CN109145100A - A kind of the Task customer service robot system and its working method of customizable process - Google Patents
A kind of the Task customer service robot system and its working method of customizable process Download PDFInfo
- Publication number
- CN109145100A CN109145100A CN201810971451.8A CN201810971451A CN109145100A CN 109145100 A CN109145100 A CN 109145100A CN 201810971451 A CN201810971451 A CN 201810971451A CN 109145100 A CN109145100 A CN 109145100A
- Authority
- CN
- China
- Prior art keywords
- task
- user
- module
- customer service
- word slot
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Abstract
The present invention provides a kind of Task customer service robot system of customizable process and its working methods, including rule settings module, flow of task to construct module, preprocessing module, information extraction model, intention assessment model, task matching module.Invention proposes a kind of Task customer service robot design scheme of customizable process, so that robot primary development is adapted to a variety of different tasks.The present invention combines specific area task humanoid robot accuracy rate height and the strong advantage of Opening field task humanoid robot scalability, it can allow common employee after simple study, energy customized process goes to complete task, and it allows entire flow of task to become transparent and is easy maintenance, on the one hand reduce human input, on the other hand also make system more reliable and more stable.
Description
Technical field
The present invention relates to network technique fields, and in particular to a kind of Task customer service robot system of customizable process
And its working method.
Background technique
Customer service is enterprise's answer user's query, solves the important channel of user's problem, and traditional phone customer service and
Line customer service requires enterprise and a large amount of manpower and material resources is spent to go to safeguard.Nowadays, the rise of customer service robot is so that artificial customer service
Demand decline, has greatly saved entreprise cost.
It is divided by the target that robot customer service needs to complete, can be divided into two classes, be inquiry answer class (FAQ) and completion respectively
Task class.Humanoid robot customer service relative maturity is answered in inquiry, can solve most of user's problem.And task humanoid robot visitor
It is then more extensively and complicated to take application scenarios, be related to take turns dialogue managements, multiple problems such as word slot, which is collected, to be inherited, and logic jumps.
Task humanoid robot customer service example is as follows:
Task humanoid robot customer service makes robot customer service not only have the ability answerred questions, with more the energy for solving customer problem
Power.In general solution, task equipment people's customer service is the robot of specific area particular task, such as electric business is handled and moved back
The robot of goods not can solve the task of predetermined air ticket, to complete the task and need to develop again.And appointing for Opening field
Business humanoid robot can then face and need to collect the problem of word slot information is excessive, and accuracy rate declines without process auxiliary, influence to use
Family experience.
The purpose of task humanoid robot customer service be collect need word slot information, thus for client provide corresponding information or
Person's solution, and under the premise of guaranteeing accuracy rate, the limitation of prior art causes when there is new task to occur
It needs developer to be developed again, keeps linear velocity and stability in new task all undesirable, in addition, as new task is more next
More, robot maintenance difficulties also ramp.
Summary of the invention
To solve the above problems, the present invention provides a kind of Task customer service robot system of customizable process, packet
Include rule settings module, flow of task building module, preprocessing module, information extraction model, intention assessment model, task matching
Module.
The Rulemaking module is used for user according to business needs, in the pre-set word for needing to extract of system background
Slot information category and its matching rule.
Flow of task building module constructs mission flow diagram for user according to their business needs；Each mission flow diagram
Including the word slot information category for needing to collect and collection sequence, online service information feedback action.
The language that the word slot information category and its rule that information extraction modules are set according to rule settings module input user
Sentence extracts word slot information.
Intention assessment model is used for the sentence according to user, word slot information prediction user is intended to.
State tracking module is used to that the state of the wheel to be gone to next round after the completion of the dialogue of every wheel.
Task matching module is used for after user is intended to completion task, according to the degree of approximation of user's question sentence and task
Carry out task marking matches the flow of task of specified quantity according to degree of approximation ranking.
It further, further include preprocessing module, for being pre-processed to the sentence that user inputs.
Further, the state of the wheel include the word slot information of the wheel, the wheel task marking, the wheel system generate
Answer.
Further, the workflow of task matching module includes the following steps:
S1: user's read statement is segmented, and being converted into corresponding term vector indicates；
S2: calculating the similarity of user's question sentence question sentence similar to task, and the similarity is that user's question sentence is similar to task
The distance of question sentence；
S3: the similarity is ranked up；
S4: the task of the preceding preset quantity of similarity ranking is selected.
Further, user's question sentence is COS distance at a distance from similar question sentence with task.
The working method of the Task customer service robot system of above-mentioned customizable process, which is characterized in that including such as
Lower step:
Step 1: the word slot information category and extracting rule collected required for being set in advance in system background.
Step 2: needing previously according to own service, constructs flow of task, and stored.
Step 3: user's read statement.
Step 4: information extraction model carries out letter to sentence according to the word slot information category and matching rule of required collection
Breath extracts.
Step 5: the feature of the information and information extraction model that are extracted is input to intention assessment mould as input parameter
Type, prediction user are intended to.
Step 6: intention assessment module judges that user is task to be completed or to chat；If it is chat, then not
Subsequent step is carried out, subsequent step is otherwise carried out.
Step 7: task matching module is according to the intention matching task process of judgement, according to matching degree to task progress
Rapid seven: task matching module gives a mark to task according to matching degree according to the intention matching task process of judgement, according to point
Number height carries out task priority sequence.
Step 8: system judges whether to collect the task for the current highest priority that is over according to the word slot information collected
Required whole word slot information are over if collected, access related service, and otherwise state tracking module is by word slot obtained
The answer that information, institute's matching task, system generate goes to the system and client connection state of next round.
Step 9: system generates corresponding answer guidance user and completes related term slot information input；
Step 10: step 3 is repeated to step 9, until completing all matched flow of task.
Subsequent step includes access related service, back services result.
9. it is further, user's read statement is pre-processed before step 4.
It further, is that the character string inputted using regular expression to user is matched in step 4.
The invention has the benefit that
The invention proposes a kind of Task customer service robot design schemes of customizable process, so that robot is primary
Exploitation is adapted to a variety of different tasks.This design scheme combines specific area task humanoid robot accuracy rate height and opens
The strong advantage of field task humanoid robot scalability is put, can allow common employee after simple study, it can be voluntarily
Customization process goes to complete task, and allows entire flow of task to become transparent and be easy maintenance, on the one hand reduces human input,
On the other hand also make system more reliable and more stable.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is express delivery order taking responsibility process.
Fig. 2 is aircraft order taking responsibility process.
Fig. 3 is express delivery querying flow example.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical solution of the present invention will be carried out below
Detailed description.Obviously, described embodiment is only that the present invention divides embodiment on one side, rather than comprehensive embodiment.Base
Embodiment in the present invention, those of ordinary skill in the art are obtained all without making creative work
Other embodiment belongs to the range that the present invention is protected.
Before being illustrated to this system and working method, first to task humanoid robot word slot fill method of the invention into
Row explanation.
System of the present invention is illustrated below.
System of the present invention includes that following rule settings module, flow of task building module, preprocessing module, information mention
Modulus type, intention assessment model, task matching module.
Rule settings module needs to believe in the pre-set word slot for needing to extract of system background for user according to business
Cease type and its matching rule.Word slot information category citing: cell-phone number, order number, temporal information, city name, mobile phone verifying
Code.Can also further matching rule formulation be carried out to each information category, if order number is 11 or nine consecutive numbers
Word collects identifying code as continuous five or six bit digitals.It should be noted that user can choose good common of systemic presupposition
Word slot information category, can also be with customized type and rule.
Flow of task building module constructs mission flow diagram for user according to their business needs.Each mission flow diagram
Including the word slot information, collection sequence and online service feedback information prompt process for needing to collect.For example: such as Fig. 1
It show express delivery order taking responsibility process.Word slot information collection sequence are as follows: collect order number -> collection cell-phone number -> collection mobile phone and test
Demonstrate,prove query result on code -> feedback line.It is illustrated in figure 2 aircraft order taking responsibility process.Flow of task are as follows: be collected simultaneously position of taking off
It sets and in-position -> feeding back to alternative Flight Information -> and feeds back to predetermined result.
The sentence that preprocessing module is used to input user pre-processes, to reduce the identification word of information extraction modules
Number.Pretreatment operation may include removing function word, as " ", " ", punctuation mark.After having pre-processed, preferably again into
Pedestrian's work or machine amendment, to guarantee not omit important information.The setting of preprocessing module is optimal technical scheme.
The language that the word slot information category and its rule that information extraction modules are set according to rule settings module input user
Sentence carries out information matches and extraction.Information extraction modules are using the prior art.The collection of word slot information can be using predetermined
Adopted rule carries out canonical matching, for example matching specific format is order number, and 11 bit digitals of 1 beginning are cell-phone number, and city is entitled
It sets out in-position etc., the sequence labelling model that deep learning also can be used marks out word groove location, can be combined with above
Two methods.
Intention assessment model is used to be intended to according to the word slot information of collection and the input question sentence prediction user of user.Its mould
Type input is the feature of user's sentence and information extraction model.Here user is intended to refer to that user is intended to chat or inquire
Some problem still completes some task dispatching.The feature extracted from information extraction model can effectively filter intention, such as exist
If extracting order number and cell-phone number in user's sentence, maximum probability user is intended to inquiry express delivery.For being judged as the use of chat
Family question sentence can transfer to chat robot to carry out judgement reply, be intended to if it is task, then can carry out this using task humanoid robot
The workflow of literary subsequent descriptions.
State tracking module is used to say that the status information of epicycle goes to next round after the completion of the dialogue of every wheel.Status information can
To include word slot information, the marking of epicycle task, the answer etc. that system generates.Every wheel dialogue includes that primary information extracts process, one
Secondary intention assessment process, user input the process of relevant information.
Task matching module is used for after determining that user is intended to completion task, according to user's question sentence and each task
Matching degree task marking and be ranked up, taking top n, (N is customized number, and the present embodiment N takes 3) matching is corresponding to appoint
Business process.The workflow of the module are as follows:
S1: user's question sentence is segmented, and being converted into corresponding term vector indicates.
S2: calculating the similarity of user's question sentence question sentence similar to task, and the similarity is that user's question sentence is similar to task
The distance of question sentence, for example, cos distance, the cos distance is bigger, and similarity is higher.
S3: the similarity is ranked up.
S4: the task of the preceding preset quantity of similarity ranking is selected.
The quantity of candidate word slot can be reduced, by screening task convenient for screening corresponding word slot of going out on missions as early as possible.
The summarizing property of working method of above system is illustrated below, this method can be summarized as following steps:
Step 1: the word slot information category and extracting rule collected required for being set in advance in system background.
Step 2: needing previously according to own service, constructs flow of task, and stored.
Step 3: user's read statement.
Step 4: information extraction model carries out pre- sentence according to the word slot information category and extracting rule of required collection
Information extraction.
Preferably, sentence is pre-processed using preprocessing module before step 4, is helped as removed the tone being not required to
Word etc..
Step 5: the feature of the information and information extraction model that are extracted is input to intention assessment mould as input parameter
Type, prediction user are intended to.
Step 6: intention assessment module judges that user is task to be completed or to chat；If it is chat, then not
Chat robot is gone to, without subsequent step, otherwise carries out subsequent step.
Step 7: task matching module carries out task according to matching degree according to the intention matching task process of judgement
Marking carries out task priority sequence according to score height.
If being matched to multiple tasks process, can at this time be received according to the priority for the multiple tasks process being matched to
Collection.For example: user's input " helps me to order plane ticket, then opens an invoice ", at this moment can first carry out " ordering air ticket " process, then into
Row " drawing a bill | " process, draws a bill, no air ticket cannot also draw a bill because ordering air ticket priority and being higher than.
Step 8: system judges whether to collect the task for the current highest priority that is over according to the word slot information collected
Required whole word slot information are over if collected, access related service, and otherwise state tracking module is by word slot obtained
The answer that information, institute's matching task, system generate goes to the system and client connection state of next round.
Step 9: system generates corresponding answer guidance user and completes related term slot information input.
Step 10: step 3 is repeated to step 10, until completing flow of task.
It should be noted that the flow of task that can be advanced into first according to it is collected when user continues input, if
User refers to that other tasks are intended to, and can also collect new task and be intended to corresponding word slot.
Step 11: access related service.
Step 12: back services result.
Express delivery querying flow example is shown with Fig. 3 below and carries out step explanation.
Step 1: word slot information, including " express delivery " and/or " package " text, order number, hand are set in system background in advance
Machine number.Setting order number is 9 continuous numbers；It is continuous number that cell-phone number, which is 11,.
Step 2: the flow chart such as Fig. 1 is established, and is stored.
Step 3: user's read statement: " mine is delivered to which fastly? ".
Step 4: which information extraction model " will be delivered to fastly " according to the word slot information category and extracting rule of required collection
In " express delivery " extract.
Preprocessing module pre-processes sentence, remove " I ", " ", " " and question mark.
Step 5: the feature of " express delivery " and information extraction model that are extracted is input to intention assessment mould as input parameter
Type；
Step 7: intention assessment model prediction user is intended that preparation inquiry express delivery.
Step 8: task matching module matches corresponding express delivery order taking responsibility process.
Step 9: system judgement is not collected into order number information, cell-phone number information also, therefore it is defeated to generate answer prompt user
Enter order number and cell-phone number.
Step 10: state tracking module goes to down the answer that word slot information obtained, institute's matching task, system generate
The system and client connection state of one wheel.
Step 11: user inputs the sentence containing order number, cell-phone number.
Step 12: information extraction model according to the word slot information category of required collection and extracting rule by order number,
Cell-phone number extracts.
Preprocessing module pre-processes sentence, remove " I ", " ", " " and question mark.
Step 13: the feature of the order number, cell-phone number and the information extraction model that are extracted is input to as input parameter
Intention assessment model；
Step 14: intention assessment model prediction user is intended that the task of being ready to complete.
Step 15: task matching module matches corresponding express delivery order inquiries flow of task.
Step 10 six: system according to collected order number, collect a number judgement also need to collect mobile phone identifying code.
Step 10 seven: user, which inputs, collects identifying code.
Step 10 eight: after identifying code is collected in system verifying, access Express Logistics information inquires online service, and feeds back knot
Fruit.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It is above-described, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, appoints
What those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, answer
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be with the scope of protection of the claims
Subject to.
Claims (8)
1. a kind of Task customer service robot system of customizable process, which is characterized in that including rule settings module, task
Process constructs module, preprocessing module, information extraction model, intention assessment model, task matching module；
The Rulemaking module, according to business needs, is believed for user in the pre-set word slot for needing to extract of system background
Cease type and its matching rule；
Flow of task building module constructs mission flow diagram for user according to their business needs；Each mission flow diagram includes
The word slot information category for needing to collect and collection sequence, online service information feedback action；
The word slot information category and its rule that information extraction modules are set according to rule settings module mention the sentence of user's input
Take word slot information；
Intention assessment model is used for the sentence according to user, word slot information prediction user is intended to；
State tracking module is used to that the state of the wheel to be gone to next round after the completion of the dialogue of every wheel；
Task matching module is used for after user is intended to completion task, is carried out according to the degree of approximation of user's question sentence and task
Task marking, the flow of task of specified quantity is matched according to degree of approximation ranking.
2. the Task customer service robot system of customizable process as described in claim 1, which is characterized in that further include pre-
Processing module, for being pre-processed to the sentence that user inputs.
3. the Task customer service robot system of customizable process as described in claim 1, which is characterized in that the described wheel
State include the word slot information of the wheel, the wheel task marking, the wheel system generate answer.
4. the Task customer service robot system of customizable process as described in claim 1, which is characterized in that task matching
The workflow of module includes the following steps:
S1: user's read statement is segmented, and being converted into corresponding term vector indicates；
S2: calculating the similarity of user's question sentence question sentence similar to task, and the similarity is user's question sentence question sentence similar to task
Distance；
S3: the similarity is ranked up；
S4: the task of the preceding preset quantity of similarity ranking is selected.
5. the Task customer service robot system of customizable process as claimed in claim 4, which is characterized in that user's question sentence
It is COS distance at a distance from similar question sentence with task.
6. the working method of the Task customer service robot system of customizable process as claimed in any one of claims 1 to 5,
It is characterized by comprising the following steps:
Step 1: the word slot information category and extracting rule collected required for being set in advance in system background；
Step 2: needing previously according to own service, constructs flow of task, and stored；
Step 3: user's read statement；
Step 4: information extraction model carries out information to sentence according to the word slot information category and matching rule of required collection and mentions
It takes；
Step 5: the feature of the information and information extraction model that are extracted is input to intention assessment model as input parameter, in advance
User is surveyed to be intended to；
Step 6: intention assessment module judges that user is task to be completed or to chat；If it is chat, then without
Otherwise subsequent step carries out subsequent step；
Step 7: task matching module gives a mark to task according to matching degree according to the intention matching task process of judgement,
Task priority sequence is carried out according to score height；
Step 8: system judges whether to collect the required by task for the current highest priority that is over according to the word slot information collected
Whole word slot information, if collect be over, access related service, otherwise state tracking module believes word slot obtained
The answer that breath, institute's matching task, system generate goes to the system and client connection state of next round；
Step 9: system generates corresponding answer guidance user and completes related term slot information input；
Step 10: step 3 is repeated to step 9, until completing all matched flow of task.
7. the working method of the Task customer service robot system of customizable process as claimed in claim 6, feature exist
In being pre-processed before step 4 to user's read statement.
8. the working method of the Task customer service robot system of customizable process as claimed in claim 6, feature exist
In being that the character string inputted using regular expression to user is matched in step 4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810971451.8A CN109145100A (en) | 2018-08-24 | 2018-08-24 | A kind of the Task customer service robot system and its working method of customizable process |
| PCT/CN2019/100310 WO2020038251A1 (en) | 2018-08-24 | 2019-08-13 | Process customizing system and method, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810971451.8A CN109145100A (en) | 2018-08-24 | 2018-08-24 | A kind of the Task customer service robot system and its working method of customizable process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109145100A true CN109145100A (en) | 2019-01-04 |
Family
ID=64827783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810971451.8A Pending CN109145100A (en) | 2018-08-24 | 2018-08-24 | A kind of the Task customer service robot system and its working method of customizable process |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109145100A (en) |
| WO (1) | WO2020038251A1 (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109829729A (en) * | 2019-01-18 | 2019-05-31 | 青牛智胜(深圳)科技有限公司 | A kind of intelligence outgoing call system and method |
| CN109857487A (en) * | 2019-02-02 | 2019-06-07 | 上海奔影网络科技有限公司 | Data processing method and device for task execution |
| CN110110338A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨理工大学 | A kind of Dialogue management model application method based on LSTM and slot filling |
| CN110297850A (en) * | 2019-05-28 | 2019-10-01 | 北京奇艺世纪科技有限公司 | Feature operation set dissemination method, device, electronic equipment and storage medium |
| CN110472030A (en) * | 2019-08-08 | 2019-11-19 | 网易（杭州）网络有限公司 | Man-machine interaction method, device and electronic equipment |
| CN110516035A (en) * | 2019-07-05 | 2019-11-29 | 同济大学 | A kind of man-machine interaction method and system of mixing module |
| WO2020038251A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳追一科技有限公司 | Process customizing system and method, and computer readable storage medium |
| CN111510566A (en) * | 2020-03-16 | 2020-08-07 | 深圳追一科技有限公司 | Method and device for determining call label, computer equipment and storage medium |
| CN114493164A (en) * | 2021-12-30 | 2022-05-13 | 重庆特斯联智慧科技股份有限公司 | Robot task analysis method and system based on edge calculation |
| CN114888804A (en) * | 2022-05-18 | 2022-08-12 | 深圳鹏行智能研究有限公司 | Robot control device and method based on working chain, medium and robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186154A1 (en) * | 2013-12-31 | 2015-07-02 | Next It Corporation | Virtual assistant team customization |
| CN107015964A (en) * | 2017-03-22 | 2017-08-04 | 北京光年无限科技有限公司 | The self-defined intention implementation method and device developed towards intelligent robot |
| CN107133052A (en) * | 2017-05-27 | 2017-09-05 | 杭州迪脉信息科技有限公司 | The method and device that flow is created |
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9111248B2 (en) * | 2012-03-28 | 2015-08-18 | Global Eprocure | Procurement system |
| CN104731895B (en) * | 2015-03-18 | 2018-09-18 | 北京京东尚科信息技术有限公司 | The method and apparatus of automatic-answering back device |
| CN107590216A (en) * | 2017-08-31 | 2018-01-16 | 北京百度网讯科技有限公司 | Answer preparation method, device and computer equipment |
| CN107958059B (en) * | 2017-12-01 | 2020-07-10 | 北京百度网讯科技有限公司 | Intelligent question answering method, device, terminal and computer readable storage medium |
| CN109145100A (en) * | 2018-08-24 | 2019-01-04 | 深圳追科技有限公司 | A kind of the Task customer service robot system and its working method of customizable process |
-
2018
- 2018-08-24 CN CN201810971451.8A patent/CN109145100A/en active Pending
-
2019
- 2019-08-13 WO PCT/CN2019/100310 patent/WO2020038251A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186154A1 (en) * | 2013-12-31 | 2015-07-02 | Next It Corporation | Virtual assistant team customization |
| CN107015964A (en) * | 2017-03-22 | 2017-08-04 | 北京光年无限科技有限公司 | The self-defined intention implementation method and device developed towards intelligent robot |
| CN107133052A (en) * | 2017-05-27 | 2017-09-05 | 杭州迪脉信息科技有限公司 | The method and device that flow is created |
| CN108197167A (en) * | 2017-12-18 | 2018-06-22 | 深圳前海微众银行股份有限公司 | Human-computer dialogue processing method, equipment and readable storage medium storing program for executing |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020038251A1 (en) * | 2018-08-24 | 2020-02-27 | 深圳追一科技有限公司 | Process customizing system and method, and computer readable storage medium |
| CN109829729A (en) * | 2019-01-18 | 2019-05-31 | 青牛智胜(深圳)科技有限公司 | A kind of intelligence outgoing call system and method |
| CN109857487A (en) * | 2019-02-02 | 2019-06-07 | 上海奔影网络科技有限公司 | Data processing method and device for task execution |
| CN110110338A (en) * | 2019-05-13 | 2019-08-09 | 哈尔滨理工大学 | A kind of Dialogue management model application method based on LSTM and slot filling |
| CN110297850A (en) * | 2019-05-28 | 2019-10-01 | 北京奇艺世纪科技有限公司 | Feature operation set dissemination method, device, electronic equipment and storage medium |
| CN110516035A (en) * | 2019-07-05 | 2019-11-29 | 同济大学 | A kind of man-machine interaction method and system of mixing module |
| CN110472030A (en) * | 2019-08-08 | 2019-11-19 | 网易（杭州）网络有限公司 | Man-machine interaction method, device and electronic equipment |
| CN111510566A (en) * | 2020-03-16 | 2020-08-07 | 深圳追一科技有限公司 | Method and device for determining call label, computer equipment and storage medium |
| CN111510566B (en) * | 2020-03-16 | 2021-05-28 | 深圳追一科技有限公司 | Method and device for determining call label, computer equipment and storage medium |
| CN114493164A (en) * | 2021-12-30 | 2022-05-13 | 重庆特斯联智慧科技股份有限公司 | Robot task analysis method and system based on edge calculation |
| CN114493164B (en) * | 2021-12-30 | 2024-04-09 | 重庆特斯联智慧科技股份有限公司 | Robot task analysis method and system based on edge calculation |
| CN114888804A (en) * | 2022-05-18 | 2022-08-12 | 深圳鹏行智能研究有限公司 | Robot control device and method based on working chain, medium and robot |
| CN114888804B (en) * | 2022-05-18 | 2024-03-12 | 深圳鹏行智能研究有限公司 | Robot control device and method based on working chain, medium and robot |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020038251A1 (en) | 2020-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145100A (en) | A kind of the Task customer service robot system and its working method of customizable process | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN109635117A (en) | A kind of knowledge based spectrum recognition user intention method and device | |
| CN111144723A (en) | Method and system for recommending people's job matching and storage medium | |
| CN107153965A (en) | A kind of intelligent customer service solution of multiple terminals | |
| US20120330662A1 (en) | Input supporting system, method and program | |
| US20040158562A1 (en) | Data quality system | |
| CN110633960A (en) | Human resource intelligent matching and recommending method based on big data | |
| CN106378781A (en) | Service robot guide system and method | |
| CN109598517B (en) | Commodity clearance processing, object processing and category prediction method and device thereof | |
| KR102210504B1 (en) | System of customized education program using ai education platform based on big data | |
| CN111105209A (en) | Job resume matching method and device suitable for post matching recommendation system | |
| CN110309182A (en) | A kind of information input method and device | |
| CN112380870A (en) | User intention analysis method and device, electronic equipment and computer storage medium | |
| CN111797202B (en) | Customer service conversation method based on artificial intelligence | |
| CN110381115B (en) | Information pushing method and device, computer readable storage medium and computer equipment | |
| CN110489198A (en) | A kind of method and system of worksheet | |
| CN103593412A (en) | Tree-structure-based question answering system and method | |
| CN110377743B (en) | Text labeling method and device | |
| CN108961082A (en) | A kind of vehicle insurance loss assessment system and method based on AI image recognition | |
| CN115564393A (en) | Recruitment requirement similarity-based job recommendation method | |
| CN112507092A (en) | Implementation method for completing work order intelligent filling function based on AI text robot | |
| CN111062220A (en) | End-to-end intention recognition system and method based on memory forgetting device | |
| CN112434501A (en) | Work order intelligent generation method and device, electronic equipment and medium | |
| CN110929108A (en) | Inquiring method and system for railway passenger transport service and robot |
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: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |