CN109658173A - A kind of food and beverage sevice customization method and system - Google Patents
A kind of food and beverage sevice customization method and system Download PDFInfo
- Publication number
- CN109658173A CN109658173A CN201810421841.8A CN201810421841A CN109658173A CN 109658173 A CN109658173 A CN 109658173A CN 201810421841 A CN201810421841 A CN 201810421841A CN 109658173 A CN109658173 A CN 109658173A
- Authority
- CN
- China
- Prior art keywords
- service scenarios
- food
- classification
- feature
- beverage sevice
- 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
- 235000013305 food Nutrition 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 52
- 235000013361 beverage Nutrition 0.000 title claims abstract description 48
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 37
- 238000000605 extraction Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010411 cooking Methods 0.000 description 4
- 235000012054 meals Nutrition 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of food and beverage sevice customization method and system, is related to technical field of the computer network；Existing user is solved the problems, such as using the catering information network platform is cumbersome, inefficiency.This method comprises: starting customized process when detecting trigger condition；User instruction is detected, service scenarios are identified from the user instruction that detection obtains and extracts attribute information；It is customized to generate the food and beverage sevice scheme for being directed to user according to the service scenarios and attribute information.Technical solution provided by the invention realizes the catering information service of convenient close friend.
Description
Technical field
This application involves technical field of the computer network, in particular to a kind of food and beverage sevice customization method and system.
Background technique
Current information-based food and beverage sevice is concentrated mainly on food and drink class information and provides, by the network platform by a large amount of dining rooms
Relevant information concentrates publication, in order to user query.
However, user demand be multiplicity and it is complicated, issue catering information the network platform provide service mode operate
Cumbersome, inefficiency affects user experience.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of food and beverage sevice customization method and system, to solve the prior art
Present in technological deficiency.
The embodiment of the present application discloses a kind of food and beverage sevice customization method, comprising:
When detecting trigger condition, start customized process；
User instruction is detected, service scenarios are identified from the user instruction that detection obtains and extracts attribute information；
It is customized to generate the food and beverage sevice scheme for being directed to user according to the service scenarios and attribute information.
Preferably, the user instruction includes phonetic order, this method further include:
Configure at least one service scenarios classification；
The corresponding classification mould of each service scenarios classification is identified according to the training in advance of at least one described service scenarios classification
Type, to identify corresponding service scenarios classification according to the disaggregated model.
Preferably, the disaggregated model is trained by the following method:
Training data is collected for each service scenarios classification, the training data includes a plurality of corpus；
Feature selecting is carried out to each corpus in the corresponding training data of a service scenarios classification by the verification of card side,
Select at least one feature to the service scenarios classification with discrimination；
The weighted value for calculating the feature, the vector for obtaining the feature indicate；
It is trained according to the expression of the vector of the feature, obtains the disaggregated model of the service scenarios classification.
Preferably, the detection user instruction identifies service scenarios from the user instruction that detection obtains and extracts attribute
The step of information includes:
Speech recognition is carried out to the user instruction, obtains instruction text；
Service scenarios identification is carried out to described instruction text, obtains corresponding service scenarios classification；
According to the service scenarios classification that identification obtains, attribute information is extracted by information extraction.
Preferably, according to the service scenarios and attribute information, the customized step for generating the food and beverage sevice scheme for user
Suddenly include:
According to the service scenarios and attribute information, food and drink platform is accessed, issues service request；
Obtain the food and beverage sevice scheme generated according to the service scenarios and attribute information.
Preferably, the trigger condition includes at least any or any number of combination in the following conditions:
Vice activation instruction, clicks start button.
The embodiment of the present application also discloses a kind of food and beverage sevice customization system, comprising:
Starting module, for when detecting trigger condition, starting customized process；
Service scenarios identification and information extraction module are known from the user instruction that detection obtains for detecting user instruction
Other service scenarios simultaneously extract attribute information；
Schemes generation module, for according to the service scenarios and attribute information, the customized food and drink clothes generated for user
Business scheme.
Preferably, the user instruction includes phonetic order, the system further include:
Service scenarios configuration module, for configuring at least one service scenarios classification；
Disaggregated model training module, for training to identify each service in advance according at least one described service scenarios classification
The corresponding disaggregated model of scene type, to identify corresponding service scenarios classification according to the disaggregated model.
Preferably, the disaggregated model training module includes:
Data collection module, for collecting training data for each service scenarios classification, the training data includes a plurality of
Corpus；
Characteristic filter unit, for being verified by card side to each item in the corresponding training data of a service scenarios classification
Corpus carries out feature selecting, selects at least one feature to the service scenarios classification with discrimination；
Feature weight computing unit, for calculating the weighted value of the feature, the vector for obtaining the feature is indicated；
Model training unit obtains the service scenarios classification for being trained according to the expression of the vector of the feature
Disaggregated model.
The embodiment of the present application also discloses a kind of calculating equipment, including memory, processor and storage are on a memory simultaneously
The computer instruction that can be run on a processor, the processor realize such as the customized side of above-mentioned food and beverage sevice when executing described instruction
The step of method.
The embodiment of the present application also discloses a kind of computer readable storage medium, is stored with computer instruction, the instruction
It realizes when being executed by processor such as the step of above-mentioned food and beverage sevice customization method.
Food and beverage sevice customization method provided by the present application and system start customized process, open when detecting trigger condition
User instruction is detected after moving customized process, service scenarios are identified from the user instruction that detection obtains and extracts attribute information, then
It is customized to generate the food and beverage sevice scheme for being directed to user according to the service scenarios and attribute information.It solves existing user to use
The problem of catering information network platform is cumbersome, inefficiency, realizes the catering information service of convenient close friend.
Detailed description of the invention
Fig. 1 is a kind of flow diagram for food and beverage sevice customization method that the embodiment of the present invention provides；
Fig. 2 is the idiographic flow schematic diagram of the step 102 in Fig. 1；
Fig. 3 is the idiographic flow schematic diagram of the step 104 in Fig. 1；
Fig. 4 is the idiographic flow schematic diagram of the step 105 in Fig. 1；
Fig. 5 is a kind of configuration diagram for food and beverage sevice customization system that the embodiment of the present invention provides；
Fig. 6 is the structural schematic diagram of disaggregated model training module 505 in Fig. 5.
Specific embodiment
Many details are explained in the following description in order to fully understand the application.But the application can be with
Much it is different from other way described herein to implement, those skilled in the art can be without prejudice to the application intension the case where
Under do similar popularization, therefore the application is not limited by following public specific implementation.
Current information-based food and beverage sevice is concentrated mainly on food and drink class information and provides, by the network platform by a large amount of dining rooms
Relevant information concentrates publication, in order to user query.
However, user demand be multiplicity and it is complicated, issue catering information the network platform provide service mode operate
Cumbersome, inefficiency affects user experience.
To solve the above-mentioned problems, the embodiment provides a kind of food and beverage sevice customization method and systems.According to
User instruction, be the customized food and beverage sevice scheme of user, solve existing user using the catering information network platform it is cumbersome, effect
The low problem of rate realizes the catering information service of convenient close friend.
In recent years, pass of human-computer dialogue due to its huge potentiality and tempting commercial value by more and more researchers
Note.The technology that one complete interactive system is related to is extremely wide, such as voice technology, natural language processing, machine
Study, knowledge engineering etc..Interactive system is divided into task orientation type conversational system and non task guidance type conversational system (also referred to as
For chat robots).
One of embodiment according to the present invention provides a kind of food and beverage sevice customization method, and user can be helped more convenient
Use look for the service relevant to food and drink such as dining room, queuing, reservation, navigation, bring more friendly and convenient and fast food and drink to take to user
Business experience.The customized process of food and beverage sevice is completed using this method as shown in Figure 1, including step 101 to step 105.
Step 101 configures at least one service scenarios classification.
In the embodiment of the present invention, according to the demand of practical application, it can configure multiple service scenarios classifications.For example, being configured to:
Look for the service scenarios classification that dining room, queuing, reservation etc. are different.
Step 102 identifies that each service scenarios classification is corresponding according to the training in advance of at least one described service scenarios classification
Disaggregated model, to identify corresponding service scenarios classification according to the disaggregated model.
This step generates the disaggregated model for identifying service scenarios from the user instruction, it is specific as shown in Fig. 2,
Including step 1021 to step 1024.
Step 1021 collects training data for each service scenarios classification, and the training data includes a plurality of corpus.
In this step, need to prepare corresponding corpus as training data, corpus can be obtained by collecting under line, such as different
User is to the text representation under the different service scenarios such as " looking for dining room ", " queuing ", " reservation ".Such as: " it is good which Zhangjiang nearby has
This corpus of the chafing dish eaten ", it should be classified as this service scenarios classification of " looking for dining room ".
To the obtained corpus of collection before carrying out text classification, need Chinese sentence being converted to computer it will be appreciated that
Vector form.Such as bigram language model is used to extract words as feature, it is therein for the still above predicate sentence
" Zhangjiang ", " river is attached ", " near ", " closely having ", " which has ", the words such as " which " can be used as feature.
Step 1022 carries out each corpus in the corresponding training data of a service scenarios classification by the verification of card side
Feature selecting selects at least one feature to the service scenarios classification with discrimination.
In this step, feature selecting is carried out to corpus, needs to consider distribution of the feature between different service scenarios classifications.Institute
The probability that the feature of selection should occur in a certain service scenarios classification is general greater than occurring in other service scenarios classifications
Rate.Here feature selecting is carried out with card side's method of calibration, selects the feature for dividing for corpus and having discrimination.What card side verified
Calculation formula is as shown in formula 1.1:
Wherein, the meaning of parameters is as follows in formula:
N: training dataset total number of documents is indicated；
A: indicate to include entry t, while belonging to the number of documents of classification c；
B: indicate to include entry t, but be not belonging to the number of documents of classification c；
C: expression belongs to classification c, but does not include the number of documents of entry t；
D: expression had both been not belonging to classification c, while also including the number of documents of entry t.
After the chi-square value for calculating each feature, according to the sequence of chi-square value from big to small to each feature ordering, card side
Value shows that more greatly corresponding feature and current service scenarios classification degree of conformity are higher, chooses the n forward feature t1 that sort,
Feature of the t2 ..., tn as current service scene type.It should be noted that with chi-square value great thing feature and service field
The higher criterion of scape classification degree of conformity is a kind of mode of more typical screening feature, the invention is not limited in this regard,
It can be realized and screened to obtain the scheme of validity feature within that scope of the present invention to language material feature.
Step 1023, the weighted value for calculating the feature, the vector for obtaining the feature indicate.
In this step, the weight of each feature is calculated after step 1022 completes Feature Selection, it is inverse with word frequency-here
Document frequency (TF-IDF) for the weighted value of feature as being illustrated.The calculation formula of TF-IDF is as shown in formula 1.2:
TF-IDF=TF*IDF (formula 1.2)
Wherein, word frequency (TF) is exactly the total number of word with the numbers of Feature Words divided by document, and the meter of inverse document frequency (IDF)
Formula is calculated as shown in formula 1.3:
Wherein, E indicates total number of documents, and Ew indicates the number of documents that the specific word occurs in entire document sets.So far it counts
Calculate the vector expression (x1, x2 ... xn) of n feature choosing of features described above.
Step 1024 is trained according to the expression of the vector of the feature, obtains the classification mould of the service scenarios classification
Type.
After having the vector expression of feature, so that it may obtain the corresponding classification mould of each service scenarios classification by training
Type.Support vector machines, naive Bayesian etc. can be used in sorting algorithm, here with being illustrated for algorithm of support vector machine.
Support vector machines is defined in the classifier of the margin maximization on feature space, supports multivariate classification, has good classification
Performance.
It should be noted that step 101 and building service scenarios classification and corresponding disaggregated model described in step 102
Process and subsequent step have no strict sequential order relationship.In system initialization, basis can be carried out by step 101 and step 102
Configuration；It is synchronous with food and drink subscribed services are provided for user during follow-up operation, it can also be with multipass step 101
And step 102 pair configuration is updated, to adapt to operating environment needs.
Step 103, when detecting trigger condition, start customized process.
Trigger condition involved in the embodiment of the present invention includes, but is not limited to any or any more in the following conditions
The combination of item:
Vice activation instruction, clicks start button.
Wherein, vice activation instruction is the voice messagings such as preset sentence, phrase, one section of song hummed or melody, can
It is preset in the remote platforms such as the machine or cloud；
Clicking start button can be starting by some virtual pattern key in the entity key or application of configurating terminal
Button is realized；
Step 104, detection user instruction identify service scenarios from the user instruction that detection obtains and extract attribute letter
Breath.
This step detects user instruction, so that user information necessary to customized food and beverage sevice is obtained, it is specific to flow
Journey is as shown in figure 3, including step 1041 to step 1043.
Step 1041 carries out speech recognition to the user instruction, obtains instruction text.
Step 1042 carries out service scenarios identification to described instruction text, obtains corresponding service scenarios classification.
Step 1043, the service scenarios classification obtained according to identification, extract attribute information by information extraction.
In this step, after determining service scenarios classification, it can be obtained by way of information extraction corresponding in text
Attribute information, such as " looking for dining room " this service scenarios classification, including commercial circle described in user, brand, the style of cooking, distance, price
Equal attribute informations.For example, combining the method based on template using the Chinese word segmentation based on hidden Markov model, viterbi algorithm
Obtain corresponding attribute information.
Hidden Markov model is statistical model, it is used to describe the markov mistake containing implicit unknown parameter
Journey, including a hidden state sequence and an observation sequence.In Chinese word segmentation, original statement belongs to observation sequence, participle
As a result belong to hidden state sequence.Such as: the chafing dish which Zhangjiang nearby has nice.The participle knot that this sentence finally obtains
Fruit: Zhangjiang/nearby/has/which/be fond of eating// chafing dish.
The above word segmentation result is the optimal dividing obtained by viterbi algorithm.Viterbi algorithm is a kind of Dynamic Programming calculation
Method is the shortest route problem for the digraph of hedge network and is proposed.It can effectively solve status switch according to the observation
Find a most probable hidden state sequence problem.
For some information hardly resulted in by Chinese word cutting method, solved by the method based on template.
Step 105, according to the service scenarios and attribute information, it is customized to generate the food and beverage sevice scheme for being directed to user.
This step is specific as shown in figure 4, including step 1051 to step 1052.
Step 1051, according to the service scenarios and attribute information, access food and drink platform, issue service request.
Step 1052 obtains the food and beverage sevice scheme generated according to the service scenarios and attribute information.
In this step, by the way that the information that food and drink platform returns is presented to user, by a wheel or more wheel dialogues, it is finally completed
To the customized of food and beverage sevice scheme.
For example, passing through classification after receiving " chongqing chafing dish shop nearest to me " this user instruction that user says
Model identifies that this is " looking for dining room " service scenarios classification；After " looking for dining room " this service scenarios classification, taken out by information
It takes, extracts " chongqing chafing dish shop " this " brand " attribute information；Service can be issued to food and drink platform according to the attribute information to ask
It asks, the chongqing chafing dish shop list that food and drink platform returns is presented to the user by modes such as screen or voice broadcasts.
In another embodiment of the application, with the concrete example of " reservation " this service scenarios classification:
User says phonetic order " Zhangjiang is nearby either with or without nice chafing dish ".
System identifies identify it is " looking for dining room " according to phonetic order " Zhangjiang is nearby either with or without nice chafing dish "
Scene, extracts " Zhangjiang " commercial circle attribute information and " chafing dish " style of cooking attribute information, and system is based on commercial circle attribute information and the style of cooking
Attribute information goes to match corresponding shops in the database, finds " fishing out Zhangjiang shop in seabed ", and matching result is informed user and is mentioned
Show the service scenarios that custom system can be supported at present.
User provides predetermined instruction by phonetic order " me is helped to fish out in predetermined lower seabed " according to the service scenarios of support.
System identifies phonetic order, identifies it is " reservation " scene, extracts " seabed fishing " brand generic information,
And issue the user with inquiry message inquiry user's time for eating meals and number of having dinner.
User provides the phonetic order of " ten two points of noon of next Wednesday, three people " time for eating meals and number.
System identifies the phonetic order of user, extract at ten two points " next Wednesday at noon " time for eating meals attribute information and
Number of having dinner " 3 ", and reservation business is called based on time for eating meals attribute information and number of having dinner, realization helps user to subscribe dining room.
Here more wheels dialogue is to combine food and drink associated scenario and service, is realized with caching mechanism.By man-machine
Interaction carries out more wheel dialogues and obtains users having dinner intention and relevant information, helps user to realize and the service such as is lined up, subscribes.It is preferred that
, third-party platform can also be accessed, for example, user's navigation can be helped to go to dining room, identifies the navigation Service scene of user
And after the attribute informations such as brand, specific shops is navigated to, the location information where the shops is obtained in the database, by shops
Location information input third party's navigation Service interface navigates etc..
One of embodiment according to the present invention additionally provides a kind of food and beverage sevice customization system, framework as shown in figure 5,
Include:
Starting module 501, for when detecting trigger condition, starting customized process；
Service scenarios identification and information extraction module 502, for detecting user instruction, from the user instruction that detection obtains
Identification service scenarios simultaneously extract attribute information；
Schemes generation module 503, for according to the service scenarios and attribute information, the customized food and drink generated for user
Service plan.
Preferably, the user instruction includes phonetic order, the system further include:
Service scenarios configuration module 504, for configuring at least one service scenarios classification；
Disaggregated model training module 505, for each according to the training identification in advance of at least one described service scenarios classification
The corresponding disaggregated model of service scenarios classification, to identify corresponding service scenarios classification according to the disaggregated model.
Preferably, the structure of the disaggregated model training module 505 is as shown in Figure 6, comprising:
Data collection module 5051, for collecting training data for each service scenarios classification, the training data includes
A plurality of corpus；
Characteristic filter unit 5052, for being verified by card side in the corresponding training data of a service scenarios classification
Each corpus carries out feature selecting, selects at least one feature to the service scenarios classification with discrimination；
Feature weight computing unit 5053, for calculating the weighted value of the feature, the vector for obtaining the feature is indicated；
Model training unit 5054 obtains the service scenarios for being trained according to the expression of the vector of the feature
The disaggregated model of classification.
Above-mentioned food and beverage sevice customization system can be integrated in such as smart phone, tablet computer, in PC personal terminal；It can also
Another part is placed in the remote platforms such as cloud platform while its part of module function is integrated in personal terminal, it is complete by network
At being connected in system, to realize system function.
One of embodiment according to the present invention, additionally provides a kind of calculating equipment, including memory, processor and is stored in
On memory and the computer instruction that can run on a processor, the processor realize such as aforementioned food and drink when executing described instruction
Step in service subscription method.
One of embodiment according to the present invention additionally provides a kind of computer readable storage medium, is stored with computer
Instruction is realized when the instruction is executed by processor such as the step in aforementioned food and beverage sevice customization method.
A kind of exemplary scheme of above-mentioned computer readable storage medium for the present embodiment.It should be noted that this is deposited
The technical solution of storage media and the technical solution of above-mentioned food and beverage sevice customization method belong to same design, the technology of storage medium
The detail content that scheme is not described in detail may refer to the description of the technical solution of above-mentioned food and beverage sevice customization method.
The embodiment provides a kind of food and beverage sevice customization methods and system to open when detecting trigger condition
Customized process is moved, detects user instruction after starting customized process, service scenarios are identified from the user instruction that detection obtains and is taken out
Attribute information is taken, it is customized to generate the food and beverage sevice scheme for being directed to user further according to the service scenarios and attribute information.Pass through base
It looks for dining room, queuing, reservation etc. to have dinner intentions in the natural language processing technique identification user of phonetic order, is identifying user's meaning
After figure, use information extraction technique obtains commercial circle, brand, the style of cooking, distance, the information such as price, in conjunction with food and drink associated scenario and
Service realizes more wheel dialogues with caching mechanism, realizes for user and the food and beverage sevices such as be lined up, subscribe.Solving existing user makes
With the problem of food and drink information network platform is cumbersome, inefficiency, the catering information service of convenient close friend is realized.
The computer instruction includes computer program code, the computer program code can for source code form,
Object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include: that can carry institute
State any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, the computer storage of computer program code
Device, read-only memory (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), electricity
Carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the content that the computer-readable medium includes
Can according to making laws in jurisdiction and the requirement of patent practice carries out increase and decrease appropriate, such as in certain jurisdictions,
It does not include electric carrier signal and telecommunication signal according to legislation and patent practice, computer-readable medium.
It should be noted that for the various method embodiments described above, describing for simplicity, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, certain steps can use other sequences or carry out simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules might not all be this Shen
It please be necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
The application preferred embodiment disclosed above is only intended to help to illustrate the application.There is no detailed for alternative embodiment
All details are described, are not limited the invention to the specific embodiments described.Obviously, according to the content of this specification,
It can make many modifications and variations.These embodiments are chosen and specifically described to this specification, is in order to preferably explain the application
Principle and practical application, so that skilled artisan be enable to better understand and utilize the application.The application is only
It is limited by claims and its full scope and equivalent.
Claims (11)
1. a kind of food and beverage sevice customization method characterized by comprising
When detecting trigger condition, start customized process；
User instruction is detected, service scenarios are identified from the user instruction that detection obtains and extracts attribute information；
It is customized to generate the food and beverage sevice scheme for being directed to user according to the service scenarios and attribute information.
2. food and beverage sevice customization method according to claim 1, which is characterized in that the user instruction includes that voice refers to
It enables, this method further include:
Configure at least one service scenarios classification；
The corresponding disaggregated model of each service scenarios classification is identified according to the training in advance of at least one described service scenarios classification, with
Corresponding service scenarios classification is identified according to the disaggregated model.
3. food and beverage sevice customization method according to claim 2, which is characterized in that train the classification by the following method
Model:
Training data is collected for each service scenarios classification, the training data includes a plurality of corpus；
Feature selecting, selection are carried out to each corpus in the corresponding training data of a service scenarios classification by the verification of card side
At least one feature to the service scenarios classification with discrimination out；
The weighted value for calculating the feature, the vector for obtaining the feature indicate；
It is trained according to the expression of the vector of the feature, obtains the disaggregated model of the service scenarios classification.
4. food and beverage sevice customization method according to claim 2 or 3, which is characterized in that the detection user instruction, from inspection
Service scenarios are identified in the user instruction measured and include: the step of extracting attribute information
Speech recognition is carried out to the user instruction, obtains instruction text；
Service scenarios identification is carried out to described instruction text, obtains corresponding service scenarios classification；
According to the service scenarios classification that identification obtains, attribute information is extracted by information extraction.
5. food and beverage sevice customization method according to claim 4, which is characterized in that believed according to the service scenarios and attribute
Breath, it is customized generate be directed to user food and beverage sevice scheme the step of include:
According to the service scenarios and attribute information, food and drink platform is accessed, issues service request；
Obtain the food and beverage sevice scheme generated according to the service scenarios and attribute information.
6. food and beverage sevice customization method according to claim 1, which is characterized in that the trigger condition includes at least following
Any or any number of combination in condition:
Vice activation instruction, clicks start button.
7. a kind of food and beverage sevice customization system characterized by comprising
Starting module, for when detecting trigger condition, starting customized process；
Service scenarios identification and information extraction module identify clothes for detecting user instruction from the user instruction that detection obtains
Business scene simultaneously extracts attribute information；
Schemes generation module, for according to the service scenarios and attribute information, the customized food and beverage sevice side generated for user
Case.
8. food and beverage sevice customization system according to claim 7, which is characterized in that the user instruction includes that voice refers to
It enables, the system further include:
Service scenarios configuration module, for configuring at least one service scenarios classification；
Disaggregated model training module, for training to identify each service scenarios in advance according at least one described service scenarios classification
The corresponding disaggregated model of classification, to identify corresponding service scenarios classification according to the disaggregated model.
9. food and beverage sevice customization system according to claim 7, which is characterized in that the disaggregated model training module packet
It includes:
Data collection module, for collecting training data for each service scenarios classification, the training data includes a plurality of corpus；
Characteristic filter unit, for being verified by card side to each corpus in the corresponding training data of a service scenarios classification
Feature selecting is carried out, at least one feature to the service scenarios classification with discrimination is selected；
Feature weight computing unit, for calculating the weighted value of the feature, the vector for obtaining the feature is indicated；
Model training unit obtains point of the service scenarios classification for being trained according to the expression of the vector of the feature
Class model.
10. a kind of calculating equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine instruction, which is characterized in that the processor is realized as described in any one of claim 1-6 when executing described instruction
The step of method.
11. a kind of computer readable storage medium, is stored with computer instruction, which is characterized in that the instruction is held by processor
The step of method as claimed in any one of claims 1 to 6 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810421841.8A CN109658173A (en) | 2018-05-04 | 2018-05-04 | A kind of food and beverage sevice customization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810421841.8A CN109658173A (en) | 2018-05-04 | 2018-05-04 | A kind of food and beverage sevice customization method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109658173A true CN109658173A (en) | 2019-04-19 |
Family
ID=66110100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810421841.8A Pending CN109658173A (en) | 2018-05-04 | 2018-05-04 | A kind of food and beverage sevice customization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658173A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008720A (en) * | 2019-12-09 | 2020-04-14 | 上海博泰悦臻电子设备制造有限公司 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
| CN112837133A (en) * | 2021-03-10 | 2021-05-25 | 口碑(上海)信息技术有限公司 | Package information providing method and device and electronic equipment |
| CN116108288A (en) * | 2023-02-06 | 2023-05-12 | 苏州大学 | Method and system for searching optimal get-on and get-off points in taxi taking service |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103187060A (en) * | 2011-12-28 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted speech processing device |
| CN103995876A (en) * | 2014-05-26 | 2014-08-20 | 上海大学 | Text classification method based on chi square statistics and SMO algorithm |
| CN107025613A (en) * | 2017-04-18 | 2017-08-08 | 腾讯科技（上海）有限公司 | A kind of automatic method of ordering and terminal |
-
2018
- 2018-05-04 CN CN201810421841.8A patent/CN109658173A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103187060A (en) * | 2011-12-28 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted speech processing device |
| CN103995876A (en) * | 2014-05-26 | 2014-08-20 | 上海大学 | Text classification method based on chi square statistics and SMO algorithm |
| CN107025613A (en) * | 2017-04-18 | 2017-08-08 | 腾讯科技（上海）有限公司 | A kind of automatic method of ordering and terminal |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111008720A (en) * | 2019-12-09 | 2020-04-14 | 上海博泰悦臻电子设备制造有限公司 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
| CN112837133A (en) * | 2021-03-10 | 2021-05-25 | 口碑(上海)信息技术有限公司 | Package information providing method and device and electronic equipment |
| CN116108288A (en) * | 2023-02-06 | 2023-05-12 | 苏州大学 | Method and system for searching optimal get-on and get-off points in taxi taking service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609101B (en) | Intelligent interaction method, equipment and storage medium | |
| CN106096576B (en) | A kind of intelligent Service method of robot | |
| CN107818781B (en) | Intelligent interaction method, equipment and storage medium | |
| WO2018214163A1 (en) | Providing product recommendation in automated chatting | |
| CN108346075B (en) | Information recommendation method and device | |
| CN108153800B (en) | Information processing method, information processing apparatus, and recording medium | |
| US11935029B2 (en) | Classification by natural language grammar slots across domains | |
| US20190221208A1 (en) | Method, user interface, and device for audio-based emoji input | |
| CN109885713A (en) | Facial expression image recommended method and device based on voice mood identification | |
| CN109658173A (en) | A kind of food and beverage sevice customization method and system | |
| EP2734938A1 (en) | Method and system of classification in a natural language user interface | |
| CN114549874A (en) | Training method of multi-target image-text matching model, image-text retrieval method and device | |
| CN109451147B (en) | Information display method and device | |
| CN103577386A (en) | Method and device for dynamically loading language model based on user input scene | |
| CN109508441B (en) | Method and device for realizing data statistical analysis through natural language and electronic equipment | |
| CN110909222A (en) | User portrait establishing method, device, medium and electronic equipment based on clustering | |
| CN111291158B (en) | Information query method and device, electronic equipment and storage medium | |
| WO2018176913A1 (en) | Search method and apparatus, and non-temporary computer-readable storage medium | |
| JP7058574B2 (en) | Information processing equipment, information processing methods, and programs | |
| CN105940394B (en) | Interactive server and method for control server | |
| WO2014180402A1 (en) | Contact list setting method and device | |
| CN110085217A (en) | Phonetic navigation method, device and terminal device | |
| CN111161726A (en) | Intelligent voice interaction method, equipment, medium and system | |
| CN111242721B (en) | Voice meal ordering method and device, electronic equipment and storage medium | |
| CN110472057A (en) | The generation method and device of topic label |
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: 20190419 |
|
| RJ01 | Rejection of invention patent application after publication |