CN118070807A

CN118070807A - Data processing method, device, equipment, storage medium and program product

Info

Publication number: CN118070807A
Application number: CN202211444827.2A
Authority: CN
Inventors: 朱明媛
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-11-18
Filing date: 2022-11-18
Publication date: 2024-05-24

Abstract

The embodiment of the application discloses a data processing method, a device, equipment, a storage medium and a program product, wherein the method comprises the following steps: identifying text triggering scene information corresponding to a first participation object, and acquiring target text keywords associated with the text triggering scene information from the text keywords based on the triggering scene information corresponding to the text keywords; acquiring candidate document data comprising target document keywords, and acquiring object information of a second participation object aimed at by the document triggering scene information; and generating a target document based on the object information of the second participation object and the candidate document data. By adopting the embodiment of the application, the matching degree of the target document and the document triggering scene information in the Internet page can be improved.

Description

Data processing method, device, equipment, storage medium and program product

Technical Field

The present application relates to the field of artificial intelligence, and in particular, to a data processing method, apparatus, device, storage medium, and program product.

Background

When a user performs operations in the internet, such as transferring, collecting, and sending a message, a corresponding document is often generated for viewing by the other party, so as to remind the user to know relevant information of the operations, for example, when transferring, document data for prompting transfer is generated, and when collecting, document data for prompting collection is generated. Generally, the pre-written text data under each application scene is pre-written in the application program, so that when a user enters a certain application scene, the pre-written text data corresponding to the application scene is displayed, and the method has universality due to the requirement of all users who want to adapt to the application program, namely, the language is generally reasonable, and for the requirement, the pre-written text data cannot adapt to different users, so that individuation and readability of the text data are poor.

Disclosure of Invention

The embodiment of the application provides a data processing method, a device, equipment, a storage medium and a program product, which can improve the matching degree of target text and text triggering scene information in an internet page.

In one aspect, an embodiment of the present application provides a data processing method, including:

Identifying text triggering scene information corresponding to a first participation object, and acquiring target text keywords associated with the text triggering scene information from the text keywords based on the triggering scene information corresponding to the text keywords;

Acquiring candidate document data comprising target document keywords, and acquiring object information of a second participation object aimed at by the document triggering scene information;

and generating a target document based on the object information of the second participation object and the candidate document data.

In one aspect, an embodiment of the present application provides a data processing apparatus, including:

The scene recognition module is used for recognizing the text triggering scene information corresponding to the first participation object;

the keyword acquisition module is used for acquiring target document keywords associated with the document triggering scene information from the document keywords based on the triggering scene information corresponding to the document keywords;

The document acquisition module is used for acquiring candidate document data comprising target document keywords;

The information acquisition module is used for acquiring object information of a second participation object aimed at by the text triggering scene information;

and the document generation module is used for generating a target document based on the object information of the second participation object and the candidate document data.

Wherein, scene recognition module includes:

The response unit is used for responding to the text triggering operation of the first participation object, acquiring the operation attribute information corresponding to the text triggering operation and acquiring the operation scene corresponding to the operation attribute information;

The scene information determining unit is used for acquiring a second participation object aimed at by the text triggering operation and determining text triggering scene information corresponding to the first participation object based on the operation scene and the second participation object.

Wherein, the document acquisition module includes:

the template acquisition unit is used for acquiring a first document template corresponding to the document triggering scene information;

And the candidate document determining unit is used for acquiring a second document template comprising the target document keyword from the first document template and determining the second document template as candidate document data.

Wherein, the file acquisition module still includes:

The history file acquisition unit is used for acquiring history file data, and performing data cleaning processing on the history file data to obtain conventional file data;

the feature extraction unit is used for carrying out keyword feature extraction processing on the conventional text data to obtain text keywords;

The information conversion unit is used for identifying the composition structure information of the conventional text data, determining the information to be filled corresponding to the conventional text data and the filling position information corresponding to the information to be filled based on the composition structure information and the text keywords, and converting the information to be filled into filling placeholders;

the placeholder combination unit is used for carrying out combination processing on the text keywords and the filling placeholders based on filling position information corresponding to the information to be filled, and generating a text template corresponding to the conventional text data; the document template comprises a first document template;

The scene information association unit is used for detecting trigger scene information corresponding to conventional text data, associating text keywords with the trigger scene information and associating text templates with the trigger scene information.

Wherein, the document generation module includes:

A parameter determination unit for determining document parameter information based on object information of the second participation object; the text parameter information comprises text language and reminding objects;

the target document acquisition unit is used for acquiring a target document conforming to document parameter information from the candidate document data; the expression mood of the target document is the mood of the document, and the target document aims at the reminding object.

Wherein, the document generation module still includes:

A template determination unit for determining a target document template from the candidate document data based on the object information of the second participation object;

the position information acquisition unit is used for acquiring the target filling placeholder in the target document template and the target filling position information corresponding to the target filling placeholder;

the filling content determining unit is used for determining filling content corresponding to the target filling placeholder based on the object information of the second participation object and the text triggering scene information;

and the filling content replacing unit is used for replacing the filling content with the target filling placeholder in the target document template based on the target filling position information to generate the target document.

Wherein, the data processing device still includes:

the response module is used for responding to the cancel operation aiming at the target file and acquiring the edited file data submitted by the input editing area;

The detection module is used for carrying out detection processing on the edited document data, determining the edited document data passing the detection as an alternative document, and outputting the alternative document.

In one aspect, the application provides a computer device comprising: a processor, a memory, a network interface;

The processor is connected to the memory and the network interface, where the network interface is used to provide a data communication function, the memory is used to store a computer program, and the processor is used to call the computer program to make the computer device execute the method in the embodiment of the present application.

In one aspect, embodiments of the present application provide a computer readable storage medium having a computer program stored therein, the computer program being adapted to be loaded by a processor and to perform a method according to embodiments of the present application.

In one aspect, embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium; the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method in the embodiment of the present application.

In the embodiment of the application, the computer equipment can identify the text triggering scene information corresponding to the first participation object, and acquire the target text keywords associated with the text triggering scene information from the text keywords based on the triggering scene information corresponding to the text keywords. In addition, the computer device may further obtain candidate document data including the target document keyword, and obtain object information of the second participation object for which the document triggering scene information is aimed. The computer device may then generate a target document based on the object information of the second participant and the candidate document data. According to the embodiment of the application, the association relation between the text triggering scene information and the target text keywords can be established by identifying the text triggering scene information corresponding to the first participation object, and the target text associated with the text triggering scene information is selected from the candidate text data comprising the target text keywords based on the association relation between the text triggering scene information and the target text keywords. Meanwhile, the suitability of the target document and the second participation object can be improved by analyzing the object information of the second participation object. In summary, the embodiment of the application can enable the generated target document to be adapted to different users, improve the matching degree of the target document and the document triggering scene information, and improve the individuation and individual readability (namely, the readability for different users) of the document data.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a diagram of a network interaction architecture for document data use provided by an embodiment of the present application;

fig. 2 is a schematic view of a scenario for acquiring a target document according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of a data processing method according to an embodiment of the present application;

FIG. 4a is a schematic view of a scenario for obtaining a document template according to an embodiment of the present application;

FIG. 4b is a schematic view of a scenario for text selection according to an embodiment of the present application;

FIG. 5 is a schematic view of another scenario for document selection provided by an embodiment of the present application;

FIG. 6a is a schematic view of a scenario in which a target document is used according to an embodiment of the present application;

FIG. 6b is a schematic view of another scenario using a target document according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a data processing apparatus according to an embodiment of the present application;

Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

It will be appreciated that in the specific embodiments of the present application, related data such as object information is involved, and when the above embodiments of the present application are applied to specific products or technologies, user permissions or consents need to be obtained, and the collection, use and processing of related data need to comply with related laws and regulations and standards of related countries and regions.

