CN115509485A - Filling-in method and device of business form, electronic equipment and storage medium - Google Patents
Filling-in method and device of business form, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115509485A CN115509485A CN202210998236.3A CN202210998236A CN115509485A CN 115509485 A CN115509485 A CN 115509485A CN 202210998236 A CN202210998236 A CN 202210998236A CN 115509485 A CN115509485 A CN 115509485A
- Authority
- CN
- China
- Prior art keywords
- model
- target
- intention
- business form
- filling
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/177—Editing, e.g. inserting or deleting of tables; using ruled lines
- G06F40/18—Editing, e.g. inserting or deleting of tables; using ruled lines of spreadsheets
Abstract
The embodiment of the invention provides a method and a device for filling a service form, electronic equipment and a storage medium, wherein the method comprises the following steps: receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting an intention model; when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention; receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting an intention model; and when a second action instruction model corresponding to the second target intention is related to the filling target business form model, filling operation is carried out on the target business form model according to the second action instruction model and the second voice instruction. By the embodiment of the invention, the automatic filling of the business form is realized based on the voice recognition without manual input of the user.
Description
Technical Field
The present invention relates to the technical field of data processing, and in particular, to a method and an apparatus for filling a service form, an electronic device, and a storage medium.
Background
According to statistics, about 20% of villagers still use non-smart phones in China at present; even if the smart phone is used, the business form is difficult to fill in the smart phone for more elderly villagers due to low culture level; and even if it takes a lot of time to complete the filling, there may be a lot of filling errors.
Disclosure of Invention
In view of the above problems, it is proposed to provide a method, an apparatus, an electronic device and a storage medium for filling out a service form, which overcome or at least partially solve the above problems, including:
a method of filling out a business form, the method comprising:
creating a business form model for different businesses, an intent model for identifying intent for the business form model, and a plurality of action instruction models for performing fill-related operations for the business form model; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively;
receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting the intention model;
when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention;
receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting the intention model;
when a second action instruction model corresponding to the second target intent is relevant to populating the target business form model, and filling the target service form model according to the second action instruction model and the second voice instruction.
Optionally, the presenting a target business form model corresponding to the first target intention includes:
determining the type of target equipment of terminal equipment for displaying the target business form model;
when the type of the target equipment is a first type, displaying the target business form model in a voice interaction mode;
and when the type of the target equipment is a second type, displaying the target business form model in the terminal equipment.
Optionally, the method further comprises:
when the first target intention cannot be determined and/or the second target intention cannot be determined, recording first abnormal log data;
updating the intention model according to the first abnormal log data;
optionally, the method further comprises:
when filling operation is performed on the target service form model according to the second action instruction model and the second voice instruction, and filling abnormality occurs, second abnormal log data are generated;
and updating the action instruction models according to the second abnormal log data, and updating the intention model.
Optionally, the target business form model includes a plurality of fields, and the filling operation on the target business form model according to the second action instruction model and the second voice instruction includes:
determining a target field aimed at by the second voice instruction, and extracting first text information aimed at the target field from the second voice instruction;
and filling the first text information into the target field according to a target algorithm in the second action instruction model.
Optionally, the method further comprises:
detecting whether the filled target field has filling content abnormity;
when the filled target field has abnormal filling content, prompting the target field;
and when the filled target field has no filling content abnormity, storing the data filled in the target field.
Optionally, the determining, by using the intention model, a first target intention corresponding to the first voice instruction includes:
converting the first voice instruction into corresponding second text information;
extracting target keywords for intention recognition from the second text information by adopting natural language processing;
and determining a first target intention corresponding to the target keyword by adopting the intention model.
The embodiment of the invention also provides a device for filling the service form, which comprises:
a creation module for creating business form models for different businesses, an intent model for identifying intent for the business form models, and a plurality of action instruction models for performing fill-in related operations for the business form models; corresponding relations exist between the intents in the intention model and the business form model and between the intents in the intention model and the action instruction model respectively;
the first intention determining module is used for receiving a first voice instruction and determining a first target intention corresponding to the first voice instruction by adopting the intention model;
the display module is used for displaying a target business form model corresponding to the first target intention when the first action instruction model corresponding to the first target intention is a displayed business form model;
the second intention determining module is used for receiving a second voice instruction in the process of displaying the target business form model and determining a second target intention corresponding to the second voice instruction by adopting the intention model;
and the filling module is used for filling the target business form model according to the second action instruction model and the second voice instruction when a second action instruction model corresponding to the second target intention is related to the filling of the target business form model.
Optionally, the display module includes:
the target equipment type determining submodule is used for determining the target equipment type of the terminal equipment for displaying the target service form model;
the voice interaction display sub-module is used for displaying the target business form model in a voice interaction mode when the type of the target equipment is a first type;
and the display sub-module is used for displaying the target business form model in the terminal equipment when the type of the target equipment is a second type.
