CN108810254A - Call localization method, device, computer equipment and storage medium - Google Patents
Call localization method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN108810254A CN108810254A CN201810486335.7A CN201810486335A CN108810254A CN 108810254 A CN108810254 A CN 108810254A CN 201810486335 A CN201810486335 A CN 201810486335A CN 108810254 A CN108810254 A CN 108810254A
- Authority
- CN
- China
- Prior art keywords
- location
- location information
- mobile terminal
- layer
- hidden layer
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72457—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to geographic location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/64—Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations
- H04M1/65—Recording arrangements for recording a message from the calling party
- H04M1/656—Recording arrangements for recording a message from the calling party for recording conversations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/74—Details of telephonic subscriber devices with voice recognition means
Abstract
This application involves a kind of call localization method, device, computer equipment and storage mediums.The method includes：The dialog context recorded in communication process is obtained, content is input in speech recognition detection model, obtains location information, location information is the position text information in dialog context, within a mapping application display location information.By being recorded to the dialog context in communication process, and according to the content of recording in map display location information, the position occurred in communication process can be quickly found, to improve the efficiency of position searched and occurred in communication process.
Description
Technical field
This application involves mobile communication technology fields, more particularly to a kind of call localization method, device, computer equipment
And storage medium.
Background technology
More and more abundant with the function of mobile terminal, user can be conversed by mobile terminal, done shopping, be surfed the Internet
Deng, user can arrange meeting place and time by mobile terminal, when mobile terminal is in talking state, the desired note of user
The meeting place arranged in record communication process can only be recorded or be allowed the friend on side to help by paper pen and record stipulated place
Text information.And it records the place arranged and after the time, when user is unfamiliar with the place of agreement, generally requires in map
The text information in place is inputted in application software, then determines the route for reaching stipulated place.
However, the mode of current this lookup route is extremely complex, and there are problems that inefficiency.
Invention content
Based on this, it is necessary to which in view of the above technical problems, efficient call localization method, dress can be carried by providing one kind
It sets, computer equipment and storage medium.
A kind of call localization method, the method includes：
Obtain the dialog context recorded in communication process；
The content is input in speech recognition detection model, location information is obtained, the location information is described logical
Talk about the position text information in content；
The location information is shown within a mapping application.
Before showing the location information within a mapping application in one of the embodiments, the method is also wrapped
It includes：
The talking state of mobile terminal is detected；
When it is end of conversation to detect the talking state, the location information is stored；
The location information is imported into the map application.
It is described in one of the embodiments, to show the location information within a mapping application, including：
Current location and the corresponding location point of the location information of the mobile terminal are obtained, the location point is institute
State location information corresponding point in the map application；
The current location and the location point are marked in the map application；
Shown in the map application current location to the location point route.
Show the current location to the location point in the map application in one of the embodiments,
After route, the method further includes：
Obtain the current location to the location point arrival pattern；
The time needed for the current location to the location point is calculated separately according to the arrival pattern；
Prompt the arrival pattern of the location point and time corresponding with the arrival pattern.
The method further includes in one of the embodiments,：
Obtain the trigger action generated by mobile terminal；
The detection to the talking state is opened according to the trigger action.
The speech recognition detection model is to train to obtain using deep neural network model in one of the embodiments,
's；
Described that the content is input in speech recognition detection model, the step of obtaining location information, includes：
Input layer sequence is obtained according to the content, is projected the input layer sequence to obtain first hidden
The corresponding hidden node sequence of layer, using the first hidden layer as currently processed hidden layer；
According to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron node of currently processed hidden layer
Weight and deviation the hidden node sequence of next layer of hidden layer is obtained using Nonlinear Mapping, using next layer of hidden layer as current place
Hidden layer is managed, repeats to enter according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each nerve of currently processed hidden layer
The step of corresponding weight of first node and deviation obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping, until defeated
Go out layer, obtains the location information probability matrix corresponding with the content of output layer output.
The method further includes in one of the embodiments,：
The current location of the mobile terminal is compared with the location information；
When the current location of the mobile terminal and the location information there are it is Chong Die when, send out prompt message.
A kind of call positioning device, described device include：
Content obtaining module, for obtaining the dialog context recorded in communication process；
Data obtaining module obtains location information for the content to be input in speech recognition detection model, described
Location information is the position text information in the dialog context；
Information display module, for showing the location information within a mapping application.
A kind of electronic equipment, including memory and processor, the memory are stored with computer program, the processor
Following steps are realized when executing the computer program：
Obtain the dialog context recorded in communication process；
The content is input in speech recognition detection model, location information is obtained, the location information is described logical
Talk about the position text information in content；
The location information is shown within a mapping application.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Following steps are realized when row：
Obtain the dialog context recorded in communication process；
The content is input in speech recognition detection model, location information is obtained, the location information is described logical
Talk about the position text information in content；
The location information is shown within a mapping application.
