CN108629011A - Method and apparatus for sending feedback information - Google Patents
Method and apparatus for sending feedback information Download PDFInfo
- Publication number
- CN108629011A CN108629011A CN201810425676.3A CN201810425676A CN108629011A CN 108629011 A CN108629011 A CN 108629011A CN 201810425676 A CN201810425676 A CN 201810425676A CN 108629011 A CN108629011 A CN 108629011A
- Authority
- CN
- China
- Prior art keywords
- information
- feedback
- mentioned
- user
- category
- 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
Landscapes
- Electrically Operated Instructional Devices (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for sending feedback information.One specific implementation mode of this method includes：Receive user's input information that first terminal is sent；Above-mentioned user's input information is imported to the feedback information pre-established and generates model, obtain the matching degree between the corresponding target category information of above-mentioned user's input information, feedback information and above-mentioned user's input information problem information corresponding with above-mentioned feedback information, wherein, above-mentioned feedback information generates the classification of model information for identification, and match information question and answer corresponding with the classification identified to the problems in set information, according to matching degree from question and answer to determining reply message as feedback information in set；It is more than preset threshold value in response to the above-mentioned matching degree of determination, above-mentioned feedback information is sent to above-mentioned first terminal.The embodiment is realized sends feedback information for user's input information.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for sending feedback information.
Background technology
To promote QoS of customer, enterprise would generally establish the customer complaint channel for listening attentively to user voice, pass through
Customer complaint Channels user can submit the information such as complaint opinion, feedback opinion to product.Currently, enterprise can be by artificial
The information such as complaint opinion, the feedback opinion that the mode of processing submits user are replied.Since the information that user submits exists
Certain general character, therefore, staff need to do a large amount of repeated works when replying the information that user submits
Make.Enterprise can also be replied by the information that the form that intelligent robot automatically replies submits user, although intelligent machine
The reply to user information, but underaction sometimes may be implemented in device people to a certain extent, this can inevitably bring not to user
Good experience.
Invention content
The embodiment of the present application proposes the method and apparatus for sending feedback information.
In a first aspect, the embodiment of the present application provides a kind of method for sending feedback information, this method includes：It receives
User's input information that first terminal is sent；Above-mentioned user's input information is imported to the feedback information pre-established and generates model,
Obtain the corresponding target category information of above-mentioned user's input information, feedback information and above-mentioned user's input information with it is above-mentioned anti-
Matching degree between the corresponding problem information of feedforward information, wherein above-mentioned feedback information generates the classification of model information for identification,
And match information question and answer corresponding with the classification identified to the problems in set information, according to matching degree from asking
It answers questions and determines reply message as feedback information in set；It is more than preset threshold value in response to the above-mentioned matching degree of determination, it will be above-mentioned
Feedback information is sent to above-mentioned first terminal.
In some embodiments, the above method further includes：It is less than above-mentioned threshold value in response to the above-mentioned matching degree of determination, it will be above-mentioned
User's input information, target category information and feedback information are sent to second terminal.
In some embodiments, the above method further includes：The first update information that above-mentioned second terminal is sent is received,
In, above-mentioned first update information is determined based on above-mentioned user's input information, target category information and feedback information, above-mentioned
First update information includes the first feedback modifiers information；Above-mentioned first feedback modifiers information is sent to above-mentioned first terminal.
In some embodiments, above-mentioned first update information further includes first category update information；And the above method is also
Including：Model is generated using above-mentioned first category update information and the above-mentioned feedback information of above-mentioned first feedback modifiers Advance data quality.
In some embodiments, above-mentioned feedback information generates the classification identification that model includes information generic for identification
Network；And the above-mentioned first category update information of above-mentioned use and the above-mentioned feedback information of above-mentioned first feedback modifiers Advance data quality are given birth to
At model, including：It is different from above-mentioned first category update information in response to the above-mentioned target category information of determination, above-mentioned user is defeated
Enter information as input, using above-mentioned first category update information as output, the above-mentioned classification of training identifies network；In response to determination
Above-mentioned first feedback modifiers information is not present in the corresponding question and answer of classification indicated by above-mentioned first category update information to set
In, above-mentioned user's input information and above-mentioned first feedback modifiers information believe storage to above-mentioned first category amendment as question and answer
The indicated corresponding question and answer of classification of breath are in set.
In some embodiments, the above method further includes：Receive the second update information that second terminal is sent, wherein on
It includes second category update information and the second feedback modifiers information to state the second update information, and above-mentioned second update information is based on upper
State what first terminal was determined for the negative reviews information that above-mentioned feedback information is beamed back；Using above-mentioned second category update information and
The above-mentioned above-mentioned feedback information of second feedback modifiers Advance data quality generates model.
In some embodiments, above-mentioned feedback information generates the classification identification that model includes information generic for identification
Network；And the above-mentioned second category update information of above-mentioned use and the above-mentioned feedback information of above-mentioned second feedback modifiers Advance data quality are given birth to
At model, including：It is different from above-mentioned second category update information in response to the above-mentioned target category information of determination, above-mentioned user is defeated
Enter information as input, using above-mentioned second category update information as output, the above-mentioned classification of training identifies network；In response to determination
Above-mentioned second feedback modifiers information is not present in the corresponding question and answer of classification indicated by above-mentioned second category update information to set
In, above-mentioned user's input information and above-mentioned second feedback modifiers information believe storage to above-mentioned second category amendment as question and answer
The indicated corresponding question and answer of classification of breath are in set.
Second aspect, the embodiment of the present application provide a kind of device for sending feedback information, and device includes：First connects
Unit is received, is configured to receive user's input information that first terminal is sent；Import unit is configured to input above-mentioned user
Information imports the feedback information that pre-establishes and generates model, obtains the corresponding target category information of above-mentioned user's input information, anti-
Matching degree between feedforward information and above-mentioned user's input information problem information corresponding with above-mentioned feedback information, wherein above-mentioned
Feedback information generates the classification of model information for identification, and by information question and answer corresponding with the classification identified to gathering
The problems in information matched, according to matching degree from question and answer in set determine reply message as feedback information；First hair
Unit is sent, is configured in response to determine that above-mentioned matching degree is more than preset threshold value, above-mentioned feedback information is sent to above-mentioned the
One terminal.
In some embodiments, above-mentioned apparatus further includes：Second transmission unit is configured in response to determine above-mentioned matching
Degree is less than above-mentioned threshold value, and above-mentioned user's input information, target category information and feedback information are sent to second terminal.
In some embodiments, above-mentioned apparatus further includes：Second receiving unit is configured to receive above-mentioned second terminal hair
The first update information sent, wherein above-mentioned first update information be based on above-mentioned user's input information, target category information and
What feedback information determined, above-mentioned first update information includes the first feedback modifiers information；Third transmission unit, being configured to will be upper
It states the first feedback modifiers information and is sent to above-mentioned first terminal.
In some embodiments, above-mentioned first update information further includes first category update information；And above-mentioned apparatus is also
Including：First optimization unit, is configured to use above-mentioned first category update information and above-mentioned first feedback modifiers Advance data quality
Above-mentioned feedback information generates model.
In some embodiments, above-mentioned feedback information generates the classification identification that model includes information generic for identification
Network；And above-mentioned first optimization unit is further configured to：In response to the above-mentioned target category information of determination and above-mentioned first
Classification update information is different, and above-mentioned user is entered information as input, using above-mentioned first category update information as output, instruction
Practice above-mentioned classification and identifies network；It is not present in above-mentioned first category update information in response to the above-mentioned first feedback modifiers information of determination
The corresponding question and answer of indicated classification are in set, using above-mentioned user's input information and above-mentioned first feedback modifiers information as asking
Storage is answered questions to the corresponding question and answer of classification indicated by above-mentioned first category update information in set.
In some embodiments, above-mentioned apparatus further includes：Third receiving unit is configured to receive what second terminal was sent
Second update information, wherein above-mentioned second update information includes second category update information and the second feedback modifiers information, above-mentioned
Second update information is determined for the negative reviews information that above-mentioned feedback information is beamed back based on above-mentioned first terminal；Second is excellent
Change unit, is configured to use above-mentioned second category update information and the above-mentioned above-mentioned feedback information of second feedback modifiers Advance data quality
Generate model.
In some embodiments, above-mentioned feedback information generates the classification identification that model includes information generic for identification
Network；And above-mentioned second optimization unit is further configured to：In response to the above-mentioned target category information of determination and above-mentioned second
Classification update information is different, and above-mentioned user is entered information as input, using above-mentioned second category update information as output, instruction
Practice above-mentioned classification and identifies network；It is not present in above-mentioned second category update information in response to the above-mentioned second feedback modifiers information of determination
The corresponding question and answer of indicated classification are in set, using above-mentioned user's input information and above-mentioned second feedback modifiers information as asking
Storage is answered questions to the corresponding question and answer of classification indicated by above-mentioned second category update information in set.
The third aspect, the embodiment of the present application provide a kind of server, which includes：One or more processors；
Storage device is stored thereon with the one or more programs of storage, when said one or multiple programs are by said one or multiple places
When managing device execution so that said one or multiple processors realize the method as described in any realization method in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program,
In, the method as described in any realization method in first aspect is realized when which is executed by processor.
Method and apparatus provided by the embodiments of the present application for sending feedback information receive the transmission of the first client first
User's input information, user's input information is then imported into the feedback information that pre-establishes and generates model, obtains user's input
Between the corresponding target category information of information, feedback information and user's input information problem information corresponding with feedback information
Matching degree is finally more than preset threshold value in response to the above-mentioned matching degree of determination, and above-mentioned feedback information is sent to above-mentioned first visitor
Family end.It is directed to user's input information transmission feedback information to realize, to reduce cost of labor.Further, since user
Match degree is greater than the preset threshold between input information problem information corresponding with feedback information, thus it is guaranteed that transmitted
The accuracy of feedback information.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart according to one embodiment of the method for sending feedback information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for sending feedback information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for sending feedback information of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for sending feedback information of the application；
Fig. 6 is adapted for the structural schematic diagram of the computer system of the server for realizing the embodiment of the present application.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the embodiment of the present application for sending the method for feedback information or for sending feedback letter
The exemplary system architecture 100 of the device of breath.
As shown in Figure 1, system architecture 100 may include first terminal equipment 101, network 102, network 103, server
104 and second terminal equipment 105.Network 102 between first terminal equipment 101 and server 104 providing communication link
Medium.Network 103 between server 104 and second terminal equipment 105 provide communication link medium.Network 102
May include various connection types, such as wired, wireless communication link or fiber optic cables etc. with network 103.
User can be interacted by network 102 with server 104 using first terminal equipment 101, be disappeared with receiving or sending
Breath etc..Various telecommunication customer end applications, such as web browser applications, shopping class can be installed in first terminal equipment 101
Using, searching class application, instant messaging tools, mailbox client, social platform software etc..