Optionally, the apparatus further comprises:
the first updating module is used for recording first abnormal log data when the first target intention cannot be determined and/or the second target intention cannot be determined;
updating the intention model according to the first abnormal log data;
optionally, the apparatus further comprises:
the second updating module is used for generating second abnormal log data when filling operation is performed on the target service form model according to the second action instruction model and the second voice instruction and filling is abnormal; and updating the action instruction models according to the second abnormal log data, and updating the intention model.
Optionally, the target business form model includes a plurality of fields, and the filling module is configured to determine a target field for which the second voice instruction is directed, and extract first text information for the target field from the second voice instruction; and filling the first text information into the target field according to a target algorithm in the second action instruction model.
Optionally, the apparatus further comprises:
the anomaly detection module is used for detecting whether the filled target field has filling content anomaly; when the filled target field has abnormal filling content, prompting the target field; and when the filled target field has no filling content abnormity, storing the data filled in the target field.
Optionally, the first intent determination module is configured to convert the first voice instruction into corresponding second text information; extracting target keywords for intention recognition from the second text information by adopting natural language processing; and determining a first target intention corresponding to the target keyword by adopting the intention model.
The embodiment of the present invention further provides an electronic device, which includes a processor, a memory, and a computer program stored on the memory and capable of running on the processor, and when the computer program is executed by the processor, the method for filling the service form is implemented.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the filling method of the service form is realized.
The embodiment of the invention has the following advantages:
in the embodiment of the invention, a business form model aiming at different businesses, an intention model used for identifying the intention aiming at the business form model and a plurality of action instruction models used for filling related operations aiming at the business form model can be created in advance; corresponding relations exist between the intents in the intention model and the business form model and between the intents in the intention model and the action instruction model respectively; receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting an intention model; when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention; receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting an intention model; and when a second action instruction model corresponding to the second target intention is related to the filling target business form model, filling operation is carried out on the target business form model according to the second action instruction model and the second voice instruction. Through the embodiment of the invention, the automatic filling of the business form is realized based on the voice recognition, and the manual input of the user is not needed; the efficiency of filling in the business form by the user is improved, and the learning cost of filling in the business form by the user is reduced; and the filling of the business form is automatically completed based on the intention of the voice, so that the filling accuracy of the business form of the user is improved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings required to be used in the description of the present invention will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings may be obtained according to the drawings without inventive labor.
Fig. 1 is a flowchart illustrating steps of a method for filling a service form according to an embodiment of the present invention;
FIG. 2 is a flow chart of steps of another method for filling out a business form according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a scenario of an embodiment of the present invention;
FIG. 4 is a schematic flow chart of a filling manner of a service form according to an embodiment of the present invention;
fig. 5 is a block diagram of a service form filling apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
According to the research result, the problems existing in the prior village are as follows:
according to statistics, about 20% of villagers in China still use non-smart phones at present, and the acceptance degree of other villagers on smart phones is not high; the popularization rate of the computers in the rural areas is low at present, so that various obstacles exist in handling business of villagers; for example: it is difficult to complete the entry of the business form. Aiming at the problem, the embodiment of the invention provides a business form filling method which can help villagers to finish automatic filling of business forms based on voice recognition without manual input of the villagers, so that the efficiency of filling the business forms by the villagers is improved, and the learning cost of filling the business forms by the villagers is reduced; and the filling of the business form is automatically completed based on the intention of the voice, so that the filling accuracy of the business form of the villagers is improved.
Referring to fig. 1, a flowchart illustrating steps of a method for filling a service form according to an embodiment of the present invention may include the following steps:
In practical application, different services may correspond to different service forms; aiming at different services, a service form model of a corresponding service form can be created; the service form model may include a form name, a form ID (Identity document) stored in a database, a form category, and the like.
The form name may refer to the name of the form in real life, such as "the accumulation fund extraction application form"; the form ID may refer to an identification for uniquely identifying the form in the database, and may be identified in the form of numbers and letters, such as "a123456"; the form type may refer to a type corresponding to the form, for example: applications, evaluations, and the like.
Form field information can be created for different business form models and stored in a database; form field information may include: form field ID, form field identification, data type and field classification; the form field ID can refer to an identifier for uniquely identifying the form field in the database, and can be identified in the form of numbers and letters; form field identification may refer to an identification for letting developers know the information to which the form field corresponds, such as: "identity card number"; the data types may include types of data in the fill value form fields, such as: time type, numerical type, text type, etc.; the field classification may refer to the type corresponding to the form field, for example: express bill number, identification card number, time, and the like, which are not limited in this embodiment of the present invention.
For each field classification, a mapping relation with the corresponding keyword identification can be set; thus, when a keyword is included in the voice instruction input by the user, the form field to be filled in can be determined from the business form based on the corresponding keyword identification.