The embodiment of the application provides a method for generating a target document, and relates to the field of artificial intelligence. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.

The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology (voice technology), a natural language processing technology, machine learning/deep learning, automatic driving, intelligent traffic and other directions.

In the embodiment of the present application, please refer to fig. 1, fig. 1 is a network interaction architecture diagram for document data according to an embodiment of the present application. The server 100 may perform data interaction with a terminal cluster, where the terminal cluster may include: the terminal device 200a, the terminal device 200b, the terminal devices 200c, …, and the terminal device 200n, it will be appreciated that the above system may include one or more terminal devices, and the present application is not limited to the number of terminal devices. The server 100 may be a device for generating document data, and the server 100 and the terminal cluster are both devices that can use the document data. The server 100 may identify the document triggering scenario information corresponding to the first participating object, and obtain, from the document keywords, the target document keywords associated with the document triggering scenario information based on the triggering scenario information corresponding to the document keywords. Here, the participating object refers to a person or other non-human thing (such as a software program, etc.) that operates the server 100 or any one of the terminal devices in the terminal cluster. In addition, the server 100 may acquire candidate document data including the target document keyword, and acquire object information of the second participation object for which the document triggering scene information is directed. Further, the server 100 may generate the target document based on the object information of the second participation object and the candidate document data. The server 100 may then use the target document to communicate with the terminal cluster.

The server 100 and the terminal cluster may form a communication system, and in a case of using the communication system, the server 100 may perform data communication with any one of the terminal devices (e.g., the terminal device 200 a) in the terminal cluster. In a system usage situation, the server 100 may be used as a database or a transit server, and any one of the terminal devices (such as the terminal device 200 a) in the terminal cluster may perform data communication with other terminal devices. Optionally, any one of the terminal devices in the server 100 and the terminal cluster may run an application client (such as a social client, an office client, a conference client, and a game client) capable of using the text data. In particular, the application client here may include a client of communication interaction software, and may even be a client of real-time communication interaction software. In addition, any one of the server 100 and the terminal cluster may perform real-time text messaging, file messaging, voice communication, video communication, etc. between at least two participating objects through the client of the real-time interaction software. The above-mentioned terminal device may be an electronic device, including but not limited to a mobile phone, a tablet computer, a desktop computer, a notebook computer, a palm computer, a vehicle-mounted device, an augmented Reality/Virtual Reality (AR/VR) device, a head-mounted display, a smart television, a wearable device, a smart speaker, a digital camera, a camera, and other mobile internet devices (mobile INTERNET DEVICE, MID) with network access capability, or a terminal device in a train, a ship, a flight, or the like.

The computer device mentioned in the present application may be a server or a terminal device, or may be a system composed of a server and a terminal device.

Wherein a communication connection may exist between the terminal clusters, for example, a communication connection exists between the terminal device 200a and the terminal device 200b, and a communication connection exists between the terminal device 200a and the terminal device 200 c. Meanwhile, any terminal device in the terminal cluster may have a communication connection with the server 100, for example, a communication connection exists between the terminal device 200a and the server 100, where the communication connection is not limited to a connection manner, and may be directly or indirectly connected through a wired communication manner, may be directly or indirectly connected through a wireless communication manner, or may also be other manners, and the application is not limited herein.

Further, referring to fig. 2, fig. 2 is a schematic view of a scenario for acquiring a target document according to an embodiment of the present application. As shown in fig. 2, the computer device may obtain the document trigger scene information after the communication software page 201 responds to the trigger operation of the first participant. In the communication software page 201, regarding the communication software interaction group payment operation initiated by the first participant object zima, the communication software interaction group payment operation needs to collect 180 yuan, 9 people have paid, 18 yuan are paid for each person, and the current state is the unfilled state. Meanwhile, the computer equipment can recognize the text triggering scene information, and acquire target text keywords matched with the text triggering scene information from the text management database. Further, the computer device may obtain object information of a second participant object for which the document triggers the scene information. Further, the computer device may obtain the target document according to the target document keyword and the object information of the second participation object.

Further, referring to fig. 3, fig. 3 is a flow chart of a data processing method according to an embodiment of the application. As shown in fig. 3, the method may be performed by a computer device, which may be any one of the terminal devices in the terminal cluster shown in fig. 1, for example, the terminal device 200a, or may be the server 100 shown in fig. 1, which is not limited herein. For ease of understanding, embodiments of the present application will be described with the method being performed by a computer device, and the data processing method may include at least the following steps S101 to S103:

step S101, identifying text triggering scene information corresponding to a first participation object, and acquiring target text keywords associated with the text triggering scene information from the text keywords based on the triggering scene information corresponding to the text keywords.

The first participation object may refer to a participation object operating the computer device, that is, the scene in the document triggering scene information may be a scene created or selected by the first participation object. Further, the document triggering scenario information may refer to scenario information satisfying conditions constituting a document triggering event. In particular, the document keywords may include keywords that are intercepted from the document data. The document data may be document data stored in a pre-constructed document management database, and the document keywords may be words already contained in the document data; alternatively, the text keywords may be words that do not exist in the text data, but have the same meaning as the expression of the keywords in the text data. Specifically, the computer device can recognize whether the meaning of a word is the same as that of a key word in the document data through the existing semantic recognition technology.

Specifically, the process of the computer device identifying the context trigger scene information corresponding to the first participant object may be as follows: the computer equipment can respond to the text triggering operation of the first participation object, acquire the operation attribute information corresponding to the text triggering operation, and acquire the operation scene corresponding to the operation attribute information. Meanwhile, the computer equipment can acquire a second participation object aimed at by the text triggering operation, and based on the operation scene and the second participation object, the text triggering scene information corresponding to the first participation object is determined. The document triggering operation refers to an operation for triggering generation of document data, for example, the document triggering operation may be a triggering operation for a target component, such as a clicking operation, a double-clicking operation, or a right-click operation, where the target component refers to any component that needs to generate the document data when triggered. The computer device may respond to the document triggering operation of the first participant to obtain operation attribute information corresponding to the document triggering operation, for example, the document triggering operation herein is a triggering operation for a target component, and it is assumed that the target component is a transfer component, and at this time, the operation attribute information corresponding to the document triggering operation may be obtained as "transfer". Further, the associated media data of the text triggering operation can be obtained, and the operation scene corresponding to the operation attribute information is determined according to the associated media data of the text triggering operation and the operation attribute information. For example, the text triggering operation is triggered when session interaction is performed in the social platform, and can obtain an associated session message and the like generated before the text triggering operation is triggered, determine the associated session message as associated media data, analyze the associated media data and the operation attribute information, and obtain an operation scene corresponding to the operation attribute information, for example, the associated media data comprises "I eat things in XX but are delicious today" and "I pay XX money altogether", and the like, and can obtain the operation scene as "eat and transfer". Meanwhile, the computer device may acquire a second participation object aimed at by the document triggering operation "clicking operation", where the second participation object may refer to a viewing participation object of the target document triggered and generated by the document triggering operation, in short, to whom (i.e. the second participation object) the target document is viewed, for example, the target document triggered and generated by the document triggering operation is to be sent to the user a for viewing, and then the user a is the second participation object. Then, the computer device may determine that the context trigger scenario information corresponding to the first participant object is "transfer, single person" based on the operation scenario "eat, transfer" and the second participant object.

For another example, the document triggering operation herein is a triggering operation for a target component, and it is assumed that the target component is a money receiving component, and at this time, the operation attribute information corresponding to the document triggering operation may be acquired as "collection". Further, the associated media data of the text triggering operation can be obtained, and the operation scene corresponding to the operation attribute information is determined according to the associated media data of the text triggering operation and the operation attribute information. For example, the text triggering operation is triggered when session interaction is performed in the social platform, and can obtain an associated session message and the like generated before the text triggering operation is triggered, determine the associated session message as associated media data, analyze the associated media data and the operation attribute information, and obtain an operation scene corresponding to the operation attribute information, for example, the associated media data includes "I or me ten people eat things in XX at present and" I pay XX money altogether ", and the like, and can obtain the operation scene as" eat and collect food ". At the same time, the computer device may acquire a second participant object for which the document triggering operation "click operation" is directed. Then, the computer device may determine, based on the operation scene "eat, collect" and the second participant, that the document trigger scene information corresponding to the first participant is: "collect, many people".

For another example, the document triggering operation herein is a triggering operation for a target component, and it is assumed that the target component is a message sending component, and at this time, operation attribute information corresponding to the document triggering operation may be acquired as "message sending". Further, the associated media data of the text triggering operation can be obtained, and the operation scene corresponding to the operation attribute information is determined according to the associated media data of the text triggering operation and the operation attribute information. For example, the text triggering operation is triggered when session interaction is performed in the social platform, and may obtain an associated session message generated before the text triggering operation is triggered, and the associated session message is determined to be associated media data, and the associated media data and the operation attribute information are parsed to obtain an operation scenario corresponding to the operation attribute information, where, for example, the associated media data includes "please select something of your virtual love object" and "something of say: you really see "etc. today, the operation scene is" virtual friends making, communication interaction ". At the same time, the computer device may acquire a second participant object for which the document triggering operation is directed. Then, the computer device may determine, based on the operation scenario "virtual friend making, communication interaction" and the second participation object, that the document triggering scenario information corresponding to the first participation object is: virtual friend making, communication interaction.

Further, the computer device may acquire the document keyword and the trigger scene information corresponding to the document keyword from the document management database, perform the document trigger scene information retrieval process on the trigger scene information in the document management database, determine the document keyword corresponding to the retrieved document trigger scene information as the target document keyword, and then the computer device may execute step S102. For example, the document keywords may include, but are not limited to, "equity", "lifetime", and "party", etc., the trigger scenario information corresponding to the document keywords "equity" may be "collection," the trigger scenario information corresponding to the "lifetime" may be "communication interaction," and the trigger scenario information corresponding to the "party" may be "communication interaction, multiple persons. Further, according to the document triggering scene information (such as "collection, multiple persons") corresponding to the first participation object obtained by the computer, selecting the document keyword "average" from the document keyword "average", the document keyword "lifetime" and the document keyword "party" as the target document keyword associated with the document triggering scene information corresponding to the first participation object.

Optionally, if the computer device does not retrieve the document triggering scene information in the document management database, that is, indicates that the computer device does not acquire the target document keyword in the document management database, the computer device may acquire the first document data submitted by the input editing area, and output the first document data. Alternatively, the computer device may display a document retrieval failure message while simultaneously displaying the input edit area. Further, the first document data submitted by the input editing area is acquired. Alternatively, the computer device may perform data detection processing for the input editing data of the input editing region, and determine the input editing data passed through the detection as the first document data. The data detection process may be a filtering process for unique words, or may be a filtering process according to a specific rule. Optionally, the computer device may identify the first document data by using a keyword to obtain a first document keyword included in the first document data, and store the first document keyword and the document triggering scene information in association, for example, in the document management database, where the first document keyword becomes a document keyword in the document management database. Optionally, the trigger display data and the first document data associated with the document trigger operation are displayed. Wherein the trigger presentation data may be used to represent data displayed by the computer device in response to a document trigger operation. For example, the trigger display data corresponding to the text trigger operation with the operation attribute information of "transfer" may include transfer information (such as a transfer object, transfer amount, transfer instruction information, etc.) displayed on the internet page during the transfer. Further, optionally, the computer device may perform a document keyword search process on the first document data, obtain a document keyword included in the first document data and keyword attribute information corresponding to the document keyword, and store the document keyword included in the first document data, the keyword attribute information corresponding to the document keyword, and the document triggering scene information in association with the document management database. The keyword attribute information is information for classifying attributes of the document keywords. For example, if the document keyword is "autumn", the keyword attribute information of the document keyword "autumn" is "season". Alternatively, the keyword attribute information may include categories such as "season", "crowd", "place", "activity type", and "others".

The text keywords may be manually input keywords acquired by the computer device, that is, the computer device may display a keyword management page, acquire the text keywords submitted by the keyword management page, trigger scene information and keyword attribute information associated with the text keywords through the keyword management page, and store the text keywords submitted by the keyword management page, the trigger scene information and the keyword attribute information associated with the text keywords in a text management database in an associated manner.

Alternatively, the text keywords may be parsed from the text data. That is, the computer device may acquire the document data submitted manually, or may acquire the document data from the internet, acquire the document data from the history application data of the target application, which is public application data or authorized application data (i.e., application data that can be read or used) generated by the history of the target application, or the like, wherein the target application may be an application that recognizes the document trigger scene information corresponding to the document data, or may also be an application that can generate the document data, or the like. Further, the computer device may analyze the document data to obtain the document keywords and trigger scene information corresponding to the document keywords. For example, a specific manner of parsing the document data by the computer device may be a natural language processing (NLP, natural Language Processing) manner.

It should be noted that the construction process of the document management database may be as follows: specifically, the computer device may perform keyword extraction on the document data to obtain a document keyword of the document data, and perform keyword attribute extraction processing on the document keyword to obtain keyword attribute information associated with the document keyword. The triggering scene information corresponding to the text data can be identified, and text keywords included in the text data and the triggering scene information corresponding to the text data can be associated and stored, for example, stored in a text management database. Further, the computer device may associate keyword attribute information of the document keyword with the document keyword, and the computer device may store the document data, the document keyword, and the keyword attribute information associated with the document keyword in association with the document management database. In summary, the computer device may obtain the document keywords from the already constructed document management database. The computer equipment stores the corresponding relation among the text data, the text keywords and the keyword attribute information associated with the text keywords in the text management database.

In the embodiment of the application, the corresponding relation among the text data, the text keywords and the keyword attribute information associated with the text keywords is clarified by constructing the text management database by the computer equipment, and the trigger scene information corresponding to the text keywords is clarified, so that the computer equipment can directly search the text trigger scene information when recognizing the text trigger scene information, and the target text keywords corresponding to the text trigger scene information are obtained. Moreover, based on the constructed document management database, the search time of the document keywords is reduced, and the efficiency of acquiring the document keywords is improved.

Step S102, candidate document data comprising target document keywords is obtained, and object information of a second participation object aimed at by the document triggering scene information is obtained.

Specifically, the computer device may acquire candidate document data including the target document keyword in two alternative ways:

In one manner ①, the computer device may directly obtain candidate document data including the target document keyword from the document data. At this time, the candidate document data may be regarded as the complete document data preliminarily acquired. Further, the object information of the second participation object may include age information, preference information, and other information of the second participation object.

Specifically, in one manner ②, the computer device may obtain a first document template corresponding to the document triggering scene information. The first document template is a document template applicable to the current document triggering scene information, for example, if the current document triggering scene information is "dinner together", the first document template is a document template associated with "dinner together". At the same time, the computer device may obtain a second document template including the target document keyword from the first document template, and determine the second document template as candidate document data. Specifically, the computer device may obtain the document keywords corresponding to the first document templates respectively, and compare the document keywords corresponding to the first document templates respectively with the target document keywords, and obtain, from the first document templates, second document templates including the target document keywords, where the second document templates are candidate document data. The number of the first document templates may be b, where b is a positive integer. The number of second document templates may be c, c being a positive integer less than or equal to b. Specifically, the computer device may first trigger scene information through the document to perform primary screening of the document templates, reduce the number of document templates to be matched, and then determine a second document template including the target document keywords from the document templates (i.e., the first document templates) selected by the primary screening, thereby improving the matching efficiency of the document templates.

In particular, the computer device may be configured to obtain a first document template from the document templates. The document template can be considered to be pre-generated before the target document is generated, and optionally, the document template can be updated in the process of generating the target document. Specifically, the computer device may acquire the history document data, and perform data cleaning processing on the history document data to obtain the conventional document data. Further, the computer device can perform keyword feature extraction processing on the conventional text data to obtain text keywords. In addition, the computer device can identify the composition structure information of the conventional text data, determine the to-be-filled information corresponding to the conventional text data and the filling position information corresponding to the to-be-filled information based on the composition structure information and the text keywords, and convert the to-be-filled information into the filling placeholder. The composition structure information can be used for representing the phrase included in the document data, the position information of each phrase and the like, and the phrase comprises the document keywords in the conventional document data. Then, the computer device can perform combination processing on the text keywords and the filling placeholders based on filling position information corresponding to the information to be filled, and generate a text template corresponding to the conventional text data. Meanwhile, the computer equipment can detect trigger scene information corresponding to conventional document data, correlate the document keywords with the trigger scene information and correlate the document templates with the trigger scene information.

For ease of understanding, please refer to fig. 4a, fig. 4a is a schematic view of a scenario of obtaining a document template according to an embodiment of the present application. The document template may include a first document template, and a specific process of acquiring the document template by the computer device may be as follows: as shown in fig. 4a, a computer device may obtain historical document data. The historical document data may be document data obtained from a document management database. Optionally, the historical document data may also be document data obtained by manual input. Further, the computer device can perform data cleaning on the historical document data to obtain the conventional document data. Data cleansing may include, but is not limited to, content filtering, deduplication, and unifying specification, among others. Specifically, the specific procedure of the content filtering process may be as follows: the computer device may perform content detection on the historical document data, identify abnormal document data in the historical document data, and delete the abnormal document data, where the abnormal document data may be regarded as document data whose content does not conform to a document template generation condition, such as document data including a preset abnormal vocabulary, or document data whose content type is a preset filter type, and the like. Further, the specific procedure of the deduplication process may be as follows: the computer device can judge and screen repeated items of the historical document data, and delete the historical document data judged to be repeated items. It will be appreciated that the data cleansing process may include any one of content filtering, deduplication, and unified specification, or may be a combination of at least two of these.

Further, in the process of acquiring the document template, the computer equipment extracts keywords from the conventional document data to obtain the document keywords included in the conventional document data. The composition structure information of the conventional document data can be identified, and the composition structure information can comprise N phrases included in the conventional document data and position information corresponding to each phrase. Determining the phrases except the text key words in the N phrases as information to be filled; or the auxiliary content can be identified in the content data except the text keywords and the phrases except the text keywords and the auxiliary content are determined to be the information to be filled, wherein the auxiliary content refers to the words of the language qi, the connecting words among the phrases and the like without actual meaning, such as 'Jiang', 'end' or 'place', and the like. Or, the phrases with attribute information can be identified from the N phrases except the text keywords, and the phrases with attribute information are determined as the information to be filled, wherein the phrases with attribute information can refer to a specific object, namely, the phrases with corresponding filling placeholders exist, and the object can be tangible or intangible. Further, the position information corresponding to the information to be filled may be determined as filling position information, and N is a positive integer. Further, the information to be filled in the conventional document data can be switched to the filling placeholder corresponding to the information to be filled, so that the document template corresponding to the conventional document data is obtained. And acquiring triggering scene information corresponding to the conventional text data, and storing the triggering scene information corresponding to the conventional text data and the text template in an associated manner. Optionally, the number of the conventional document data may be at least two, and through the above process, a document template corresponding to each conventional document data may be obtained.

For example, in a possible case where the document data is "handled by a limited version of the XX production, taking the position information of the phrase included in the document data as the sequence number in the document data as an example, it is assumed that the document keyword is identified as" handled ", the information to be filled in the document data is identified as" XX ", the information to be filled in" XX "has an attribute information" place ", the information to be filled in" XX "in the conventional document data is switched to the corresponding filling placeholder based on the filling position information corresponding to the information to be filled in the conventional document data, and if the filling placeholder after the switching of the information to be filled in" XX "is" place name ", the computer device can obtain the document template" handled by the limited version of the XX production.