Above-mentioned call localization method, device, electronic equipment and storage medium are recorded by acquisition in communication process logical
Content is talked about, content is input in speech recognition detection model, obtains location information, location information is the position in dialog context
Text information, within a mapping application display location information.By being recorded to the dialog context in communication process, and root
According to the content of recording in map display location information, the position occurred in communication process can be quickly found, to improve
Search the efficiency of the position occurred in communication process.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is the internal structure chart of electronic equipment in one embodiment；
Fig. 2 is the flow diagram of call localization method in one embodiment；
Fig. 3 is the method flow diagram that location information is imported to map application in one embodiment；
Fig. 4 is the method flow diagram of display location information within a mapping application in one embodiment；
Fig. 5 is the surface chart of display location information within a mapping application in one embodiment；
Fig. 6 is the method flow diagram that arrival pattern and time are prompted in one embodiment；
Fig. 7 is the surface chart that arrival pattern and time are prompted in one embodiment；
Fig. 8 is to train to obtain the method flow of speech recognition detection model using deep neural network in one embodiment
Figure；
Fig. 9 is the structure diagram of call positioning device in one embodiment；
Figure 10 is the structure diagram of call positioning device in another embodiment.
Specific implementation mode
It is with reference to the accompanying drawings and embodiments, right in order to make the object, technical solution and advantage of the application be more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
In one embodiment, a kind of electronic equipment is provided, which can be terminal, and internal structure chart can
With as shown in Figure 1.The electronic equipment includes processor, memory, network interface and the database connected by system bus.Its
In, the processor of the electronic equipment is for providing calculating and control ability.The memory of the electronic equipment includes non-volatile deposits
Storage media, built-in storage.The non-volatile memory medium is stored with operating system, computer program and database.The interior storage
Device provides environment for the operation of operating system and computer program in non-volatile memory medium.The network of the electronic equipment connects
Mouth with server by network connection for being communicated.To realize a kind of call positioning side when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 1, is only tied with the relevant part of application scheme
The block diagram of structure, does not constitute the restriction for the electronic equipment being applied thereon to application scheme, and specific electronic equipment can be with
Including than more or fewer components as shown in the figure, either combining certain components or being arranged with different components.
In one embodiment, as shown in Fig. 2, providing a kind of call localization method, include the following steps：
Step 202, the dialog context recorded in communication process is obtained.
Wherein, when dialog context refers to that mobile terminal is in talking state, the talk of the two parties of mobile terminal is used
Content.Mobile terminal can be detected call, and mobile terminal may be at talking state, be also in end of conversation shape
State.
When mobile terminal is in talking state, dialog context recording function can be opened, in the call in communication process
Appearance is recorded.After the completion of recording, mobile terminal can get the dialog context recorded in communication process.
Step 204, content is input in speech recognition detection model, obtains location information, location information is in call
Position text information in appearance.
Speech recognition detection model can be advance trained model, for identification the location information in dialog context.
Location information refers to the position text information in dialog context.Have in this way for example, location information can be " feux rouges main road 69 "
The position text information of body.
The dialog context got can be input in advance trained speech recognition detection model by mobile terminal, language
Sound recognition detection model can be handled the dialog context of input, output position information again after processing.Mobile terminal can be with
The location information exported according to speech recognition detection model.
Step 206, display location information within a mapping application.
Map application refers to the application journey for positioning and showing geographical location that may be mounted on mobile terminal
Sequence.The location information that mobile terminal can be shown within a mapping application.
By obtaining the dialog context recorded in communication process, content is input in speech recognition detection model, is obtained
To location information, location information is the position text information in dialog context, within a mapping application display location information.It is logical
Cross and the dialog context in communication process recorded, and according to the content of recording in map display location information, can be fast
The position occurred in communication process is found in quick checking, to improve the efficiency for searching the position occurred in communication process.
As shown in figure 3, in one embodiment, a kind of call localization method provided can also include leading location information
Enter the process of map application, specific steps include：
Step 302, the talking state of mobile terminal is detected.
Mobile terminal can be detected talking state.Mobile terminal may be at talking state, be also in logical
Talk about end state.Wherein, talking state refers to that mobile terminal establishes connection with another mobile terminal, and can realize voice communication
State；End of conversation state refers to that mobile terminal is disconnected with another mobile terminal, terminates the state of voice communication.
Mobile terminal can be detected talking state by the monitor of itself.
Step 304, when it is end of conversation to detect talking state, storage location information.
When detecting that mobile terminal is in end of conversation state, mobile terminal can will pass through speech recognition detection model
Obtained location information is stored.Location information can be stored in local by mobile terminal, can also store location information
Onto server, when needing with location information, mobile terminal directly can obtain location information from local, can also be from service
Location information is obtained on device.
Step 306, location information is imported into map application.
When location information stores when local, mobile terminal can obtain location information from local, then location information is led
Enter to map application.When location information stores on the server, mobile terminal can obtain position letter from server
Breath, then location information is directed into map application.
It is detected by the talking state to mobile terminal, when it is end of conversation to detect talking state, stores position
Confidence ceases, and location information is imported map application.When it is end of conversation to detect talking state, mobile terminal just aligns
Confidence breath is stored, and is imported in map application, can be improved and obtain to avoid the location information omitted in dialog context
Take the accuracy of location information.
In one embodiment, as shown in figure 4, a kind of call localization method provided can also be included in map application journey
The process of display location information, specific steps include in sequence：
Step 402, current location and the corresponding location point of location information of mobile terminal are obtained, location point is believed for position
Cease corresponding point within a mapping application.
Global position system GPS (Global Positioning System), mobile terminal can be housed in mobile terminal
After location information is imported map application, the current location of mobile terminal can be got by GPS.Mobile terminal obtains
To location information can have multiple, each location information within a mapping application can be there are one corresponding location point.Example
Such as, location information includes " feux rouges main road 69 ", " school ", " shopping center ", within a mapping application, " feux rouges main road 69
Number " corresponding there are one location points, " school " is corresponding, and there are one location points, and " shopping center " is also corresponding, and there are one location points.
Mobile terminal can obtain current location, can also obtain the location information exported by speech recognition detection model
Location point within a mapping application.
Step 404, current location and location point are marked within a mapping application.
The current location of acquisition and location point can be marked by mobile terminal within a mapping application.Specifically
, mark mode can be highlighted within a mapping application.When location point only there are one when, mobile terminal only needs
Current location and a location point are marked in map application；When location point has it is multiple when, mobile terminal can be to current
Position and multiple location points are all marked.
Step 406, within a mapping application displaying current location to location point route.
After mobile terminal is within a mapping application marked current location and location point, map application can
With show current location to location point route.Likewise, when location point only there are one when, can show in map application
Route of the current location to this location point；When location point there are it is multiple when, can show in map application and work as simultaneously
Route of the front position to each location point.
By obtaining current location and the corresponding location point of location information of mobile terminal, location point is that location information exists
Corresponding point in map application marks current location and location point, in map application within a mapping application
Route of the middle displaying current location to location point.Mobile terminal can show current location to the route of location point in map,
The position occurred in communication process can be quickly found, to improve the efficiency for searching the position occurred in communication process.
In one embodiment, the surface chart of display location information is as shown in Figure 5 within a mapping application.Mobile terminal
When it is end of conversation to detect talking state, location information can be stored, then location information is directed into map and is answered
With in program.Within a mapping application, location information can be converted to corresponding location point in map application, mobile whole
End can show current location and location point within a mapping application, and to current location and location point into rower
Note.Map application can show current location to the route of location point.
For mobile terminal when it is end of conversation to detect talking state, mobile terminal can be to obtaining according to dialog context
Location information is stored, for example, the location information that mobile terminal obtains includes " school ", " second community ", " shopping center "
And " the first market ".Mobile terminal can import these location informations in map application.Meanwhile mobile terminal can be with
Obtain current location and location information corresponding location point within a mapping application.Mobile terminal can be obtained and be answered in map
With the current location 500 in program, the location point, the location point of second community 520, school in the first market 510 can also be obtained
530 location point and the location point in shopping center 540.Also, current location 500, the first market 510, second community 520,
School 530 and shopping center 540 can be marked with highlighting.After label, map application can also be shown
Current location 500 is respectively to the route in the first market 510, second community 520, school 530 and shopping center 540.
As shown in fig. 6, in one embodiment, a kind of call localization method provided can also include prompt arrival pattern
With the process of time, specific steps include：
Step 602, arrival pattern of the acquisition current location to location point.
Arrival pattern can be the concrete mode of current location in-position point.For example, arrival pattern can take public affairs
It hands over, takes subway, calls a taxi, walking and the modes such as ride.Current location shown in map application to the side of location point
Formula can there are many.Mobile terminal can show arrival pattern according to the trigger action of user in map application interface,
Wherein, the trigger action of user can be the control clicked on mobile terminal display screen, can also be on pressing mobile terminal
Button.Mobile terminal can get current location to the arrival pattern of location point.
Step 604, the time needed for current location to location point is calculated separately according to arrival pattern.
Mobile terminal can calculate the time that current location reaches location point needs according to arrival pattern.Map application journey
Arrival pattern shown in sequence can there are many, mobile terminal can calculate current location in place according to different arrival patterns
Set a little required time.For example, location point is school, the arrival pattern of current location to school can take pubic transport, multiply
It by the subway and calls a taxi, mobile terminal can calculate separately out the required time of taking pubic transport from current location to school, multiply
By the subway from current location to school the required time, call a taxi the required time from current location to school.
Step 606, the arrival pattern of location point and time corresponding with arrival pattern are prompted.
Mobile terminal can prompt the arrival side of location point after calculating current location to location point required time
Formula and time corresponding with arrival pattern.Mobile terminal can also calculate the distance between current location and location point, and
Prompt the distance between current location and location point.Specifically, the mode of prompt can be speech play, pop-up prompting frame etc..
For example, the location point that acquisition for mobile terminal arrives is school, arrival pattern includes taking pubic transport, taking subway and beat
Vehicle.It is 3.2 kilometers that mobile terminal, which can calculate the distance between current location and school, and mobile terminal can also calculate separately
It is to reach school when taking pubic transport from current location and need 20 minutes to go out arrival pattern；Arrival pattern is when taking subway, from working as
Front position reaches school and needs 15 minutes；Arrival pattern is to reach school when calling a taxi from current location and need 10 minutes.It is mobile whole
End can prompt the arrival pattern of location point and time corresponding with arrival pattern by way of speech play, can also lead to
The mode for crossing pop-up prompting frame prompts the arrival pattern of location point and time corresponding with arrival pattern.
By obtaining current location to the arrival pattern of location point, current location is calculated separately to position according to arrival pattern
Time needed for point, prompt the arrival pattern of location point and time corresponding with arrival pattern.Arrival can quickly be found
The arrival pattern of location point and the time of needs, to improve the efficiency for searching location point.
In one embodiment, prompt arrival pattern and the surface chart of time as shown in Figure 7.The position that acquisition for mobile terminal arrives
Set includes a little the first market 710, second community 720, school 730 and shopping center 740.Mobile terminal is in map application
In these location points are marked after, can be calculated separately out according to arrival pattern current location 700 arrive the first quotient of location point
710, distance and the required time in second community 720, school 730 and shopping center 740.For example, current location
The distance between 700 and school 730 are 3.2 kilometers, take bus 233, about 20 minutes and reach；Current location 700 and second
The distance between cell 720 is 5 kilometers, takes subway Line 1 and changes to No. 6 lines, reaches within about 45 minutes；Current location 700 and purchase
The distance between object center 740 is 10 kilometers, takes No. 6 lines of subway, is reached within about 60 minutes；Current location 700 and the first market
The distance between 710 be 10 kilometers, takes No. 6 lines of subway and changes to Line 1, reaches within about 60 minutes.
In one embodiment, a kind of call localization method provided can also include the detection opened to talking state
Process specifically includes：The trigger action generated by mobile terminal is obtained, the inspection to talking state is opened according to trigger action
It surveys.
Wherein, trigger action can be generated by the button on mobile terminal, can also be by mobile terminal
Display screen generate.Mobile terminal opens the detection to talking state by obtaining trigger action.That is, mobile terminal is opened
After the detection of talking state, it can detect that the talking state of mobile terminal is to be in call in talking state at any time
End state.
In one embodiment, as shown in figure 8, a kind of call localization method provided can also include using depth nerve
Network model trains to obtain the process of speech recognition detection model, and specific steps include：
Step 802, input layer sequence is obtained according to content, is projected the input layer sequence to obtain first hidden
The corresponding hidden node sequence of layer, using the first hidden layer as currently processed hidden layer.
Wherein, speech recognition detection model is using deep neural network (DNN, Deep Neural Networks) model
What training obtained.Deep neural network model includes input layer, hidden layer and output layer, wherein hidden layer can be multilayer.Input layer
Sequence node refers to being input to each input parameter of input layer to put in order, and is formed according to phonetic feature matrix itself
Sequence.Such as, it is assumed that input be a N-dimensional phonetic feature, then corresponding input layer sequence refers to this N-dimensional
The sequence that N number of input parameter is formed in sequence in phonetic feature.The effect of input layer is that the parameter of input is carried out projection change
It changes processing, obtains the corresponding hidden node sequence of the first hidden layer, i.e., it is the output of input layer is corresponding as the defeated of the first hidden layer
Enter, hidden node sequence refers to the sequence of the input parameter corresponding to the hidden layer.Using the first hidden layer as currently processed hidden layer, so
Input of the output of currently processed hidden layer as next layer of hidden layer is obtained afterwards.
Step 804, according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each god of currently processed hidden layer
Weight and deviation through first node obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping.
Wherein, input layer, hidden layer and output layer are all made of neuron, one as equivalent layer of each neuron
Neuron node.Adjacent neuron between layers all connects entirely, that is to say, that any one in i-th layer
Neuron is centainly adjacent with any one neuron of i+1 layer.Each neuron node in each hidden layer and output layer
It is corresponding with corresponding weight and deviation, input layer does not have weight and deviation.Getting the corresponding hidden layer section of currently processed hidden layer
After point sequence, according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron node of currently processed hidden layer
Weight and deviation calculate a median, the hidden of next layer of hidden layer then is obtained using Nonlinear Mapping to obtained median
Node layer sequence.
Step 806, using next layer of hidden layer as currently processed hidden layer, judge whether currently processed hidden layer is last layer hidden
Layer, if so, 808 are entered step, if it is not, then entering step 804.
Specifically, using the next layer of hidden layer got as currently processed hidden layer, judge whether currently processed hidden layer is most
Later layer hidden layer, if so, corresponding each according to the corresponding hidden node sequence of currently processed hidden layer and currently processed hidden layer
The corresponding output layer sequence node of output layer is calculated using Nonlinear Mapping in the weight and deviation of neuron node, if not
It is, then according to the power of the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron node of currently processed hidden layer
Weight and deviation obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping, and so on, until output layer.
Step 808, according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each god of currently processed hidden layer
Weight and deviation through first node obtain the corresponding output layer sequence node of output layer using Nonlinear Mapping, according to output layer section
Point sequence obtains the location information probability matrix corresponding with dialog context of output layer output.
Specifically, according to the weight and deviation of last layer of hidden layer corresponding hidden node sequence and each neuron node
The corresponding output layer sequence node of output layer is obtained using Nonlinear Mapping, i.e., using the output of last layer of hidden layer as output layer
Input, then output layer according to the weight of corresponding output layer sequence node and the corresponding each neuron node of output layer and partially
Simultaneously location information probability matrix corresponding with dialog context is calculated using Nonlinear Mapping in difference.
In one embodiment, a kind of call localization method provided can also include that current location is Chong Die with location information
When, the process of prompt message is sent out, is specifically included：The current location of mobile terminal is compared with location information, works as movement
The current location of terminal and location information there are it is Chong Die when, send out prompt message.
Current location can also be compared by mobile terminal with location information, if the current location and position of mobile terminal
There is overlapping in confidence breath, indicate that user is currently in the location information mentioned in dialog context, at this point, mobile terminal can be sent out
Go out prompt message.
In one embodiment, a kind of call localization method provided can also include obtaining to be arranged by mobile terminal
The process of distance range, specifically includes：The distance range parameter being arranged by mobile terminal is obtained, is shown within a mapping application
Show range corresponding with distance range parameter.
Distance range parameter is a numerical value, and distance range refers to the point centered on mobile terminal current location, with setting
Distance range parameter be radius range.Distance range parameter value can be user oneself setting, distance range parameter value
Unit can be kilometer.
Specifically, user can be by the display screen transmission range range parameter of mobile terminal, it can also be by movement
Display screen slide chosen distance range parameter.Acquisition for mobile terminal to setting distance range parameter after, can according to away from
Show corresponding range within a mapping application from range parameter.For example, the distance range parameter value that acquisition for mobile terminal arrives
It it is 10 kilometers, mobile terminal can within a mapping application be shown centered on mobile terminal current location, be with 10 kilometers
One range of radius.Mobile terminal can first judge the location information before location information is imported map application
Whether in distance range, if location information is being imported map application and is being shown；If not existing, position is not believed
Breath imports map application.
In one embodiment, a kind of call localization method is provided, which executes as follows：
First, mobile terminal can obtain the dialog context recorded in communication process.Mobile terminal is in talking state
When, dialog context recording function can be opened, the dialog context in communication process is recorded.It is mobile whole after the completion of recording
End can get the dialog context recorded in communication process.
Then, content can be input in speech recognition detection model by mobile terminal, obtain location information.Speech recognition
Detection model can be advance trained model, for identification the location information in dialog context.Location information refers to call
Position text information in content.For example, location information can be " feux rouges main road 69 " position text information specific in this way.
The dialog context got can be input in advance trained speech recognition detection model by mobile terminal, speech recognition inspection
The dialog context of input can be handled by surveying model, output position information again after processing.Mobile terminal can be according to voice
The location information that recognition detection model is exported.
Then, mobile terminal can be detected talking state.Mobile terminal may be at talking state, can also locate
In end of conversation state.Wherein, talking state refers to that mobile terminal establishes connection with another mobile terminal, and can realize that voice is logical
The state of words；End of conversation state refers to that mobile terminal is disconnected with another mobile terminal, terminates the state of voice communication.When
When detecting that talking state is end of conversation, mobile terminal can be with storage location information.It converses when detecting that mobile terminal is in
When end state, mobile terminal can store the location information obtained by speech recognition detection model.Mobile terminal
Location information can be stored in local, location information can also be stored onto server, when needing with location information, moved
Dynamic terminal directly can obtain location information from local, and location information can also be obtained from server.Mobile terminal can be with
Location information is imported into map application.
Then, mobile terminal can also obtain distance range parameter, and display and distance range within a mapping application
The corresponding range of parameter.Distance range parameter is a numerical value, and distance range refers to the point centered on mobile terminal current location,
Using the distance range parameter of setting as the range of radius.Distance range parameter value can be user oneself setting, distance range
The unit of parameter value can be kilometer.User can also be led to by the display screen transmission range range parameter of mobile terminal
Cross display screen sliding chosen distance range parameter on the move.It, can after acquisition for mobile terminal to the distance range parameter of setting
To show corresponding range within a mapping application according to distance range parameter.Location information is being imported map by mobile terminal
Before application program, the location information can be first judged whether in distance range, if location information importing map is being answered
With program and show；If not existing, location information map application is not imported into.
Then, mobile terminal can also display location information within a mapping application.Map application refers to can be with
The application program for positioning and showing geographical location of installation on mobile terminals.Mobile terminal can be in map application
It is middle to show obtained location information.Mobile terminal can also obtain current location and the corresponding position of location information of mobile terminal
It sets a little, location point is location information corresponding point within a mapping application.Mobile terminal can within a mapping application, will
The current location of acquisition and location point are marked.Mobile terminal is within a mapping application to current location and location point
After being marked, map application can show current location to the route of location point.When location point only there are one when, map
Can be shown in application program current location to this location point route；When location point there are it is multiple when, map application journey
Can be shown simultaneously in sequence current location to each location point route.
Mobile terminal can also obtain current location to the arrival pattern of location point.Arrival pattern can be that current location is arrived
Up to the concrete mode of location point.For example, arrival pattern can be take pubic transport, take subway, call a taxi, walking and the side such as ride
Formula.Current location shown in map application to location point mode can there are many.Mobile terminal can be according to user
Trigger action show arrival pattern in map application interface, wherein the trigger action of user can be click movement
Control on terminal display screen can also be the button pressed on mobile terminal.Mobile terminal can get current location and arrive
The arrival pattern of location point.Mobile terminal can calculate the time that current location reaches location point needs according to arrival pattern.
Mobile terminal after calculating current location to location point required time, can prompt location point arrival pattern and with
The arrival pattern corresponding time.
Mobile terminal can also open the detection to talking state by obtaining trigger action.That is, mobile terminal is opened
After the detection of talking state, it can detect that the talking state of mobile terminal is to be in call in talking state at any time
End state.Current location can also be compared by mobile terminal with location information, when the current location and position of mobile terminal
When confidence breath has overlapping, prompt message is sent out.
It should be understood that although each step in above-mentioned flow chart is shown successively according to the instruction of arrow, this
A little steps are not that the inevitable sequence indicated according to arrow executes successively.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, in above-mentioned flow chart at least
A part of step may include that either these sub-steps of multiple stages or stage are not necessarily in same a period of time to multiple sub-steps
Quarter executes completion, but can execute at different times, the execution in these sub-steps or stage be sequentially also not necessarily according to
Secondary progress, but can either the sub-step of other steps or at least part in stage in turn or replace with other steps
Ground executes.
In one embodiment, as shown in figure 9, providing a kind of call positioning device, including：Content obtaining module 910,
Data obtaining module 920 and information display module 930, wherein：
Content obtaining module 910, for obtaining the dialog context recorded in communication process.
Data obtaining module 920 obtains location information, position for content to be input in speech recognition detection model
Information is the position text information in dialog context.
Information display module 930, for display location information within a mapping application.
In one embodiment, as shown in Figure 10, a kind of call positioning device provided can also include：State-detection mould
Block 940, information storage module 950 and information import modul 960, wherein：
State detection module 940 is detected for the talking state to mobile terminal.
Information storage module 950, for when detect talking state be end of conversation when, storage location information.
Information import modul 960, for location information to be imported map application.
In one embodiment, information display module 930 can be also used for obtaining the current location and position of mobile terminal
Confidence ceases corresponding location point, and location point is location information corresponding point within a mapping application, within a mapping application
Current location and location point are marked, within a mapping application the route of displaying current location to location point.
In one embodiment, information display module 930 can be also used for obtaining current location to the arrival side of location point
Formula calculates separately the time needed for current location to location point according to arrival pattern, prompt location point arrival pattern and with
The arrival pattern corresponding time.
In one embodiment, content obtaining module 910 can be also used for obtaining the triggering behaviour generated by mobile terminal
Make, the detection to talking state is opened according to trigger action.
In one embodiment, data obtaining module 920 can be also used for obtaining input layer sequence according to content, will
Input layer sequence is projected to obtain the corresponding hidden node sequence of the first hidden layer, using the first hidden layer as currently processed hidden
Layer, according to the weight of the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron node of currently processed hidden layer
The hidden node sequence of next layer of hidden layer is obtained using Nonlinear Mapping with deviation, using next layer of hidden layer as currently processed hidden
Layer repeats to enter according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron section of currently processed hidden layer
The step of corresponding weight of point and deviation obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping, until output
Layer obtains the location information probability matrix corresponding with content of output layer output.
In one embodiment, information display module 930 can be also used for believing the current location of mobile terminal and position
Breath is compared, when the current location of mobile terminal and location information there are it is Chong Die when, send out prompt message.
Specific about call positioning device limits the restriction that may refer to above for call localization method, herein not
It repeats again.Modules in above-mentioned call positioning device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in or independently of in the processor in computer equipment, can also store in a software form in the form of hardware
In memory in electronic equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes following steps when being executed by processor：The dialog context recorded in communication process is obtained, content is input to
In speech recognition detection model, location information is obtained, location information is the position text information in dialog context, in map application
Display location information in program.
In one embodiment, following steps are also realized when computer program is executed by processor：Mobile terminal is led to
Speech phase is detected, and when it is end of conversation to detect talking state, storage location information answers location information importing map
Use program.
In one embodiment, computer program is executed by processor display location information within a mapping application, packet
It includes：Current location and the corresponding location point of location information of mobile terminal are obtained, location point is location information in map application
Corresponding point in program marks current location and location point within a mapping application, and displaying within a mapping application is worked as
Route of the front position to location point.
In one embodiment, following steps are also realized when computer program is executed by processor：Current location is obtained to arrive
The arrival pattern of location point calculates separately the time needed for current location to location point according to arrival pattern, prompts location point
Arrival pattern and time corresponding with arrival pattern.
In one embodiment, following steps are also realized when computer program is executed by processor：It obtains by mobile whole
The trigger action generated is held, the detection to talking state is opened according to trigger action.
In one embodiment, computer program, which is executed by processor, is input to content in speech recognition detection model,
Location information is obtained, including：Input layer sequence is obtained according to content, is projected input layer sequence to obtain first
The corresponding hidden node sequence of hidden layer, using the first hidden layer as currently processed hidden layer, according to the corresponding hidden layer of currently processed hidden layer
The weight and deviation of sequence node and the corresponding each neuron node of currently processed hidden layer are obtained next using Nonlinear Mapping
The hidden node sequence of layer hidden layer repeats to enter according to currently processed hidden layer pair using next layer of hidden layer as currently processed hidden layer
The corresponding weight of the corresponding each neuron node of the hidden node sequence and currently processed hidden layer answered and deviation are using non-linear
The step of mapping obtains the hidden node sequence of next layer of hidden layer obtains the corresponding with content of output layer output until output layer
Location information probability matrix.
In one embodiment, following steps are also realized when computer program is executed by processor：By working as mobile terminal
Front position is compared with location information, when the current location of mobile terminal and location information there are it is Chong Die when, send out prompt letter
Breath.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the flow of the embodiment of above-mentioned each method.Wherein,
Any reference to memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above example can be combined arbitrarily, to keep description succinct, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield is all considered to be the range of this specification record.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the protection domain of the application patent should be determined by the appended claims.
Claims (10)
1. a kind of call localization method, the method includes：
Obtain the dialog context recorded in communication process；
The content is input in speech recognition detection model, location information is obtained, the location information is in the call
Position text information in appearance；
The location information is shown within a mapping application.
2. according to the method described in claim 1, it is characterized in that, show within a mapping application the location information it
Before, the method further includes：
The talking state of mobile terminal is detected；
When it is end of conversation to detect the talking state, the location information is stored；
The location information is imported into the map application.
3. according to the method described in claim 1, it is characterized in that, described show the position letter within a mapping application
Breath, including：
Current location and the corresponding location point of the location information of the mobile terminal are obtained, the location point is institute's rheme
Confidence breath corresponding point in the map application；
The current location and the location point are marked in the map application；
Shown in the map application current location to the location point route.
4. according to the method described in claim 3, it is characterized in that, showing the current location in the map application
To after the route of the location point, the method further includes：
Obtain the current location to the location point arrival pattern；
The time needed for the current location to the location point is calculated separately according to the arrival pattern；
Prompt the arrival pattern of the location point and time corresponding with the arrival pattern.
5. according to the method described in claim 1, it is characterized in that, the method further includes：
Obtain the trigger action generated by mobile terminal；
The detection to the talking state is opened according to the trigger action.
6. according to the method described in claim 1, it is characterized in that, the speech recognition detection model is using depth nerve net
Network model training obtains；
Described that the content is input in speech recognition detection model, the step of obtaining location information, includes：
Input layer sequence is obtained according to the content, is projected the input layer sequence to obtain the first hidden layer pair
The hidden node sequence answered, using the first hidden layer as currently processed hidden layer；
According to the power of the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron node of currently processed hidden layer
Weight and deviation obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping, using next layer of hidden layer as currently processed hidden
Layer repeats to enter according to the corresponding hidden node sequence of currently processed hidden layer and the corresponding each neuron section of currently processed hidden layer
The step of corresponding weight of point and deviation obtain the hidden node sequence of next layer of hidden layer using Nonlinear Mapping, until output
Layer obtains the location information probability matrix corresponding with the content of output layer output.
7. method according to any one of claims 1 to 6, which is characterized in that the method further includes：
The current location of the mobile terminal is compared with the location information；
When the current location of the mobile terminal and the location information there are it is Chong Die when, send out prompt message.
8. a kind of call positioning device, which is characterized in that described device includes：
Content obtaining module, for obtaining the dialog context recorded in communication process；
Data obtaining module obtains location information, the position for the content to be input in speech recognition detection model
Information is the position text information in the dialog context；
Information display module, for showing the location information within a mapping application.
9. a kind of electronic equipment, including memory and processor, the memory are stored with computer program, which is characterized in that
The processor realizes the step of any one of claim 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claim 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486335.7A CN108810254A (en) | 2018-05-21 | 2018-05-21 | Call localization method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810486335.7A CN108810254A (en) | 2018-05-21 | 2018-05-21 | Call localization method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108810254A true CN108810254A (en) | 2018-11-13 |
Family
ID=64092749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810486335.7A Pending CN108810254A (en) | 2018-05-21 | 2018-05-21 | Call localization method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108810254A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117354717A (en) * | 2023-12-04 | 2024-01-05 | 宁波菊风系统软件有限公司 | Real-time position sharing method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000019743A1 (en) * | 1998-09-25 | 2000-04-06 | Call Technologies, Inc. | Mobile telephone location-based directory system |
| CN103167118A (en) * | 2012-07-05 | 2013-06-19 | 深圳市金立通信设备有限公司 | System and method for quickly positioning places in mobile phone calling process |
| CN105430612A (en) * | 2015-10-28 | 2016-03-23 | 惠州Tcl移动通信有限公司 | Method and system of realizing emergency positioning based on hand-held terminal |
| CN105466416A (en) * | 2015-11-17 | 2016-04-06 | 广东欧珀移动通信有限公司 | A route recommending method and a user terminal |
| CN105992127A (en) * | 2015-02-28 | 2016-10-05 | 中兴通讯股份有限公司 | IVR system and method thereof for realizing mobile phone voice service |
-
2018
- 2018-05-21 CN CN201810486335.7A patent/CN108810254A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000019743A1 (en) * | 1998-09-25 | 2000-04-06 | Call Technologies, Inc. | Mobile telephone location-based directory system |
| CN103167118A (en) * | 2012-07-05 | 2013-06-19 | 深圳市金立通信设备有限公司 | System and method for quickly positioning places in mobile phone calling process |
| CN105992127A (en) * | 2015-02-28 | 2016-10-05 | 中兴通讯股份有限公司 | IVR system and method thereof for realizing mobile phone voice service |
| CN105430612A (en) * | 2015-10-28 | 2016-03-23 | 惠州Tcl移动通信有限公司 | Method and system of realizing emergency positioning based on hand-held terminal |
| CN105466416A (en) * | 2015-11-17 | 2016-04-06 | 广东欧珀移动通信有限公司 | A route recommending method and a user terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117354717A (en) * | 2023-12-04 | 2024-01-05 | 宁波菊风系统软件有限公司 | Real-time position sharing method, device, equipment and storage medium |
| CN117354717B (en) * | 2023-12-04 | 2024-03-19 | 宁波菊风系统软件有限公司 | Real-time position sharing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106201424B (en) | A kind of information interacting method, device and electronic equipment | |
| CN106816149A (en) | The priorization content loading of vehicle automatic speech recognition system | |
| CN109643331A (en) | By automating natural language task/dialog authoring using existing content | |
| CN107493400A (en) | Upgrading to human operator who | |
| Zhao et al. | Stop detection in smartphone-based travel surveys | |
| CN105874530A (en) | Predicting recognition quality of a phrase in automatic speech recognition systems | |
| CN107222865A (en) | The communication swindle real-time detection method and system recognized based on suspicious actions | |
| CN105512228A (en) | Bidirectional question-answer data processing method and system based on intelligent robot | |
| CN108899012A (en) | Interactive voice equipment evaluating method, system, computer equipment and storage medium | |
| CN109753560B (en) | Information processing method and device of intelligent question-answering system | |
| CN107767053A (en) | Matching method, device, storage medium and the computer equipment of rideshare trip | |
| CN110121142A (en) | A kind of subway blind guiding system and method based on Android platform | |
| CN103151037A (en) | Correcting unintelligible synthesized speech | |
| CN110395200A (en) | Detect the device and method of wheel alignment situation | |
| CN106203306A (en) | The Forecasting Methodology at age, device and terminal | |
| CN106340308A (en) | Speech reply method and device | |
| CN110610698B (en) | Voice labeling method and device | |
| CN107589889A (en) | Image processing triggering method and device, electronic equipment and storage medium | |
| CN107104994A (en) | Audio recognition method, electronic installation and speech recognition system | |
| CN108595609A (en) | Generation method, system, medium and equipment are replied by robot based on personage IP | |
| CN109739969A (en) | Answer generation method and intelligent conversational system | |
| Ma et al. | Landmark-based location belief tracking in a spoken dialog system | |
| Safi et al. | ATLAS Project–Developing a mobile-based travel survey | |
| US10319376B2 (en) | Geo-spatial event processing | |
| CN106488015A (en) | Incoming call processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |
|
| RJ01 | Rejection of invention patent application after publication |