Meanwhile, a corresponding intention model can be established aiming at the business form model; specifically, the intention model may include all intents corresponding to filling out the business form, for example: opening a business form model, filling in a form field, modifying content, submitting a form, specifying a link address, popping up a form, closing a current page, and the like. For different intents, corresponding intention corpora can be uploaded to train the intention model. For example: the intention model training may be performed by a convolutional neural network or a cyclic neural network algorithm, which is not limited in this embodiment of the present invention.
In filling out a business form, different operations may need to be performed, such as: filling text information corresponding to the voice instruction into a form field, converting the text information corresponding to the voice instruction and then filling the converted text information into the form field, closing a business form model, opening the business form model, opening a link, amplifying a window and the like; in this regard, one or more action instruction models for performing filling-related operations on the business form model may be created in advance.
Specifically, the action instruction calling mode (such as filling, processing and returning) and the required parameter information (namely the information to be filled) can be saved in the database in the form of an action instruction model; the action instruction model may include: action instruction ID, method name, return value type, parameter table, etc.
The action instruction ID can refer to an identifier for uniquely identifying the action instruction model in a database, and can be identified in the form of numbers and letters; the method name may include the name of the algorithm used to process the voice instruction; the return value type may refer to the next step after the operation is completed; the parameter table may include parameters for multiple steps to ensure that after the action command model is executed, the next step may be automatically executed.
In practical application, a business form model, an intention model and an action instruction model are created in advance, and the corresponding relation between the intention in the intention model and the business form model and the action instruction model can be established; so that after receiving the voice command input by the user, the business form model to be filled in and what kind of filling operation needs to be carried out on the business form model can be determined based on the corresponding intention of the voice command.
And 102, receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting an intention model.
When a user needs to fill in a service form, the operation of generating a first voice instruction can be executed on the terminal equipment; for example: "i want to transact traffic" to the end device; the terminal equipment can generate a corresponding first voice instruction according to the words spoken by the user and uploads the first voice instruction to the server.
After receiving the first voice command, the server can adopt a pre-created intention model to recognize the first voice command so as to determine the intention of the user corresponding to the first voice command; for ease of distinction, this intent is referred to as the first target intent.
As an example, the first target intent may be to open a business form model, which is not limited by the embodiment of the present invention.
And 103, when the first action instruction model corresponding to the first target intention is a business form model, displaying a target business form model corresponding to the first target intention.
In practical application, the intention model can include not only the intention for the business form, but also other intentions; for example: questions, comparisons, suggestions, thanks you, etc.
After determining the first target intent corresponding to the first voice instruction, a target business form model and a first action instruction model corresponding to the first target intent may be determined based on correspondence of the intent to the action instruction model and the business form model.
If the operation corresponding to the first action instruction model is to display the business form model, the target business form model can be displayed on the terminal equipment of the user, so that the user can fill in the business form based on the target business form displayed on the terminal equipment.
And 104, receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting the intention model.
In the process of presenting the target business form model by the terminal device, the user may perform an operation of generating a second voice instruction with respect to the content in the target business form model, for example: "my identification number is"; the terminal device may generate a corresponding second voice command based on the "my identification number is" spoken by the user.
After the terminal device generates the second voice instruction, the terminal device may upload the second voice instruction to the server, so that the server may determine a second target intention corresponding to the second voice instruction by using the intention model.
As an example, the second target intention may be a filling intention for the target business form model, or may also be a closing intention, a submitting intention for the target business form model, and the like, which is not limited in this embodiment of the present invention.
And 105, when a second action instruction model corresponding to the second target intention is related to the filling target business form model, filling the target business form model according to the second action instruction model and the second voice instruction.
After determining the second target intent, a second action instruction model corresponding to the second target intent may be determined; if the second action instruction model is related to the filling business form model, filling operation can be carried out on the target business form model according to the second action instruction model and the second voice instruction so as to complete filling of the target business form model.
After the target business form model is filled, the target business form model may be uploaded to a corresponding server for storage, which is not limited in the embodiment of the present invention.
In the embodiment of the invention, a business form model aiming at different businesses, an intention model used for identifying the intention aiming at the business form model and a plurality of action instruction models used for filling related operations aiming at the business form model can be created in advance; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively; receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting an intention model; when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention; receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting an intention model; and when a second action instruction model corresponding to the second target intention is related to the filling target business form model, filling operation is carried out on the target business form model according to the second action instruction model and the second voice instruction. Through the embodiment of the invention, the automatic filling of the business form is realized based on the voice recognition, and the manual input of the user is not needed; the efficiency of filling in the business form by the user is improved, and the learning cost of filling in the business form by the user is reduced; and the filling of the business form is automatically completed based on the intention of the voice, so that the filling accuracy of the business form of the user is improved.