Or the conventional text data can be input into a template generation model, in the template generation model, phrase splitting is carried out on the conventional text data, the information content of each phrase is detected, the information to be filled is determined based on the information content, and in the template generation model, fuzzy processing is carried out on the information to be filled in the conventional text data, so that the text template corresponding to the conventional text data is obtained. The blurring process is a process of converting information to be filled into corresponding filling placeholders. The template generation model is obtained through training a template label corresponding to the document data sample.

Or the conventional text data can be split to obtain N phrases, the word parts of the phrases corresponding to the N phrases are detected, the text keywords are determined based on the word parts of the phrases and the position information corresponding to the N phrases, and N is a positive integer. Determining other word groups except the text key words as information to be filled; or identifying auxiliary content in the text data based on the word part of the word and the position information corresponding to the N word groups respectively, and determining the word groups except the text keywords and the auxiliary content as information to be filled. And analyzing word senses of the information to be filled, and determining filling placeholders corresponding to the information to be filled based on the word senses and the word parts of the word groups of the information to be filled. Further, the information to be filled in the conventional text data is replaced by the corresponding filling placeholders, and the text templates corresponding to the text keywords are obtained. Or the filling placeholder corresponding to the information to be filled and the text keyword can be combined into the text template corresponding to the text keyword based on the word part of the word group corresponding to the information to be filled and the word part of the word group corresponding to the text keyword.

The above is several optional methods for generating the document template, and the method for generating the document template is not limited herein.

Alternatively, it is assumed that the number of conventional document data is M, M being a positive integer. The triggering scene information corresponding to the M conventional text data can be identified, and the M conventional text data is divided into k text clusters based on the triggering scene information corresponding to the M conventional text data, wherein k is a positive integer. In each document cluster, determining a document template corresponding to conventional document data included in each document cluster by adopting the generation mode of the document template, wherein in the document template corresponding to the conventional document data included in the same document cluster, the document keywords can be associated with trigger scene information corresponding to the document cluster.

In addition, in the process of acquiring the related data of the second participation object, the computer equipment can acquire the object information of the second participation object aimed at by analyzing the related data of the second participation object. Wherein the related data of the second participant object may be communication interaction data of the second participant object. Specifically, the related data of the second participant, which is acquired by the computer device, may refer to daily usage data of real-time communication software of the second participant, session record data of the real-time communication software, browsing content data of the real-time communication software, and the like. The object information of the second participant may include, but is not limited to, basic information of the second participant and an object relationship between the second participant and the first participant, for example, the basic information of the second participant may include age interval, gender, social preference information of the second participant, where the social preference information refers to a mood and a style of a published message that the second participant prefers to use when social contact is performed; the object relationship between the second participating object and the first participating object may include, but is not limited to, a young relationship, a peer relationship, a colleague relationship, and a friend relationship (such as a girlfriend or a brother, etc.), wherein the object information of the second participating object is information that the second participating object has authorized public, that is, the object information of the second participating object is authorized by the second participating object. For example, the document triggering operation identified by the computer device may be a "transfer operation", in which the computer device may acquire object information of the second participation object, for example, assuming that the object information acquired of the second participation object includes an age interval of "about 20 years old", a gender "woman", social preference information "lovely, a second order element", an object relationship "friend relationship" with the first participation object, and the like.

It should be noted that, the relevant data of the second participant (i.e., the object information of the second participant, such as the communication interaction data) acquired by the computer device is the data allowed to be acquired by the second participant, and the process of analyzing the relevant data of the second participant is only completed on the terminal device used by the second participant, or the second participant performs public authorization, and then uploads the data to the server. That is, the computer device may upload, in a case where the permission of the second participation object passes, object information of a part of the second participation object permitted by the second participation object to the server, and then, perform save processing by the server. That is, the computer device may acquire the object information of the second participation object from the device in which the second participation object is located, or acquire the object information of the second participation object disclosure authority from the server, or the like.

The number of the text keywords acquired by the computer equipment can be a, and a is a positive integer. For example, taking a as3, the text keywords may be "party," equity, "" ancestor. Further, the correspondence between the document keyword and the document triggering operation may be a correspondence in which one document keyword corresponds to only one document triggering operation, or a correspondence in which one document keyword corresponds to a plurality of document triggering operations. For example, the document keyword "equity" may correspond to the document triggering operation "collection operation".

Further, in the above-described respective modes, object information of the second participation object may be acquired. As shown in step S101, in the transfer scenario, the second participating object may be a participating object transferred by the first participating object.

Step S103, generating a target document based on the object information of the second participation object and the candidate document data.

Specifically, the generation of the target document may have two alternative ways:

In the manner ① described above, the computer device may determine the document parameter information based on the object information of the second participant object. The text parameter information comprises text language and gas and reminding objects. Specifically, the computer device may determine the document mood and the reminding object in the document parameter information based on the basic information (such as age information) of the second participant, the preference information (such as preference content and offensive content), and other information (such as personalized analysis content).

The specific process of determining the text parameter information (i.e. the text mood and the reminding object) by the computer device may be as follows: for example, the computer device may obtain age information of the first participant, determine a difference between the age information of the second participant and the age information of the first participant as the lifetime information. Specifically, if people like you minutes of information is greater than or equal to 20 years, the computer device may determine that the second participation object is a lifetime of the first participation object; people like you years or more and less than 20 years of information, the computer device may determine the second participation object as a ancestor; people like you years or more and less than 5 years of information, the computer device may determine the second participation object as a sibling of the first participation object; the people like you points information is less than-5 years, the computer device may determine the second participant object as the ancestor of the first participant object. Further, the computer device may determine the lifetime information of the second participant object as a specific class partition of the reminder object. For example, the reminder object for the first participant object may be a ancestor (second participant object), a sibling (second participant object), or a ancestor (second participant object). At the same time, the computer device may determine a case mood of the first participant object for the second participant object based on the lifetime information. For example, if the second participant is a lifetime of the first participant, the document mood may be "respect", and the document mood may be expressed as "respect" specifically, and the language may be used in the document with respect to the lifetime and with blessing; if the second participation object is judged to be the ancestor of the first participation object, the language gas of the language document can be formal, and the formal language gas of the language document can be expressed as a general written term in the language document; if the second participation object is the sibling of the first participation object, the language gas of the language case can be "nickname", and the language gas of the language case can be specifically expressed as a naughty term or a turn-around term; if the second participant is the evening of the first participant, the language may be "guidance" and the language "guidance" may be expressed specifically as that the language may use the term of the saluting and advice and encouragement encouraged class for the evening.

In addition, the computer device may obtain a target document conforming to the document parameter information from the candidate document data. The expression mood of the target document is the mood of the document, and the target document aims at the reminding object. For example, if the reminder object obtained by the computer device is sibling (second participant object) and the document mood is "nick", the computer device may select a target document that meets the "nick" mood from the candidate document data and is suitable for use between siblings.

In the manner ② described above, the computer device may determine a target document template from the candidate document data based on the object information of the second participant. Specifically, the computer device may analyze based on the acquired related data of the second participant object to obtain object information such as social preference information of the second participant object, and select, according to the object information such as social preference information of the second participant object, a target document template that conforms to the object information such as social preference information of the second participant object from the candidate document data. For example, if the social preference information of the second participant obtained by the computer device is in a lovely style, selecting candidate document data with words such as "ou", "ha" and the like as a target document template; if the computer equipment does not acquire the social preference information of the second participation object, randomly selecting candidate document data from the candidate document data as a target document template. The specific process of the computer device obtaining the target document template may refer to the specific process of generating the first document template in step S102 in fig. 3, which is not described herein. For example, the target document template may be "& crowd audience + share + & crowd audience.

Further, the computer device may obtain the target fill placeholder in the target document template and target fill location information corresponding to the target fill placeholder. Further, the computer device may determine the filler content corresponding to the target filler placeholder based on the object information of the second participant object and the document trigger scene information. The computer device may then replace the filler content with the target filler placeholder in the target document template based on the target filler location information, generating the target document. For example, if the target document template is "& crowd audience + share + & crowd audience", the computer device may obtain the target fill placeholders as "& crowd audience" (subject) and "& crowd audience" (subject). Further, the computer device may determine the filler content corresponding to the target filler placeholder based on the object information of the second participant object and the document trigger scene information. For example, if the second participating object acquired by the computer device is "colleague", the document triggering scene information is "collection, multiple persons", the filling content corresponding to the "& crowd audience" (subject) may be "colleague", and the filling content corresponding to the "& crowd audience" (subject) may be a specific object requiring transfer, that is, the "& crowd audience" (subject) indicates who needs to transfer money to. The computer device may then replace the filler content with the target filler placeholder in the target document template based on the target filler location information, generating the target document. For example, the computer device may replace the filling content (i.e., "each co-worker") corresponding to the "& crowd-of-people" (subject) in the target document template, and may replace the filling content (i.e., who needs to transfer money) corresponding to the "& crowd-of-people" (subject) in the target document template, so as to obtain the target document: "colleagues are shared to XXX".

It should be noted that, the computer device may not only select the target document, but also cancel the selection of the target document. Specifically, the computer device may obtain the edited document data submitted by the input editing area in response to the cancel operation for the target document. Further, the computer device may perform detection processing on the edited document data, determine the edited document data passing the detection as an alternative document, and output the alternative document.

For ease of understanding, please refer to fig. 4b, fig. 4b is a schematic view of a scenario for text selection provided in an embodiment of the present application. As shown in fig. 4b, the document triggering scenario information may be "collect, multiple people. In fig. 4b, the first participating object is a group collection initiator Zima, the second participating object is 10 people, namely, bright, coral Ling Shan, cabbage and junxian …, each person needs to pay 18 yuan, and Zima needs to receive 180 yuan. Currently, the computer device has detected that nine out of 10 people have paid, and that 1 person has not paid. At this time, in the real-time communication software page 401, the computer device produces the target document "whether the target document is hashed by the water group screen" through the document template, remembers the payment. The computer device can respond to the first participation object to click the image pen, cancel the selection of the target document and enter a custom document editing mode. Further, in the real-time communication software page 402, the computer device enters a custom document editing mode, acquires the edited document data "ancestors" submitted in the input editing area, remembers the cost of the current party for the stay group message, and spreads all the costs, and is hard to support my. Alternatively, the computer device may determine the edited document data passing through the detection as an alternative document, and set the alternative document as the default target document of the group, and then set the alternative document as the default target document of the group, and the alternative document is preferentially displayed in the recommended documents. Further, in the real-time communication software page 403, the computer device sets the target document "whether the target document is hashed by the water group, remembers that the payment is set as the default target document of the group, and a" setting success "prompt appears in the upper right corner area of the real-time communication software page 403. Further, in the real-time communication software page 404, the computer device may respond to the "change to change" clicked by the first participant, select the target document "old iron" from the document library, and remember whether the payment to "replace target document" is brushed by the water group with a haha, and remember the payment to "loose.

For ease of understanding, please refer to fig. 5, fig. 5 is a schematic diagram of another scenario selection provided in an embodiment of the present application. As shown in fig. 5, the document triggering scenario is "communication interaction". In the game application, the computer device may respond to the click operation of the first participating object (i.e. the current player of the game application), and open the object session interface, as shown in the game application interface 501 of fig. 5, and the computer device may respond to the instruction of the first participating object, and further open the object session interface between the first participating object and the second participating object (i.e. the game friends Miruku _lee of the current player in fig. 5). Wherein in the object session interface, the computer device may generate the target document "how is this done all the way black? Is the and end soon? Is the lower office together? ". Further, the computer device may set the selected target file as a default invitation file in the game application in response to a "set to default" operation of the first participant. Wherein, like the game application software interface 502 in fig. 5, the selected target document is successfully set as the interface schematic diagram of the default invitation document in the game application software for the computer device to respond to the "set to default" operation of the first participation object. Optionally, the computer device may cancel selection of the target document in response to the first participant clicking on the image "pen" and enter the custom document editing mode. For a detailed step of the "default setting" operation and entering the custom document editing mode, please refer to fig. 4b, which is a detailed description of the "default setting" operation and entering the custom document editing mode, and will not be repeated herein.

It can be understood that when the context trigger scene information is "virtual friend making, communication interaction", the computer device can perform semantic analysis on the sent message to obtain an operation scene. For example, when the operation scenario is "messaging with the computer device", that is, messaging is performed between the first participation object and the computer device, and the second participation object (that is, the first participation object) is the viewer of the target document, the computer device may send the generated target document as a message of the third participation object (such as the non-player character NPC) to the first participation object, and display the target document.

For ease of understanding, please refer to fig. 6a, fig. 6a is a schematic view of a scenario of using a target document according to an embodiment of the present application. As shown in fig. 6a, in the communication interactive software interface 601, a first participant sends a first session message 602, such as "hello, is very happy to know that you are your colleague xxx", where a message sending operation for the first session message 602 may be considered as a case triggering operation of the first participant, operation attribute information corresponding to the case triggering operation is obtained, for example, the operation attribute information corresponding to the case triggering operation may be determined according to the message sending operation shown in fig. 6a, the content of the first session message 602, and an application scenario where the message sending operation is located, such as here, a session scenario between the first participant and the third participant, etc., where the operation attribute information corresponding to the case triggering operation is determined, and the operation attribute information may be obtained as "a message reply for the first session message 602", and the operation scenario is determined as "a message reply, and is first questionable according to the operation attribute information. Further, the computer device may determine that the context trigger scenario information is "message reply, first question" according to the operation scenario "message reply, first question" and the second participation object (here, the first participation object). At this time, the computer device performs recognition processing based on the document trigger scene information, assuming that the target document keyword "first meeting" is acquired from the document management database. Further, the computer device obtains candidate document data including the target document keyword, and obtains object information of a second participation object for which the document triggering scene information is aimed, here, object information of the first participation object. Finally, based on the object information of the second participating object and the candidate document data, a target document 603 is generated, such as "hello, i is xxxxxx, first meet, please refer to multiple directions. For a specific process of generating the target document 603, please refer to the specific description of the generation of the target document from step S101 to step S103 in fig. 3, which is not repeated here.

For ease of understanding, please refer to fig. 6b, fig. 6b is a schematic view of another scenario using a target document according to an embodiment of the present application. As shown in fig. 6b, the text trigger scenario information corresponding to the first participant identified by the computer device is "transfer, single person". At the same time, the computer device generates a trade order, where the trade order is empty. Alternatively, the computer device may be a client a, and then the client a may perform a message interaction for applying for a transaction request with the server, and the server may perform a data interaction for confirming the transaction environment with the client B. Further, the computer device may select the usage target document or select the usage alternative document in response to a selection operation of the first participation object. When the computer device selects to use the target document in response to the first participant, the computer device may generate the target document through the specific generation step of the target document in fig. 3. At the same time, the computer device initiates a payment process using the target document synchronously generated from the document library. The computer device may then present the target document sent from the document library to the second participant at the payment interface. Correspondingly, when the computer device selects to use the alternative document in response to the first participation object, the computer device may generate the alternative document through the specific production process steps of the alternative document in fig. 3. In addition, the computer device may store the detected candidate document in the document library as candidate document data, and the computer device may further apply the detected candidate document to the payment interface to display to the second participant.

For example, triggering a scenario information "transfer for a document, the use of a target document under a single person" may be as follows: (1) And the first participated object initiates the transfer request through the computer equipment corresponding to the first participated object. (2) And the cloud server associated with the computer equipment corresponding to the first participated object receives the transfer request and simultaneously sends the transfer request to the computer equipment corresponding to the second participated object. (3) And the computer equipment corresponding to the second participation object receives the transfer request, and in addition, the object information of the second participation object is sent to a cloud server associated with the computer equipment corresponding to the first participation object. (4) And the cloud server is associated with the computer equipment corresponding to the first participation object and sends the object information of the second object to the computer equipment corresponding to the first participation object. In addition, the computer equipment corresponding to the first participation object determines the document parameter information, and obtains the target document conforming to the document parameter information from the candidate document data. The computer device herein may include any one of the server 100 and the terminal device in the terminal cluster in fig. 1, which is not specifically limited herein.

For another example, the usage process of the target document under the scenario information "collect, multiple people" for the document trigger scenario information may be as follows: (1) And the first participation object initiates a communication interaction software group collection request through the computer equipment corresponding to the first participation object. (2) And the cloud server associated with the computer equipment corresponding to the first participation object receives the communication interaction software group collection request, and simultaneously, the communication interaction software group collection request is sent to the computer equipment corresponding to the second participation object. (3) And the computer equipment corresponding to the second participation object receives the communication interaction software group collection request, and in addition, the object information of the second participation object is sent to a cloud server associated with the computer equipment corresponding to the first participation object. (4) And the cloud server is associated with the computer equipment corresponding to the first participation object and sends the object information of the second object to the computer equipment corresponding to the first participation object. In addition, the computer equipment corresponding to the first participation object determines the document parameter information, and obtains the target document conforming to the document parameter information from the candidate document data.

For another example, the usage process of the target document under the scenario information "virtual resource distribution, multiple persons" for the document triggering may be as follows: (1) And the first participation object initiates a virtual resource distribution (such as sending a red packet) request in the communication interaction software group chat through the computer equipment corresponding to the first participation object. (2) And the cloud server associated with the computer equipment corresponding to the first participation object receives the request for sending the red packet in the communication interaction software group chat, and simultaneously, sends the request for sending the red packet in the communication interaction software group chat to the computer equipment corresponding to the second participation object. (3) And the computer equipment corresponding to the second participation object receives the request for sending the red packet in the communication interaction software group chat, and in addition, the object information of the second participation object is sent to a cloud server associated with the computer equipment corresponding to the first participation object. (4) And the cloud server is associated with the computer equipment corresponding to the first participation object and sends the object information of the second object to the computer equipment corresponding to the first participation object. In addition, the computer equipment corresponding to the first participation object determines the document parameter information, and obtains the target document conforming to the document parameter information from the candidate document data.

In the embodiment of the application, the computer equipment realizes the association between the document triggering scene and the target document through the target document keywords. In addition, the computer equipment associates the candidate document data with the document triggering scene, so that the target document which is more applicable to different document triggering scenes than the prior art is obtained. The computer equipment associates the text triggering operation, the text keywords and the operation attribute information corresponding to the text triggering operation with the text triggering scene information, so that the time for generating the target text is reduced, and the efficiency of generating the target text is improved. The computer equipment uses the candidate document data produced by the document template with the placeholder, so that the target document obtained after the placeholder is replaced has more selectivity than the prior art, and further, among a plurality of selectable target documents, the target document with higher relevance to the document triggering scene is selected, and the relevance of the target document and the document triggering scene is further improved. In addition, through the alternative text which can be edited in a self-defined way, the variety of text selection is increased, and the expandable area of the text is enlarged. In summary, the embodiment of the application can improve the matching degree of the target document and the document triggering scene information in the internet page. The target document is generated aiming at specific triggering scene information and object information of a specific object (namely a second participation object), so that the target document can be adapted to specific users, specific application scenes, and individuation and readability of the target document are improved.

Further, referring to fig. 7, fig. 7 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application. The data processing means may be a computer program (comprising program code) running in a computer device, for example the data processing means is an application software; the device can be used for executing corresponding steps in the method provided by the embodiment of the application. As shown in fig. 7, the data processing apparatus 1 may include: a scene recognition module 11, a keyword acquisition module 12, a document acquisition module 13, an information acquisition module 14, and a document generation module 15.

The scene recognition module 11 is configured to recognize the text triggering scene information corresponding to the first participation object;

The keyword obtaining module 12 is configured to obtain, from the document keywords, target document keywords associated with the document triggering scene information based on triggering scene information corresponding to the document keywords;

a document acquisition module 13, configured to acquire candidate document data including a target document keyword;

An information obtaining module 14, configured to obtain object information of a second participating object for which the scenario triggering information is directed;

the document generation module 15 is configured to generate a target document based on the object information of the second participation object and the candidate document data.

The specific functional implementation manners of the scene recognition module 11, the keyword obtaining module 12, the document obtaining module 13, the information obtaining module 14, and the document generating module 15 may refer to step S101 to step S103 in the corresponding embodiment of fig. 3, and are not described herein.

