CN106815224A - Service acquisition method and apparatus - Google Patents
Service acquisition method and apparatus Download PDFInfo
- Publication number
- CN106815224A CN106815224A CN201510849832.5A CN201510849832A CN106815224A CN 106815224 A CN106815224 A CN 106815224A CN 201510849832 A CN201510849832 A CN 201510849832A CN 106815224 A CN106815224 A CN 106815224A
- Authority
- CN
- China
- Prior art keywords
- text message
- service
- user
- information
- text
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application discloses service acquisition method and apparatus.One specific embodiment of methods described includes：The first text message is obtained and shows, wherein, first text message is obtained based on the text information to user input, pictorial information or voice messaging analyzing and processing；The second text message is received, wherein, second text message is user to the text message after first text information processing；Based on the service list that prestores using have supervision, the machine learning algorithm with disaggregated model classified calculating is carried out to second text message；At least one service in the service list is chosen based on classified calculating result and shows the user.Because the method carries out classified calculating to the information of user input using backstage based on service list, and user is showed according to classified calculating result selection at least one service, so as to facilitate the operation of user, while also saving the time of user.
Description
Technical field
The application is related to field of computer technology, and in particular to Internet technical field, especially relates to
And service acquisition method and apparatus.
Background technology
At present, the development of various websites and application (application, APP), for people provide
The service of the various aspects of covering daily life.So that people can just handle respectively without going out
The items such as class commercial affairs class, government affairs class, largely for the life of people is provided convenience.
However, various websites and APP are when all kinds of services are provided a user with, it is in many of webpage
Access service entrance on the multilevel menu of level menu or APP.Due to needing user to be familiar with menu
Function title and functional structure, carrying out multistage access could open service entrance, that is, be inconvenient to use
Family uses, and also wastes the time of user.
The content of the invention
The purpose of the application is to propose a kind of improved service acquisition method and apparatus to solve
The technical problem that background section above is mentioned.
In a first aspect, this application provides a kind of service acquisition method, methods described includes：Obtain
The first text message is taken and shows, wherein, first text message is based on to user input
Text information, pictorial information or voice messaging analyzing and processing are obtained；The second text message is received,
Wherein, second text message is user to the text envelope after first text information processing
Breath；Being used based on the service list for prestoring has supervision, the machine learning calculation with disaggregated model
Method carries out classified calculating to second text message；The clothes are chosen based on classified calculating result
At least one service in business list shows the user.
In certain embodiments, the machine learning algorithm for having supervision includes：SVMs
Algorithm or NB Algorithm.
In certain embodiments, it is described based on the service list that prestores using have supervision, have
The machine learning algorithm of disaggregated model carries out classified calculating to second text message, including：
Feature dictionary is set up, the Feature Words are the notional word for including noun, adjective, verb；It is based on
The feature dictionary carries out cutting to second text message, sets up word frequency vector；Based on pre-
The service list deposited is used has supervision, the machine learning algorithm with disaggregated model to institute's predicate
Frequency vector carries out classified calculating.
In certain embodiments, methods described also includes：Record user to displaying described at least
One selection result of service；The selection result is perhaps tested into content feed as in learning
To disaggregated model with adjusting parameter.
In certain embodiments, it is described to obtain and show that the first text message includes：When user is defeated
When the information for entering is pictorial information, the pictorial information is converted to by text using image-recognizing method
This information；When the information of user input is for voice messaging, will be described using audio recognition method
Voice messaging is converted to text message.
Second aspect, the present embodiment provides a kind of service acquisition device of example, and described device includes：
First text message is obtained and display unit, is configured to obtain and show the first text message,
Wherein, first text message is to the text information of user input, pictorial information or voice
Information analysis treatment is obtained.Second text message receiving unit, is configured to receive the second text
Information, wherein, second text message be user to first text information processing after
Text message；Classified calculating unit, being configured to be used based on the service list for prestoring has supervision
, the machine learning algorithm with disaggregated model classified calculating is carried out to second text message；
Choose and display unit, be configured to based in the classified calculating result selection service list
At least one service shows the user.
In certain embodiments, the supervision machine learning algorithm includes：Algorithm of support vector machine
Or NB Algorithm.
In certain embodiments, the classified calculating unit is further configured to：Set up feature
Dictionary, the Feature Words are the notional word for including noun, adjective, verb；Based on the feature
Dictionary carries out cutting to second text message, sets up word frequency vector；Based on the service for prestoring
List carries out classified calculating using the machine learning algorithm for having supervision to the word frequency vector.
In certain embodiments, described device also includes：Recording unit, is configured to record and uses
The selection result of at least one service of the family to showing；Feedback unit, is configured to institute
State selection result as study in perhaps test content feed to disaggregated model with adjusting parameter.
In certain embodiments, first text message is obtained and further configured with display unit
For：
When the information of user input is pictorial information, using image-recognizing method by the pictorial information
Be converted to text message；When the information of user input is for voice messaging, using speech recognition side
The voice messaging is converted to text message by method.
The service acquisition device that the application is provided, by the text information, the figure that obtain user input
First text message of piece information and voice messaging simultaneously shows user；Then user couple is received
The second text message after first text information processing；Being used based on the service list for prestoring again is had
The machine learning algorithm of supervision carries out classified calculating to the second text message, is counted finally according to classification
Calculation result chooses at least one service in service list and shows user.Because the method is used
Backstage carries out classified calculating to the information of user input based on service list, and according to classified calculating
Result chooses at least one service and shows user, so as to facilitate the operation of user, while
Save the time of user.
Brief description of the drawings
Retouched with reference to the detailed of being made to non-limiting example of being made of the following drawings by reading
State, other features, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart of one embodiment of the service acquisition method according to the application；
Fig. 3 is the flow chart of another embodiment of the service acquisition method according to the application；
Fig. 4 is the structural representation of one embodiment of the service acquisition device according to the application；
The structure that Fig. 5 is adapted for the computer system for realizing the embodiment of the present application server is shown
It is intended to.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is appreciated that
, specific embodiment described herein is used only for explaining related invention, rather than to the hair
Bright restriction.It also should be noted that, for the ease of description, be illustrate only in accompanying drawing with
About the related part of invention.
It should be noted that in the case where not conflicting, embodiment and embodiment in the application
In feature can be mutually combined.Describe this in detail below with reference to the accompanying drawings and in conjunction with the embodiments
Application.
Fig. 1 shows can apply the service acquisition method of the application or the reality of service acquisition device
Apply the exemplary system architecture 100 of example.
As shown in figure 1, system architecture 100 can include terminal device 101,102,103,
Network 104 and server 105.Network 104 is used in the and of terminal device 101,102,103
The medium of communication link is provided between server 105.Network 104 can include various connection classes
Type, such as wired, wireless communication link or fiber optic cables etc..
User can be with using terminal equipment 101,102,103 by network 104 and server 105
Interaction, to receive or send message etc..Can be provided with terminal device 101,102,103
Various telecommunication customer end applications, such as web browser applications, the application of shopping class, searching class are answered
With, JICQ, mailbox client, social platform software etc..
Terminal device 101,102,103 can be with display screen and support that moving APP answers
With or web page browsing various intelligent electronic devices, including but not limited to smart mobile phone, flat board electricity
Brain, computer etc..
Server 105 can be to provide the server of various services, for example to terminal device 101,
102nd, the service content shown on 103 provides the background service supported and chooses server.Backstage takes
Business chooses server and can the data such as the user input information that receives is analyzed to wait and processes,
And result (service for example chosen according to user input information) is fed back into terminal device.
It should be noted that the information acquisition method that the embodiment of the present application is provided is general by servicing
Device 105 is performed, and correspondingly, information acquisition device is generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only to illustrate
Property.According to needs are realized, can have any number of terminal device, network and server.
With continued reference to Fig. 2, one embodiment of the service acquisition method according to the application is shown
Flow 200.Described service acquisition method, comprises the following steps：
Step 201, obtains and shows the first text message, wherein, the first text message is based on
Text message, pictorial information or voice messaging analyzing and processing to user input is obtained.
Generally, user opens webpage to select to service dish using the browser installed on terminal device
Classification single or that open APP selects services menu, into service entrance.In the present embodiment,
User can be by clear on terminal device (such as shown in Fig. 1 101,102,103)
Text message, picture letter are input at unification, the simple Initial Entry look in device or in APP
Breath or voice messaging, are transported by network (such as scheming shown 104) to service acquisition method
Row electronic equipment (such as the server shown in Fig. 1) thereon initiates service acquisition request.
In the present embodiment, the text message of user input can be passage information, also may be used
Being a group or a keyword.The pictorial information of user input can be an at least pictures,
Between picture can with it is relevant can also onrelevant；User can select to carry out the picture of automatic network,
The picture collected using various image acquisition devices can also be selected, for example, is clapped using camera
The local picture in kind of the user that takes the photograph.The voice messaging of user input can be one section of voice,
A word or several words；Can collect voice messaging using any audio collection device.
Text message, pictorial information or the voice messaging that above-mentioned electronic equipment will be received are converted to
First text message.When user input be text message when, electronic equipment is directly defeated by user
The text message for entering is used as the first text message.The first text envelope that electronic equipment will be converted to
Breath is by network display to terminal device.
In some optional implementations of the present embodiment, when user input be pictorial information when,
Electronic equipment, can be converted to a series of text envelopes using the method for image recognition by pictorial information
Breath is used as the first text message.When user input be voice messaging when, electronic equipment can be with
Voice messaging is converted to using the method for speech recognition for a series of text messages as the first text
Information.Above-mentioned image-recognizing method and audio recognition method are widely studied methods, herein not
Repeat.
Step 202, receives the second text message, wherein, the second text message is user to institute
State the text message after the first text information processing.
In step 201, the first text message that electronic equipment will be obtained shows terminal device.
First text message of the user on the terminal device to being shown does precision treatment, obtains second
Text message.Such as user from showing by above-mentioned electronic equipment according to user on the terminal device
Selection is best suitable for oneself purpose one in a series of text messages that the pictorial information of input is converted to
Individual text message is used as the second text message.User can also enter to the content of the first text message
Row is deleted and obtains the second text message.
In some optional implementations of the present embodiment, it is also possible to by other methods to
One text message does precision treatment.For example, being entered to the first text message using special device
The treatment of row precision.
In the present embodiment, electronic equipment receives the second text message by network.
Step 203, has supervision, with disaggregated model based on the service list use for prestoring
Machine learning algorithm carries out classified calculating to second text message.
In the present embodiment, service acquisition method operation electronic equipment thereon can be deposited in advance
Service list of the storage comprising a plurality of service.Thus, above-mentioned electronic equipment is using the machine for having supervision
Multinomial service of the learning algorithm to the second text message in service list carries out classified calculating.
For in this sense, namely calculate the items that the second text message is belonged in service list
The probability of service.
There is the machine learning algorithm of supervision, for example, can be by the sample of known class (i.e.
Primary data and its corresponding output) disaggregated model of training machine is removed to adjust disaggregated model
Parameter, reaches optimal (be optimally represented in certain interpretational criteria under be optimal), recycles
All of input is mapped as corresponding output by this model, output simply judge from
And the purpose classified is realized, also just it is provided with the ability classified to unknown data.
In the present embodiment, early stage can be by manually to a number of second text message root
Classified according to service list, obtained a number of known class with high accuracy
Sample is trained to disaggregated model.
In some optional implementations of the present embodiment, training data (known class
Sample) less (ten thousand grades lower) when, it is for instance possible to use SVMs (Support
Vector Machine, SVM) algorithm classifies to above-mentioned second text message；In training number
During according to more (100,000 grades higher), it is for instance possible to use naive Bayesian (Naive Bayes
Classifier, NB) algorithm classifies to above-mentioned second text message.
It is pointed out that the intendant such as above-mentioned algorithm of support vector machine and NB Algorithm
Device learning algorithm is widely studied and application known technology, be will not be repeated here.
Step 204, at least one service exhibition in service list is chosen based on classified calculating result
Show to user.
According to above-mentioned classified calculating result, above-mentioned electronic equipment can be chosen from service list to
One item missing is serviced.For example, above-mentioned electronic equipment can be chosen at using under Nae Bayesianmethod
It is calculated at least one service of the probability of occurrence more than certain threshold value.Above-mentioned probability of occurrence is big
In certain threshold value at least one service according to the big minispread of probability of occurrence, show user
User selects any one service interested at least one service of displaying, enters
Enter service entrance to conduct interviews.
In some optional implementations of the present embodiment, the choosing of service of the record user to showing
Result is selected, and the selection result and corresponding second text message is anti-as study content
Disaggregated model of feeding carries out model training.Or by the selection result and corresponding second text
Information carries out model evaluation as test content feed to disaggregated model.In model training or model
In evaluation process, the parameter of model, the performance of Optimum Classification model are adjusted.
The method that above-described embodiment of the application is provided by obtain user input text information,
First text message of pictorial information and voice messaging simultaneously shows user；Then user is received
To the second text message after the first text information processing；Used based on the service list for prestoring again
The machine learning algorithm for having supervision carries out classified calculating to the second text message, finally according to classification
Result of calculation chooses at least one service in service list and shows user.Because the method is adopted
Classified calculating is carried out based on service list to the information of user input with backstage, and is counted according to classification
Calculate result selection at least one service and show user, so as to facilitate the operation of user, while
Also save the time of user.
With further reference to Fig. 3, it illustrates the flow of another embodiment of service acquisition method
300.The flow 300 of the service acquisition method, comprises the following steps：
Step 301, obtains and shows the first text message, wherein, the first text message is based on
Text message, pictorial information or voice messaging analyzing and processing to user input is obtained.
In the present embodiment, user can by terminal device (such as shown in Fig. 1 101,
102nd, 103) on browser in or APP in unification, simple Initial Entry at be input into
Text message, pictorial information or voice messaging run on it by network to service acquisition method
On electronic equipment (such as the server shown in Fig. 1) initiate service acquisition request.
Text message, pictorial information or the voice messaging that above-mentioned electronic equipment will be received are converted to
First text message.When user input be text message when, electronic equipment is directly defeated by user
The text message for entering is used as the first text message.The first text envelope that electronic equipment will be converted to
Breath is by network display to terminal device.
Step 302, receives the second text message, wherein, the second text message is user to institute
State the text message after the first text information processing.
In step 301, the first text message that electronic equipment will be obtained shows terminal device.
User does precision treatment to the first text message on the terminal device, obtains the second text message.
Such as user from showing by above-mentioned electronic equipment according to the picture of user input on the terminal device
Selection is best suitable for oneself one text message of purpose in a series of text messages that information is converted to
As the second text message.User can also be deleted the content of the first text message
Second text message.
In the present embodiment, electronic equipment receives the second text message by network.
Step 303, carries out word and cuts based on the feature dictionary for pre-building to the second text message
Point.
In the present embodiment, feature dictionary is pre-build, the source of feature dictionary can be language material
Storehouse or dictionary.In some optional implementations of the present embodiment, feature dictionary mainly retains
Noun, verb, adjective, number class notional word in corpus or dictionary.In the present embodiment
In, keyword, the sentence of each bar service in service list are also included in feature dictionary.
In the present embodiment, based on the second text message obtained in step 302, above-mentioned electronics
The content of the second text message is cut into Feature Words by equipment.It is pointed out that having many at present
The ripe method that text message is cut into Feature Words is planted, is not described in detail herein.
Step 304, based on above-mentioned word segmentation, sets up the word frequency vector of the second text message.
What each Feature Words obtained to the second text message cutting to above-mentioned segmenting method method occurred
Frequency is counted, and sets up word frequency vector.Word frequency vector similar to<The frequency of occurrences of word 1,
The frequency of occurrences ... 0 ... of word 2, the word N frequencies of occurrences>Sparse vector.
In some optional implementations of the present embodiment, by what is obtained using statistics cutting method
The frequency of occurrences is added in feature dictionary higher than the neologisms of predetermined threshold.
Step 305, being used based on the service list for prestoring has supervision, the machine with disaggregated model
Device learning algorithm carries out classified calculating to word frequency vector.
In the present embodiment, can be advance on service acquisition method operation electronic equipment thereon
Service list of the storage comprising a plurality of service.Thus, above-mentioned electronic equipment using have supervision,
Machine learning algorithm with disaggregated model is arranged the word frequency vector of the second text message according to service
Multinomial service in table carries out classified calculating.For in this sense, namely calculate the second text
This information belongs to the probability of the respective services in service list.
In some optional implementations of the present embodiment, training data (known class
Sample) less (ten thousand grades lower) when, it is for instance possible to use SVMs (Support
Vector Machine, SVM) algorithm classifies to the word frequency vector of above-mentioned second text message
Calculate；At training data more (100,000 grades higher), it is for instance possible to use simple pattra leaves
This (Naive Bayes Classifier, NB) algorithm to the word frequency of above-mentioned second text message to
Amount carries out classified calculating.
Step 306, at least one clothes in the service list are chosen based on classified calculating result
Business shows user.
According to above-mentioned classified calculating result, above-mentioned electronic equipment can be chosen from service list to
One item missing is serviced.For example, above-mentioned electronic equipment can be chosen at using under Nae Bayesianmethod
At least one service of the probability of occurrence being calculated more than certain threshold value.By above-mentioned probability of occurrence
More than certain threshold value at least one service according to the big minispread of probability of occurrence, show user.
User selects any one service interested at least one service of displaying, enters
Enter service entrance to conduct interviews.
In some optional implementations of the present embodiment, the choosing of service of the record user to showing
Result is selected, and the selection result and corresponding second text message is anti-as study content
Disaggregated model of feeding carries out model training.Or by the selection result and corresponding second text
Information carries out model evaluation as test content feed to disaggregated model.In model training or model
In evaluation process, the parameter of model, the performance of Optimum Classification model are adjusted.
From figure 3, it can be seen that the main difference of embodiment corresponding with Fig. 2 is, this reality
To apply increased in example and set up feature dictionary, feature based dictionary carries out cutting to the second text message,
The step of the word frequency vector of the second text message is set up, and classified calculating is based on the clothes for prestoring
Business list carries out classified calculating using the machine learning algorithm for having supervision to word frequency vector.Due to this
Embodiment carries out classified calculating using word frequency vector, can improve the accuracy rate of classification.
With further reference to Fig. 4, used as the realization to method shown in above-mentioned each figure, the application is provided
A kind of one embodiment of service acquisition device, the device embodiment and the method shown in Fig. 2
Embodiment is corresponding, and the device specifically can apply in various electronic equipments.
As shown in figure 4, the service acquisition device 400 described in the present embodiment includes：First text
Acquisition of information and display unit 401, the second text message receiving unit 402, classified calculating unit
403 and service choose with display unit 404.Wherein, the first text message is obtained and display unit
401, it is configured to obtain and show the first text message, wherein, first text message is
Text message, pictorial information or voice messaging analyzing and processing to user input is obtained；Second text
This receiving unit 402, is configured to receive the second text message, wherein, second text
Information is user to the text message after first text information processing；Classified calculating unit
403, being configured to be used based on the service list for prestoring has supervision, the machine with disaggregated model
Device learning algorithm carries out classified calculating to second text message；Service is chosen and display unit
404, it is configured to choose at least one service in the service list based on classified calculating result
Show the user.
In the present embodiment, the first text message of service acquisition device 400 obtains single with displaying
It is input at first 401 unification, simple Initial Entry by user in browser or APP
Text message, pictorial information, voice messaging are converted to a series of text message as the first text
This information.In some optional implementations of the present embodiment, when the information of user input is
During pictorial information, the pictorial information is converted to by the first text message using image-recognizing method；
When the information of user input is voice messaging, using audio recognition method by the voice messaging
Be converted to the first text message.
In the present embodiment, the second text message receiving unit 402 is received by user to first
The second text message that text information processing is obtained.
In the present embodiment, in the present embodiment, service acquisition device can be prestored and included
The service list of multinomial service.Thus, classified calculating unit 403 using using have supervision,
Machine learning algorithm with disaggregated model is multinomial in service list to the second text message
Service carries out classified calculating.For in this sense, namely calculate the second text message ownership
The probability of the respective services in service list.
In some optional implementations of the present embodiment, have supervision, with disaggregated model
Machine learning algorithm include algorithm of support vector machine or NB Algorithm.
In the present embodiment, service is chosen with display unit 404 according to classified calculating unit 403
The result being calculated, chooses at least one service from service list.For example, service is chosen
Can be chosen at using being calculated probability of occurrence under Nae Bayesianmethod with display unit 404
More than at least one service of certain threshold value.By above-mentioned probability of occurrence more than certain threshold value at least
One service, user is showed according to probability of occurrence size.
User selects any one service interested at least one service of displaying, enters
Enter service entrance to conduct interviews.
In some optional implementations of the present embodiment, service acquisition device also includes record
Unit and feedback unit.Recording unit is configured to record at least one service of the user to displaying
Selection result.Feedback unit is configured to selection result and corresponding second text envelope
Content feed is perhaps tested in breath conduct study to disaggregated model so that disaggregated model adjusting parameter.
It will be understood by those skilled in the art that above-mentioned service acquisition device 400 also includes some its
His known features, such as processor, memory etc., in order to unnecessarily obscure the reality of the disclosure
Example is applied, these known structures are not shown in fig. 4.
Below with reference to Fig. 5, it illustrates the terminal device being suitable to for realizing the embodiment of the present application
Or the structural representation of the computer system 500 of server.
As shown in figure 5, computer system 500 includes CPU (CPU) 501, its
Can be according to program of the storage in read-only storage (ROM) 502 or from storage part 508
The program that is loaded into random access storage device (RAM) 503 and perform various appropriate actions
And treatment.In RAM 503, the system that is also stored with 500 operates required various program sums
According to.CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input
/ output (I/O) interface 505 is also connected to bus 504.
I/O interfaces 505 are connected to lower component：Including keyboard, mouse, touch-screen, camera
Deng importation 506；Including such as cathode-ray tube (CRT), liquid crystal display (LCD)
Deng and loudspeaker etc. output par, c 507；Storage part 508 including hard disk etc.；And bag
Include the communications portion 509 of the NIC of LAN card, modem etc..Communication unit
509 are divided to perform communication process via the network of such as internet.Driver 510 is also according to needs
It is connected to I/O interfaces 505.Detachable media 511, such as disk, CD, magneto-optic disk, half
Conductor memory etc., as needed on driver 510, in order to read from it
Computer program be mounted into as needed storage part 508.
Especially, in accordance with an embodiment of the present disclosure, the process above with reference to flow chart description can be with
It is implemented as computer software programs.For example, embodiment of the disclosure includes a kind of computer journey
Sequence product, it includes being tangibly embodied in the computer program on machine readable media, the meter
Calculation machine program bag is containing the program code for the method shown in execution flow chart.In such implementation
In example, the computer program can be downloaded and installed by communications portion 509 from network,
And/or be mounted from detachable media 511.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application,
The architectural framework in the cards of method and computer program product, function and operation.This point
On, each square frame in flow chart or block diagram can represent module, program segment or a code
A part, a part for the module, program segment or code is used for comprising one or more
Realize the executable instruction of the logic function of regulation.It should also be noted that at some as replacement
In realization, the function of being marked in square frame can also be sent out with different from the order marked in accompanying drawing
It is raw.For example, two square frames for succeedingly representing can essentially be performed substantially in parallel, they
Sometimes can also perform in the opposite order, this is depending on involved function.It is also noted that
It is, the square frame in each square frame and block diagram and/or flow chart in block diagram and/or flow chart
Combination, can be realized with the function of regulation or the special hardware based system of operation is performed,
Or can be realized with the combination of computer instruction with specialized hardware.
Be described in involved unit in the embodiment of the present application can by way of software reality
It is existing, it is also possible to be realized by way of hardware.Described unit can also be arranged on treatment
In device, for example, can be described as：The first text message is obtained and shows, wherein, described
One text message is based at the text information to user input, pictorial information or voice messaging analysis
Reason is obtained；The second text message is received, wherein, second text message is user to described
Text message after first text information processing；Based on the service list that prestores using have supervision,
Machine learning algorithm with disaggregated model carries out classified calculating to second text message；Base
At least one service in classified calculating result chooses the service list shows the use
Family.
As on the other hand, present invention also provides a kind of nonvolatile computer storage media,
The nonvolatile computer storage media can be described in above-described embodiment included in device
Nonvolatile computer storage media；Can also be individualism, it is non-in terminal without allocating into
Volatile computer storage medium.Above-mentioned nonvolatile computer storage media be stored with one or
Person's multiple program, when one or more of programs are performed by an equipment so that described
Equipment：Obtain and show the first text message, wherein, first text message be based on to
Text information, pictorial information or the voice messaging analyzing and processing that family is input into are obtained；Receive the second text
This information, wherein, second text message be user to first text information processing after
Text message；Being used based on the service list for prestoring has supervision, the machine with disaggregated model
Device learning algorithm carries out classified calculating to second text message；Based on the choosing of classified calculating result
Take at least one service in the service list and show the user.