Referring to fig. 2, a flowchart illustrating steps of another method for filling a service form according to an embodiment of the present invention is shown, and may include the following steps:
In practical application, different services may correspond to different service forms; aiming at different services, a service form model of a corresponding service form can be created; meanwhile, a corresponding intention model can be established for the business form model, and one or more action instruction models for filling related operations to the business form model are created
After receiving the first voice command, the server may first use an ASR (Automatic Speech Recognition) technology to recognize the first voice command into the second text information by calling a voice Recognition interface.
And step 203, extracting target keywords for intention recognition from the second text information by adopting natural language processing.
Then, the server may extract a target keyword that can be used for intention recognition from the second text information by using NLP (Natural Language Processing) technology.
And 204, determining a first target intention corresponding to the target keyword by adopting an intention model.
After obtaining the target keyword, the server may identify an intention corresponding to the target keyword by using an intention model to determine a first target intention corresponding to the target keyword.
As an example, intent recognition may be based on word segmentation, part-of-speech tagging, named entity recognition, dependency parsing, semantic analysis, or rule parsing, among other ways.
For example: the intention is identified by means of rule parsing:
the second text message is "{ me } to do low insurance", and a rule template can be used to extract and obtain the first target intention: [ user ]: [ transaction ] [ low insurance ].
In an example, the [ transaction ] associated action instruction model may be an [ pop-up form ] action instruction model, and the [ low-security ] associated business form model may be a [ low-security transaction form ] business form model, which is not limited by the embodiment of the present invention.
After determining the first target intent corresponding to the first voice command, a target business form model and a first action command model corresponding to the first target intent may be determined based on correspondence of the intent to the action command model and the business form model.
If the operation corresponding to the first action instruction model is to display the business form model, the target business form model can be displayed on the terminal equipment of the user, so that the user can fill in the business form based on the target business form displayed on the terminal equipment.
In practical application, because the popularity of intelligent equipment is low in rural areas, terminal equipment of part of users may not have a human-computer interaction interface, and a target service form template may be difficult to display; therefore, before the target business form model is displayed, the embodiment of the invention can determine the type of the target equipment of the terminal equipment displaying the target business form model.
As an example, the target device types may include a first type without human-machine interface, and a second type with human-machine interface.
And step 206, when the type of the target equipment is the first type, displaying the target business form model in a voice interaction mode.
If the type of the target equipment of the terminal equipment is the first type, the terminal equipment can be represented to have no human-computer interaction interface; at this time, the target business form model can be presented in a voice interaction mode.
For example: corresponding voice prompt tones can be synthesized according To information in the target service form model through a TTS (Text To Speech) technology, and the voice prompt tones are played To a user through a terminal device To prompt the user of contents and formats required To be filled in.
And step 207, when the type of the target equipment is the second type, displaying the target business form model in the terminal equipment.
If the type of the target equipment of the terminal equipment is the second type, the terminal equipment can be represented to have a human-computer interaction interface; at this time, the target business form model may be directly displayed on the terminal device so that the user can fill in based on the displayed target business form model.
And step 208, in the process of displaying the target business form model, receiving a second voice instruction, and determining a second target intention corresponding to the second voice instruction by adopting the intention model.
In the process of displaying the target business form model by the terminal equipment, the user can execute the operation of generating a second voice instruction according to the content in the target business form model; the terminal device can generate a corresponding second voice instruction based on the words spoken by the user.
After the terminal device generates the second voice instruction, the second voice instruction can be uploaded to the server, so that the server can determine a second target intention corresponding to the second voice instruction by using the intention model.
As an example, when the target business form model is exposed by way of voice interaction, a voice instruction received after each output voice may be taken as a second voice instruction.
As another example, when the target business form model is presented by way of display, the voice command received during the display process may be taken as the second voice command.
In practical applications, the target business form model may include a plurality of fields to be filled in; therefore, after receiving the second voice instruction, the field which needs to be filled by the user currently can be determined based on the second voice instruction; for example: the target business form model includes the following fields: "name", "age", "sex", "address", "identification card number"; when the second voice instruction is "my identification number is 123456789", the "identification number" field may be used as the target field, which is not limited in the embodiment of the present invention.
After the target field is determined, first text information aiming at the target field can be extracted from the second voice instruction; as the above example, "123456789" may be taken as the first text information.
And step 210, filling the first text information into a target field according to a target algorithm in the second action instruction model.
After determining the first text information, the server may populate the first text information into the target field according to a target algorithm in the second action instruction model. For example: the first text information can be directly filled into the target field; or, when the target field is selected to be filled, determining a target option from options corresponding to the target field according to the first text information to fill, which is not limited in the embodiment of the present invention.
After all fields in the target business form model are filled, the target business form model may be uploaded to a corresponding server for storage, which is not limited in the embodiment of the present invention.
In an embodiment of the present invention, after the target field is filled, the method may further include the following steps:
detecting whether the filled target field has filling content abnormity; when the filled target field has abnormal filling content, prompting the target field; and when the filled target field has no filling content abnormity, storing the data filled in the target field.
