, or may be implemented by being embedded in the intelligent interaction platform. Referring to fig. 3, the apparatus includes:
the interaction engine acquisition module is used for acquiring a first interaction engine shared by a third party;
the extraction module is used for extracting a first element in the first interaction engine and first data information associated with the first element;
the matching module is used for acquiring a second element matched with the first element in a second interaction engine;
and the filling module is used for filling the first data information into a second element in the second interaction engine.
Preferably, the first element comprises a first slot;
the second element comprises a second slot position;
the first data information associated with the first element comprises first key knowledge data associated with a first slot;
the first interaction engine and the second interaction engine have the same task attributes.
The intelligent interaction platform can open an interface to a user, so that the user can create own tasks through the open interface, and an interaction engine based on the tasks is generated by packaging the tasks created and completed by the user. And simultaneously, the user can also directly upload the packaged interaction engine which accords with the platform format by using the interface which is opened to the user.
Specifically, the interaction engine acquisition module is further configured to acquire one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform; or one or more interaction engines shared in a network platform captured through network searching. For example, acquiring one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform; the multiple users upload the interaction engine1, the interaction engine2, … … and the interaction engine n based on the same task on the intelligent interaction platform. In step 101, based on the task attribute of the interaction engine to be optimized, an interaction engine shared by a third party and conforming to the same task can be first found on the intelligent interaction platform, so that the interaction engine initially developed in the intelligent interaction platform and based on the task can be subsequently optimized by using the interaction engines. Or, for example, in some public resource sharing platforms, there are interaction engines where users voluntarily share and provide communication downloads; the interaction engine of the type can be captured by utilizing network search, and the interaction engines initially developed in the intelligent interaction platform based on the task can be optimized by utilizing the interaction engines in the follow-up process.
Specifically, the apparatus further creates a module;
the matching module is further used for judging whether a slot position matched with the first slot position exists in a second interaction engine; if not, the creating module creates a second slot position matched with the first slot position.
Specifically, the second slot has a plurality of candidate bits;
the filling module is further configured to fill the first key knowledge data into the plurality of candidate bits according to the priority of the first key knowledge data.
Specifically, the device further comprises a priority determining module
The priority determining module is used for acquiring the download quantity and/or the recommendation value of the first interaction engine, and determining the priority level of the first key knowledge data associated with the first slot position in the first interaction engine according to the download quantity and/or the recommendation value. For example, the download amount and recommendation value of each interactive ENGINE are counted through the interactive ENGINE information list, the priority level of the key knowledge data extracted from the interactive ENGINE is set by how much the download amount is, or the priority level of the key knowledge data extracted from the interactive ENGINE is set by the level of the evaluation value, or the value weight of the interactive ENGINE is calculated by combining the download amount and the recommendation value, and the priority level of the key knowledge data extracted from the interactive ENGINE is set by the level of the value weight, for example, for the same TASK attribute TASK2, it is known that the value weight of the ENGINE3 created by the UE3 is the highest by calculation, and thus the slot extracted from the ENGINE3 and the priority level of the key knowledge data associated with the slot are the highest.
Specifically, the apparatus further includes a screening module configured to screen the plurality of key knowledge data filled in the second slot to delete the error data. For example, for the same slot in the same task, if the slot description information is the same slot for transfer, the key knowledge data filled in the slot is used as the station a in the shared ENGINE1 by the user 1; the key knowledge data that the user 2 fills the slot in the shared entry 2 is the station B; the key knowledge data that user 5 fills in the slot in his shared ENGINE5 is the C site. The station A and the station B belong to optional transfer stations of two transfer lines, and the station C is not a transfer station and may be error data which is key knowledge data filled in the slot position due to the fact that a user fills in errors. In order to avoid providing error information to the user when the interaction engine is subsequently used, the filled multiple pieces of key knowledge data need to be screened, the error data is found, and the error data is removed, so that the use experience of the optimized interaction engine is guaranteed.
Specifically, the device further comprises a feedback module
The matching module is further used for judging whether a third slot position which is not filled exists in the second interaction engine;
and if so, the feedback module feeds back the slot missing information to the third party.
For example, when the users share the interaction engine, the intelligent interaction platform counts the related information of the shared users. When the interactive engine optimization is executed and the slot position designed in the interactive engine is found not to obtain the fillable key knowledge data from other interactive engines with the same task, the sharing user corresponding to the interactive engine can be searched in the interactive engine information list, slot position data missing information is fed back to the user to request the response of the user, and if the user responds to the feedback request and carries available key knowledge data, the key knowledge data can be filled in the corresponding slot position in a supplementing manner.
Based on the same concept as the message pushing method in the foregoing embodiment, an embodiment of the present invention further provides a terminal device, where the terminal device includes the intelligent interaction engine optimization apparatus in the foregoing second embodiment.
Specifically, the terminal device may be a computer, a tablet computer, a mobile phone, a smart assistant, a vehicle-mounted terminal, and the like.
Based on the same concept as the message pushing method in the foregoing embodiment, an embodiment of the present invention further provides a computer device, where the computer device includes a processor and a memory, where a computer program operable on the processor is stored in the memory, and when the computer program is executed by the processor, the computer program implements a corresponding intelligent interaction engine optimization method.
Based on the same concept as the intelligent interaction engine optimization method in the foregoing embodiments, the embodiments of the present invention further provide a computer-readable storage medium, in which a computer program operable on a processor is stored, and when the computer program is executed, the method for implementing intelligent interaction engine optimization is implemented.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, it should be noted that, for those skilled in the art, many modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (17)
1. An interaction engine optimization method for an intelligent interaction platform is characterized by comprising the following steps:
101, acquiring a first interaction engine shared by a third party in an intelligent interaction platform; wherein, intelligent interactive platform includes: the system comprises a human-computer interaction interface, a processing module and a database; the processing module comprises a plurality of interaction engines, and each interaction engine comprises a semantic understanding module, a conversation management and control module, a conversation generation module and a command execution module; the interaction engine comprises an interaction engine which is generated by a user through creating a task through an open interface of the intelligent interaction platform and packaging the task created by the user, and the packaged interaction engine which is uploaded by the user through the open interface of the intelligent interaction platform and accords with a platform format;
step 102, extracting a first element in the first interaction engine and first data information associated with the first element; the first element comprises a first slot position; the first data information associated with the first element comprises first key knowledge data associated with a first slot location;
103, acquiring a second element matched with the first element in a second interaction engine; the second element comprises a second slot position; the first interaction engine and the second interaction engine have the same task attribute;
and 104, filling the first data information into a second element in a second interaction engine.
2. The method of claim 1, wherein the step 101 further comprises
Based on the task attribute of the interaction engine needing to be optimized;
acquiring one or more interaction engines which are created or uploaded by a third party through an open interface of an intelligent interaction platform and are in accordance with the requirements for completing the same task;
or
And capturing one or more interaction engines which are shared in the network platform and are consistent with the same task through network search.
3. The method of claim 1, wherein step 103 further comprises
Judging whether a slot position matched with the first slot position exists in a second interaction engine; and if not, creating a second slot position matched with the first slot position.
4. The method of claim 1, wherein the step 104 further comprises
The second slot position is provided with a plurality of candidate positions;
and filling the candidate bits according to the priority level of the first key knowledge data.
5. The method of claim 4,
and acquiring the download quantity and/or the recommended value of the first interaction engine, and determining the priority level of the first key knowledge data associated with the first slot position in the first interaction engine according to the download quantity and/or the recommended value.
6. The method of claim 4,
and screening a plurality of key knowledge data filled in the second slot position, and deleting error data.
7. The method of claim 1, further comprising step 105
Judging whether a third slot position which is not filled exists in the second interaction engine;
and if so, feeding back slot data missing information to the third party.
8. An interaction engine optimization apparatus of an intelligent interaction platform, the apparatus comprising:
the interaction engine acquisition module is used for acquiring a first interaction engine shared by a third party in the intelligent interaction platform; wherein, intelligent interactive platform includes: the system comprises a human-computer interaction interface, a processing module and a database; the processing module comprises a plurality of interaction engines, and each interaction engine comprises a semantic understanding module, a conversation management and control module, a conversation generation module and a command execution module; the interaction engine comprises an interaction engine which is generated by a user through creating a task through an open interface of the intelligent interaction platform and packaging the task created by the user, and the packaged interaction engine which is uploaded by the user through the open interface of the intelligent interaction platform and accords with a platform format;
the extraction module is used for extracting a first element in the first interaction engine and first data information associated with the first element; the first element comprises a first slot position; the first data information associated with the first element comprises first key knowledge data associated with a first slot location;
the matching module is used for acquiring a second element matched with the first element in a second interaction engine; the second element comprises a second slot position; the first interaction engine and the second interaction engine have the same task attribute;
and the filling module is used for filling the first data information into a second element in the second interaction engine.
9. The apparatus of claim 8, wherein the interaction engine obtaining module is further configured to obtain the data from the interaction engine
Acquiring one or more interaction engines created or uploaded by a third party through an open interface of an intelligent interaction platform;
or
And one or more interaction engines shared in the network platform are captured through network searching.
10. The apparatus of claim 8, wherein the apparatus further creates a module;
the matching module is further used for judging whether a slot position matched with the first slot position exists in a second interaction engine; and if not, the creating module creates a second slot position matched with the first slot position.
11. The apparatus of claim 8,
the second slot position is provided with a plurality of candidate positions;
the filling module is further configured to fill the first key knowledge data to the plurality of candidate bits according to the priority of the first key knowledge data.
12. The apparatus of claim 11, wherein the apparatus further comprises a priority determination module
The priority determining module is used for acquiring the download quantity and/or the recommendation value of the first interaction engine, and determining the priority level of the first key knowledge data associated with the first slot position in the first interaction engine according to the download quantity and/or the recommendation value.
13. The apparatus of claim 11, further comprising a filtering module configured to filter the plurality of key knowledge data populated in the second slot to remove erroneous data.
14. The apparatus of claim 8, further comprising a feedback module
The matching module is further used for judging whether a third slot position which is not filled exists in the second interaction engine;
and if so, the feedback module feeds back the slot missing information to the third party.
15. A terminal device characterized by: comprising the intelligent interaction engine optimization device of claims 8-14.
16. A computer arrangement, characterized in that the computer arrangement comprises a processor and a memory, in which a computer program is stored which is executable on the processor, which computer program, when being executed by the processor, carries out the method according to any one of claims 1 to 7.
17. A computer-readable storage medium, in which a computer program that is executable on a processor is stored, which computer program, when being executed, carries out the method according to any one of claims 1 to 7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910141273 | 2019-02-26 | ||
| CN2019101412730 | 2019-02-26 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110472113A CN110472113A (en) | 2019-11-19 |
| CN110472113B true CN110472113B (en) | 2022-08-26 |
Family
ID=68508529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910706655.3A Active CN110472113B (en) | 2019-02-26 | 2019-08-01 | Intelligent interaction engine optimization method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472113B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111128154B (en) * | 2019-12-03 | 2022-06-03 | 杭州蓦然认知科技有限公司 | Method and device for forming interaction engine cluster by aggregation |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844506A (en) * | 2016-12-27 | 2017-06-13 | 竹间智能科技（上海）有限公司 | The knowledge retrieval method and the automatic improving method of knowledge base of a kind of artificial intelligence dialogue |
| WO2019055905A1 (en) * | 2017-09-15 | 2019-03-21 | Glicq, Inc. | Platform agnostic secured object processing |
| CN109241519B (en) * | 2018-06-28 | 2022-08-12 | 平安科技（深圳）有限公司 | Quality evaluation model acquisition method and device, computer equipment and storage medium |
| CN109033229B (en) * | 2018-06-29 | 2021-06-11 | 北京百度网讯科技有限公司 | Question and answer processing method and device |
| CN109241269B (en) * | 2018-07-27 | 2020-07-17 | 深圳追一科技有限公司 | Task-based robot word slot filling method |
-
2019
- 2019-08-01 CN CN201910706655.3A patent/CN110472113B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472113A (en) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107102941B (en) | Test case generation method and device | |
| CN107515857B (en) | Semantic understanding method and system based on customization technology | |
| US10783874B2 (en) | Method and apparatus for providing voice feedback information to user in call | |
| CN113268498A (en) | Service recommendation method and device with intelligent assistant | |
| CN112036577B (en) | Method and device for applying machine learning based on data form and electronic equipment | |
| CN110442697B (en) | Man-machine interaction method, system, computer equipment and storage medium | |
| CN110309339B (en) | Picture tag generation method and device, terminal and storage medium | |
| US20170277526A1 (en) | Software categorization method and electronic device | |
| CN109271503A (en) | Intelligent answer method, apparatus, equipment and storage medium | |
| CN113806503A (en) | Dialog fusion method, device and equipment | |
| CN109086276A (en) | Data translating method, device, terminal and storage medium | |
| CN107852422A (en) | Connected from the server interface with different API to obtain ad data | |
| CN113868538B (en) | Information processing method, device, equipment and medium | |
| CN110472113B (en) | Intelligent interaction engine optimization method, device and equipment | |
| CN105786941A (en) | Information mining method and device | |
| KR102205686B1 (en) | Method and apparatus for ranking candiate character and method and device for inputting character | |
| CN113626512A (en) | Data processing method, device, equipment and readable storage medium | |
| CN107623620B (en) | Processing method of random interaction data, network server and intelligent dialogue system | |
| CN112966076A (en) | Intelligent question and answer generating method and device, computer equipment and storage medium | |
| CN115409553B (en) | Advertisement putting system and method based on big data and position information | |
| CN109964473A (en) | The method and device of voice service response | |
| CN110929014A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN106294395A (en) | The method and device that a kind of task processes | |
| CN110442695B (en) | Intelligent interaction platform training method, device and equipment | |
| CN112905792A (en) | Text clustering method, device and equipment based on non-text scene and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220104 Address after: 310024 floor 5, zone 2, building 3, Hangzhou cloud computing Industrial Park, Zhuantang street, Xihu District, Hangzhou City, Zhejiang Province Applicant after: Hangzhou suddenly Cognitive Technology Co.,Ltd. Address before: Room 401, gate 2, block a, Zhongguancun 768 Creative Industry Park, 5 Xueyuan Road, Haidian District, Beijing 100083 Applicant before: BEIJING MORAN COGNITIVE TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231016 Address after: Room 820, 8th floor, No. 390-408 Beijing East Road, Huangpu District, Shanghai, 200001 Patentee after: Guangyulaite Digital Technology (Shanghai) Co.,Ltd. Address before: 310024 floor 5, zone 2, building 3, Hangzhou cloud computing Industrial Park, Zhuantang street, Xihu District, Hangzhou City, Zhejiang Province Patentee before: Hangzhou suddenly Cognitive Technology Co.,Ltd. |