CN111382237B - Data processing method, device and task dialogue system - Google Patents
Data processing method, device and task dialogue system Download PDFInfo
- Publication number
- CN111382237B CN111382237B CN201811612816.4A CN201811612816A CN111382237B CN 111382237 B CN111382237 B CN 111382237B CN 201811612816 A CN201811612816 A CN 201811612816A CN 111382237 B CN111382237 B CN 111382237B
- Authority
- CN
- China
- Prior art keywords
- task
- model
- dialogue model
- task dialogue
- private data
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 56
- 230000008569 process Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 10
- 230000003993 interaction Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a data processing method, a data processing device and a task dialogue system. The method is applied to a second task dialogue model, wherein a task dialogue system to which the second task dialogue model belongs comprises a first task dialogue model, and the first task dialogue model is different from the second task dialogue model in type, and the method comprises the following steps: determining private data of the second task conversation model that requires use of the first task conversation model; the private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model; the private data is used. The method and the device realize point-to-point private data sharing among task dialogue models, solve the technical problem of single data sharing mode in the task dialogue system in the prior art, and improve the completeness of data sharing.
Description
Technical Field
The present invention relates to the field of software technologies, and in particular, to a data processing method, a data processing device, and a task dialogue system.
Background
In a task dialog system, a set of task dialogs designed to achieve a certain purpose may be expressed by a flowchart itself and a logic control method required for each node therein are called a Flow or task dialog model.
In general, in a task dialogue system, a user is supported to use one or more flows, each Flow is connected to the task dialogue system, and history data input or output in the execution process of the flows is uniformly stored and managed by the task dialogue system. The running process and the interactive data of the cross-drop type flows, namely, the flows of different types, such as the flows of booking air tickets and the flows of booking special vehicles, in the task dialogue system are mutually independent, the data sharing among the cross-drop type flows can only be carried out through the center of the task dialogue system, and only the public data uploaded to the center can be obtained, and the data sharing mode is single.
Disclosure of Invention
The embodiment of the invention provides a data processing method, a data processing device and a task dialogue system, which are used for providing a new method for sharing cross-drop task dialogue data and increasing a data sharing mode in the task dialogue system.
In a first aspect, an embodiment of the present invention provides a data processing method, applied to a second task session model, where a task session system to which the second task session model belongs includes a first task session model, where the first task session model is different from the second task session model in type, and the method includes:
Determining private data of the second task conversation model that requires use of the first task conversation model;
the private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
Optionally, the step of determining that the second task session model needs to use private data of the first task session model includes:
judging whether the slot position information required by the second task dialogue model can be obtained from the NUL analysis result understood by the current natural language and/or the output data of the second task dialogue model;
if not, determining that the second task dialogue model needs to use the private data of the first task dialogue model.
Optionally, the first task dialog model runs before the second task dialog model and is adjacent to the second task dialog model; or (b)
The first task dialog model is run before the second task dialog model and is a most recently run task dialog model of task dialog models associated with the second task dialog model.
Optionally, before the obtaining the private data of the first task dialogue model, the method further includes:
designating a source of private data to be used as a first task dialogue model in a configuration file of the second task dialogue model;
determining that the second task dialogue model is included in the target task dialogue model, which is specified in the configuration file of the first task dialogue model and can use private data of the target task dialogue model.
Optionally, the storing in a specified form includes: saved to the specified target location with the specified name.
Optionally, the obtaining private data of the first task dialogue model includes:
obtaining the serialized private data from a target position corresponding to the first task dialogue model;
and performing deserialization on the serialized private data to obtain the private data.
Optionally, after obtaining the private data of the first task dialogue model, the method further includes:
and identifying the private data, wherein the identification is used for indicating that the private data is sourced from the outside of the second task dialogue model.
In a second aspect, an embodiment of the present invention provides a task dialogue system, where the task dialogue system includes at least two different types of task dialogue models, and a data link is established between the different types of task dialogue models, where the system includes:
The first task dialogue model is used for storing private data generated in the operation process of the first task dialogue model in a specified form, authorizing the private data to a second task dialogue model for use, and the private data has no output record in the operation process of the first task dialogue model;
the second task dialogue model is different from the first task dialogue model in type; the second task dialog model is for: and when the private data of the first task dialogue model is determined to be needed, acquiring the private data of the first task dialogue model, and using the private data.
In a third aspect, an embodiment of the present invention provides a data processing apparatus applied to a second task session model, where a task session system to which the second task session model belongs includes a first task session model, and the first task session model is different from the second task session model in type, where the apparatus includes:
the judging unit is used for determining that the second task dialogue model needs to use private data of the first task dialogue model;
the acquisition unit is used for acquiring private data of the first task dialogue model, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
And the data query unit is used for using the private data.
Optionally, the judging unit is specifically configured to:
judging whether the slot position information required by the second task dialogue model can be obtained from the NUL analysis result understood by the current natural language and/or the output data of the second task dialogue model;
if not, determining that the second task dialogue model needs to use the private data of the first task dialogue model.
Optionally, the first task dialog model runs before the second task dialog model and is adjacent to the second task dialog model; or (b)
The first task dialog model is run before the second task dialog model and is a most recently run task dialog model of task dialog models associated with the second task dialog model.
Optionally, the apparatus further includes:
the configuration unit is used for designating the source of the private data to be used as the first task dialogue model in the configuration file of the second task dialogue model before acquiring the private data of the first task dialogue model; determining that the second task dialogue model is included in the target task dialogue model, which is specified in the configuration file of the first task dialogue model and can use private data of the target task dialogue model.
Optionally, the storing in a specified form includes: saved to the specified target location with the specified name.
Optionally, the acquiring unit is specifically configured to:
obtaining the serialized private data from a target position corresponding to the first task dialogue model;
and performing deserialization on the serialized private data to obtain the private data.
Optionally, the acquiring unit is further configured to:
after obtaining the private data of the first task dialogue model, identifying the private data, wherein the identification is used for indicating that the private data is sourced from the outside of the second task dialogue model.
In a fourth aspect, embodiments of the present application provide an electronic device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
determining private data of a first task dialogue model required to be used by a second task dialogue model, wherein the first task dialogue model and the second task dialogue model belong to the same task dialogue system, and the types of the first task dialogue model and the second task dialogue model are different;
The private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
In a fifth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
determining private data of a first task dialogue model required to be used by a second task dialogue model, wherein the first task dialogue model and the second task dialogue model belong to the same task dialogue system, and the types of the first task dialogue model and the second task dialogue model are different;
the private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
The above technical solutions in the embodiments of the present application at least have the following technical effects:
The embodiment of the application provides a data processing method applied to a second task dialogue model, wherein a task dialogue system to which the second task dialogue model belongs comprises a first task dialogue model, and the types of the first task dialogue model and the second task dialogue model are different, and the method comprises the following steps: determining that the second task conversation model requires private data using the first task conversation model; the private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model; the private data is used for realizing the point-to-point private data sharing between model pairs in the task dialogue system, solving the technical problem of single data sharing mode in the task dialogue system in the prior art, and the private data sharing method also solves the technical problem that the private data cannot be acquired due to the fact that the private data does not exist in dialogue records in the prior art, and improves the completeness of data sharing.
Drawings
FIG. 1 is a schematic diagram of a conversational task system according to an embodiment of the present application;
fig. 2 is a flow chart of a first task dialogue model side data processing method provided in an embodiment of the present application;
FIG. 3 is a flowchart illustrating a second task dialogue model side data processing method according to an embodiment of the present application;
FIG. 4 is a block diagram of a data processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the technical scheme provided by the embodiment of the application, a data processing method is provided, point-to-point private data sharing is performed between task dialogue models, and a data sharing mode in a task dialogue system is increased, so that the technical problem of single data sharing mode in the task dialogue system in the prior art is solved.
The following describes in detail the main implementation principles of the technical solution of the embodiments of the present application, the specific implementation manner and the corresponding beneficial effects.
Examples
First, the present embodiment classifies data generated in a task dialog model, i.e., a Flow running process, into public data and private data. The public data refers to interaction data generated in the interaction process of the task dialogue model and the user, such as the data of points, slots and the like, and the public data is usually output by the task dialogue model or input by the user. Private data refers to data of no output record generated in the running process of the task dialogue model. In general, private data is generated by a task dialogue model according to user-defined variables, exists in the Flow, and cannot appear in dialogue records between the model and the user. In the technical scheme of the embodiment of the application, the task dialogue model stores private data generated in the running process in a designated form and grants the private data to the designated task dialogue model for use, so that point-to-point private data sharing is realized.
Further, referring to fig. 1, the task dialogue system includes at least two different types of task dialogue models 11 and 12, where the different types of task dialogue models 11 and 12 may be connected to each other or connected in a unidirectional manner, so as to establish a point-to-point data link between the task dialogue models for private data sharing. In addition, the task dialogue system further comprises a storage center 10 for storing and managing public data generated by the task dialogue model. For public data management, the storage center 10 may also acquire public data of any first task dialogue model, find preset type data from the public data, and then send the acquired preset type data to an authorized object of the first task dialogue model, that is, a second task dialogue model. A task dialog model may obtain common data belonging to any other model of the same task dialog system from the memory center 10 of the task dialog system, thereby enabling sharing of the common data. Further, a private data sharing mode may be set for each task session model in the task session system to control sharing of private data, and a public data sharing mode may be set to control sharing of public data.
Based on the task dialogue system, the present embodiment further provides a data processing method, which is applied to the first task dialogue system, please refer to fig. 2, and the method includes:
s20: private data generated by a first task dialogue model is obtained;
s22: and storing the private data to a target position in a specified form, and authorizing the private data to be used by a second task dialogue model.
In a specific implementation process, the first task dialogue model may be any task dialogue model in the task dialogue system. And (3) further executing S20 in the process of operating the first task dialogue model, or detecting the operation state when operating the first task dialogue model, judging whether the private data sharing mode and/or the public data sharing mode of the task dialogue model are/is started, entering S20 if the private data sharing mode is started, jumping to the following public data sharing step if the public data sharing mode is started, prohibiting private data sharing if the private data sharing mode is closed, and prohibiting public data sharing if the public data sharing mode is closed.
For example: the session process between a certain booking task session model and a user is as follows:
query: "I want to order 8 months 10 # flying ticket to go to the sea"
answer: "Informa for your query for air ticket information from Beijing No. 8 month No. 10 to Shanghai"
query: 'help me to order earliest class economy class'
answer: "order your 8 months 10 Beijing to Shanghai 6 morning 35 minutes air ticket"
query: special vehicle for helping me to reserve side and connect with machine "
During the operation of this ticketing task dialog model, data is generated as a result of user input variables: the flight number "XXX" of the ticket ordered for the user is private data, but this value does not exist in the session, which is acquired S20. In addition, in the session, "help me reserve the on-line special car" indicates that the user needs to reserve the on-line special car, and the reserved on-line special car needs to use the on-line task session model, so that the user needs to jump to the on-line task session model, if the on-line special car is reserved through the on-line task session model, the flight number of the user needs to be acquired, but the flight number of the user cannot be acquired in the session record of the on-line task session model or the ticket booking task session model, and at this time, the private data stored in S22 needs to be used.
When the private data generated by the obtained first task dialogue model is saved to the target location in the specified form, the private data may be uniformly placed in a table with a specific name, for example, in the lua script language, the private data may be placed in a table with a name fe, and other dynamic languages are similar. For the first task dialog model, i.e. the source Flow, a destination Flow, i.e. a destination task dialog model that authorizes permission to invoke the private data, may be specified. Accordingly, the destination task session model needs to specify the source Flow of the private data when invoking the private data of other task session models. When the destination Flow or the source Flow is specified, the name of the private data destination Flow or the source Flow is specified in the Flow configuration file of the Flow. Furthermore, in order to improve the security of the private data, the private data can be encrypted according to the convention, so that the private data is prevented from being leaked.
During the running of the first task dialog model, a jump operation may be received from the user to jump from the first task dialog model to the second task dialog model. Specifically, whether the input content of the user contains preset content indicating the model switching can be detected, and if so, the user is confirmed to execute the jump operation. For example: the user inputs 'help me reserve the side to connect with the special car' in the booking task dialogue model, if the input content comprises the preset content 'reserve' and 'connect with the special car', the user is confirmed to execute the jump operation from the current model to the task dialogue model 'connect with the special car', the jump operation is received and the next step is entered. Of course, a switch button for switching the task model may be provided on the interface of the task dialogue model, and the user jump operation may be received by receiving the user operation of the switch button.
In a task dialog system, a jump is allowed by a first task dialog model to a second task dialog model specified by any second task dialog model or protocol in the system. In the running process of the second task session model, another data processing method provided in this embodiment is executed to share private data generated by the first task session model, please refer to fig. 3, and the method includes:
S30: determining that a second task conversation model requires private data of the first task conversation model;
s32: obtaining private data of a first task dialogue model, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by a second task dialogue model;
s34: the private data is used.
Before executing S30, it may be determined whether there is a first task session model that authorizes the second task session model, allowing it to acquire private data. If so, executing the private data sharing method; if not, the start of the method step is prohibited. For example: whether the name of the source Flow is written in the configuration file of the second task dialogue model can be searched first, if so, the first task dialogue model which authorizes the first task dialogue model is judged to exist, otherwise, the first task dialogue model does not exist.
In the running process of the second task dialogue model, the analysis result is generally obtained by adopting any mode as follows for the slot position information to be used: in a first mode, searching and obtaining from internal data of a second task dialogue model, wherein the internal data comprises: user input data, output data generated based on user input data, private data generated by the second task dialog model itself, and the like. And secondly, searching and acquiring public data stored in a storage center of the task dialogue system. In this embodiment, a new acquisition mode is further added, and S30-S34 are executed to acquire private data of the first task dialogue model, and the acquired private data is searched for slot position information to be used.
To enable the second task dialog model to use private data of the first task dialog model, the second task dialog model may be first configured, including: designating a source of private data to be used as a first task dialogue model in a configuration file of a second task dialogue model; and determining that the second task dialogue model is included in the destination task dialogue model specified in the configuration file of the first task dialogue model to which private data can be used, i.e. determining that the first task dialogue model authorizes the second task dialogue model to use the private data.
For the second task dialogue model with the configuration completed, it may be determined whether slot information required for the second task dialogue model can be obtained from the current natural language understanding NUL (Natural Language Understanding) parsing result and/or the output data of the second task dialogue model when S30 is performed. The natural language understanding NUL is used for analyzing input data of a user to obtain data which can be identified by the second task dialogue model. If the judgment result is yes, the required slot position information is directly inquired and obtained from the internal data of the second task model. If the judgment result is negative, determining that the second task dialogue model needs to use the private data of the first task dialogue model.
When the private data of the first task dialogue model is acquired in S32, based on different processing manners of the private data by the first task dialogue model, the private data is acquired in different manners:
1. the first task dialogue model sequences the generated private data, namely, converting the state information of the private data into a form capable of being stored or transmitted; then, the serialized private data is transmitted to a second task dialogue model; then, the second task dialogue model deserializes the received serialized private data to obtain the deserialized private data, so that the problem that the private data cannot be shared due to different supported data formats between the first task dialogue model and the second task dialogue model is avoided.
2. The first task dialogue model sequences the generated private data, and stores the serialized private data to a target position, such as a table with a specific name; then, the second task dialogue model obtains the serialized private data from the target position corresponding to the first task dialogue model; and then, deserializing the serialized private data to obtain final private data.
In a specific implementation, the source task dialogue model specified in the second task dialogue model may be multiple, and the second task dialogue model may select one or more first task dialogue models from the multiple source task dialogue models to obtain private data. In particular, the first task dialog model selected from the source task dialog models may be a model that runs before and is adjacent to the second task dialog model. Alternatively, the first task dialog model may be a task dialog model that was run before the second task dialog model and that was most recently run among the task dialog models associated with the second task dialog model. In this embodiment, the first task dialogue model and the second task dialogue model associated with the processed task content may be associated in advance, and private data use authorization may be performed, for example: the task processed by one task dialogue model is air ticket booking, the task dialogue model processed by the other task dialogue model is on-line, and the task content related to the air ticket booking comprises: passenger name, aircraft departure time, aircraft arrival time, etc., while the mission content involved in the connection includes: the passenger name, the airplane arrival time, the hotel address and the like contain common content, the airplane arrival time is related to the flight arrival time, the probability of using private data of the opposite party is high during operation, the two task dialogue models can be associated, and therefore the second task model can obtain the private data preferentially from the associated task dialogue model which operates recently, so that the user can inquire and obtain the required slot information from the associated task dialogue model, and the slot information obtaining efficiency is improved.
The second task dialogue model can further identify the obtained private data to obtain identified private data, the identified private data represents that the data is sourced from the outside of the second task dialogue model, and the private data is effectively distinguished from the data in the second task dialogue model, so that the private data generated by the first task dialogue model is prevented from polluting variables in the second task dialogue model.
After obtaining the private data of the first task dialogue model, executing S34 to use the obtained private data to perform data information query, and obtaining the slot information to be used.
The private data sharing provided by this embodiment is illustrated by a complete example:
for example: if private data of the air ticket is wanted to be shared in each Flow, private class data of the air ticket can be put into the table named fe, for example, private data representing the number of the determined airplane flight can be put into a variable named fe.flight_number, and the destination Flow which can use the private data is specified in a configuration file.
When the user executes the receiver Flow, the private data, which is a variable in the ticket booking, can be used, and the private data source Flow is specified in the rule file of the receiver Flow (destination), and at this time, the system or the source Flow sequences all the variables placed in the fe table in the air_ticket Flow and sends the serialized variables to the receiver Flow.
Of course, which Flow to jump specifically to may be triggered by the end user language, e.g. the user inquires about weather, triggers the Flow corresponding to weather, and if the user orders a vehicle, triggers the special vehicle Flow.
It can be seen that in the pick-up Flow, when the platform user uses the custom variable, if the pick-up flight number is represented by fe.pick up_flight_number, this value can have two sources, 1, given by the end user, for example, "pick-up of me reservation day mu 6573", 2, when this value is empty, it can try to get from the private data of the other (same task dialog system) flows.
Compared with private data, the embodiment can also obtain the public data generated by the first task dialogue model in the process of operating the first task dialogue model for the public data of the task dialogue model. And storing the public data of the first task dialogue model to a storage center of the task dialogue system, wherein the data in the storage center can be used by any task dialogue model in the task dialogue system to realize sharing of the public data. Similarly, each task dialogue model can also set a common data sharing mode, and when the common data sharing mode is started, common data generated in the running process of the task dialogue model is stored in a storage center for other task dialogue models to use.
The data size of the public data of the task dialogue model is usually larger, especially the public data generated by multiple rounds of dialogues, the dialogues are lengthy and destination and time transformed multiple times, the public data needing to be traced back and the user answer are numerous, the time for searching the variables to be used from the public data in multiple rounds of dialogues one by one is longer and errors are easy to generate, and in order to save the time cost of sharing the public data and reduce the error rate, the embodiment further executes the following steps:
acquiring public data generated by a first task dialogue model; searching and obtaining preset type data from the public data, wherein the preset type data comprises the following steps: time, place, flight number, number of turns, etc.; if the second task dialogue model is an authorized object of the first task dialogue model, the preset type data is sent to the second task dialogue model or the preset type data is stored in another target position, so that the second task dialogue model can quickly obtain the variable to be used from the preset type data, the time cost of searching and obtaining from the public data is saved, and the efficiency of sharing the public data is improved. Likewise, the present embodiment may also perform serialization and/or identification operations on the preset type of data to increase the readability and the recognizability of the preset type of data. Correspondingly, the second task dialogue model may acquire preset type data obtained by searching from the public data generated by the first task model when the judgment result obtained in S30 is no; furthermore, the value of the current query data is obtained based on the obtained query of the preset type data, and the efficiency of obtaining the external data by the second task dialogue model is greatly improved.
In the above embodiment, the data interaction architecture of the task dialogue system is extended, and the point-to-point interaction is increased on the basis of the center mode. The private data generated by the task dialogue model operation is stored and shared, so that the technical problem that the private data cannot be acquired because the private data does not exist in the dialogue records in the prior art is solved, and the data sharing mode of the task dialogue system is increased. Furthermore, the embodiment also extracts the data of the preset type from the public data of the task dialogue model to share, so that the public data sharing efficiency is improved, and the public data acquisition error rate is reduced.
For the foregoing embodiment, a data processing method is provided, and an embodiment of the present application correspondingly provides a data processing device, which is applied to a second task dialogue model, where a task dialogue system to which the second task dialogue model belongs includes a first task dialogue model, and the types of the first task dialogue model and the second task dialogue model are different, please refer to fig. 4, where the device includes:
a judging unit 41, configured to determine that the second task session model needs to use private data of the first task session model;
An obtaining unit 42, configured to obtain private data of the first task session model, where the private data of the first task session model is generated during the operation of the first task session model, has no output record, is stored in a specified form, and is authorized for use by the second task session model;
a data query unit 43 for using the private data.
Specifically, in determining whether private data of the first task dialogue model is required, the determining unit 41 may determine whether slot information required for the second task dialogue model is available from the NUL analysis result understood by the current natural language and output data of the second task dialogue model; if not, determining that the second task dialogue model needs to use the private data of the first task dialogue model. Wherein the first task dialog model runs before the second task dialog model and is adjacent to the second task dialog model; or, the first task dialog model is run before the second task dialog model and is the most recently run task dialog model of the task dialog models associated with the second task dialog model. When the first task dialogue model stores private data in a specified form, a specified name may be stored to a specified target location.
In order to achieve the point-to-point private data sharing of the task session model, the apparatus further comprises a configuration unit 44, configured to designate, in the configuration file of the second task session model, a source of private data to be used as the first task session model, before acquiring the private data of the first task session model; determining that the second task dialogue model is included in the target task dialogue model, which is specified in the configuration file of the first task dialogue model and can use private data of the target task dialogue model.
To facilitate private data sharing between two task dialog models, the acquisition unit 42 may be specifically configured to: obtaining the serialized private data from a target position corresponding to the first task dialogue model; and performing deserialization on the serialized private data to obtain the private data.
Further, in order to avoid data pollution of the internal data by the external data, the obtaining unit 42 may be further configured to: after obtaining the private data of the first task dialogue model, identifying the private data, wherein the identification is used for indicating that the private data is sourced from the outside of the second task dialogue model.
The specific manner in which the individual units perform the operations in relation to the apparatus of the above embodiments has been described in detail in relation to the embodiments of the method and will not be described in detail here.
Fig. 5 is a block diagram illustrating an electronic device 800 for implementing data processing according to an example embodiment. For example, electronic device 800 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.
Referring to fig. 5, an electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/presentation (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen between the electronic device 800 and the user that provides a presentation interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to present and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for rendering audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the electronic device 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in position of the electronic device 800 or a component of the electronic device 800, the presence or absence of a user's contact with the electronic device 800, an orientation or acceleration/deceleration of the electronic device 800, and a change in temperature of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices, either wired or wireless. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of electronic device 800 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
A non-transitory computer readable storage medium, which when executed by a processor of a mobile terminal, causes the mobile terminal to perform a data processing method, the method comprising: determining private data of a first task dialogue model required to be used by a second task dialogue model, wherein the first task dialogue model and the second task dialogue model belong to the same task dialogue system, and the types of the first task dialogue model and the second task dialogue model are different; the private data of the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model; the private data is used.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (15)
1. A data processing method, which is applied to a second task dialogue model, wherein a task dialogue system to which the second task dialogue model belongs includes a first task dialogue model, the first task dialogue model is different from the second task dialogue model in type, and a point-to-point data link is established between the first task dialogue model and the second task dialogue model, the method includes:
the second task dialogue model is configured: designating a source of private data to be used as a first task dialogue model in a configuration file of the second task dialogue model, and determining that a destination task dialogue model capable of using the private data is designated in the configuration file of the first task dialogue model, wherein the second task dialogue model is included in the destination task dialogue model;
For a second task dialogue model with complete configuration, when private data of the first task dialogue model is determined to be needed to be used by the second task dialogue model, private data authorized to be used by the second task dialogue model by the first task dialogue model is obtained, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
2. The method of claim 1, wherein the step of determining that the second task conversation model requires private data using the first task conversation model comprises:
judging whether the slot position information required by the second task dialogue model can be obtained from the NUL analysis result understood by the current natural language and/or the output data of the second task dialogue model;
if not, determining that the second task dialogue model needs to use the private data of the first task dialogue model.
3. A method according to claim 1 or 2, wherein the first task dialog model runs before the second task dialog model and is adjacent to the second task dialog model; or (b)
The first task dialog model is run before the second task dialog model and is a most recently run task dialog model of task dialog models associated with the second task dialog model.
4. The method of claim 1, wherein the saving in a specified form comprises:
saved to the specified target location with the specified name.
5. The method of claim 1, wherein the obtaining private data of the first task conversation model comprises:
obtaining the serialized private data from a target position corresponding to the first task dialogue model;
and performing deserialization on the serialized private data to obtain the private data.
6. The method according to any one of claims 4 to 5, wherein after obtaining the private data of the first task session model, the method further comprises:
and identifying the private data, wherein the identification is used for indicating that the private data is sourced from the outside of the second task dialogue model.