In order to avoid submitting the service form filled with the error information, whether the filled target field has abnormal filling content or not can be detected. For example: the time of overlapping, wrongly written words, wrongly formatted sentences and sentences with inconsistent questions and answers, etc., are not limited in this embodiment of the present invention.
If the filling content is abnormal, prompting can be carried out on the target field so as to remind the user that the target field is wrongly filled and written and needs to be refilled; when prompted, a prompt may be made based on the type of error to inform the user how the modification is needed.
If the filling content is not abnormal, the data filled into the target field can be saved; for example: when the data filled in the target field is the first text information, the first text information may be included under the target field; when the data filled in the target field is a target option determined from options corresponding to the target field according to the first text information, the target option may be included in the target field, which is not limited in the embodiment of the present invention.
In an embodiment of the present invention, the method may further include the following steps:
when the first target intention cannot be determined and/or the second target intention cannot be determined, recording first abnormal log data; updating the intention model according to the first abnormal log data;
if the intention model fails to determine a first target intention based on the first voice instruction and/or fails to determine a second target intention based on the second voice instruction, it may indicate that a difficult-to-recognize voice (e.g., dialect), failed intention analysis occurred at this time; at this time, the first abnormal log data may be recorded for the abnormal process and saved to the database.
When the intention model needs to be updated, the reason of the abnormity occurrence can be analyzed based on the first abnormity log data; then updating the intention model based on the reason of the abnormal occurrence; for example: adding dialect voice database, adjusting corpus corresponding to the intention, and the like, so as to further improve the accuracy of intention identification and form filling.
In an embodiment of the present invention, the method may also include the following steps:
when filling operation is performed on the target service form model according to the second action instruction model and the second voice instruction, and filling abnormality occurs, second abnormal log data are generated; and updating the action instruction models and the intention model according to the second abnormal log data.
Of course, errors may also occur during the process of filling out the business form model, such as: the user speaks the content to be filled in by the dialect, but the current database does not have a voice database corresponding to the dialect; or, an exception occurs when the action instruction model is matched and/or executed; at this time, second exception log data may be recorded for the exception process and saved to the database.
When the intention model or the action instruction model needs to be updated, the reason for the occurrence of the abnormality can be analyzed based on the second abnormal log data; the intent model and action instruction model are then updated based on the reason for the occurrence of the anomaly.
As an example, when the action command model is updated, the correspondence between the intention in the intention model and the action command model may be adjusted, or the calling manner, the required parameter information, and the like in the action command model may be adjusted, which is not limited in the embodiment of the present invention.
FIG. 3 is a schematic diagram illustrating a scenario according to an embodiment of the present invention; the terminal equipment can perform voice interaction with a user so as to fill a business form model; the server can perform recognition based on the voice command uploaded by the terminal equipment and store the filled-in business form model.
Fig. 4 is a schematic flow chart illustrating a filling manner of a service form according to an embodiment of the present invention;
s1, dynamically designing a service form model, an intention model and an action instruction model which need to be filled in, and establishing an intention model library and an intention sentence library according to the country service. And respectively associating the business form model and the action instruction model with the intention model.
Designing an intention model:
1) Creating a corresponding intent model from the business form, for example: affirmation, negation, questioning, providing information, transacting, comparing, suggesting, thanking, etc.;
2) After the creation of the intention model is completed, uploading corresponding intention corpora, wherein the intention corpora are used for carrying out intention identification according to the text;
3) After the linguistic data are uploaded, intention model training is carried out through algorithms such as a convolutional neural network and a cyclic neural network, and algorithm parameters can be finely adjusted according to business data characteristics.
Designing an intention sentence pattern library:
1) Establishing an intention sentence pattern data structure, comprising: sentence pattern ID, sentence pattern name, sentence pattern description, sentence pattern formula, associated intention model, keyword set, and create an intention sentence pattern library management function according to the data structure, including: creating, editing and deleting functions;
2) And (4) inputting basic data, namely inputting information into the intention sentence pattern library according to actual services. For example: { I } transacts { accumulation fund } { extract } business; { me } is to transact { social security } { query } traffic.
Designing a dynamic business form model:
1) Creating a business form model in a visual manner, wherein the business form model comprises: form name, storing form ID and form category in a database;
2) Creating form fields and storing the form fields in a database, wherein the form field information comprises: form field ID, form field identification, data type and field classification;
3) Establishing form field classification type and keyword identification mapping;
4) And establishing a mapping relation between the form ID and the intention model, wherein the incidence relation is many-to-many.
Designing an action instruction model:
action instructions, i.e. methods in a programming language, can control the current operation of an application, for example: jump to a specified link address, pop-up form, close current page, submit form, etc. Storing information such as a method calling mode, required parameters and the like into a database, wherein the information comprises the following steps: action instruction ID, method name, return value type, parameter table;
the action instruction ID is associated with the intent model.
S2, the user wakes up the equipment terminal (such as intelligent terminal equipment) through voice, and the terminal uploads the voice instruction to the server.
And S3, after the server receives the voice instruction, recognizing the voice instruction into a text by calling a voice recognition interface by utilizing an ASR (asynchronous serial port) technology, extracting keywords by an NLP (non-line segment) technology, and performing intention recognition on the current keywords.
Intention recognition:
and performing intention identification based on the modes of word segmentation, part of speech tagging, named entity identification, dependency syntax analysis, semantic analysis or rule analysis.
Wherein, the intention of the query can be obtained by a rule analysis mode.
For example: "{ me } to do a low security", a rule template may be used to extract and obtain the result: [ user ]: [ transaction ] [ Low Security ]. The [ transact ] associated action command is [ pop-up form ], and the [ low-security ] associated form is [ low-security transaction form ].
And then, corresponding operation can be carried out according to the type of equipment used by the current user, and whether multiple rounds of interactive response are started to fill in the form is judged.
And S4, after the intention is recognized, matching the corresponding action instruction model and the corresponding service form model, namely opening the service form model related to the intention, jumping to the corresponding link, performing interactive session and other operations, filling the related service form model according to the action instruction model corresponding to the intention, recording the filling process, and storing in a log form.
Matching the business form model:
and identifying and analyzing whether the intention belongs to the form operation intention or not through the intention, if so, inquiring the form ID associated with the intention according to the intention data, and judging whether to jump to a form operation interface or not according to the type of the intelligent equipment. If the intelligent device unmanned aerial vehicle interface, such as intelligent stereo set, the system will adopt the interactive mode of many rounds of conversations to carry out form content filling.
Voice filling-in form
When the form is filled in, whether the intelligent equipment used by the user has a human-computer interface or not is firstly confirmed, if so, the system enters the corresponding form interface to be filled in, and the user can carry out voice input according to the form content.
If the human-computer interface is not available or the situation that the human-computer interface is difficult to use occurs, the system can start multiple rounds of session interaction to complete form content filling. The system sets the number of sessions according to the number of fields in the form, and carries out interaction one by one, and the specific mode is as follows: and synthesizing voice according to the field name by a TTS technology, prompting the content and format required to be filled by the user, and verifying and storing the system after the user input is finished.
After the form data is completely filled, analyzing the form data, prompting the data with problems to be filled, and after the user finishes the modification, automatically sending the form back to a background; the analysis range of the question data includes overlapping time, wrongly written words, wrongly formatted sentences and sentences with inconsistent question and answer.
And S5, analyzing the difficult-to-recognize voice and the failed intention analysis process in the form filling process by the server background, and updating the business form model, the intention model and the action instruction model so as to improve the accuracy of intention recognition and form filling.
In the embodiment of the invention, a business form model aiming at different businesses, an intention model used for identifying the intention aiming at the business form model and a plurality of action instruction models used for filling related operations aiming at the business form model can be created in advance; receiving a first voice instruction, and converting the first voice instruction into corresponding second text information; extracting target keywords for intention recognition from the second text information by adopting natural language processing; determining a first target intention corresponding to the target keyword by adopting an intention model; when a first action instruction model corresponding to the first target intention is a business form display model, determining a target device type of terminal equipment for displaying the target business form model; when the type of the target equipment is a first type, displaying a target business form model in a voice interaction mode; when the type of the target equipment is a second type, displaying a target service form model in the terminal equipment; receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting an intention model; when a second action instruction model corresponding to a second target intention is a filling-in business form model, determining a target field to which a second voice instruction aims, and extracting first text information aiming at the target field from the second voice instruction; and filling the first text information into the target field according to a target algorithm in the second action instruction model. Through the embodiment of the invention, the automatic filling of the business form is realized based on the voice recognition, and the manual input of the user is not needed; the efficiency of filling in the business form by the user is improved, and the learning cost of filling in the business form by the user is reduced; and the filling of the business form is automatically completed based on the intention of the voice, so that the filling accuracy of the business form of the user is improved.
In addition, the mode of displaying the business form model is determined based on the type of the terminal equipment, so that the terminal equipment without a human-computer interaction interface can fill in the business form based on voice interaction.
It should be noted that for simplicity of description, the method embodiments are shown as a series of combinations of acts, but those skilled in the art will recognize that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 5, a schematic structural diagram of a device for filling a service form according to an embodiment of the present invention is shown, and may include the following modules:
a creating module 501 for creating a business form model for different businesses, an intention model for identifying an intention for the business form model, and a plurality of action instruction models for performing filling-in related operations for the business form model; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively;
a first intention determining module 502, configured to receive a first voice instruction, and determine a first target intention corresponding to the first voice instruction by using an intention model;
the display module 503 is configured to display a target business form model corresponding to the first target intention when the first action instruction model corresponding to the first target intention is a display business form model;
a second intention determining module 504, configured to receive a second voice instruction in a process of displaying the target business form model, and determine a second target intention corresponding to the second voice instruction by using an intention model;
and a filling module 505, configured to perform a filling operation on the target business form model according to the second action instruction model and the second voice instruction when the second action instruction model corresponding to the second target intention is related to the filling target business form model.
In an alternative embodiment of the present invention, the display module 503 comprises:
the target equipment type determining submodule is used for determining the type of target equipment of terminal equipment for displaying the target business form model;
the voice interaction display sub-module is used for displaying the target business form model in a voice interaction mode when the type of the target equipment is a first type;
and the display sub-module is used for displaying the target business form model in the terminal equipment when the type of the target equipment is the second type.
In an optional embodiment of the invention, the apparatus further comprises:
the first updating module is used for recording first abnormal log data when the first target intention cannot be determined and/or the second target intention cannot be determined;
updating the intention model according to the first abnormal log data;
in an optional embodiment of the invention, the apparatus further comprises:
the second updating module is used for generating second abnormal log data when filling operation is performed on the target service form model according to the second action instruction model and the second voice instruction and filling abnormality occurs; and updating the action instruction models and the intention model according to the second abnormal log data.
In an optional embodiment of the present invention, the target business form model includes a plurality of fields, and the filling module 505 is configured to determine a target field to which a second voice instruction is directed, and extract first text information for the target field from the second voice instruction; and filling the first text information into the target field according to the target algorithm in the second action instruction model.
In an optional embodiment of the invention, the apparatus further comprises:
the abnormity detection module is used for detecting whether the filled target field has abnormal filling content; when the filled target field has abnormal filling content, prompting the target field; and when the filled target field has no filling content abnormity, storing the data filled in the target field.
In an optional embodiment of the present invention, the first intention determining module 502 is configured to convert the first voice instruction into corresponding second text information; extracting target keywords for intention recognition from the second text information by adopting natural language processing; and determining a first target intention corresponding to the target keyword by adopting an intention model.
In the embodiment of the invention, a business form model aiming at different businesses, an intention model used for identifying the intention aiming at the business form model and a plurality of action instruction models used for filling related operations aiming at the business form model can be created in advance; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively; receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting an intention model; when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention; receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting an intention model; and when a second action instruction model corresponding to the second target intention is related to the target business form filling model, filling operation is carried out on the target business form model according to the second action instruction model and the second voice instruction. By the embodiment of the invention, the automatic filling of the business form is realized based on the voice recognition, and the manual input of the user is not needed; the efficiency of filling in the business form by the user is improved, and the learning cost of filling in the business form by the user is reduced; and the filling of the business form is automatically completed based on the intention of the voice, so that the filling accuracy of the business form of the user is improved.
The embodiment of the invention also provides electronic equipment, which comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein when the computer program is executed by the processor, the filling method of the service form is realized.
The embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and when being executed by a processor, the computer program realizes the filling method of the service form.
For the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for relevant points.
The embodiments in the present specification are all described in a progressive manner, and each embodiment focuses on differences from other embodiments, and portions that are the same and similar between the embodiments may be referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or terminal apparatus that comprises the element.
The method, the apparatus, the electronic device and the storage medium for filling a service form are described in detail, and a specific example is applied in the description to explain the principle and the implementation of the present invention, and the description of the embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for filling out a service form, the method comprising:
creating a business form model for different businesses, an intention model for identifying an intention for the business form model, and a plurality of action instruction models for performing fill-in-related operations for the business form model; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively;
receiving a first voice instruction, and determining a first target intention corresponding to the first voice instruction by adopting the intention model;
when the first action instruction model corresponding to the first target intention is a business form display model, displaying a target business form model corresponding to the first target intention;
receiving a second voice instruction in the process of displaying the target business form model, and determining a second target intention corresponding to the second voice instruction by adopting the intention model;
and when a second action instruction model corresponding to the second target intention is related to filling the target service form model, filling the target service form model according to the second action instruction model and the second voice instruction.
2. The method of claim 1, wherein said exposing the target business form model corresponding to the first target intent comprises:
determining a target device type of a terminal device for displaying the target service form model;
when the type of the target equipment is a first type, displaying the target business form model in a voice interaction mode;
and when the type of the target equipment is a second type, displaying the target business form model in the terminal equipment.
3. The method of claim 1, further comprising:
when the first target intention cannot be determined and/or the second target intention cannot be determined, recording first abnormal log data;
updating the intention model according to the first abnormal log data.
4. The method of claim 1, further comprising:
when filling operation is performed on the target service form model according to the second action instruction model and the second voice instruction, and filling abnormality occurs, second abnormal log data are generated;
and updating the action instruction models according to the second abnormal log data, and updating the intention model.
5. The method of claim 1, wherein the target business form model comprises a plurality of fields, and wherein filling out the target business form model according to the second action instruction model and the second voice instruction comprises:
determining a target field aimed at by the second voice instruction, and extracting first text information aimed at the target field from the second voice instruction;
and filling the first text information into the target field according to a target algorithm in the second action instruction model.
6. The method of claim 5, further comprising:
detecting whether the filled target field has filling content abnormity;
when the filled target field has abnormal filling content, prompting the target field;
and when the filled target field has no filling content abnormity, storing the data filled in the target field.
7. The method according to any of claims 1-6, wherein said determining a first target intent corresponding to the first speech instruction using the intent model comprises:
converting the first voice instruction into corresponding second text information;
extracting target keywords for intention recognition from the second text information by adopting natural language processing;
and determining a first target intention corresponding to the target keyword by adopting the intention model.
8. An apparatus for filling out a service form, the apparatus comprising:
a creation module for creating a business form model for different businesses, an intent model for identifying intent for the business form model, and a plurality of action instruction models for performing fill-in related operations for the business form model; corresponding relations exist between the intentions in the intention model and the business form model and between the intentions in the intention model and the action instruction model respectively;
the first intention determining module is used for receiving a first voice instruction and determining a first target intention corresponding to the first voice instruction by adopting the intention model;
the display module is used for displaying a target business form model corresponding to the first target intention when the first action instruction model corresponding to the first target intention is a display business form model;
the second intention determining module is used for receiving a second voice instruction in the process of displaying the target business form model and determining a second target intention corresponding to the second voice instruction by adopting the intention model;
and the filling module is used for filling the target business form model according to the second action instruction model and the second voice instruction when a second action instruction model corresponding to the second target intention is related to the filling of the target business form model.
9. An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing a method of filling out a business form as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of filling out a service form according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210998236.3A CN115509485A (en) | 2022-08-19 | 2022-08-19 | Filling-in method and device of business form, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210998236.3A CN115509485A (en) | 2022-08-19 | 2022-08-19 | Filling-in method and device of business form, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115509485A true CN115509485A (en) | 2022-12-23 |
Family
ID=84501085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210998236.3A Pending CN115509485A (en) | 2022-08-19 | 2022-08-19 | Filling-in method and device of business form, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115509485A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115841098A (en) * | 2023-02-24 | 2023-03-24 | 天津爱波瑞科技发展有限公司 | Interactive batch filling method and system based on data identification |
| CN116524926A (en) * | 2023-04-27 | 2023-08-01 | 百洋智能科技集团股份有限公司 | Method for generating service form through voice control at mobile terminal |
-
2022
- 2022-08-19 CN CN202210998236.3A patent/CN115509485A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115841098A (en) * | 2023-02-24 | 2023-03-24 | 天津爱波瑞科技发展有限公司 | Interactive batch filling method and system based on data identification |
| CN116524926A (en) * | 2023-04-27 | 2023-08-01 | 百洋智能科技集团股份有限公司 | Method for generating service form through voice control at mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10937413B2 (en) | Techniques for model training for voice features | |
| US9582757B1 (en) | Scalable curation system | |
| US8170880B2 (en) | Systems and methods for monitoring speech data labelers | |
| CN110164435A (en) | Audio recognition method, device, equipment and computer readable storage medium | |
| CN115509485A (en) | Filling-in method and device of business form, electronic equipment and storage medium | |
| US10854189B2 (en) | Techniques for model training for voice features | |
| CN109545185B (en) | Interactive system evaluation method, evaluation system, server, and computer-readable medium | |
| US10977155B1 (en) | System for providing autonomous discovery of field or navigation constraints | |
| CN112579733B (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
| CN111611382A (en) | Dialect model training method, dialog information generation method, device and system | |
| CN112307770A (en) | Sensitive information detection method and device, electronic equipment and storage medium | |
| CN111177307A (en) | Test scheme and system based on semantic understanding similarity threshold configuration | |
| CN111723870B (en) | Artificial intelligence-based data set acquisition method, apparatus, device and medium | |
| CN111753090A (en) | Document auditing method, device, equipment and medium based on RPA and AI | |
| CN112149419A (en) | Method, device and system for normalized automatic naming of fields | |
| CN111553138A (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN105096952A (en) | Speech recognition-based auxiliary processing method and server | |
| CN112288584A (en) | Insurance application processing method and device, computer readable medium and electronic equipment | |
| CN112116181B (en) | Classroom quality model training method, classroom quality evaluation method and classroom quality evaluation device | |
| CN112562658A (en) | Groove filling method and device | |
| CN109684357B (en) | Information processing method and device, storage medium and terminal | |
| CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
| KR20220042103A (en) | Method and Apparatus for Providing Hybrid Intelligent Customer Consultation | |
| CN114783424A (en) | Text corpus screening method, device, equipment and storage medium | |
| CN110276001B (en) | Checking page identification method and device, computing equipment and medium |
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 |