CN110175242A - Human-computer interaction association method, device and the medium of knowledge based map - Google Patents
Human-computer interaction association method, device and the medium of knowledge based map Download PDFInfo
- Publication number
- CN110175242A CN110175242A CN201910467616.2A CN201910467616A CN110175242A CN 110175242 A CN110175242 A CN 110175242A CN 201910467616 A CN201910467616 A CN 201910467616A CN 110175242 A CN110175242 A CN 110175242A
- Authority
- CN
- China
- Prior art keywords
- entity
- association
- candidate
- human
- kernel
- 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
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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The human-computer interaction association method of knowledge based map provided by the invention obtains the voice signal of user's input, the voice signal is converted to letter signal；Extract the kernel entity of the letter signal；Candidate association's entity is extracted in preset knowledge mapping according to the kernel entity；All candidate association's entities are ranked up, defining relevance strongest k candidate association's entity is association's result；Return information is generated according to association's result.This method can imitate the associative ability of the mankind, and the reply inputted to user is generated according to the result of association, can both realize the robot autonomous conversion between topic, can also ensure the correlation newly to change the topic of conversation between current topic.The intelligence degree of hoisting machine people simultaneously, while user being allowed to feel that the reply of robot is more life-like and personalizes.
Description
Technical field
The invention belongs to human-computer interaction technique fields, and in particular to human-computer interaction association method, the dress of knowledge based map
It sets and medium.
Background technique
Currently, machine generates there are many methods replied in field of human-computer interaction, and such as: the side by presetting question and answer library
Formula allows machine to retrieve one in question and answer library and replies to user, or by machine learning, deep learning etc. it is artificial
Intelligent method generates answer etc. by machine.
Although these methods have obtained more in-depth study and more universal application, but its disadvantage is also especially prominent
Out, the former needs to preset sufficiently large question and answer library, and the Recovery Process of substantially machine and any intelligence is not present, and machine is not yet
It can understand the input of user；The latter, often there is syntax error in the answer that machine generates or the answer height of machine is identical.
In addition, reply all more mechanization that above two technology generates, influence the communication experience of user, basic reason be machine not
Associative ability with the mankind cannot carry out association and according to association according to knowledge, to understanding, chat context of user etc.
As a result the reply to user's input is generated.
Summary of the invention
For the defects in the prior art, the present invention provides a kind of human-computer interaction association method of knowledge based map, dress
It sets and medium, imitates the associative ability of the mankind, and generate the reply inputted to user according to the result of association.
In a first aspect, a kind of human-computer interaction association method of knowledge based map, comprising the following steps:
The voice signal for obtaining user's input, is converted to letter signal for the voice signal；
Extract the kernel entity of the letter signal；
Candidate association's entity is extracted in preset knowledge mapping according to the kernel entity；
All candidate association's entities are ranked up, defining relevance strongest k candidate association's entity is associative bond
Fruit；
Return information is generated according to association's result.
Preferably, this method it is described the voice signal is converted into letter signal after, it is described to extract the text
Before the kernel entity of signal, further includes:
The text information is segmented, part-of-speech tagging and syntactic analysis, obtains word processing result.
Preferably, the kernel entity for extracting the letter signal specifically includes:
According to the word processing as a result, the core noun and/or subject of the letter signal are extracted, as the core
Entity.
Preferably, the candidate association entity that extracted in preset knowledge mapping according to the kernel entity specifically wraps
It includes:
The kernel entity is positioned in preset knowledge mapping；
In preset knowledge mapping, extracting with the physical distance of the kernel entity is a jump and/or important multi-hop
Entity in range, defining the entity is candidate association's entity.
Preferably, this method extracts candidate association in fact according to the kernel entity described in preset knowledge mapping
After body, it is described all candidate association's entities are ranked up before, further includes:
Candidate association's entity is screened according to preset beta pruning feature, weeds out and is unsatisfactory for the beta pruning feature
Candidate association's entity.
Preferably, the beta pruning feature includes hot topic event, user's memory map and contextual information.
Preferably, this method extracts candidate association in fact according to the kernel entity described in preset knowledge mapping
After body, it is described all candidate association's entities are ranked up before, further includes:
In preset knowledge mapping, entity relevant to candidate's association's entity is obtained, it is described for defining the entity
Candidate association entity.
Second aspect, a kind of device, including processor, input equipment, output equipment and memory, it is the processor, defeated
Enter equipment, output equipment and memory to be connected with each other, wherein the memory is for storing computer program, the computer
Program includes program instruction, and the processor is configured for calling described program instruction, executes method described in first aspect.
The third aspect, a kind of computer readable storage medium, the computer storage medium are stored with computer program, institute
Stating computer program includes program instruction, and described program instruction makes the processor execute first aspect when being executed by a processor
The method.
As shown from the above technical solution, the human-computer interaction association method of knowledge based map provided by the invention, device and
Medium can imitate the associative ability of the mankind, and generate the reply inputted to user according to the result of association, can both realize machine
People's independently conversion between topic can also ensure the correlation newly to change the topic of conversation between current topic.Hoisting machine people simultaneously
Intelligence degree, while user being allowed to feel that the reply of robot is more life-like and personalize.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art are briefly described.In all the appended drawings, similar element
Or part is generally identified by similar appended drawing reference.In attached drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 is the flow chart for the human-computer interaction association method that the embodiment of the present invention one provides.
Fig. 2 is the module frame chart for the device that the embodiment of the present invention four provides.
Specific embodiment
It is described in detail below in conjunction with embodiment of the attached drawing to technical solution of the present invention.Following embodiment is only used for
Clearly illustrate technical solution of the present invention, therefore be only used as example, and cannot be used as a limitation and limit protection model of the invention
It encloses.It should be noted that unless otherwise indicated, technical term or scientific term used in this application are should be belonging to the present invention
The ordinary meaning that field technical staff is understood.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
Embodiment one:
A kind of human-computer interaction association method of knowledge based map, referring to Fig. 1, comprising the following steps:
S1: the voice signal of user's input is obtained, the voice signal is converted into letter signal；
S2: the kernel entity of the letter signal is extracted；
S3: candidate association's entity is extracted in preset knowledge mapping according to the kernel entity；
Specifically, knowledge mapping is a kind of information storage means, and comprising the relationship between entity and entity, entity is knowledge graph
Point in spectrum, the relationship between entity are the side in knowledge mapping, and knowledge mapping is substantially exactly the figure being made of side and point.
S4: all candidate association's entities are ranked up, and defining relevance strongest k candidate association's entity is association
As a result；Such as: the candidate association's entity of top ranked k is defined as association's result.
S5: return information is generated according to association's result.
Specifically, the voice signal that user inputs is converted to letter signal by this method, and extracts the core in letter signal
Heart entity, for the principal entities that are intended by the voice signal of identity user input.Then found out in knowledge mapping with
The relevant entity of kernel entity is associated entity as candidate, and is screened to candidate association entity, and it is strongest to select relevance
Several entities, and replied according to the entity selected.
Such as: in interactive process, when the voice signal of user's input is " wanting to eat grape ", then this method can basis
The history intersection record of user, association user also like apple in addition to liking grape in fruit, thus it is possible to generate reply letter
It ceases " I remember you, and favorite fruit is grape, but you also very like apple in my impression ".
This method can imitate the associative ability of the mankind, and the reply inputted to user is generated according to the result of association, both
The robot autonomous conversion between topic can be achieved, can also ensure the correlation newly to change the topic of conversation between current topic.Simultaneously
The intelligence degree of hoisting machine people, while user being allowed to feel that the reply of robot is more life-like and personalizes.
Embodiment two:
Embodiment two increases the following contents on the basis of example 1:
This method it is described the voice signal is converted into letter signal after, the core for extracting the letter signal
Before heart entity, further includes:
The text information is segmented, part-of-speech tagging and syntactic analysis, obtains word processing result.
Specifically, part-of-speech tagging refers to the mistake that the word in specified sentence is marked by its meaning and context
Journey.This method also carries out syntactic analysis to the text information for completing part-of-speech tagging, facilitates and subsequent accurately extracts kernel entity.
Preferably, the kernel entity for extracting the letter signal specifically includes:
According to the word processing as a result, the core noun and/or subject of the letter signal are extracted, as the core
Entity.
Specifically, such as: the voice signal of user's input is " star A preside over program A to have started broadcasting recently ", then fixed
Core noun " program A " in the adopted voice signal is kernel entity.User input voice signal be " film B will be shown,
I, which wants to go to well, sees ", then defining the subject " film B " in voice signal is kernel entity.
Method provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned side
Corresponding contents in method embodiment.
Embodiment three:
Embodiment three increases the following contents on the basis of other embodiments:
The candidate association entity that extracted in preset knowledge mapping according to the kernel entity specifically includes:
The kernel entity is positioned in preset knowledge mapping；
In preset knowledge mapping, extracting with the physical distance of the kernel entity is a jump and/or important multi-hop
Entity in range, defining the entity is candidate association's entity.
Specifically, the entity being connected directly in knowledge mapping with kernel entity is exactly to jump model with kernel entity distance for one
In enclosing, i.e., one jump is reachable.If with the entity being connected among kernel entity across other entities, be exactly with kernel entity away from
From within the scope of double bounce.If the entity with being connected among kernel entity across other N number of entities, is exactly and kernel entity distance
It is jumped in range for N+1.
It can be configured by user according to own situation within the scope of important multi-hop.It is strong for sequence ranking height, correlation
Entity, then it is assumed that be important multi-hop.This method thinks to be a jump and/or important multi-hop with the physical distance of the kernel entity
Entity in range is candidate association's entity.
If candidate association physical quantities are more, need to carry out beta pruning screening to candidate association entity.This method is described
It is described to associate all candidates after extracting candidate association's entity in preset knowledge mapping according to the kernel entity
Before entity is ranked up, further includes:
Candidate association's entity is screened according to preset beta pruning feature, weeds out and is unsatisfactory for the beta pruning feature
Candidate association's entity.
Wherein, the beta pruning feature includes hot topic event, user's memory map and contextual information.
Specifically, when candidate association, physical quantities are more, by screening to candidate association entity, obtain more valuable
Association's result.Such as when carrying out beta pruning according to hot topic event, it is believed that the hot ticket information occurred in the recent period is for right
More valuable, more excellent information content is talked about, entity relevant to hot ticket should be returned preferentially.When according to user remember map into
When row beta pruning, it is believed that entity related to user should be returned preferentially.When based on context carrying out beta pruning, it is believed that context pair
During words, the entity above once mentioned should be returned preferentially.This method associates candidate by above-mentioned diversity index
Entity carries out beta pruning, and same candidate association's entity is avoided repeatedly to be returned, and reduces the weight of the candidate association's entity repeatedly returned.
If candidate association physical quantities are less, need to add more candidate association's entities, such as can use term vector
Mode adds more candidates.This method extracts candidate association according to the kernel entity described in preset knowledge mapping
After entity, it is described all candidate association's entities are ranked up before, further includes:
In preset knowledge mapping, entity relevant to candidate's association's entity is obtained, it is described for defining the entity
Candidate association entity.Such as assume in knowledge mapping, grape is related to red wine, and red wine belongs to drinks, with brandy
Correlation, when user says that oneself likes drinking red wine, the candidate association's entity extracted is grape wine, at this point, this method can
Increasing brandy for candidate association's entity, then candidate association's entity at this time includes red wine and brandy, then may be used
Do to reply user: you like brandy?
Method provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned side
Corresponding contents in method embodiment.
Example IV:
A kind of device, referring to fig. 2, including processor 801, input equipment 802, output equipment 803 and memory 804, institute
It states processor 801, input equipment 802, output equipment 803 and memory 804 to be connected with each other by bus 805, wherein described to deposit
Reservoir 804 is for storing computer program, and the computer program includes program instruction, and the processor 801 is configured for
Described program instruction is called, above-mentioned method is executed.
It should be appreciated that in embodiments of the present invention, alleged processor 801 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
Input equipment 802 may include that Trackpad, fingerprint adopt sensor (for acquiring the finger print information and fingerprint of user
Directional information), microphone etc., output equipment 803 may include display (LCD etc.), loudspeaker etc..
The memory 804 may include read-only memory and random access memory, and to processor 801 provide instruction and
Data.The a part of of memory 804 can also include nonvolatile RAM.For example, memory 804 can also be deposited
Store up the information of device type.
Device provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned side
Corresponding contents in method embodiment.
Embodiment five:
A kind of computer readable storage medium, the computer storage medium are stored with computer program, the computer
Program includes program instruction, and described program instruction makes the processor execute above-mentioned method when being executed by a processor.
The computer readable storage medium can be the internal storage unit of device described in aforementioned any embodiment, example
Such as the hard disk or memory of device.The computer readable storage medium is also possible to the External memory equipment of described device, such as
The plug-in type hard disk being equipped in described device, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, the computer readable storage medium can also be wrapped both
The internal storage unit for including described device also includes External memory equipment.The computer readable storage medium is described for storing
Other programs and data needed for computer program and described device.The computer readable storage medium can be also used for temporarily
When store the data that has exported or will export.
Medium provided by the embodiment of the present invention, to briefly describe, embodiment part does not refer to place, can refer to aforementioned system
Corresponding contents in embodiment of uniting.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (9)
1. a kind of human-computer interaction association method of knowledge based map, which comprises the following steps:
The voice signal for obtaining user's input, is converted to letter signal for the voice signal；
Extract the kernel entity of the letter signal；
Candidate association's entity is extracted in preset knowledge mapping according to the kernel entity；
All candidate association's entities are ranked up, defining relevance strongest k candidate association's entity is association's result；
Return information is generated according to association's result.
2. the human-computer interaction association method of knowledge based map according to claim 1, which is characterized in that
This method it is described the voice signal is converted into letter signal after, the core for extracting the letter signal is real
Before body, further includes:
The text information is segmented, part-of-speech tagging and syntactic analysis, obtains word processing result.
3. the human-computer interaction association method of knowledge based map according to claim 2, which is characterized in that
The kernel entity for extracting the letter signal specifically includes:
It is real as the core according to the word processing as a result, extracting the core noun and/or subject of the letter signal
Body.
4. the human-computer interaction association method of knowledge based map according to claim 1, which is characterized in that
The candidate association entity that extracted in preset knowledge mapping according to the kernel entity specifically includes:
The kernel entity is positioned in preset knowledge mapping；
In preset knowledge mapping, extracting with the physical distance of the kernel entity is a jump and/or important multi-hop range
Interior entity, defining the entity is candidate association's entity.
5. the human-computer interaction association method of knowledge based map according to claim 1, which is characterized in that
This method it is described candidate association's entity is extracted according to the kernel entity in preset knowledge mapping after, it is described
Before all candidate association's entities are ranked up, further includes:
Candidate association's entity is screened according to preset beta pruning feature, weeds out the time for being unsatisfactory for the beta pruning feature
Choosing association entity.
6. the human-computer interaction association method of knowledge based map according to claim 5, which is characterized in that
The beta pruning feature includes hot topic event, user's memory map and contextual information.
7. the human-computer interaction association method of knowledge based map according to claim 1, which is characterized in that
This method it is described candidate association's entity is extracted according to the kernel entity in preset knowledge mapping after, it is described
Before all candidate association's entities are ranked up, further includes:
In preset knowledge mapping, entity relevant to candidate's association's entity is obtained, defining the entity is the candidate
Associate entity.
8. a kind of device, which is characterized in that the processor, defeated including processor, input equipment, output equipment and memory
Enter equipment, output equipment and memory to be connected with each other, wherein the memory is for storing computer program, the computer
Program includes program instruction, and the processor is configured for calling described program instruction, is executed such as any one of claim 1-7
The method.
9. a kind of computer readable storage medium, which is characterized in that the computer storage medium is stored with computer program, institute
Stating computer program includes program instruction, and described program instruction executes the processor as right is wanted
Seek the described in any item methods of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910467616.2A CN110175242A (en) | 2019-05-31 | 2019-05-31 | Human-computer interaction association method, device and the medium of knowledge based map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910467616.2A CN110175242A (en) | 2019-05-31 | 2019-05-31 | Human-computer interaction association method, device and the medium of knowledge based map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110175242A true CN110175242A (en) | 2019-08-27 |
Family
ID=67696096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910467616.2A Pending CN110175242A (en) | 2019-05-31 | 2019-05-31 | Human-computer interaction association method, device and the medium of knowledge based map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110175242A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112163077A (en) * | 2020-09-28 | 2021-01-01 | 华南理工大学 | Domain-oriented question-answering knowledge graph construction method |
| CN114238589A (en) * | 2020-09-09 | 2022-03-25 | 中移智行网络科技有限公司 | Man-machine conversation control method and device and terminal |
| US11620855B2 (en) * | 2020-09-03 | 2023-04-04 | International Business Machines Corporation | Iterative memory mapping operations in smart lens/augmented glasses |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095433A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Recommendation method and device for entities |
| US20170169095A1 (en) * | 2015-12-15 | 2017-06-15 | Yahoo! Inc. | Method and system for mapping notable entities to their social profiles |
| CN108509563A (en) * | 2018-03-23 | 2018-09-07 | 深圳狗尾草智能科技有限公司 | Robot reasoning association method, device, equipment and the medium of knowledge based collection of illustrative plates |
-
2019
- 2019-05-31 CN CN201910467616.2A patent/CN110175242A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095433A (en) * | 2015-07-22 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Recommendation method and device for entities |
| US20170169095A1 (en) * | 2015-12-15 | 2017-06-15 | Yahoo! Inc. | Method and system for mapping notable entities to their social profiles |
| CN108509563A (en) * | 2018-03-23 | 2018-09-07 | 深圳狗尾草智能科技有限公司 | Robot reasoning association method, device, equipment and the medium of knowledge based collection of illustrative plates |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11620855B2 (en) * | 2020-09-03 | 2023-04-04 | International Business Machines Corporation | Iterative memory mapping operations in smart lens/augmented glasses |
| CN114238589A (en) * | 2020-09-09 | 2022-03-25 | 中移智行网络科技有限公司 | Man-machine conversation control method and device and terminal |
| CN114238589B (en) * | 2020-09-09 | 2023-11-21 | 中移智行网络科技有限公司 | Man-machine conversation control method and device and terminal |
| CN112163077A (en) * | 2020-09-28 | 2021-01-01 | 华南理工大学 | Domain-oriented question-answering knowledge graph construction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11322153B2 (en) | Conversation interaction method, apparatus and computer readable storage medium | |
| JP6305389B2 (en) | Method and apparatus for intelligent chat between human and machine using artificial intelligence | |
| CN110263324A (en) | Text handling method, model training method and device | |
| CN108664472B (en) | Natural language processing method, device and equipment | |
| CN110175242A (en) | Human-computer interaction association method, device and the medium of knowledge based map | |
| CN107704482A (en) | Method, apparatus and program | |
| CN107590192A (en) | Mathematicization processing method, device, equipment and the storage medium of text question | |
| CN109918494A (en) | Context relation based on figure replys generation method, computer and medium | |
| CN110580516B (en) | Interaction method and device based on intelligent robot | |
| EP3620994A1 (en) | Methods, apparatuses, devices, and computer-readable storage media for determining category of entity | |
| CN106844341A (en) | News in brief extracting method and device based on artificial intelligence | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| CN110209777A (en) | The method and electronic equipment of question and answer | |
| CN112633504A (en) | Wisdom cloud knowledge service system and method for fruit tree diseases and insect pests based on knowledge graph | |
| CN110413751A (en) | Drug searching method, device, terminal device and storage medium | |
| CN113409907A (en) | Intelligent pre-inquiry method and system based on Internet hospital | |
| CN109325178A (en) | Method and apparatus for handling information | |
| CN106250366B (en) | A kind of data processing method and system for question answering system | |
| CN110309271A (en) | Intelligent knowledge study and question and answer technology | |
| CN110187780A (en) | Long text prediction technique, device, equipment and storage medium | |
| CN110489519A (en) | The session method and Related product of dialogue-based prediction model | |
| US20190332721A1 (en) | Electronic device and method for providing virtual assistance (va)-based content interaction | |
| CN109815379A (en) | A kind of intelligent search recommended method, storage medium and terminal for content | |
| CN109190116A (en) | Semantic analytic method, system, electronic equipment and storage medium | |
| CN111651989A (en) | Named entity recognition method and device, storage medium and electronic device |
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 |