Staff (such as contact staff) can use second terminal equipment 105 to be handed over by network 103 and server 104
Mutually, to receive or send information etc..Various telecommunication customer end applications, such as webpage can be installed in second terminal equipment 105
Browser application, the application of shopping class, searching class application, instant messaging tools, mailbox client, social platform software etc..
First terminal equipment 101 and second terminal equipment 105 can be hardware, can also be software.When first terminal is set
Standby 101 and second terminal equipment 105 when being hardware, can there is display screen and the various electronics of supported web page browsing are set
It is standby, including but not limited to smart mobile phone, tablet computer, E-book reader, MP3 player (Moving Picture
Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving
Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) player, knee
Mo(u)ld top half pocket computer and desktop computer etc..It, can when first terminal equipment 101 and second terminal equipment 105 are software
With in above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing point in it
Cloth service), single software or software module can also be implemented as.It is not specifically limited herein.
Server 104 can be to provide the server of various services, for example, the information that first terminal equipment 101 is sent into
The background server of row processing.Background server can carry out the user's input information received the processing such as to analyze, and will place
Reason result (such as feedback information) feeds back to terminal device.
It should be noted that the method for sending feedback information that the embodiment of the present application is provided is generally by server
104 execute, and correspondingly, the device for sending feedback information is generally positioned in server 104.
It should be noted that server can be hardware, can also be software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server can also be implemented as.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software can also be implemented as
Module.It is not specifically limited herein.
It should be understood that the number of the first terminal equipment, network, server and second terminal equipment in Fig. 1 is only to show
Meaning property.According to needs are realized, can have any number of first terminal equipment, network, server and second terminal equipment.
With continued reference to Fig. 2, the stream of one embodiment of the method for sending feedback information according to the application is shown
Journey 200.The method for being used to send feedback information, includes the following steps：
Step 201, user's input information that first terminal is sent is received.
In the present embodiment, the executive agent (such as server 104 shown in FIG. 1) of the method for sending feedback information
User's input information that first terminal is sent can be received by wired connection mode or radio connection.Herein, on
It can refers to terminal device used by a user (such as first terminal equipment 101 shown in FIG. 1) to state first terminal, and user can be with
Various information are sent by above-mentioned first terminal, such as to the complaint opinion of product, feedback opinion etc..As an example, above-mentioned
User's input information may include at least one of following：Text message, pictorial information and voice messaging.Believe when above-mentioned user inputs
When breath includes pictorial information, before subsequent processing, above-mentioned executive agent can carry out semantics recognition to picture, generate and scheme
The relevant text message of piece.When above-mentioned user's input information includes voice messaging, before subsequent processing, above-mentioned execution master
Body can carry out speech recognition to voice messaging, generate and the relevant text message of voice.It is clear that being carried out to picture semantic
The technology of identification, and it is the known technology studied and applied extensively at present that the technology of speech recognition is carried out to voice, therefore this
In repeat no more.
Step 202, user's input information is imported to the feedback information pre-established and generates model, obtains user's input information
Between corresponding target category information, feedback information and user's input information problem information corresponding with feedback information
With degree.
In the present embodiment, it can be stored with the feedback information pre-established in above-mentioned executive agent and generate model, it is above-mentioned
Feedback information generates model and can be used for the classification of identification information, for example, above-mentioned feedback information generate model may be used cluster,
The methods of naive Bayesian, support vector machines identification information generic.It then can be by information and the classification pair identified
The question and answer answered match the problems in set information.As an example, above-mentioned executive agent can by information with identified
The corresponding question and answer of classification to set the problems in information carry out Text similarity computing, and using obtained text similarity as
Matching degree.It is then possible to according to matching degree from question and answer to determining reply message as feedback information in set.On as an example,
Multiple question and answer can be previously stored with to set by stating in feedback information generation model, each question and answer stored are to set and one
A classification is corresponding.Each corresponding question and answer of classification include at least one question and answer pair to set, and each question and answer are to may include
Problem information and reply message.As an example, question and answer are to that can be the answer according to historical user's input information and contact staff
Statistics obtains in advance.Herein, above-mentioned classification can be set according to specific application scenarios.For example, being wrapped for one
The customer service scene of the website of product containing map class and payment class product, classification may include " map ", " payment ", " other "
Etc..In practice, classification can also be finely divided, for example, " map " is further divided into " place ", " road conditions ", " selects in path
Select " etc., " payment " can be divided into " account management ", " real name ", " withdrawing deposit " etc..
In this way, above-mentioned user's input information can be imported above-mentioned feedback information by above-mentioned executive agent generates model, to
Obtain the corresponding target category information of above-mentioned user's input information, feedback information and user's input information and above-mentioned feedback letter
Cease the matching degree between corresponding problem information.
Step 203, in response to determining that matching degree is more than preset threshold value, feedback information is sent to first terminal.
In the present embodiment, in response to the above-mentioned user's input information of determination problem information corresponding with above-mentioned feedback information it
Between matching degree be more than preset threshold value, feedback information can be sent to above-mentioned first terminal by above-mentioned executive agent, for
Family is checked.Herein, above-mentioned threshold value can be set according to actual needs.
In some optional realization methods of the present embodiment, the above-mentioned method for sending feedback information can also include
Unshowned following steps in Fig. 2：
Step 204, the second update information that second terminal is sent is received.
In this realization method, above-mentioned executive agent can receive the second update information of second terminal transmission.Wherein, on
It may include second category update information and the second feedback modifiers information to state the second update information, and above-mentioned second update information can be with
It is to be determined for the negative reviews information that above-mentioned feedback information is beamed back based on above-mentioned first terminal.
Herein, above-mentioned second terminal can refer to terminal device (example used in staff (such as contact staff)
Second terminal equipment 105 as shown in Figure 1).Feedback information is sent to after first terminal, and user can be looked by first terminal
See the feedback information.User can be directed to the feedback information and send comment information, and journey is satisfied with to the feedback information for commenting on
Degree.If user is dissatisfied to the feedback information, negative reviews information can be delivered.When staff sees that user delivers negative
After the comment information of face, the second update information can be determined based on above-mentioned user's input information and above-mentioned negative reviews information,
And the second determining update information is sent to above-mentioned executive agent.Second update information may include second category update information
With the second feedback modifiers information.Wherein, second category update information can be that staff determines for user's input information
Classification, the second feedback modifiers information can be the answer contents that staff is directed to that user's input information determines.
Step 205, model is generated using second category update information and the second feedback modifiers Advance data quality feedback information.
In this realization method, above-mentioned executive agent can use the second category update information received in step 204
Model is generated with the above-mentioned feedback information of the second feedback modifiers Advance data quality.It can make feedback by optimizing feedback information generation model
It is more accurate that information generates the feedback information that model generates.
In some optional realization methods, it may include the affiliated class of information for identification that above-mentioned feedback information, which generates model,
Other classification identifies network.As an example, above-mentioned classification identification network can be neural network, for example, convolutional neural networks, deep
Spend neural network etc..Above-mentioned steps 205 can specifically include the following contents：
Step 2051, in response to determining that target category information is different from second category update information, by user's input information
As input, using second category update information as output, training classification identifies network.
Herein, in response to determining that target category information is different from second category update information, above-mentioned executive agent can be with
Above-mentioned user is entered information as into the input that above-mentioned classification identifies network, using above-mentioned second category update information as above-mentioned class
Not Shi Bie network output, the above-mentioned classification of training identifies network.As an example, above-mentioned executive agent can identify net according to classification
Network outputs and inputs the network parameter for adjusting above-mentioned classification identification network.
Step 2051, in response to determining that the second feedback modifiers information is not present in the class indicated by second category update information
Not corresponding question and answer to storage as question and answer in set, second category is arrived using user's input information and the second feedback modifiers information
The corresponding question and answer of classification indicated by update information are in set.
Herein, it is not present in above-mentioned second category update information meaning in response to the above-mentioned second feedback modifiers information of determination
The corresponding question and answer of classification shown, will in set, above-mentioned user can be entered information as problem information by above-mentioned executive agent
Above-mentioned second feedback modifiers information is as reply message, by above-mentioned user's input information and above-mentioned second feedback modifiers information to ask
The form answered questions is stored to the corresponding question and answer of classification indicated by above-mentioned second category update information in set.
It is one of the application scenarios of the method according to the present embodiment for sending feedback information with continued reference to Fig. 3, Fig. 3
Schematic diagram.In the application scenarios of Fig. 3, user sends user's input information by first terminal 301 to server 302 first
" webpage has flame ".Later, user's input information " webpage has flame " can be imported and be pre-established by server 302
Feedback information generate model, obtain corresponding target category information " the bad letter of user's input information " webpage has flame "
Breath report ", feedback information " thanking to your report, we can handle flame as early as possible " and user's input information and feedback
Matching degree between the corresponding problem information of information.Finally, it is more than preset threshold value, server in response to the above-mentioned matching degree of determination
Feedback information " thanking to your report, we can handle flame as early as possible " can be sent to first terminal 301 by 302.
The method that above-described embodiment of the application provides is realized sends feedback information for user's input information, to drop
Low cost of labor.Further, since the matching degree between user's input information problem information corresponding with feedback information is more than in advance
If threshold value, thus it is guaranteed that the accuracy of transmitted feedback information.
With further reference to Fig. 4, it illustrates the flows 400 of another embodiment of the method for sending feedback information.
This is used to send the flow 400 of the method for feedback information, includes the following steps：
Step 401, user's input information that first terminal is sent is received.
In the present embodiment, the executive agent (such as server 104 shown in FIG. 1) of the method for sending feedback information
User's input information that first terminal is sent can be received by wired connection mode or radio connection.Herein, on
It can refers to terminal device used by a user (such as first terminal equipment 101 shown in FIG. 1) to state first terminal, and user can be with
Various information are sent by above-mentioned first terminal, such as to the complaint opinion of product, feedback opinion etc..
Step 402, user's input information is imported to the feedback information pre-established and generates model, obtains user's input information
Between corresponding target category information, feedback information and user's input information problem information corresponding with feedback information
With degree.
In the present embodiment, it can be stored with the feedback information pre-established in above-mentioned executive agent and generate model, it is above-mentioned
Feedback information generates model and can be used for the classification of identification information, can then ask information is corresponding with the classification identified
It answers questions the problems in set information to be matched, according to matching degree from question and answer to determining reply message as feedback letter in set
Breath.In this way, above-mentioned user's input information can be imported above-mentioned feedback information by above-mentioned executive agent generates model, on obtaining
It is corresponding with above-mentioned feedback information to state the corresponding target category information of user's input information, feedback information and user's input information
The problem of information between matching degree.
Step 403, in response to determining that matching degree is more than preset threshold value, feedback information is sent to first terminal.
In the present embodiment, in response to the above-mentioned user's input information of determination problem information corresponding with above-mentioned feedback information it
Between matching degree be more than preset threshold value, feedback information can be sent to above-mentioned first terminal by above-mentioned executive agent, for
Family is checked.Herein, above-mentioned threshold value can be set according to actual needs.
Step 404, in response to determining that matching degree is less than threshold value, by user's input information, target category information and feedback
Information is sent to second terminal.
In the present embodiment, it is less than above-mentioned threshold value in response to the above-mentioned matching degree of determination, above-mentioned executive agent can will be above-mentioned
User's input information, target category information and feedback information are sent to second terminal.Herein, above-mentioned second terminal can be
Refer to terminal device (such as second terminal equipment 105 shown in FIG. 1) used in staff (such as contact staff).
Step 405, the first update information that second terminal is sent is received.
In the present embodiment, above-mentioned executive agent can receive the first update information that above-mentioned second terminal is sent.It is above-mentioned
First update information can be determined based on above-mentioned user's input information, target category information and feedback information, above-mentioned
One update information may include the first feedback modifiers information.
In practice, user's input information, target category information and feedback information are sent to second by above-mentioned executive agent
After terminal, by the display of second terminal, staff can check user's input information, target category information and feedback letter
Breath, staff can determine the first update information based on the user's input information, target category information and feedback information seen.
As an example, staff can determine reply message for user's input information, and using determining reply message as first
Feedback modifiers information is sent to above-mentioned executive agent.
Step 406, the first feedback modifiers information is sent to first terminal.
In the present embodiment, above-mentioned first feedback modifiers information can be sent to above-mentioned first eventually by above-mentioned executive agent
End, so that above-mentioned first terminal is shown to user.
In some optional realization methods of the present embodiment, above-mentioned first update information can also be repaiied including first category
Positive information.As an example, above-mentioned first category update information can be the classification that staff is directed to that user's input information determines.
In this realization method, the above-mentioned method for sending feedback information can also include unshowned following steps in Fig. 4：
Step 407, model is generated using first category update information and the first feedback modifiers Advance data quality feedback information.
In this realization method, above-mentioned executive agent can use above-mentioned first category update information and above-mentioned first feedback
Update information optimizes above-mentioned feedback information and generates model.Feedback information can be made to generate mould by optimizing feedback information generation model
The feedback information that type generates is more accurate.
In some optional realization methods, it may include the affiliated class of information for identification that above-mentioned feedback information, which generates model,
Other classification identifies network, as an example, above-mentioned classification identification network can be neural network, for example, convolutional neural networks, deep
Spend neural network etc..And above-mentioned steps 407 can specifically include the following contents：
Step 4071, in response to determining that target category information is different from first category update information, by user's input information
As input, using first category update information as output, training classification identifies network.
Herein, different from above-mentioned first category update information in response to the above-mentioned target category information of determination, above-mentioned execution
Above-mentioned user can be entered information as the input of above-mentioned classification identification network by main body, and above-mentioned first category update information is made
Identify that the output of network, the above-mentioned classification of training identify network for above-mentioned classification.As an example, above-mentioned executive agent can be according to class
Not Shi Bie network output and input the network parameter for adjusting above-mentioned classification identification network.
Step 4072, in response to determining that the first feedback modifiers information is not present in the class indicated by first category update information
Not corresponding question and answer to storage as question and answer in set, first category is arrived using user's input information and the first feedback modifiers information
The corresponding question and answer of classification indicated by update information are in set.
Herein, it is not present in above-mentioned first category update information meaning in response to the above-mentioned first feedback modifiers information of determination
The corresponding question and answer of classification shown, will in set, above-mentioned user can be entered information as problem information by above-mentioned executive agent
Above-mentioned first feedback modifiers information is as reply message, by above-mentioned user's input information and above-mentioned first feedback modifiers information to ask
The form answered questions is stored to the corresponding question and answer of classification indicated by above-mentioned first category update information in set.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, it is used to send feedback information in the present embodiment
The flow 400 of method is highlighted when the matching degree between user's input information problem information corresponding with feedback information is less than threshold value
When, the step of user's input information, target category information and feedback information are sent to second terminal, is believed by inputting user
Breath, target category information and feedback information are sent to second terminal used in staff, can obtain staff's determination
The first feedback modifiers letter.The scheme of the present embodiment description can start when matching degree is less than threshold value and manually reply as a result,
Mode, to keep the answer for user's input information more accurate.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, it is anti-for sending that this application provides one kind
One embodiment of the device of feedforward information, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which specifically may be used
To be applied in various electronic equipments.
As shown in figure 5, the device 500 for sending feedback information of the present embodiment includes：First receiving unit 501 is led
Enter unit 502 and the first transmission unit 503.Wherein, the first receiving unit 501 is configured to receive the user that first terminal is sent
Input information；Import unit 502 is configured to importing above-mentioned user's input information into the feedback information generation model pre-established,
Obtain the corresponding target category information of above-mentioned user's input information, feedback information and above-mentioned user's input information with it is above-mentioned anti-
Matching degree between the corresponding problem information of feedforward information, wherein above-mentioned feedback information generates the classification of model information for identification,
And match information question and answer corresponding with the classification identified to the problems in set information, according to matching degree from asking
It answers questions and determines reply message as feedback information in set；First transmission unit 503 is configured in response to determine above-mentioned matching
Degree is more than preset threshold value, and above-mentioned feedback information is sent to above-mentioned first terminal.
In the present embodiment, the first receiving unit 501 of the device 500 for sending feedback information, 502 and of import unit
The specific processing of first transmission unit 503 and its caused technique effect can be respectively with reference to steps in 2 corresponding embodiment of figure
201, the related description of step 202 and step 203, details are not described herein.
In some optional realization methods of the present embodiment, above-mentioned apparatus 500 further includes：Second transmission unit is (in figure
It is not shown), it is configured in response to determine that above-mentioned matching degree is less than above-mentioned threshold value, by above-mentioned user's input information, target category
Information and feedback information are sent to second terminal.
In some optional realization methods of the present embodiment, above-mentioned apparatus 500 further includes：Second receiving unit is (in figure
It is not shown), it is configured to receive the first update information that above-mentioned second terminal is sent, wherein above-mentioned first update information is base
It is determined in above-mentioned user's input information, target category information and feedback information, above-mentioned first update information includes first anti-
Present update information；Third transmission unit (not shown) is configured to above-mentioned first feedback modifiers information being sent to above-mentioned
First terminal.
In some optional realization methods of the present embodiment, above-mentioned first update information further includes first category amendment letter
Breath；And above-mentioned apparatus 500 further includes：First optimization unit (not shown), is configured to repair using above-mentioned first category
Positive information and the above-mentioned feedback information of above-mentioned first feedback modifiers Advance data quality generate model.
In some optional realization methods of the present embodiment, above-mentioned feedback information generates model and includes information for identification
The classification of generic identifies network；And above-mentioned first optimization unit is further configured to：In response to the above-mentioned target of determination
Classification information is different from above-mentioned first category update information, and above-mentioned user is entered information as input, by above-mentioned first category
Update information identifies network as output, the above-mentioned classification of training；It is not present in response to the above-mentioned first feedback modifiers information of determination
Corresponding question and answer of classification indicated by above-mentioned first category update information are in set, by above-mentioned user's input information and above-mentioned the
One feedback modifiers information is as question and answer to storing to the corresponding question and answer of classification indicated by above-mentioned first category update information to collection
In conjunction.
In some optional realization methods of the present embodiment, above-mentioned apparatus 500 further includes：Third receiving unit is (in figure
It is not shown), it is configured to receive the second update information that second terminal is sent, wherein above-mentioned second update information includes second
Classification update information and the second feedback modifiers information, above-mentioned second update information are to be directed to above-mentioned feedback based on above-mentioned first terminal
What the negative reviews information that information is beamed back determined；Second optimization unit (not shown), is configured to use above-mentioned second class
Other update information and the above-mentioned feedback information of above-mentioned second feedback modifiers Advance data quality generate model.
In some optional realization methods of the present embodiment, above-mentioned feedback information generates model and includes information for identification
The classification of generic identifies network；And above-mentioned second optimization unit is further configured to：In response to the above-mentioned target of determination
Classification information is different from above-mentioned second category update information, and above-mentioned user is entered information as input, by above-mentioned second category
Update information identifies network as output, the above-mentioned classification of training；It is not present in response to the above-mentioned second feedback modifiers information of determination
Corresponding question and answer of classification indicated by above-mentioned second category update information are in set, by above-mentioned user's input information and above-mentioned the
Two feedback modifiers information are as question and answer to storing to the corresponding question and answer of classification indicated by above-mentioned second category update information to collection
In conjunction.
Below with reference to Fig. 6, it illustrates the computer systems 600 suitable for the server for realizing the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU, Central Processing Unit)
601, it can be according to the program being stored in read-only memory (ROM, Read Only Memory) 602 or from storage section
606 programs being loaded into random access storage device (RAM, Random Access Memory) 603 and execute various appropriate
Action and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.CPU 601、ROM
602 and RAM 603 is connected with each other by bus 604.Input/output (I/O, Input/Output) interface 605 is also connected to
Bus 604.
It is connected to I/O interfaces 605 with lower component：Storage section 606 including hard disk etc.；And including such as LAN (locals
Net, Local Area Network) card, modem etc. network interface card communications portion 607.Communications portion 607 passes through
Communication process is executed by the network of such as internet.Driver 608 is also according to needing to be connected to I/O interfaces 605.Detachable media
609, such as disk, CD, magneto-optic disk, semiconductor memory etc., as needed be mounted on driver 608 on, in order to from
The computer program read thereon is mounted into storage section 606 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed by communications portion 607 from network, and/or from detachable media
609 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.
It should be noted that computer-readable medium described herein can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two arbitrarily combines.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to：Electrical connection with one or more conducting wires, just
It takes formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type and may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In this application, can be any include computer readable storage medium or storage journey
The tangible medium of sequence, the program can be commanded the either device use or in connection of execution system, device.And at this
In application, computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned
Any appropriate combination.The behaviour for executing the application can be write with one or more programming languages or combinations thereof
The computer program code of work, described program design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully, partly be executed on the user computer, as an independence on the user computer
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes LAN (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as profit
It is connected by internet with ISP).
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses
The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet
Include the first receiving unit, import unit and the first transmission unit.Wherein, the title of these units is not constituted under certain conditions
Restriction to the unit itself, for example, the first receiving unit is also described as " receiving user's input that first terminal is sent
The unit of information ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should
Device：Receive user's input information that first terminal is sent；User's input information is imported to the feedback information pre-established
Model is generated, the corresponding target category information of user's input information, feedback information and user's input information are obtained
Matching degree between problem information corresponding with the feedback information, wherein the feedback information generates model to be believed for identification
The classification of breath, and information question and answer corresponding with the classification identified match the problems in set information, according to
Matching degree is from question and answer to determining reply message as feedback information in set；It is more than preset threshold in response to the determination matching degree
Value, the first terminal is sent to by the feedback information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (16)
1. a kind of method for sending feedback information, including：
Receive user's input information that first terminal is sent；
User's input information is imported to the feedback information pre-established and generates model, user's input information is obtained and corresponds to
Target category information, between feedback information and user's input information problem information corresponding with the feedback information
Matching degree, wherein the feedback information generates the classification of model information for identification, and by information and the class identified
Not corresponding question and answer match the problems in set information, according to matching degree from question and answer to determining that reply message is made in set
For feedback information；
It is more than preset threshold value in response to the determination matching degree, the feedback information is sent to the first terminal.
2. according to the method described in claim 1, wherein, the method further includes：
It is less than the threshold value in response to the determination matching degree, by user's input information, target category information and feedback
Information is sent to second terminal.
3. according to the method described in claim 2, wherein, the method further includes：
Receive the first update information that the second terminal is sent, wherein first update information is defeated based on the user
Enter what information, target category information and feedback information determined, first update information includes the first feedback modifiers information；
The first feedback modifiers information is sent to the first terminal.
4. according to the method described in claim 3, wherein, first update information further includes first category update information；With
And
The method further includes：
Model is generated using feedback information described in the first category update information and the first feedback modifiers Advance data quality.
5. according to the method described in claim 4, wherein, the feedback information generates model and includes the affiliated class of information for identification
Other classification identifies network；And
It is described to generate mould using feedback information described in the first category update information and the first feedback modifiers Advance data quality
Type, including：
It is different from the first category update information in response to the determination target category information, user's input information is made
For input, using the first category update information as output, the training classification identifies network；
The classification pair indicated by the first category update information is not present in response to determination the first feedback modifiers information
The question and answer answered are in set, arriving storage using user's input information and the first feedback modifiers information as question and answer described
The corresponding question and answer of classification indicated by first category update information are in set.
6. according to the method described in claim 1, wherein, the method further includes：
Receive the second update information that second terminal is sent, wherein second update information includes second category update information
With the second feedback modifiers information, second update information is born for what the feedback information was beamed back based on the first terminal
What face comment information determined；
Model is generated using feedback information described in the second category update information and the second feedback modifiers Advance data quality.
7. according to the method described in claim 6, wherein, the feedback information generates model and includes the affiliated class of information for identification
Other classification identifies network；And
It is described to generate mould using feedback information described in the second category update information and the second feedback modifiers Advance data quality
Type, including：
It is different from the second category update information in response to the determination target category information, user's input information is made
For input, using the second category update information as output, the training classification identifies network；
The classification pair indicated by the second category update information is not present in response to determination the second feedback modifiers information
The question and answer answered are in set, arriving storage using user's input information and the second feedback modifiers information as question and answer described
The corresponding question and answer of classification indicated by second category update information are in set.
8. a kind of device for sending feedback information, including：
First receiving unit is configured to receive user's input information that first terminal is sent；
Import unit is configured to importing user's input information into the feedback information generation model pre-established, obtains institute
State the corresponding target category information of user's input information, feedback information and user's input information and the feedback information
Matching degree between corresponding problem information, wherein the feedback information generates the classification of model information for identification, and will
Information question and answer corresponding with the classification identified match the problems in set information, according to matching degree from question and answer to collection
Determine reply message as feedback information in conjunction；
First transmission unit is configured in response to determine that the matching degree is more than preset threshold value, the feedback information is sent out
Give the first terminal.
9. device according to claim 8, wherein described device further includes：
Second transmission unit, be configured in response to determine the matching degree be less than the threshold value, by user's input information,
Target category information and feedback information are sent to second terminal.
10. device according to claim 9, wherein described device further includes：
Second receiving unit is configured to receive the first update information that the second terminal is sent, wherein described first corrects
Information is determined based on user's input information, target category information and feedback information, the first update information packet
Include the first feedback modifiers information；
Third transmission unit is configured to the first feedback modifiers information being sent to the first terminal.
11. device according to claim 10, wherein first update information further includes first category update information；
And
Described device further includes：
First optimization unit, is configured to use the first category update information and the first feedback modifiers Advance data quality institute
It states feedback information and generates model.
12. according to the devices described in claim 11, wherein the feedback information generates model including belonging to information for identification
The classification of classification identifies network；And
The first optimization unit is further configured to：
It is different from the first category update information in response to the determination target category information, user's input information is made
For input, using the first category update information as output, the training classification identifies network；
The classification pair indicated by the first category update information is not present in response to determination the first feedback modifiers information
The question and answer answered are in set, arriving storage using user's input information and the first feedback modifiers information as question and answer described
The corresponding question and answer of classification indicated by first category update information are in set.
13. device according to claim 8, wherein described device further includes：
Third receiving unit is configured to receive the second update information that second terminal is sent, wherein second update information
Including second category update information and the second feedback modifiers information, second update information is directed to based on the first terminal
What the negative reviews information that the feedback information is beamed back determined；
Second optimization unit, is configured to use the second category update information and the second feedback modifiers Advance data quality institute
It states feedback information and generates model.
14. device according to claim 13, wherein the feedback information generates model including belonging to information for identification
The classification of classification identifies network；And
The second optimization unit is further configured to：
It is different from the second category update information in response to the determination target category information, user's input information is made
For input, using the second category update information as output, the training classification identifies network；
The classification pair indicated by the second category update information is not present in response to determination the second feedback modifiers information
The question and answer answered are in set, arriving storage using user's input information and the second feedback modifiers information as question and answer described
The corresponding question and answer of classification indicated by second category update information are in set.
15. a kind of server, including：
One or more processors；
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-7.
16. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
The now method as described in any in claim 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810425676.3A CN108629011A (en) | 2018-05-07 | 2018-05-07 | Method and apparatus for sending feedback information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810425676.3A CN108629011A (en) | 2018-05-07 | 2018-05-07 | Method and apparatus for sending feedback information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108629011A true CN108629011A (en) | 2018-10-09 |
Family
ID=63695766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810425676.3A Pending CN108629011A (en) | 2018-05-07 | 2018-05-07 | Method and apparatus for sending feedback information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108629011A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726271A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Identify method, apparatus, equipment and the storage medium of customer problem content |
| CN109981577A (en) * | 2019-02-22 | 2019-07-05 | 维沃移动通信（深圳）有限公司 | A kind of content processing method, terminal device and server |
| CN112509712A (en) * | 2020-12-31 | 2021-03-16 | 曜立科技(北京)有限公司 | Tracking feedback method and system for puerpera information |
| CN113868393A (en) * | 2021-09-30 | 2021-12-31 | 南方电网数字电网研究院有限公司 | Data processing method and device for clarifying questions |
| CN117029863A (en) * | 2023-10-10 | 2023-11-10 | 中汽信息科技(天津)有限公司 | Feedback type traffic path planning method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893465A (en) * | 2016-03-28 | 2016-08-24 | 北京京东尚科信息技术有限公司 | Automatic question answering method and device |
| US20170132259A1 (en) * | 2015-11-09 | 2017-05-11 | Line Corporation | Method and system for detecting and using locations of electronic devices of users in a specific space to analyze social relationships between the users |
| CN106789595A (en) * | 2017-01-17 | 2017-05-31 | 北京诸葛找房信息技术有限公司 | Information-pushing method and device |
| CN107193811A (en) * | 2016-03-09 | 2017-09-22 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN107797984A (en) * | 2017-09-11 | 2018-03-13 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
-
2018
- 2018-05-07 CN CN201810425676.3A patent/CN108629011A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170132259A1 (en) * | 2015-11-09 | 2017-05-11 | Line Corporation | Method and system for detecting and using locations of electronic devices of users in a specific space to analyze social relationships between the users |
| CN107193811A (en) * | 2016-03-09 | 2017-09-22 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN105893465A (en) * | 2016-03-28 | 2016-08-24 | 北京京东尚科信息技术有限公司 | Automatic question answering method and device |
| CN106789595A (en) * | 2017-01-17 | 2017-05-31 | 北京诸葛找房信息技术有限公司 | Information-pushing method and device |
| CN107797984A (en) * | 2017-09-11 | 2018-03-13 | 远光软件股份有限公司 | Intelligent interactive method, equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109726271A (en) * | 2018-12-14 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Identify method, apparatus, equipment and the storage medium of customer problem content |
| CN109981577A (en) * | 2019-02-22 | 2019-07-05 | 维沃移动通信（深圳）有限公司 | A kind of content processing method, terminal device and server |
| CN112509712A (en) * | 2020-12-31 | 2021-03-16 | 曜立科技(北京)有限公司 | Tracking feedback method and system for puerpera information |
| CN113868393A (en) * | 2021-09-30 | 2021-12-31 | 南方电网数字电网研究院有限公司 | Data processing method and device for clarifying questions |
| CN117029863A (en) * | 2023-10-10 | 2023-11-10 | 中汽信息科技(天津)有限公司 | Feedback type traffic path planning method and system |
| CN117029863B (en) * | 2023-10-10 | 2023-12-22 | 中汽信息科技(天津)有限公司 | Feedback type traffic path planning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629011A (en) | Method and apparatus for sending feedback information | |
| CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
| CN109190114A (en) | Method and apparatus for generating return information | |
| CN108595628A (en) | Method and apparatus for pushed information | |
| CN107491547A (en) | Searching method and device based on artificial intelligence | |
| CN108388674A (en) | Method and apparatus for pushed information | |
| CN108121800A (en) | Information generating method and device based on artificial intelligence | |
| CN108986805B (en) | Method and apparatus for sending information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN110096584A (en) | A kind of answer method and device | |
| CN109635095A (en) | Method and apparatus for optimizing dialog model | |
| CN108520470A (en) | Method and apparatus for generating customer attribute information | |
| CN109325121A (en) | Method and apparatus for determining the keyword of text | |
| CN108280200A (en) | Method and apparatus for pushed information | |
| CN110046254A (en) | Method and apparatus for generating model | |
| CN109388548A (en) | Method and apparatus for generating information | |
| CN109522399B (en) | Method and apparatus for generating information | |
| CN110399465A (en) | Method and apparatus for handling information | |
| CN112925911B (en) | Complaint classification method based on multi-modal data and related equipment thereof | |
| CN109859006A (en) | For determining method, system, electronic equipment and the computer-readable medium of user interest profile | |
| CN109684624A (en) | A kind of method and apparatus in automatic identification Order Address road area | |
| CN110263142A (en) | Method and apparatus for output information | |
| CN109558593A (en) | Method and apparatus for handling text | |
| CN109389182A (en) | Method and apparatus 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 |