7. A task dialog system comprising at least two different types of task dialog models, between which point-to-point data links are established, the system comprising:
The first task dialogue model is used for storing private data generated in the operation process of the first task dialogue model in a specified form, authorizing the private data to a second task dialogue model for use, and the private data has no output record in the operation process of the first task dialogue model;
the second task dialogue model is different from the first task dialogue model in type; the second task dialog model is for: the second task dialogue model is configured: designating a source of private data to be used as a first task dialogue model in a configuration file of the second task dialogue model, and determining that a destination task dialogue model capable of using the private data is designated in the configuration file of the first task dialogue model, wherein the second task dialogue model is included in the destination task dialogue model; and for the second task dialogue model with the configuration completed, when the private data of the first task dialogue model is determined to be needed, acquiring the private data of the first task dialogue model, and using the private data.
8. A data processing apparatus, applied to a second task session model, where the task session system to which the second task session model belongs includes a first task session model, where the first task session model is different from the second task session model in type, and a peer-to-peer data link is established between the first task session model and the second task session model, the apparatus includes:
The configuration unit is used for designating the source of the private data to be used as the first task dialogue model in the configuration file of the second task dialogue model before acquiring the private data of the first task dialogue model; determining that the second task dialogue model is included in a target task dialogue model which is specified in a configuration file of the first task dialogue model and can use private data of the target task dialogue model;
the judging unit is used for determining that the second task dialogue model needs to use private data of the first task dialogue model for the configured second task dialogue model;
the acquisition unit is used for acquiring private data authorized to be used by the second task dialogue model by the first task dialogue model when the second task dialogue model needs to use the private data of the first task dialogue model, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
and the data query unit is used for using the private data.
9. The apparatus of claim 8, wherein the determining unit is specifically configured to:
Judging whether the slot position information required by the second task dialogue model can be obtained from the NUL analysis result understood by the current natural language and/or the output data of the second task dialogue model;
if not, determining that the second task dialogue model needs to use the private data of the first task dialogue model.
10. The apparatus of claim 8 or 9, wherein the first task dialog model runs before and adjacent to the second task dialog model; or (b)
The first task dialog model is run before the second task dialog model and is a most recently run task dialog model of task dialog models associated with the second task dialog model.
11. The apparatus of claim 8, wherein the saving in a specified form comprises:
saved to the specified target location with the specified name.
12. The apparatus of claim 8, wherein the acquisition unit is specifically configured to:
obtaining the serialized private data from a target position corresponding to the first task dialogue model;
and performing deserialization on the serialized private data to obtain the private data.
13. The apparatus according to any one of claims 8, 11-12, wherein the acquisition unit is further configured to:
after obtaining the private data of the first task dialogue model, identifying the private data, wherein the identification is used for indicating that the private data is sourced from the outside of the second task dialogue model.
14. An electronic device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
the second task dialogue model is configured: designating a source of private data to be used as a first task dialogue model in a configuration file of the second task dialogue model, and determining that a destination task dialogue model capable of using the private data is designated in the configuration file of the first task dialogue model, wherein the second task dialogue model is included in the destination task dialogue model;
for a second task dialogue model which is configured to be completed, determining private data of a first task dialogue model required to be used by the second task dialogue model, wherein the first task dialogue model and the second task dialogue model belong to the same task dialogue system, the types of the first task dialogue model and the second task dialogue model are different, and a point-to-point data link is established between the first task dialogue model and the second task dialogue model;
When determining that the second task dialogue model needs to use the private data of the first task dialogue model, acquiring the private data authorized by the first task dialogue model to be used by the second task dialogue model, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
15. A computer readable storage medium having stored thereon a computer program, characterized in that the program when executed by a processor performs the steps of:
the second task dialogue model is configured: designating a source of private data to be used as a first task dialogue model in a configuration file of the second task dialogue model, and determining that a destination task dialogue model capable of using the private data is designated in the configuration file of the first task dialogue model, wherein the second task dialogue model is included in the destination task dialogue model;
for a second task dialogue model which is configured to be completed, determining private data of a first task dialogue model required to be used by the second task dialogue model, wherein the first task dialogue model and the second task dialogue model belong to the same task dialogue system, the types of the first task dialogue model and the second task dialogue model are different, and a point-to-point data link is established between the first task dialogue model and the second task dialogue model;
When determining that the second task dialogue model needs to use the private data of the first task dialogue model, acquiring the private data authorized by the first task dialogue model to be used by the second task dialogue model, wherein the private data of the first task dialogue model is generated in the running process of the first task dialogue model, has no output record, is stored in a specified form and is authorized to be used by the second task dialogue model;
the private data is used.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811612816.4A CN111382237B (en) | 2018-12-27 | 2018-12-27 | Data processing method, device and task dialogue system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811612816.4A CN111382237B (en) | 2018-12-27 | 2018-12-27 | Data processing method, device and task dialogue system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111382237A CN111382237A (en) | 2020-07-07 |
| CN111382237B true CN111382237B (en) | 2024-02-06 |
Family
ID=71216243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811612816.4A Active CN111382237B (en) | 2018-12-27 | 2018-12-27 | Data processing method, device and task dialogue system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382237B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003316385A (en) * | 2002-04-24 | 2003-11-07 | Hitachi Ltd | Voice interaction system and voice interaction method |
| CN103942056A (en) * | 2014-05-05 | 2014-07-23 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and method based on scenes |
| CN107395711A (en) * | 2017-07-17 | 2017-11-24 | 中国农业银行股份有限公司 | Heterogeneous system session access method and relevant apparatus |
| CN108829797A (en) * | 2018-04-25 | 2018-11-16 | 苏州思必驰信息科技有限公司 | Multiple agent dialog strategy system constituting method and adaptive approach |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10096316B2 (en) * | 2013-11-27 | 2018-10-09 | Sri International | Sharing intents to provide virtual assistance in a multi-person dialog |
| US20180090141A1 (en) * | 2016-09-29 | 2018-03-29 | Microsoft Technology Licensing, Llc | Conversational interactions using superbots |
-
2018
- 2018-12-27 CN CN201811612816.4A patent/CN111382237B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003316385A (en) * | 2002-04-24 | 2003-11-07 | Hitachi Ltd | Voice interaction system and voice interaction method |
| CN103942056A (en) * | 2014-05-05 | 2014-07-23 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and method based on scenes |
| CN107395711A (en) * | 2017-07-17 | 2017-11-24 | 中国农业银行股份有限公司 | Heterogeneous system session access method and relevant apparatus |
| CN108829797A (en) * | 2018-04-25 | 2018-11-16 | 苏州思必驰信息科技有限公司 | Multiple agent dialog strategy system constituting method and adaptive approach |
Non-Patent Citations (1)
| Title |
|---|
| 基于主题森林结构的对话管理模型;邬晓钧等;《自动化学报》;第29卷(第2期);第275-283页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111382237A (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10491394B2 (en) | Method and device for processing verification code | |
| CN106547904B (en) | Cross-account information sharing method and device | |
| US20180342029A1 (en) | Method, apparatus terminal device, and computer readable storage medium for invoking a virtual public transport card | |
| CN104539789A (en) | Method and device for prompting call request | |
| CN110968362B (en) | Application running method, device and storage medium | |
| CN105511739A (en) | Message prompting method and device | |
| CN111381829A (en) | Online programming method and device, electronic equipment and storage medium | |
| CN107463372B (en) | Data-driven page updating method and device | |
| CN106657543B (en) | Voice information processing method and device | |
| CN111061452A (en) | Voice control method and device of user interface | |
| CN110704030A (en) | Interface configuration information generation method and device, electronic equipment and storage medium | |
| CN106331076A (en) | Advertisement push method and apparatus | |
| CN107402756B (en) | Method, device and terminal for drawing page | |
| CN110221813B (en) | Application data connection establishment method and device, storage medium and electronic equipment | |
| CN105306229B (en) | Method and device for communication control | |
| CN107885464B (en) | Data storage method, device and computer readable storage medium | |
| CN111382237B (en) | Data processing method, device and task dialogue system | |
| CN106354595B (en) | Mobile terminal, hardware component state detection method and device | |
| CN112486617B (en) | Ciphertext data processing architecture, method, apparatus and machine readable medium | |
| CN106485335B (en) | Service reservation processing method and device | |
| CN105607958B (en) | Information input method and device | |
| CN112732734A (en) | Information processing method and device | |
| CN112631695A (en) | Data verification method and device, electronic equipment and storage medium | |
| CN112651012A (en) | Information processing method and device | |
| CN111104110A (en) | Global style sharing method, global style sharing device and electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |