CN114356860A - Dialog generation method and device - Google Patents
Dialog generation method and device Download PDFInfo
- Publication number
- CN114356860A CN114356860A CN202210011613.XA CN202210011613A CN114356860A CN 114356860 A CN114356860 A CN 114356860A CN 202210011613 A CN202210011613 A CN 202210011613A CN 114356860 A CN114356860 A CN 114356860A
- Authority
- CN
- China
- Prior art keywords
- target
- target object
- document
- dialog
- initial document
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000013145 classification model Methods 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 description 18
- 238000004900 laundering Methods 0.000 description 17
- 238000004590 computer program Methods 0.000 description 11
- 238000012015 optical character recognition Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000002452 interceptive effect Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
Images
Abstract
The embodiment of the specification provides a dialog generation method and a dialog generation device, wherein the dialog generation method comprises the steps of obtaining a target object in a target area, processing the target object and obtaining an initial document corresponding to the target object; splitting the initial document based on a preset requirement to obtain a plurality of split target documents; the plurality of target documents are classified based on the project scenario, and at least one type of dialog corresponding to the project scenario is generated based on the classified target documents. The dialog generation method comprises the steps of extracting and splitting an initial document of a target object in a target area; the split target documents are classified according to the project scene, a plurality of types of conversations corresponding to each target area are generated through the classified target documents, the content of the target object is merged into the project scene in the conversations, the interestingness of learning the content of the target object is greatly increased through the conversation mode, and the user experience is improved.
Description
Technical Field
The embodiment of the specification relates to the technical field of compliance, in particular to a dialog generation method.
Background
In the age of rapid development of the internet, more and more cross-border e-commerce platforms supporting cross-border commerce appear, and the transaction of the deal of the cross-border e-commerce platform is the cross-border commerce; in order to ensure the safety of cross-border trade, the supervision department needs to supervise the cross-border trade.
Then, project developers of the cross-border e-commerce platform need to learn a supervision system of a supervision department for cross-border trading so as to avoid illegal cross-border operations formulated by the supervision department in the process of cross-border project development, or develop a reasonable risk and compliance prediction platform aiming at the cross-border trading according to the supervision system of the supervision department for the cross-border trading so as to ensure the normal operation of the cross-border e-commerce platform.
Traditionally, when a supervision department learns about a cross-border trade supervision system, the supervision department depends on documents, examinations and other modes, so that the system is not interesting, and the system cannot be flexibly applied when meeting a compliance scene, and the user experience is poor.
Disclosure of Invention
In view of this, the present specification provides a dialog generation method. One or more embodiments of the present specification also relate to a dialog generating apparatus, a computing device, a computer-readable storage medium, and a computer program, so as to solve the technical deficiencies of the prior art.
According to a first aspect of embodiments herein, there is provided a dialog generation method, including:
acquiring a target object of a target area, and processing the target object to obtain an initial document corresponding to the target object;
splitting the initial document based on a preset requirement to obtain a plurality of split target documents;
the plurality of target documents are classified based on the project scenario, and at least one type of dialog corresponding to the project scenario is generated based on the classified target documents.
According to a second aspect of embodiments of the present specification, there is provided a dialog generating apparatus including:
the initial document determining module is configured to acquire a target object of a target area, process the target object and acquire an initial document corresponding to the target object;
the target document determining module is configured to split the initial document based on preset requirements to obtain a plurality of split target documents;
a dialog generation module configured to classify the plurality of target documents based on a project scenario and generate at least one type of dialog corresponding to the project scenario based on the classified target documents.
According to a third aspect of embodiments herein, there is provided a computing device comprising:
a memory and a processor;
the memory is for storing computer-executable instructions and the processor is for executing the computer-executable instructions, which when executed by the processor, implement the steps of the dialog generation method described above.
According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the dialog generation method described above.
According to a fifth aspect of embodiments herein, there is provided a computer program, wherein the computer program, when executed in a computer, causes the computer to perform the steps of the dialog generating method described above.
One embodiment of the present specification implements a dialog generation method and apparatus, where the dialog generation method includes acquiring a target object in a target region, and processing the target object to obtain an initial document corresponding to the target object; splitting the initial document based on a preset requirement to obtain a plurality of split target documents; the plurality of target documents are classified based on the project scenario, and at least one type of dialog corresponding to the project scenario is generated based on the classified target documents.
Specifically, the dialog generating method comprises the steps of extracting and splitting an initial document of a target object in a target area; the split target documents are classified according to the project scene, a plurality of types of conversations corresponding to each target area are generated through the classified target documents, the content of the target object is merged into the project scene in the conversations, the interestingness of learning the content of the target object is greatly increased through the conversation mode, and the user experience is improved.
Drawings
FIG. 1 is a flow diagram of a dialog generation method provided by one embodiment of the present description;
fig. 2 is a schematic structural diagram of a dialog generating device according to an embodiment of the present specification;
fig. 3 is a block diagram of a computing device according to an embodiment of the present disclosure.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, as those skilled in the art will be able to make and use the present disclosure without departing from the spirit and scope of the present disclosure.
The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
First, the noun terms to which one or more embodiments of the present specification relate are explained.
Conversation: meaning that two or more people speak in language.
In the present specification, a dialog generation method is provided. One or more embodiments of the present specification relate to a dialog generating apparatus, a computing device, a computer-readable storage medium, and a computer program, which are described in detail one by one in the following embodiments.
Referring to fig. 1, fig. 1 is a flowchart illustrating a dialog generation method according to an embodiment of the present disclosure, which specifically includes the following steps.
Step 102: and acquiring a target object of a target area, and processing the target object to obtain an initial document corresponding to the target object.
The dialog generation method provided by the embodiment of the specification is applied to a dialog generation platform based on the cross-border payment field, various types of dialogs can be generated based on the compliance of a supervision mechanism through the dialog generation method provided by the embodiment of the specification, and the compliance of the supervision mechanism is learned with more interest through the form of the dialog, so that the experience of the user in learning the compliance is improved.
Specifically, the target area may be understood as a geographic location, such as a district, a city, a province, or a country; the target object can be understood as a regulation issued by a financial supervision institution, such as a regulation issued by the supervision institution for a third-party cross-border payment company, a regulation issued by the supervision institution for an internet financial scenario, and the like. In practical applications, target areas are different, and target objects belonging to the target areas are also different, that is, regulations issued by a regulatory agency in each area for the same project scenario are different.
Also, the type of the target object may be various, such as a video type or a document type. In the case where the type of the target object is a document type, the target object may be understood as a regulatory compliance system of the document version.
In specific implementation, a target object of a target area is obtained, the target object is processed, and an initial document corresponding to the target object is obtained; it can be understood that all the target objects of each target area are acquired, and each target object is processed to obtain an initial document corresponding to the target object.
In practical applications, the number of target areas may be multiple, and each target area corresponds to multiple target objects, so that when processing target objects, all target objects of each target area need to be determined, and all target objects of each area need to be processed, so as to obtain an initial document corresponding to a completed target object. The specific implementation mode is as follows:
the obtaining a target object in a target area and processing the target object to obtain an initial document corresponding to the target object includes:
determining a plurality of target areas, acquiring a target object of each target area, and processing the target object to obtain an initial document corresponding to the target object.
Taking the target region including country a and country b as an example, acquiring all the compliance degrees issued by the financial regulatory institution of country a and all the compliance degrees issued by the financial regulatory institution of country b; then, processing all the compliance degrees issued by the financial regulatory institution of the country a to obtain initial documents corresponding to all the compliance degrees issued by the financial regulatory institution of the country a; and simultaneously, processing all the compliance degrees issued by the financial regulatory institution of the country b to obtain initial documents corresponding to all the compliance degrees issued by the financial regulatory institution of the country b.
In practical application, there is a corresponding relationship between the number of initial documents and the number of target areas, and how many initial documents exist in how many target areas, that is, each initial document is obtained by processing all target objects in each target area.
In specific implementation, the processing mode of the target object is determined according to different types of the target object, so that the target object is accurately processed, and a relatively accurate initial document is obtained. The specific implementation mode is as follows:
the processing the target object to obtain an initial document corresponding to the target object includes:
determining the object type of the target object, and determining an extraction method for extracting characters in the target object according to the object type;
and extracting characters in the target object according to the extraction method to obtain an initial document corresponding to the target object.
The object type of the target object includes, but is not limited to, a picture type, a video type, and a document type.
The extraction method may be set according to an actual application scenario, which is not specifically limited in this specification, for example, in a case that the target object is a picture-type supervision system, the extraction method may be to extract text information in the picture-type supervision system through Optical Character Recognition (OCR); under the condition that the target object is a video type monitoring system, the extraction method can convert the video type monitoring system into a plurality of video frames and extract the character information in each video frame through optical character recognition; in the case that the target object is a document type supervision system, the extraction method may be any method capable of extracting the text information in the document.
Specifically, after a target object in a target area is obtained, an object type of the target object can be determined, and an extraction method capable of extracting text information in the target object is determined according to the object type; and after the extraction method is determined, extracting characters in the target object according to the extraction method, thereby obtaining an initial document corresponding to the target object.
Following the above example, the extraction method determined based on the object type of the target object is further described for extracting the characters in the target object.
After the regulation compliance issued by the regulatory agency of the country a aiming at the third-party cross-border payment company is obtained, the type of the regulation compliance is determined.
And under the condition that the supervision compliance system issued by the supervision institution is the picture type, determining a method for extracting characters in the picture, such as an OCR (optical character recognition) model. And then inputting the picture type supervision compliance into an OCR model, thereby obtaining a document corresponding to the picture type supervision compliance, wherein the document comprises character information in the picture type supervision compliance.
Under the condition that the supervision compliance system issued by the supervision institution is a video type, firstly, the supervision compliance system of the video type is converted into a plurality of video frames, and the plurality of video frames are input into an OCR (optical character recognition) model, so that a document corresponding to the supervision compliance system of the video type is obtained, and the document contains character information in the supervision compliance system of the video type.
Under the condition that the supervision compliance system issued by the supervision organization is a document type, extracting the characters in the supervision compliance system of the document type by any method for extracting the characters in the document, thereby obtaining the document corresponding to the supervision compliance system of the document type, wherein the document comprises the character information recorded in the supervision compliance system of the document type.
In the embodiment of the description, an extraction method for extracting the characters in the target object is determined according to the object type of the target object, so that different types of target objects are processed, the adaptability of the dialog generation method in the description is improved, the characters in the target object are extracted according to the extraction method, an initial document corresponding to the target object is obtained, and then the dialog corresponding to the target area is generated through the initial document conveniently.
Step 104: splitting the initial document based on preset requirements to obtain a plurality of split target documents.
The preset requirement may be set according to practical application, and the embodiment of the present specification is not limited in this respect. For example, the preset requirement may be understood as a legal regulation or the like associated with the text information in the initial document.
Specifically, each initial document is split based on preset requirements, and a plurality of split target documents are obtained; and under the condition that the preset requirement is a legal rule, the target document is a split document obtained by splitting the initial document based on the legal rule.
In specific implementation, the splitting the initial document based on preset requirements to obtain multiple split target documents includes:
inputting preset requirements and the initial document into a classification model, and obtaining a plurality of split target documents of the initial document.
The classification model can be a pre-trained model, and can be understood as any model capable of splitting the initial document based on preset requirements.
Specifically, after an initial document corresponding to a target object is obtained, the initial document and preset requirements can be input into a classification model, and the initial document is split based on the preset requirements through the classification model, so that a plurality of target documents after the initial document is split are rapidly and accurately obtained.
According to the above example, the preset requirements and the initial document are input into the classification model, and a plurality of target documents after the initial document is split are obtained. The initial document is a document containing the text content in the supervision compliance system issued by the supervision institution, and the preset requirement can be an anti-money laundering method.
Under the condition that the law and regulation related to the document containing the text information in the supervision compliance system is determined to be the anti-money laundering method, the anti-money laundering method and the document containing the text information in the supervision compliance system are input into a classification model, so that the document is split based on the association relation between the document containing the text information in the supervision compliance system and the anti-money laundering method, and a plurality of split documents are obtained, wherein each split document contains the supervision compliance system related to a certain law in the anti-money laundering method.
Based on the association relationship between the document containing the text information in the regulatory compliance system and the anti-money laundering method, splitting the document specifically may be: for example, the initial document includes 5 regulatory compliance systems, namely system a, system B, system C, system D and system E, issued by the regulatory agency; after obtaining an initial document, inputting the initial document into a classification model, and determining the incidence relation between 5 regulatory compliance systems in the initial document and each rule in the anti-money laundering method through the classification model, for example, if the contents of the system A and the system B in the initial document are relatively consistent with the contents of the 5 th rule in the anti-money laundering method, determining that the system A and the system B have the incidence relation with the 5 th rule in the anti-money laundering method; as above, it can be determined that system C in the initial document has an association with the anti-money laundering law regulation No. 7, and system D and system E in the initial document have an association with the anti-money laundering law regulation No. 8.
After the incidence relation between the initial document and the anti-money laundering method is determined, splitting the initial document into a plurality of documents according to the incidence relation, wherein each document comprises a supervision compliance system associated with a certain law in the anti-money laundering method; for example, the initial document is split into 3 documents according to the association relationship with 5 regulatory compliance degrees of rules 5, 7 and 8 in the anti-money laundering law, namely, 5 regulatory compliance degrees of system a, system B, system C, system D and system E: the system comprises a document a, a document B and a document c, wherein the document a comprises a system A and a system B which have an incidence relation with the 5 th bank of the anti-money laundering method; the document b contains a system C which has an association relation with the 7 th bank note of the anti-money laundering method; the document c contains a system D and a system E which have an association relationship with the 8 th bank of the anti-money laundering method.
In the embodiment of the specification, the preset requirements and the initial document are input into the classification model, so that the initial document is rapidly and accurately split, a plurality of split target documents of the initial document are obtained, and a dialog corresponding to a target area is conveniently generated based on the plurality of target documents.
Further, before the initial document is split through the classification model, the classification model needs to be trained based on sample data and sample labels, so that the initial document is rapidly and accurately split through the classification model. The specific implementation is as follows.
The training steps of the classification model are as follows:
acquiring a sample preset demand and a sample initial document generated by a sample target object;
splitting the sample initial document based on the sample preset requirement to obtain a split sample target document;
taking the sample preset requirement and the sample initial document as training samples, and taking the sample target document obtained after splitting the sample initial document as a sample label;
training a classification model based on the training samples and the sample labels corresponding to the training samples to obtain the trained classification model.
For the sample preset requirement and the sample target object, reference may be made to the preset requirement and the target object, which is not limited in this specification.
In practical application, splitting a sample initial document through manual experience based on a sample preset requirement to obtain a split sample target document; then, the sample preset requirement and the sample initial documents are used as training samples, the sample target documents obtained after splitting are used as sample labels of the training samples, and the classification model is trained through the training samples and the sample labels, so that the target documents obtained after splitting of each initial document can be obtained quickly and in preparation on the basis of the classification model obtained through training subsequently, and the document processing efficiency is improved.
Step 106: classifying the plurality of target documents based on the project scenario, and generating at least one type of dialog corresponding to the target area based on the classified target documents.
In this case, the classification of the plurality of target documents based on the project scenario may be understood as that the project scenario to which each target document is applicable is different, and therefore, each project scenario may correspond to at least one target document, that is, during the process of developing the project, at least one compliance system for compliance-limiting the project development may be followed.
Specifically, the classifying the plurality of target documents based on the project scenario and generating at least one type of dialog corresponding to the project scenario based on the classified target documents includes:
classifying the target documents based on at least one project scene to obtain at least one target document corresponding to each project scene;
and inputting at least one target document corresponding to each project scene into a conversation generating model to obtain at least one type of conversation corresponding to each project scene.
In practical application, classifying a plurality of target documents according to each project scene to obtain at least one target document corresponding to each project scene; and inputting at least one target document corresponding to each project scene into the dialogue generating model to obtain at least one type of dialogue corresponding to each project scene.
The types of the dialog include, but are not limited to, a video type, a text type, an interactive type, and the like. The video type may be understood as a video conversation, the text type may be understood as a text conversation, and the interactive type may be understood as an interactive conversation, such as presenting conversation content by selecting or clicking.
In a specific implementation, each target region corresponds to one initial document, each initial document is split into a plurality of target documents, each project scenario corresponds to at least one target document, and then after the at least one target document corresponding to each project scenario is input into the dialog generating model, the dialog generating model can output at least one type of dialog of each project scenario in each target region.
According to the above example, the target area is country a, firstly all regulatory compliance systems released by a fusion regulatory agency in country a are obtained, and then all regulatory compliance systems are subjected to document extraction to form an initial document; splitting the initial document into a plurality of target documents; and determining a target document corresponding to each project scene in the country a, and finally inputting the target document into a conversation generation model to obtain at least one type of conversation corresponding to the project scene.
If the video conversation corresponding to the project scene is carried out, the compliance in the target document is decomposed, and the target document is displayed in a mode of carrying out video conversation by two roles or three roles, so that the interestingness of compliance learning is improved.
In addition, the inputting at least one target document corresponding to each project scene into a dialog generation model to obtain at least one type of dialog corresponding to each project scene includes:
inputting the at least one target document corresponding to each project scene and the at least two conversation roles into a conversation generating model, and obtaining at least one type of conversation corresponding to each project scene.
In practical application, the number of characters of the dialog and the attribute information (such as name, image, etc.) of the characters can be set, and the interest of the dialog of the target object is further enriched.
Specifically, at least one target document corresponding to each project scene and at least two conversation characters are input into a conversation generating model, the conversation generating model outputs at least one type of conversation corresponding to each project scene and including the at least two conversation characters, and the at least one target document can be described by the at least two conversation characters through the conversation. The method is applied to a specific scene, and can enable compliance learning personnel of a third-party cross-border payment company to better and faster learn the compliance system aiming at the project issued by a supervision mechanism through a video conversation, document conversation or interactive conversation mode.
In the dialog generation method provided by the embodiment of the present specification, an initial document of a target object in a target area is extracted and split; the split target documents are classified according to the project scene, a plurality of types of conversations corresponding to each target area are generated through the classified target documents, the content of the target object is merged into the project scene in the conversations, the interestingness of learning the content of the target object is greatly increased through the conversation mode, and the user experience is improved.
Specifically, when the method is applied to practical application scenes, the compliance system of a supervision mechanism is displayed in a scene dialogue mode through the mode, interactive and dialogue videos are conducted through the scene dialogue type compliance culture declaration, compliance knowledge is integrated into each project scene in life, the purpose of culture declaration is achieved while interestingness is increased, and learning experience of users is enhanced.
Corresponding to the above method embodiment, the present specification further provides a dialog generating device embodiment, and fig. 2 shows a schematic structural diagram of a dialog generating device provided in an embodiment of the present specification. As shown in fig. 2, the apparatus includes:
an initial document determining module 202, configured to obtain a target object in a target area, and process the target object to obtain an initial document corresponding to the target object;
a target document determining module 204, configured to split the initial document based on preset requirements, and obtain multiple split target documents;
a dialog generation module 206 configured to classify the plurality of target documents based on the project scenario and generate at least one type of dialog corresponding to the project scenario based on the classified target documents.
Optionally, the initial document determination module 202 is further configured to:
determining a plurality of target areas, acquiring a target object of each target area, and processing the target object to obtain an initial document corresponding to the target object.
Optionally, the initial document determination module 202 is further configured to:
determining the object type of the target object, and determining an extraction method for extracting characters in the target object according to the object type;
and extracting characters in the target object according to the extraction method to obtain an initial document corresponding to the target object.
Optionally, the target document determining module 204 is further configured to:
inputting preset requirements and the initial document into a classification model, and obtaining a plurality of split target documents of the initial document.
Optionally, the training step of the classification model is as follows:
acquiring a sample preset demand and a sample initial document generated by a sample target object;
splitting the sample initial document based on the sample preset requirement to obtain a split sample target document;
taking the sample preset requirement and the sample initial document as training samples, and taking the sample target document obtained after splitting the sample initial document as a sample label;
training a classification model based on the training samples and the sample labels corresponding to the training samples to obtain the trained classification model.
Optionally, the dialog generation module 206 is further configured to:
classifying the target documents based on at least one project scene to obtain at least one target document corresponding to each project scene;
and inputting at least one target document corresponding to each project scene into a conversation generating model to obtain at least one type of conversation corresponding to each project scene.
Optionally, the dialog generation module 206 is further configured to:
inputting the at least one target document corresponding to each project scene and the at least two conversation roles into a conversation generating model, and obtaining at least one type of conversation corresponding to each project scene.
Optionally, the types of dialog include a video type, a text type, and an interaction type.
The dialog generating device provided by the embodiment of the present specification extracts and splits an initial document of a target object in a target region; the split target documents are classified according to the project scene, a plurality of types of conversations corresponding to each target area are generated through the classified target documents, the content of the target object is merged into the project scene in the conversations, the interestingness of learning the content of the target object is greatly increased through the conversation mode, and the user experience is improved.
The above is a schematic configuration of a dialog generating apparatus of the present embodiment. It should be noted that the technical solution of the dialog generating device is the same as that of the dialog generating method described above, and for details of the technical solution of the dialog generating device not described in detail, reference may be made to the description of the technical solution of the dialog generating method described above.
Referring to fig. 3, fig. 3 illustrates a block diagram of a computing device 300 provided according to an embodiment of the present description. The components of the computing device 300 include, but are not limited to, memory 310 and processor 320. The processor 320 is coupled to the memory 310 via a bus 330 and the database 350 is used to store data.
Computing device 300 also includes access device 340, access device 340 enabling computing device 300 to communicate via one or more networks 360. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 340 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present description, the above-described components of computing device 300 and other components not shown in FIG. 3 may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 3 is for purposes of example only and is not limiting as to the scope of the description. Those skilled in the art may add or replace other components as desired.
Computing device 300 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), a mobile phone (e.g., smartphone), a wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 300 may also be a mobile or stationary server.
Wherein the processor 320 is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the dialog generation method described above.
The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the dialog generating method described above belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the dialog generating method described above.
An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the dialog generation method described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the above-mentioned dialog generating method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the above-mentioned dialog generating method.
An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned dialog generating method.
The above is an illustrative scheme of a computer program of the present embodiment. It should be noted that the technical solution of the computer program is the same concept as the technical solution of the above-mentioned dialog generating method, and details that are not described in detail in the technical solution of the computer program can be referred to the description of the technical solution of the above-mentioned dialog generating method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts, but those skilled in the art should understand that the present embodiment is not limited by the described acts, because some steps may be performed in other sequences or simultaneously according to the present embodiment. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for an embodiment of the specification.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the embodiments. The specification is limited only by the claims and their full scope and equivalents.
Claims (10)
1. A dialog generation method comprising:
acquiring a target object of a target area, and processing the target object to obtain an initial document corresponding to the target object;
splitting the initial document based on a preset requirement to obtain a plurality of split target documents;
the plurality of target documents are classified based on the project scenario, and at least one type of dialog corresponding to the project scenario is generated based on the classified target documents.
2. The dialog generation method according to claim 1, wherein the obtaining a target object in a target region and processing the target object to obtain an initial document corresponding to the target object comprises:
determining a plurality of target areas, acquiring a target object of each target area, and processing the target object to obtain an initial document corresponding to the target object.
3. The dialog generation method according to claim 2, wherein the processing the target object to obtain an initial document corresponding to the target object includes:
determining the object type of the target object, and determining an extraction method for extracting characters in the target object according to the object type;
and extracting characters in the target object according to the extraction method to obtain an initial document corresponding to the target object.
4. The dialog generation method according to any one of claims 1 to 3, wherein splitting the initial document based on a preset requirement to obtain multiple split target documents includes:
inputting preset requirements and the initial document into a classification model, and obtaining a plurality of split target documents of the initial document.
5. The dialog generation method of claim 4, the training of the classification model comprising:
acquiring a sample preset demand and a sample initial document generated by a sample target object;
splitting the sample initial document based on the sample preset requirement to obtain a split sample target document;
taking the sample preset requirement and the sample initial document as training samples, and taking the sample target document obtained after splitting the sample initial document as a sample label;
training a classification model based on the training samples and the sample labels corresponding to the training samples to obtain the trained classification model.
6. The dialog generation method according to any one of claims 1 to 3, wherein the classifying the plurality of target documents based on the project scenario and generating at least one type of dialog corresponding to the project scenario based on the classified target documents comprises:
classifying the target documents based on at least one project scene to obtain at least one target document corresponding to each project scene;
and inputting at least one target document corresponding to each project scene into a conversation generating model to obtain at least one type of conversation corresponding to each project scene.
7. The dialog generation method of claim 6, said inputting at least one target document corresponding to said each project scenario into a dialog generation model, obtaining at least one type of dialog corresponding to said each project scenario, comprising:
inputting the at least one target document corresponding to each project scene and the at least two conversation roles into a conversation generating model, and obtaining at least one type of conversation corresponding to each project scene.
8. A dialog generation device comprising:
the initial document determining module is configured to acquire a target object of a target area, process the target object and acquire an initial document corresponding to the target object;
the target document determining module is configured to split the initial document based on preset requirements to obtain a plurality of split target documents;
a dialog generation module configured to classify the plurality of target documents based on the project scenario and generate at least one type of dialog corresponding to the target region based on the classified target documents.
9. A computing device, comprising:
a memory and a processor;
the memory is for storing computer-executable instructions, and the processor is for executing the computer-executable instructions, which when executed by the processor, implement the steps of the dialog generation method of any of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the dialog generation method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011613.XA CN114356860A (en) | 2022-01-06 | 2022-01-06 | Dialog generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011613.XA CN114356860A (en) | 2022-01-06 | 2022-01-06 | Dialog generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114356860A true CN114356860A (en) | 2022-04-15 |
Family
ID=81108006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210011613.XA Pending CN114356860A (en) | 2022-01-06 | 2022-01-06 | Dialog generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114356860A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116483981A (en) * | 2023-06-16 | 2023-07-25 | 北京好心情互联网医院有限公司 | Dialogue generation method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008145769A (en) * | 2006-12-11 | 2008-06-26 | Hitachi Ltd | Interaction scenario creation system, its method, and program |
| CN110110145A (en) * | 2018-01-29 | 2019-08-09 | 腾讯科技（深圳）有限公司 | Document creation method and device are described |
| CN110245224A (en) * | 2019-06-20 | 2019-09-17 | 网易（杭州）网络有限公司 | Talk with generation method and device |
| CN112017744A (en) * | 2020-09-07 | 2020-12-01 | 平安科技（深圳）有限公司 | Electronic case automatic generation method, device, equipment and storage medium |
| US20210125389A1 (en) * | 2019-10-23 | 2021-04-29 | Tata Consultancy Services Limited | Method and system for creating an intelligent cartoon chat strip based on dynamic content |
| JPWO2020036188A1 (en) * | 2018-08-15 | 2021-08-10 | 日本電信電話株式会社 | Training data generator, training data generation method and program |
| US20210286934A1 (en) * | 2020-12-22 | 2021-09-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Implementing text generation |
| CN113761943A (en) * | 2021-09-23 | 2021-12-07 | 阿里巴巴达摩院(杭州)科技有限公司 | Method for generating judicial dialogues, method and device for training models, and storage medium |
| CN113886560A (en) * | 2021-08-30 | 2022-01-04 | 阿里巴巴达摩院(杭州)科技有限公司 | Recommendation method and device for court trial problems |
-
2022
- 2022-01-06 CN CN202210011613.XA patent/CN114356860A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008145769A (en) * | 2006-12-11 | 2008-06-26 | Hitachi Ltd | Interaction scenario creation system, its method, and program |
| CN110110145A (en) * | 2018-01-29 | 2019-08-09 | 腾讯科技（深圳）有限公司 | Document creation method and device are described |
| JPWO2020036188A1 (en) * | 2018-08-15 | 2021-08-10 | 日本電信電話株式会社 | Training data generator, training data generation method and program |
| CN110245224A (en) * | 2019-06-20 | 2019-09-17 | 网易（杭州）网络有限公司 | Talk with generation method and device |
| US20210125389A1 (en) * | 2019-10-23 | 2021-04-29 | Tata Consultancy Services Limited | Method and system for creating an intelligent cartoon chat strip based on dynamic content |
| CN112017744A (en) * | 2020-09-07 | 2020-12-01 | 平安科技（深圳）有限公司 | Electronic case automatic generation method, device, equipment and storage medium |
| WO2021208444A1 (en) * | 2020-09-07 | 2021-10-21 | 平安科技（深圳）有限公司 | Method and apparatus for automatically generating electronic cases, a device, and a storage medium |
| US20210286934A1 (en) * | 2020-12-22 | 2021-09-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Implementing text generation |
| CN113886560A (en) * | 2021-08-30 | 2022-01-04 | 阿里巴巴达摩院(杭州)科技有限公司 | Recommendation method and device for court trial problems |
| CN113761943A (en) * | 2021-09-23 | 2021-12-07 | 阿里巴巴达摩院(杭州)科技有限公司 | Method for generating judicial dialogues, method and device for training models, and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116483981A (en) * | 2023-06-16 | 2023-07-25 | 北京好心情互联网医院有限公司 | Dialogue generation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10657969B2 (en) | Identity verification method and apparatus based on voiceprint | |
| US20220351487A1 (en) | Image Description Method and Apparatus, Computing Device, and Storage Medium | |
| Gao et al. | Deliberate attention networks for image captioning | |
| CN110781663A (en) | Training method and device of text analysis model and text analysis method and device | |
| CN112950170B (en) | Auditing method and device | |
| CN110209802B (en) | Method and device for extracting abstract text | |
| Dhingra et al. | Linguistic knowledge as memory for recurrent neural networks | |
| WO2021010744A1 (en) | Method and device for analyzing sales conversation based on speech recognition | |
| CN110555440B (en) | Event extraction method and device | |
| CN109597894B (en) | Correlation model generation method and device, and data correlation method and device | |
| CN111767883A (en) | Title correction method and device | |
| CN110555441A (en) | character recognition method and device | |
| CN111930914A (en) | Question generation method and device, electronic equipment and computer-readable storage medium | |
| CN115391499A (en) | Method for generating multitask generation model, question-answer pair generation method and related device | |
| CN115759001A (en) | Language model training method, text prediction method and device | |
| CN116644145A (en) | Session data processing method, device, equipment and storage medium | |
| CN114356860A (en) | Dialog generation method and device | |
| CN110059178A (en) | Problem distributing method and device | |
| CN116644167A (en) | Method and device for generating target answers, storage medium and electronic device | |
| CN111401854A (en) | Information processing method and device | |
| CN115934904A (en) | Text processing method and device | |
| CN116756278A (en) | Machine question-answering method and device | |
| CN110046233A (en) | Problem distributing method and device | |
| CN114138947A (en) | Text processing method and device | |
| CN114722817A (en) | Event processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |