CN108345644A - A kind of method and device of data processing - Google Patents
A kind of method and device of data processing Download PDFInfo
- Publication number
- CN108345644A CN108345644A CN201810035851.8A CN201810035851A CN108345644A CN 108345644 A CN108345644 A CN 108345644A CN 201810035851 A CN201810035851 A CN 201810035851A CN 108345644 A CN108345644 A CN 108345644A
- Authority
- CN
- China
- Prior art keywords
- question sentence
- standard
- user
- sentence
- question
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Abstract
This application discloses a kind of method and devices of data processing, user's question sentence is fished for from dialog history, according to each standard question sentence in standard exam pool, user's question sentence with any standard question matching in each user's question sentence is added in standard exam pool, it will be stored as pending question sentence with the unmatched user's question sentence of each standard question sentence, standard question sentence is determined further according to each pending question sentence, the standard question sentence determined is added in the standard exam pool later.
Description
Technical field
This application involves information technology field more particularly to a kind of method and devices of data processing.
Background technology
Online customer service is often referred to the form by instant messaging, provides the customer service form of service to the user.And it is usually online
Customer service in the user's question sentence for receiving client, can first according to common problem answer (Frequently Asked Questions,
FAQ), judge user's question sentence that user is proposed whether with standard question matching, if so, matched standard question sentence is corresponding
Model answer returns, if it is not, artificial customer service of then transferring continues offer service.
In the prior art, FAQ usually may include：Include the standard exam pool of various typical problem collection, and corresponding each mark
The model answer of quasi- problem set.Wherein, each typical problem collection also may include different form, but correspond to identical standard answer
Standard question sentence.For example, " It's lovely day", " how is weather", " today rain", " telling me weather " belong to mark
Quasi- question sentence can be summarized under the same typical problem collection (e.g., " weather forecast "), and the corresponding same model answer.Cause
Standard exam pool, can be considered as the problem of being made of multiple typical problem collection library, as shown in Figure 1 by this.Wherein, it is seen then that standard exam pool
In include 1~n typical problem collection, it includes multiple standard question sentences that each typical problem, which is concentrated,
The problem of due to client usually has the place communicated can largely save people by using the method for FAQ
The manpower demand of work customer service, and can quickly answer user's FAQs of proposition.
As it can be seen that a parts of the FAQ as customer service system, there is the important function of shunting user.And with operation expanding etc.
The influence of factor, the demand of user may be to change at any time, that is to say, that the problem of user often asks may be continually changing.
Therefore, the uniform title to FAQ is needed in order to make the standard exam pool in FAQ adapt to the question and answer demand of user in the prior art
Library is adjusted and expands.
But when standard exam pool being adjusted and expanded in the prior art, mainly by manually to receives frequency
The method that higher user's question sentence is aggregated determines the standard question sentence for needing to be added in standard exam pool.Therefore, it is necessary to
A kind of new data processing method, to improve the maintenance efficiency to standard exam pool.
Invention content
This specification embodiment provides a kind of method and device of data processing, is needed for solving existing FAQ standards exam pool
Manual maintenance is wanted, the problem that efficiency is low is caused.
This specification embodiment uses following technical proposals：
A kind of method of data processing, including：
Each user's question sentence is fished for from dialog history；
For each user's question sentence fished for, it whether there is the standard with user's question matching in criterion exam pool
Question sentence；
If so, being added to user's question sentence as standard question sentence in the standard exam pool；
If it is not, then being stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence,
The standard question sentence determined is added in the standard exam pool.
A kind of device of data processing, including：
Module is fished for, each user's question sentence is fished for from dialog history；
Judging treatmenting module whether there is and the user for each user's question sentence fished in criterion exam pool
The standard question sentence of question matching, if so, be added to user's question sentence as standard question sentence in the standard exam pool, if it is not,
It is then stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence, the mark that will be determined
Quasi- question sentence is added in the standard exam pool.
A kind of server, wherein the server includes：One or more processors and memory, memory are stored with
Program, and be configured to execute following steps by one or more processors：
Each user's question sentence is fished for from dialog history；
For each user's question sentence fished for, it whether there is the standard with user's question matching in criterion exam pool
Question sentence；
If so, being added to user's question sentence as standard question sentence in the standard exam pool；
If it is not, then being stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence,
The standard question sentence determined is added in the standard exam pool.
Above-mentioned at least one technical solution that this specification embodiment uses can reach following advantageous effect：
The method and device provided by this specification, fishes for user's question sentence, according in standard exam pool from dialog history
Each standard question sentence, user's question sentence with any standard question matching in each user's question sentence is added in standard exam pool, will be with
The unmatched user's question sentence of each standard question sentence is stored as pending question sentence, determines standard further according to each pending question sentence later
The standard question sentence determined is added in the standard exam pool by question sentence.By by with user's question sentence of standard question matching simultaneously
It is added in standard exam pool, the standard question sentence that standard exam pool Plays problem set includes can be expanded, expanding standard exam pool can cover
User's question sentence of lid.In addition, for the unmatched user's question sentence (that is, pending question sentence) of existing each standard question sentence, also
Typical problem collection, the typical problem collection number of extension standards exam pool can be created by determining standard question sentence from each pending question sentence
Amount.While reducing the cost of standard exam pool of manual maintenance FAQ, the update efficiency of standard question sentence is also improved, mark is improved
The maintenance efficiency in construction problem library.
Description of the drawings
Attached drawing described herein is used for providing further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please do not constitute the improper restriction to the application for explaining the application.In the accompanying drawings：
Fig. 1 is the composed structure schematic diagram of existing standard exam pool；
Fig. 2 is a kind of process for data processing that this specification embodiment provides；
Fig. 3 is the schematic diagram that standard question sentence is determined according to each pending question sentence that this specification provides；
Fig. 4 is a kind of structural schematic diagram for data processing equipment that this specification embodiment provides；
Fig. 5 is a kind of structural schematic diagram for server that this specification embodiment provides.
Specific implementation mode
To keep the purpose, technical scheme and advantage of this specification clearer, it is embodied below in conjunction with this specification
Technical scheme is clearly and completely described in example and corresponding attached drawing.Obviously, described embodiment is only this Shen
Please a part of the embodiment, instead of all the embodiments.Based on the embodiment in specification, those of ordinary skill in the art are not having
There is the every other embodiment obtained under the premise of making creative work, shall fall in the protection scope of this application.
Below in conjunction with attached drawing, the technical solution that each embodiment of the application provides is described in detail.
Fig. 2 is a kind of process for data processing that specification embodiment provides, and specifically may include following steps：
S100：Each user's question sentence is fished for from dialog history.
In this specification one or more embodiment, which can be to determine standard question sentence and be added to
Process in the standard exam pool of FQA, and the user that standard question sentence is usually all the user's enquirement received by customer service system asks
What sentence determined, therefore in the present specification, can the data handling procedure be executed by the server of customer service system.
And in order to make the standard question sentence in standard exam pool, it is more bonded the demand of user, which can make from user
In user's question sentence used in being putd question to when customer service system, the standard question sentence being added in standard exam pool is determined.Therefore, it takes first
Business device can fish for each user's question sentence being most recently received from dialog history.
Specifically, in the present specification, server can be according to the preset time cycle, from the dialog history of customer service system
In, the question sentence that the user received in a nearest time cycle sends is fished for, as user's question sentence.Wherein, the time cycle
It can be configured (e.g., 15 minutes) as needed, this specification does not limit this.
In addition, due to include in the dialog history of customer service system the proposition for not only having user the problem of question sentence, may be used also
Can include sentence when exchange between user and customer service, therefore server is in determination user's question sentence from dialog history, it can be with
According to statement analytical method, determine the sentence for belonging to question sentence as user's question sentence from dialog history.
Further, in the present specification, server, can also be according to screening when determining user's question sentence from dialog history
Rule screens each user's question sentence, determines user's question sentence that data processing is carried out in subsequent step.Wherein, which advises
Then it may include：The question sentence etc. that question sentence of the selection comprising keyword, selection are sent by specified geographic location.
For example, it is assumed that the keyword is the title of some business, then the user that server is screened according to the keyword
The problem of question sentence, usually user is directed to the proposition of the business.Or, it is assumed that the keyword is the adjective of event (e.g., without anti-
Answer, no response), then the question sentence screened can be enquirement of the user for the event occurred in process of service execution.Alternatively,
Assuming that when the screening rule is the question sentence that specified geographic location is sent, what is obtained by screening can be that a certain regional user proposes
The problem of.
Certainly in the present specification, which can specifically be configured as needed, and this specification does not limit this
It is fixed.
S102：For each user's question sentence fished for, whether there is and user's question matching in criterion exam pool
Standard question sentence, if so, step S104 is executed, if it is not, executing step S106.
In the present specification, after server fishes for each user's question sentence, can classify to each user's question sentence, really
User's question sentence of any standard question matching fixed and in standard exam pool, and not with each standard question sentence in standard exam pool
The user's question sentence matched, and execute different steps for user's question sentence of different classifications.
Specifically, server can be directed to the user's question sentence each fished for, whether there is and the use in criterion exam pool
The standard question sentence of family question matching, and different steps is executed according to judging result.Wherein, it is similar that character string can be used in server
Algorithm is spent, the similarity of user's question sentence and each standard question sentence in standard exam pool is calculated, and judges whether that similarity is fallen
Enter the standard question sentence of pre-set interval, and if it exists, then determine that the similarity with user's question sentence falls into the standard question sentence of pre-set interval
With user's question matching, if not, it is determined that be not present and the unmatched standard question sentence of user's question sentence.
The pre-set interval of the similarity can be configured as needed, and such as 80% to 90%, 90% to 99% etc., this theory
Bright book does not limit this.Since the similarity between identical sentence is 100%, therefore when user's question sentence and standard question sentence
When similarity is more than the upper limit of the pre-set interval, server can determine that user's question sentence and the standard question sentence are identical languages
Sentence.And identical sentence is repeated to be added in standard exam pool smaller to expanding the contribution of standard exam pool, and also result in standard
Exam pool is too fat to move, therefore passes through and pre-set interval is arranged, it may be determined that and it is not only similar to standard question sentence, but also the user different from standard question sentence ask
Sentence.
Certainly, the upper limit of the pre-set interval may be alternatively provided as 100%, then at this point, server is determining exist and the user
After the standard question sentence of question matching, it is also necessary to user's question sentence carry out duplicate removal processing, that is, judge user's question sentence and with its
Whether the standard question sentence matched is identical, and subsequent processing is carried out (that is, not using the sentence repeated as adding if so, not asking the user
It is added in standard exam pool), if it is not, thening follow the steps S104.
That is, can determine and standard question sentence similar import, but different user by step S102 servers
Sentence executes step S104.
S104：It is added to user's question sentence as standard question sentence in the standard exam pool.
It, can should after server determines user's question sentence with standard question matching in this specification embodiment
User's question sentence is added in standard exam pool.
Specifically, since usual standard exam pool can be made of several typical problem collection, and each typical problem collection Bao Kehan
At least one standard question sentence, as shown in Figure 1.Therefore, server can determine belonging to the standard question sentence with user's question matching
Typical problem collection, and the standard question sentence that user's question sentence is concentrated as the typical problem, are added in the standard exam pool.
That is which typical problem collection the matched standard question sentence belongs to, then server is just using user's question sentence as which standard
The standard question sentence of problem set is added in standard exam pool.
For example, it is assumed that server determines that user's question sentence b is matched with standard question sentence c, and standard question sentence c is typical problem collection A
In include standard question sentence, then server can be added to user's question sentence b as the quasi- question sentence of newly subscripting in typical problem collection A
In standard exam pool.
S106：It is stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence, it will
The standard question sentence determined is added in the standard exam pool.
In this specification embodiment, when server does not determine each standard question sentence in user's question sentence and standard exam pool not
Timing can be stored using user's question sentence as pending question sentence, then be handled.
Specifically, the pending question sentence can be stored in database by server, alternatively, server can also be asked pending
Sentence is stored in caching, and this specification does not limit how server specifically stores each pending question sentence.
In addition, usually there are a variety of situations for each pending question sentence.It is asked for example, pending question sentence is the unexpected winner that user proposes
Topic, that is, the problem of seldom user proposition, it is evident that matched standard question sentence is not had in standard exam pool, and or
Person has lacked the standard question sentence of certain a kind of user Chang Wen in standard exam pool, it is also possible to although lead to that user proposes is not
Belong to user's question sentence of unexpected winner problem, but matched standard question sentence is also not present in standard exam pool, then by the user
Question sentence is stored as pending question sentence.
For belonging to the pending question sentence of unexpected winner problem, the demand not being added in standard exam pool, therefore server can
Without processing.And for causing user's question sentence not have for the case where matched standard question sentence due to the missing of standard exam pool,
Server can also determine to need to be added to the standard question sentence in standard exam pool according to stored each pending question sentence, to expand
Improve standard exam pool.
Then, in the present specification, in order to determine that standard question sentence improves standard exam pool to expand from each pending question sentence,
Server can also carry out following steps, as shown in Figure 3：
S1061：Judge whether the data volume of stored each pending question sentence reaches threshold value, if so, thening follow the steps
S1062, if it is not, thening follow the steps S1063.
Due to each pending question sentence for belonging to unexpected winner problem, similarity between this kind of pending question sentence usually compared with
It is low, and quantity is also less, and for each pending question sentence for belonging to user Chang Wen, it is similar between this kind of pending question sentence
Degree is higher, and quantity is also more, therefore visible only when the quantity of pending question sentence is enough, just can be accurately from respectively waiting for
It handles and determines standard question sentence in question sentence.Then, server can judge which step of subsequent execution according to threshold value, wherein the door
Limit value can be configured this specification as needed and not limit, for example, 200,500 etc..
Specifically, due in the step s 100, server can temporally the period fished for user's question sentence, and to fishing for
Each user's question sentence judge during, may constantly there is user's question sentence to be stored as pending question sentence, therefore be
Reduction resource consumption, server can be after all user's question sentences fished for step S100 all judge, then execute step
S1061.That is, ought determine institute's question sentence to be handled in each user's question sentence that step S100 is fished for and then execute step
S1061。
S1062：Clustering processing is carried out to each pending question sentence, determines at least one pending question sentence collection that cluster obtains
It closes.
In the present specification, as described in step S1061, when in each pending question sentence there are when the question sentence of user Chang Wen,
Similarity between this kind of pending question sentence often asked is usually higher, therefore server can be by between each pending question sentence of calculating
Similarity, clustering processing is carried out to each pending question sentence.And if in each pending question sentence, pending there are user Chang Wen is asked
, then server can determine at least one pending question sentence set for clustering and obtaining.
Specifically, server can carry out each pending question sentence clustering processing, and waited for according to the determination of preset cluster radius
Handle question sentence set.Certainly, if the pending question sentence of user Chang Wen is not present in each pending question sentence, server can not pass through
Clustering processing determines pending question sentence set, then can no longer carry out subsequent processing.Wherein, cluster radius can be set as needed
This specification is set not limit this.
It should be noted which kind of clustering processing method Limited service device does not use in this specification, server can needle
To each pending question sentence, the similarity between the pending question sentence and other pending question sentences is calculated, and according to being calculated
Each similarity, determine the similarity vector of the pending question sentence.In turn, when the similarity vector for determining each pending question sentence
Afterwards, each pending question sentence is determined in vector space, is finally used clustering processing method, is determined each cluster centre.
S1063：Standard question sentence is determined not from each pending question sentence.
In the present specification, when the quantity of pending question sentence is not higher than threshold value, then it can determine and be not necessarily to from each pending
Standard question sentence is determined in question sentence.
S1064：From each pending question sentence set, determine that the quantity of pending question sentence reaches the pending of specified quantity and asks
Sentence set.
In the present specification, server can be directed to and each of determine pending question sentence set, judge the pending question sentence
In set whether the quantity of pending question sentence reaches specified quantity, and the quantity of pending question sentence is reached specified quantity and waits locating
The pending question sentence in question sentence set is managed as standard question sentence.Wherein, specified quantity can be configured as needed.
Due to, there may be the higher problems of similarity between unexpected winner problem, still, the pending question sentence of unexpected winner problem class
Quantity may be less.Therefore, for server for each pending question sentence set determined, can be judged according to the specified quantity should
Pending question sentence set whether be unexpected winner problem class pending question sentence set.When pending in pending question sentence set is asked
When the quantity of sentence reaches specified quantity, it may be determined that the pending question sentence set is not the collection of the pending question sentence of unexpected winner problem class
It closes, then it can be using the pending question sentence in the pending question sentence set as standard question sentence.
In the present specification, server can also reach the pending question sentence collection of specified quantity according to the quantity of pending question sentence
It closes, creates typical problem collection, the typical problem collection of establishment is added in the standard exam pool.That is, this is pending
Question sentence set is as the typical problem collection newly created.
Certainly, the newly-built typical problem collection is added to uniform title since in the present specification, server only determines
In library, and the model answer of the newly-built standard exam pool can be by being manually arranged.
Based on data handling procedure shown in Fig. 2, server can be by periodically fishing for user's question sentence, with therefrom true
Fixed user's question sentence with existing standard question matching is added in standard exam pool, with the standard in abundant and expansion standard exam pool
Question sentence, and for all unmatched user's question sentence of each standard question sentence, can also be by the method for cluster, from each pending question sentence
It determines new typical problem collection, is added in standard exam pool.When solving the prior art by manual maintenance standard exam pool, efficiency
Low problem.
In addition, since there is also peak period and low ebb phases for the busy extent of usual customer service system, and when the low ebb phase
The quantity of the user's question sentence received in predetermined period may be less, so in order to reduce resource consumption, server is executing step
Before rapid S102, it also can determine whether the quantity for the user's question sentence fished for is more than predetermined threshold value, if so, continuing to execute step
S102, if it is not, then store each user's question sentence fished for as temporary question sentence, also, the number of each temporary question sentence when storage
When amount is more than the predetermined threshold value, each temporary question sentence of storage is re-used as to each user's question sentence fished for, and execute step
S102, that is, for each user's question sentence fished for, whether there is the standard with user's question matching in criterion exam pool
Question sentence.
Further, it is considered as being made of multiple typical problem collection due to standard exam pool, if all standards are asked
Topic collection is all configured in customer service system application of reaching the standard grade, then may cause customer service system after receiving user's question sentence, need by
User's question sentence is matched with a large amount of standard question sentence, leads to system low-response.Therefore each standard usually in standard exam pool
Problem set not all reach the standard grade by configuration, but meeting selected section typical problem collection is configured in customer service system application of reaching the standard grade.
Therefore in the present specification, in order to accelerate system response time, typical problem is being added to uniform title by server
After in library, each typical problem collection that can be directed in standard exam pool determines that each standard that the typical problem collection includes is asked
The calling frequency of sentence, as total calling frequency of the typical problem collection, later further according to total calling frequency of each typical problem collection,
It reselects at least partly typical problem collection and is configured in customer service system application of reaching the standard grade.For example, server can be according to preset ratio
Example (e.g., 40%) calls the sequence of frequency from high to low according to the total of each typical problem collection, selects always to call the highest portion of frequency
The quasi- problem set of minute mark or server also can be according to preset quantity (e.g., 10), according to total calling frequency of each typical problem collection
The sequence of rate from high to low selects total calling highest part of standards problem set of frequency, and how this specification is for according to each mark
Total calling frequency of quasi- problem set, selection criteria problem set do not limit.
Wherein, the calling frequency of standard question sentence can be determined according to the matching result of each user's question sentence and each standard question sentence.That is,
By being determined with the quantity of user's question sentence of the standard question matching in the unit interval.Namely whenever there are one user's question sentence with
When the standard question matching, just determine that the standard question sentence is called primary.
Further, due to the expansion with standard exam pool Plays question sentence, each typical problem concentrates the mark for including
The quantity of quasi- question sentence is constantly expanding, therefore the same each standard question sentence for respectively configuring the typical problem concentration reached the standard grade is also not all
Configuration is reached the standard grade, but meeting selected section standard question sentence is configured in customer service system application of reaching the standard grade.
In the present specification, the number of matched standard question sentence is needed to reduce customer service system when receiving user's question sentence
Amount, server are reselecting after at least partly typical problem collection is configured in customer service system application of reaching the standard grade, and can be directed to each
The typical problem collection reselected determines that the typical problem concentrates the calling frequency of each standard question sentence, and according to the typical problem
The calling frequency of each standard question sentence is concentrated, at least partly standard question sentence is selected to be configured in customer service system application of reaching the standard grade.Also, this
Specification is not for how according to the calling frequency of each standard question sentence, selection criteria question sentence limits.
It should be noted that the executive agent of each step of this specification embodiment institute providing method may each be same and set
It is standby, alternatively, this method also can be by distinct device as executive agent.For example, the executive agent of step S100 and step S102 can
Think equipment 1, the executive agent of step S102 can be equipment 2；Alternatively, the executive agent of step S100 can be equipment 1, step
The executive agent of rapid S102 and step S104 can be equipment 2；Etc..It is above-mentioned that this specification specific embodiment is retouched
It states.Other embodiments are within the scope of the appended claims.In some cases, the action recorded in detail in the claims or
Step can be according to executing different from the sequence in embodiment and desired result still may be implemented.In addition, in attached drawing
The process of middle description, which not necessarily requires the particular order shown or consecutive order, could realize desired result.In certain implementations
In mode, multitasking and parallel processing is also possible or it may be advantageous.
Based on the method for data processing shown in Fig. 2, this specification embodiment also provides a kind of data processing equipment, such as schemes
Shown in 4.
Fig. 4 is a kind of structural schematic diagram for data processing equipment that this specification embodiment provides, and described device includes：
Module 200 is fished for, each user's question sentence is fished for from dialog history；
Judging treatmenting module 202 whether there is and the use for each user's question sentence fished in criterion exam pool
The standard question sentence of family question matching, if so, be added to user's question sentence as standard question sentence in the standard exam pool, if
It is no, then it is stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence, by what is determined
Standard question sentence is added in the standard exam pool.
It is described to fish for module 200, according to the preset time cycle, it is inscribed that a upper time cycle was fished for from dialog history
The user's question sentence received.
The judging treatmenting module 202, for each user's question sentence fished for, in criterion exam pool with the presence or absence of with
Before the standard question sentence of user's question matching, judge whether the quantity for each user's question sentence fished for is more than predetermined threshold value, if
It is then to be directed to each user's question sentence fished for, is asked with the presence or absence of the standard with user's question matching in criterion exam pool
Sentence, if it is not, then storing each user's question sentence fished for as temporary question sentence, until the quantity of each temporary question sentence of storage is more than
When the predetermined threshold value, each temporary question sentence of storage is re-used as to each user's question sentence fished for, and every for fishing for
A user's question sentence, with the presence or absence of judging treatmenting module described in the standard question sentence with user's question matching in criterion exam pool.
The judging treatmenting module 202 calculates each standard question sentence in the standard exam pool according to similarity of character string algorithm
With the similarity of user's question sentence, judge whether that the similarity with user's question sentence falls into the standard question sentence of pre-set interval.
The standard exam pool is made of several typical problem collection, and each typical problem collection includes at least one standard question sentence,
The judging treatmenting module 202 determines the typical problem collection belonging to the standard question sentence with user's question matching, which is asked
The standard question sentence that sentence is concentrated as the typical problem, is added in the standard exam pool.
The judging treatmenting module 202, the judging treatmenting module carry out clustering processing to each pending question sentence, determine
It clusters obtained at least one pending question sentence set and determines that the quantity of pending question sentence reaches from each pending question sentence set
To the pending question sentence set of specified quantity.
The judging treatmenting module 202 reaches the pending question sentence set of specified quantity according to the quantity of pending question sentence,
Typical problem collection is created, the typical problem collection of establishment is added in the standard exam pool.
The judging treatmenting module 202 fishes for each user's question sentence, wherein described according to screening rule from dialog history
Screening rule includes：At least one of the question sentence that question sentence of the selection comprising keyword, selection are sent by specified geographic location.
Described device further includes：
Wire module 204 in configuration, after standard question sentence is added in the standard exam pool by the judging treatmenting module,
According to the matching result of each user's question sentence and each standard question sentence, the calling frequency of each standard question sentence is determined, according to each standard question sentence
Calling frequency, determine total calling frequency of each typical problem collection, according to total calling frequency of each typical problem collection, redefine
The typical problem collection being configured on line.
Wire module 204 in the configuration, for each typical problem collection reconfigured on line, according to the typical problem
The calling frequency for each standard question sentence that concentration includes, redefines and is configured to standard question sentence on line.
Based on the method for the data processing described in Fig. 2, this specification, which corresponds to, provides a kind of server, as shown in figure 5, its
In, the server includes：One or more processors and memory, memory have program stored therein, and are configured to by one
A or multiple processors execute following steps：
Each user's question sentence is fished for from dialog history；
For each user's question sentence fished for, it whether there is the standard with user's question matching in criterion exam pool
Question sentence；
If so, being added to user's question sentence as standard question sentence in the standard exam pool；
If it is not, then being stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence,
The standard question sentence determined is added in the standard exam pool.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " patrols
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method flow can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, application-specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller includes but not limited to following microcontroller
Device：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained in the form of logic gate, switch, application-specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc. to come in fact
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit is realized can in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, the present invention can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology realizes information storage.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or other magnetic storage apparatus
Or any other non-transmission medium, it can be used for storage and can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Including so that process, method, commodity or equipment including a series of elements include not only those elements, but also wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that wanted including described
There is also other identical elements in the process of element, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Usually, program module includes routines performing specific tasks or implementing specific abstract data types, program, object, group
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage device.
Each embodiment in this specification is described in a progressive manner, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method
Part explanation.
Above is only an example of the present application, it is not intended to limit this application.For those skilled in the art
For, the application can have various modifications and variations.It is all within spirit herein and principle made by any modification, equivalent
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (21)
1. a kind of method of data processing, including：
Each user's question sentence is fished for from dialog history；
For each user's question sentence fished for, asked with the presence or absence of the standard with user's question matching in criterion exam pool
Sentence；
If so, being added to user's question sentence as standard question sentence in the standard exam pool；
If it is not, then being stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence, it will be true
The standard question sentence made is added in the standard exam pool.
2. the method as described in claim 1 is fished for each user's question sentence from dialog history, is specifically included：
According to the preset time cycle, from fishing for the user's question sentence received in a upper time cycle in dialog history.
3. the method as described in claim 1, for each user's question sentence fished for, in criterion exam pool with the presence or absence of with
Before the standard question sentence of user's question matching, the method further includes：
Judge whether the quantity for each user's question sentence fished for is more than predetermined threshold value；
If so, for each user's question sentence fished for, whether there is and user's question matching in criterion exam pool
Standard question sentence；
If it is not, then each user's question sentence fished for is stored as temporary question sentence, until the quantity of each temporary question sentence of storage is big
When the predetermined threshold value, each temporary question sentence of storage is re-used as to each user's question sentence fished for, and for fishing for
Each user's question sentence, with the presence or absence of the standard question sentence with user's question matching in criterion exam pool.
4. the method as described in claim 1, with the presence or absence of the standard question sentence with user's question matching in criterion exam pool,
It specifically includes：
According to similarity of character string algorithm, the similarity of each standard question sentence and user's question sentence in the standard exam pool is calculated；
Judge whether that the similarity with user's question sentence falls into the standard question sentence of pre-set interval.
5. method as claimed in claim 4, the standard exam pool is made of several typical problem collection, each typical problem Ji Bao
Containing at least one standard question sentence；
It is added in the standard exam pool, specifically includes using user's question sentence as standard question sentence：
Determine the typical problem collection belonging to the standard question sentence with user's question matching；
The standard question sentence that user's question sentence is concentrated as the typical problem is added in the standard exam pool.
6. method as claimed in claim 5, and standard question sentence is determined according to each pending question sentence, it specifically includes：
Clustering processing is carried out to each pending question sentence, determines at least one pending question sentence set that cluster obtains；
From each pending question sentence set, determine that the quantity of pending question sentence reaches the pending question sentence set of specified quantity.
7. method as claimed in claim 6, the standard question sentence determined is added in the standard exam pool, specifically include：
Reach the pending question sentence set of specified quantity according to the quantity of pending question sentence, typical problem collection is created, by establishment
Typical problem collection is added in the standard exam pool.
8. the method as described in claim 1 is fished for each user's question sentence from dialog history, is specifically included：
According to screening rule, each user's question sentence is fished for from dialog history；
Wherein, the screening rule includes：The question sentence that question sentence of the selection comprising keyword, selection are sent by specified geographic location
At least one of.
9. method as claimed in claim 5, after standard question sentence is added in the standard exam pool, the method is also wrapped
It includes：
According to the matching result of each user's question sentence and each standard question sentence, the calling frequency of each standard question sentence is determined；
According to the calling frequency of each standard question sentence, total calling frequency of each typical problem collection is determined；
According to total calling frequency of each typical problem collection, the typical problem collection being configured on line is redefined.
10. method as claimed in claim 9, after redefining the typical problem collection for being configured to and being applied on line, the method
Further include：
For each typical problem collection reconfigured on line, the tune for each standard question sentence for including is concentrated according to the typical problem
With frequency, redefines and be configured to standard question sentence on line.
11. a kind of device of data processing, including：
Module is fished for, each user's question sentence is fished for from dialog history；
Judging treatmenting module whether there is and user's question sentence for each user's question sentence fished in criterion exam pool
Matched standard question sentence, if so, being added to user's question sentence as standard question sentence in the standard exam pool, if it is not, then will
User's question sentence is stored as pending question sentence, and determines standard question sentence according to each pending question sentence, and the standard determined is asked
Sentence is added in the standard exam pool.
12. device as claimed in claim 11, described to fish for module, according to the preset time cycle, dragged for from dialog history
Take the user's question sentence received in a time cycle.
13. device as claimed in claim 11, the judging treatmenting module judges for each user's question sentence fished for
With the presence or absence of with before the standard question sentence of user's question matching in standard exam pool, the quantity for each user's question sentence fished for is judged
Whether it is more than predetermined threshold value, if so, for each user's question sentence fished for, whether there is and the use in criterion exam pool
The standard question sentence of family question matching, if it is not, then storing each user's question sentence fished for as temporary question sentence, until storage is each
When the quantity of temporary question sentence is more than the predetermined threshold value, each temporary question sentence of storage is re-used as each user fished for and is asked
Sentence, and it is directed to each user's question sentence fished for, it is asked with the presence or absence of the standard with user's question matching in criterion exam pool
Sentence.
14. device as claimed in claim 11, the judging treatmenting module, according to similarity of character string algorithm, described in calculating
The similarity of each standard question sentence and user's question sentence in standard exam pool judges whether that the similarity with user's question sentence is fallen into
The standard question sentence of pre-set interval.
15. device as claimed in claim 14, the standard exam pool is made of several typical problem collection, each typical problem collection
Including at least one standard question sentence, the judging treatmenting module determine the mark belonging to the standard question sentence with user's question matching
Quasi- problem set, the standard question sentence which is concentrated as the typical problem are added in the standard exam pool.
16. device as claimed in claim 15, the judging treatmenting module carry out clustering processing, really to each pending question sentence
Obtained at least one pending question sentence set is clustered calmly determines the quantity of pending question sentence from each pending question sentence set
Reach the pending question sentence set of specified quantity.
17. device as claimed in claim 16, the judging treatmenting module reach specified number according to the quantity of pending question sentence
The pending question sentence set of amount creates typical problem collection, the typical problem collection of establishment is added in the standard exam pool.
18. device as claimed in claim 11, the judging treatmenting module is fished for according to screening rule from dialog history
Each user's question sentence, wherein the screening rule includes：Question sentence of the selection comprising keyword, selection are sent out by specified geographic location
At least one of question sentence sent.
19. device as claimed in claim 15, described device further include：
Wire module in configuration, after standard question sentence is added in the standard exam pool by the judging treatmenting module, according to each
The matching result of user's question sentence and each standard question sentence determines the calling frequency of each standard question sentence, according to the calling of each standard question sentence
Frequency determines total calling frequency of each typical problem collection, according to total calling frequency of each typical problem collection, redefines and is configured to
Typical problem collection on line.
20. device as claimed in claim 19, wire module in the configuration is asked for each standard reconfigured on line
Topic collection, the calling frequency for each standard question sentence for including is concentrated according to the typical problem, redefines and is configured to standard question sentence on line.
21. a kind of server, wherein the server includes：One or more processors and memory, memory are stored with journey
Sequence, and be configured to execute following steps by one or more processors：
Each user's question sentence is fished for from dialog history；
For each user's question sentence fished for, asked with the presence or absence of the standard with user's question matching in criterion exam pool
Sentence；
If so, being added to user's question sentence as standard question sentence in the standard exam pool；
If it is not, then being stored using user's question sentence as pending question sentence, and standard question sentence is determined according to each pending question sentence, it will be true
The standard question sentence made is added in the standard exam pool.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810035851.8A CN108345644A (en) | 2018-01-15 | 2018-01-15 | A kind of method and device of data processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810035851.8A CN108345644A (en) | 2018-01-15 | 2018-01-15 | A kind of method and device of data processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108345644A true CN108345644A (en) | 2018-07-31 |
Family
ID=62961540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810035851.8A Pending CN108345644A (en) | 2018-01-15 | 2018-01-15 | A kind of method and device of data processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108345644A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109101239A (en) * | 2018-08-30 | 2018-12-28 | 杭州电子科技大学 | A kind of model answer generation method of the automatic decision system of online Verilog code |
| CN109857846A (en) * | 2019-01-07 | 2019-06-07 | 阿里巴巴集团控股有限公司 | The matching process and device of user's question sentence and knowledge point |
| CN109947927A (en) * | 2019-03-31 | 2019-06-28 | 联想(北京)有限公司 | A kind of information processing method and device |
| CN110377803A (en) * | 2019-06-14 | 2019-10-25 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN110502622A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Common medical question and answer data creation method, device and computer equipment |
| CN111159370A (en) * | 2019-12-20 | 2020-05-15 | 中国建设银行股份有限公司 | Short-session new problem generation method, storage medium and man-machine interaction device |
| CN111488442A (en) * | 2020-04-09 | 2020-08-04 | 深圳追一科技有限公司 | Data processing method, device, server and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6931398B2 (en) * | 2001-04-06 | 2005-08-16 | Fujitsu Limited | Retrieval apparatus, retrieval method and retrieval program |
| CN101201838A (en) * | 2007-08-21 | 2008-06-18 | 新百丽鞋业(深圳)有限公司 | Method for improving searching engine based on keyword index using phrase index technique |
| CN105653620A (en) * | 2015-12-25 | 2016-06-08 | 上海智臻智能网络科技股份有限公司 | Log analysis method and device of intelligent question answering system |
| CN106295807A (en) * | 2016-08-23 | 2017-01-04 | 上海智臻智能网络科技股份有限公司 | A kind of method and device of information processing |
| EP3115907A1 (en) * | 2015-07-10 | 2017-01-11 | Accenture Global Services Limited | Common data repository for improving transactional efficiencies of user interactions with a computing device |
| CN106649868A (en) * | 2016-12-30 | 2017-05-10 | 首都师范大学 | Method and device for matching between questions and answers |
-
2018
- 2018-01-15 CN CN201810035851.8A patent/CN108345644A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6931398B2 (en) * | 2001-04-06 | 2005-08-16 | Fujitsu Limited | Retrieval apparatus, retrieval method and retrieval program |
| CN101201838A (en) * | 2007-08-21 | 2008-06-18 | 新百丽鞋业(深圳)有限公司 | Method for improving searching engine based on keyword index using phrase index technique |
| EP3115907A1 (en) * | 2015-07-10 | 2017-01-11 | Accenture Global Services Limited | Common data repository for improving transactional efficiencies of user interactions with a computing device |
| CN105653620A (en) * | 2015-12-25 | 2016-06-08 | 上海智臻智能网络科技股份有限公司 | Log analysis method and device of intelligent question answering system |
| CN106295807A (en) * | 2016-08-23 | 2017-01-04 | 上海智臻智能网络科技股份有限公司 | A kind of method and device of information processing |
| CN106649868A (en) * | 2016-12-30 | 2017-05-10 | 首都师范大学 | Method and device for matching between questions and answers |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109101239A (en) * | 2018-08-30 | 2018-12-28 | 杭州电子科技大学 | A kind of model answer generation method of the automatic decision system of online Verilog code |
| CN109857846A (en) * | 2019-01-07 | 2019-06-07 | 阿里巴巴集团控股有限公司 | The matching process and device of user's question sentence and knowledge point |
| CN109857846B (en) * | 2019-01-07 | 2023-06-20 | 创新先进技术有限公司 | Method and device for matching user question and knowledge point |
| CN109947927A (en) * | 2019-03-31 | 2019-06-28 | 联想(北京)有限公司 | A kind of information processing method and device |
| CN110377803A (en) * | 2019-06-14 | 2019-10-25 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN110377803B (en) * | 2019-06-14 | 2023-04-07 | 创新先进技术有限公司 | Information processing method and device |
| CN110502622A (en) * | 2019-07-03 | 2019-11-26 | 平安科技（深圳）有限公司 | Common medical question and answer data creation method, device and computer equipment |
| CN111159370A (en) * | 2019-12-20 | 2020-05-15 | 中国建设银行股份有限公司 | Short-session new problem generation method, storage medium and man-machine interaction device |
| CN111488442A (en) * | 2020-04-09 | 2020-08-04 | 深圳追一科技有限公司 | Data processing method, device, server and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345644A (en) | A kind of method and device of data processing | |
| JP6716149B2 (en) | Blockchain-based data processing method and apparatus | |
| CN110163417B (en) | Traffic prediction method, device and equipment | |
| CN109144699A (en) | Distributed task dispatching method, apparatus and system | |
| CN108345977A (en) | A kind of method for processing business and device | |
| CN107368510B (en) | A kind of shop search ordering method and device | |
| CN109615081A (en) | A kind of Model forecast system and method | |
| CN109617829A (en) | A kind of processing method of service request data, apparatus and system | |
| CN108683692A (en) | A kind of service request processing method and device | |
| CN116167463B (en) | Distributed model training container scheduling method and device for intelligent computing | |
| CN110389842A (en) | A kind of dynamic resource allocation method, device, storage medium and equipment | |
| CN109922298A (en) | Meeting room monitoring method and device | |
| CN109284305A (en) | A kind of update method of data, apparatus and system | |
| CN108389056A (en) | A kind of determining method and device for complaining reason | |
| CN117195997B (en) | Model training method and device, storage medium and electronic equipment | |
| CN110059023A (en) | A kind of method, system and equipment refreshing cascade caching | |
| CN105868216B (en) | A kind of method, apparatus and equipment for realizing the expired operation of object | |
| CN113010312A (en) | Hyper-parameter tuning method, device and storage medium | |
| CN110032409A (en) | A kind of client screen adaptation method, device and electronic equipment | |
| CN108390914A (en) | A kind of service update method and device, system | |
| CN109886804B (en) | Task processing method and device | |
| CN116932175B (en) | Heterogeneous chip task scheduling method and device based on sequence generation | |
| CN110019260B (en) | User data updating method and related equipment | |
| CN113886033A (en) | Task processing method and device | |
| CN110046052A (en) | A kind of service calling method and 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201020 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201020 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180731 |