Above description is only the preferred embodiment of the application and saying to institute's application technology principle
It is bright.It will be appreciated by those skilled in the art that invention scope involved in the application, does not limit
In the technical scheme of the particular combination of above-mentioned technical characteristic, while should cover not departing from yet
In the case of the inventive concept, it is combined by above-mentioned technical characteristic or its equivalent feature
And other technical schemes for being formed.Such as features described above and (but not limited to) disclosed herein
The technical scheme that technical characteristic with similar functions is replaced mutually and formed.
Claims (10)
1. a kind of service acquisition method, it is characterised in that methods described includes：
The first text message is obtained and shows, wherein, first text message is based on to user
The text message of input, pictorial information or voice messaging analyzing and processing are obtained；
The second text message is received, wherein, second text message is user to described first
Text message after text information processing；
Being used based on the service list for prestoring has supervision, the machine learning calculation with disaggregated model
Method carries out classified calculating to second text message；
At least one service in the service list is chosen based on classified calculating result and shows institute
State user.
2. method according to claim 1, it is characterised in that the machine for having a supervision
Learning algorithm includes：Algorithm of support vector machine or NB Algorithm.
3. method according to claim 1, it is characterised in that described based on the clothes for prestoring
Business list is used has supervision, the machine learning algorithm with disaggregated model to second text
Information carries out classified calculating, including：
Word segmentation is carried out to the second text message based on the feature dictionary for pre-building；
Based on the word segmentation, the word frequency vector of the second text message is set up；
Being used based on the service list for prestoring has supervision, the machine learning calculation with disaggregated model
Method carries out classified calculating to the word frequency vector.
4. method according to claim 1, it is characterised in that methods described also includes：
The selection result of at least one service of the record user to showing；
The selection result is perhaps tested into content feed to disaggregated model to adjust as in learning
Parameter.
5. method according to claim 1, it is characterised in that the acquisition simultaneously shows the
One text message includes：
When the information of user input is pictorial information, using image-recognizing method by the picture
Information is converted to text message；
When the information of user input is voice messaging, using audio recognition method by the voice
Information is converted to text message.
6. a kind of service acquisition device, it is characterised in that described device includes：
First text message is obtained and display unit, is configured to obtain and show the first text envelope
Breath, wherein, first text message be to the text message of user input, pictorial information or
Voice messaging analyzing and processing is obtained；
Second text message receiving unit, is configured to receive the second text message, wherein, institute
It is user to the text message after first text information processing to state the second text message；
Classified calculating unit, being configured to be used based on the service list for prestoring has supervision, tool
The machine learning algorithm for having disaggregated model carries out classified calculating to second text message；
Service is chosen and display unit, is configured to choose the service based on classified calculating result
At least one service in list shows the user.
7. device according to claim 6, it is characterised in that the supervision machine study
Algorithm includes：Algorithm of support vector machine or NB Algorithm.
8. device according to claim 6, it is characterised in that the classified calculating unit
Further it is configured to：
Word segmentation is carried out to the second text message based on the feature dictionary for pre-building；
Based on the word segmentation, the word frequency vector of the second text message is set up；
Being used based on the service list for prestoring has supervision, the machine learning calculation with disaggregated model
Method carries out classified calculating to the word frequency vector.
9. device according to claim 6, it is characterised in that described device also includes：
Recording unit, is configured to record the selection of at least one service of the user to showing
As a result；
Feedback unit, is configured to the selection result is anti-as perhaps test content in study
Disaggregated model feed with adjusting parameter.
10. method according to claim 6, it is characterised in that first text envelope
Breath is obtained and is further configured to display unit：
When the information of user input is pictorial information, using image-recognizing method by the picture
Information is converted to the first text message；
When the information of user input is for voice messaging, using audio recognition method by the voice
Information is converted to the first text message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510849832.5A CN106815224A (en) | 2015-11-27 | 2015-11-27 | Service acquisition method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510849832.5A CN106815224A (en) | 2015-11-27 | 2015-11-27 | Service acquisition method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106815224A true CN106815224A (en) | 2017-06-09 |
Family
ID=59102111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510849832.5A Pending CN106815224A (en) | 2015-11-27 | 2015-11-27 | Service acquisition method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106815224A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107612814A (en) * | 2017-09-08 | 2018-01-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating candidate's return information |
| CN109670111A (en) * | 2018-12-20 | 2019-04-23 | 北京字节跳动网络技术有限公司 | Method and apparatus for pushed information |
| CN110377881A (en) * | 2019-06-11 | 2019-10-25 | 阿里巴巴集团控股有限公司 | Integrated approach, device and the system of text-processing service |
| CN111433786A (en) * | 2017-11-30 | 2020-07-17 | 三星电子株式会社 | Computing device and information input method of computing device |
| CN112149412A (en) * | 2020-10-23 | 2020-12-29 | 北京金和网络股份有限公司 | Catering industry service supervision method, device and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110170A (en) * | 2011-03-18 | 2011-06-29 | 北京百度网讯科技有限公司 | System with information distribution and search functions and information distribution method |
| CN103425777A (en) * | 2013-08-15 | 2013-12-04 | 北京大学 | Intelligent short message classification and searching method based on improved Bayesian classification |
-
2015
- 2015-11-27 CN CN201510849832.5A patent/CN106815224A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110170A (en) * | 2011-03-18 | 2011-06-29 | 北京百度网讯科技有限公司 | System with information distribution and search functions and information distribution method |
| CN103425777A (en) * | 2013-08-15 | 2013-12-04 | 北京大学 | Intelligent short message classification and searching method based on improved Bayesian classification |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107612814A (en) * | 2017-09-08 | 2018-01-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating candidate's return information |
| CN111433786A (en) * | 2017-11-30 | 2020-07-17 | 三星电子株式会社 | Computing device and information input method of computing device |
| CN111433786B (en) * | 2017-11-30 | 2024-05-24 | 三星电子株式会社 | Computing device and information input method for computing device |
| CN109670111A (en) * | 2018-12-20 | 2019-04-23 | 北京字节跳动网络技术有限公司 | Method and apparatus for pushed information |
| CN110377881A (en) * | 2019-06-11 | 2019-10-25 | 阿里巴巴集团控股有限公司 | Integrated approach, device and the system of text-processing service |
| CN110377881B (en) * | 2019-06-11 | 2023-04-07 | 创新先进技术有限公司 | Integration method, device and system of text processing service |
| CN112149412A (en) * | 2020-10-23 | 2020-12-29 | 北京金和网络股份有限公司 | Catering industry service supervision method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108874832B (en) | Target comment determination method and device | |
| US20190377788A1 (en) | Methods and systems for language-agnostic machine learning in natural language processing using feature extraction | |
| CN106227786B (en) | Method and apparatus for pushed information | |
| CN105095394B (en) | webpage generating method and device | |
| CN111125574B (en) | Method and device for generating information | |
| CN106815224A (en) | Service acquisition method and apparatus | |
| CN106383875B (en) | Man-machine interaction method and device based on artificial intelligence | |
| CN106407425A (en) | A method and a device for information push based on artificial intelligence | |
| CN106708940B (en) | Method and device for processing pictures | |
| CN105893344A (en) | User semantic sentiment analysis-based response method and device | |
| CN108090162A (en) | Information-pushing method and device based on artificial intelligence | |
| CN107679211A (en) | Method and apparatus for pushed information | |
| CN105786793A (en) | Method and device for analyzing semanteme of spoken language text information | |
| CN106874467A (en) | Method and apparatus for providing Search Results | |
| CN105654950A (en) | Self-adaptive voice feedback method and device | |
| CN107305551A (en) | The method and apparatus of pushed information | |
| CN108268450B (en) | Method and apparatus for generating information | |
| CN107402912A (en) | Parse semantic method and apparatus | |
| US11687711B2 (en) | Method and apparatus for generating commentary | |
| CN107632974B (en) | Chinese analysis platform suitable for multiple fields | |
| CN107291774A (en) | Error sample recognition methods and device | |
| CN114282524A (en) | Method, system and device for processing structured data of questionnaire information | |
| CN107644095A (en) | Method and apparatus for searching for information | |
| CN111428159A (en) | Online classification method and device | |
| CN109472028B (en) | Method and device for generating information |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170609 |