Referring to fig. 7, the scene recognition module 11 includes:

A response unit 111, configured to respond to a document triggering operation of the first participating object, obtain operation attribute information corresponding to the document triggering operation, and obtain an operation scene corresponding to the operation attribute information;

The scene information determining unit 112 is configured to obtain a second participation object for the document triggering operation, and determine document triggering scene information corresponding to the first participation object based on the operation scene and the second participation object.

The specific functional implementation manner of the response unit 111 and the scene information determining unit 112 may refer to step S101 in the corresponding embodiment of fig. 3, which is not described herein.

Referring to fig. 7, the document obtaining module 13 includes:

the template obtaining unit 131 is configured to obtain a first document template corresponding to the document triggering scene information;

The candidate document determining unit 132 is configured to obtain a second document template including the target document keyword from the first document template, and determine the second document template as candidate document data.

The specific functional implementation manner of the template obtaining unit 131 and the candidate document determining unit 132 may refer to step S102 in the corresponding embodiment of fig. 3, which is not described herein.

Referring to fig. 7, the document obtaining module 13 further includes:

A history file obtaining unit 133, configured to obtain history file data, and perform data cleaning processing on the history file data to obtain conventional file data;

a feature extraction unit 134, configured to perform keyword feature extraction processing on conventional document data to obtain document keywords;

An information conversion unit 135, configured to identify composition structure information of the conventional document data, determine to-be-filled information corresponding to the conventional document data and filling position information corresponding to the to-be-filled information based on the composition structure information and the document keywords, and convert the to-be-filled information into filling placeholders;

The placeholder combining unit 136 is configured to perform a combination process on the document keyword and the filling placeholder based on filling position information corresponding to the information to be filled, so as to generate a document template corresponding to the conventional document data; the document template comprises a first document template;

the scene information association unit 137 is configured to detect trigger scene information corresponding to conventional document data, associate a document keyword with the trigger scene information, and associate a document template with the trigger scene information.

The specific functional implementation manners of the history obtaining unit 133, the feature extracting unit 134, the information converting unit 135, the placeholder combining unit 136 and the scene information associating unit 137 may be referred to the step S103 in the corresponding embodiment of fig. 3, and will not be described herein.

Referring again to fig. 7, the document production module 15 includes:

A parameter determining unit 151 for determining document parameter information based on object information of the second participation object; the text parameter information comprises text language and reminding objects;

A target document obtaining unit 152, configured to obtain a target document according with the document parameter information from the candidate document data; the expression mood of the target document is the mood of the document, and the target document aims at the reminding object.

The specific functional implementation manner of the parameter determining unit 151 and the target document obtaining unit 152 may refer to step S102 in the corresponding embodiment of fig. 3, which is not described herein.

Referring to fig. 7, the document generating module 15 further includes:

a template determination unit 153 for determining a target document template from the candidate document data based on the object information of the second participation object;

A position information obtaining unit 154, configured to obtain a target filling placeholder in the target document template and target filling position information corresponding to the target filling placeholder;

a filler content determining unit 155, configured to determine filler content corresponding to the target filler placeholder based on the object information of the second participation object and the document triggering scene information;

The filling content replacing unit 156 is configured to replace the filling content with the target filling placeholder in the target document template based on the target filling position information, and generate the target document.

The specific functional implementation manner of the template determining unit 153, the location information acquiring unit 154, the filling content determining unit 155 and the filling content replacing unit 156 may refer to step S102 in the corresponding embodiment of fig. 3, and will not be described herein.

Wherein the data processing apparatus 1 further comprises:

a response module 16, configured to obtain edited document data submitted by the input editing area in response to a cancel operation for the target document;

the detection module 17 is configured to perform detection processing on the edited document data, determine the edited document data passing the detection as an alternative document, and output the alternative document.

The specific functional implementation manner of the response module 16 and the detection module 17 may refer to step S102 in the corresponding embodiment of fig. 3, which is not described herein.

Further, referring to fig. 8, fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 8, the computer device 1000 may include: at least one processor 1001, such as a CPU, at least one network interface 1004, a user interface 1003, a memory 1005, at least one communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), a Keyboard (Keyboard), and the network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 1005 may also optionally be at least one storage device located remotely from the aforementioned processor 1001. As shown in fig. 8, the memory 1005, which is one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and a device control application.

In the computer device 1000 shown in FIG. 8, the network interface 1004 may provide network communication functions; while user interface 1003 is primarily used as an interface for providing input to a user; and the processor 1001 may be used to invoke a device control application stored in the memory 1005 to implement:

Identifying text triggering scene information corresponding to a first participation object, and acquiring target text keywords associated with the text triggering scene information from the text keywords based on the triggering scene information corresponding to the text keywords; acquiring candidate document data comprising target document keywords, and acquiring object information of a second participation object aimed at by the document triggering scene information; and generating a target document based on the object information of the second participation object and the candidate document data.

It should be understood that the computer device 1000 described in the embodiments of the present application may perform the description of the data processing method in the embodiments corresponding to fig. 2, 3, 4a, 4b, 5, 6a and 6b, and may also perform the description of the data processing apparatus 1 in the embodiments corresponding to fig. 7, which are not repeated herein. In addition, the description of the beneficial effects of the same method is omitted.

The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored, where the computer program includes program instructions, where the program instructions, when executed by a processor, implement a data processing method provided by each step in fig. 2, fig. 3, fig. 4a, fig. 4b, fig. 5, fig. 6a, and fig. 6b, and specifically refer to an implementation manner provided by each step in fig. 2, fig. 3, fig. 4a, fig. 4b, fig. 5, fig. 6a, and fig. 6b, which are not repeated herein. In addition, the description of the beneficial effects of the same method is omitted.

The computer readable storage medium may be the data processing apparatus provided in any one of the foregoing embodiments or an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), etc. that are provided on the computer device. Further, the computer-readable storage medium may also include both internal storage units and external storage devices of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

Embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device can execute the data processing method in the embodiments corresponding to fig. 2, 3, 4a, 4b, 5, 6a and 6b, which are not described herein. In addition, the description of the beneficial effects of the same method is omitted.

The term "comprising" and any variations thereof in the description of embodiments of the application and in the claims and drawings is intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or modules but may, in the alternative, include other steps or modules not listed or inherent to such process, method, apparatus, article, or device.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The method and related apparatus provided in the embodiments of the present application are described with reference to the flowchart and/or schematic structural diagrams of the method provided in the embodiments of the present application, and each flow and/or block of the flowchart and/or schematic structural diagrams of the method may be implemented by computer program instructions, and combinations of flows and/or blocks in the flowchart and/or block diagrams. 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 apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, 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 structural diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or structures.

The foregoing disclosure is illustrative of the present application and is not to be construed as limiting the scope of the application, which is defined by the appended claims.

Claims

1. A method of data processing, comprising:

Acquiring candidate document data comprising the target document keywords, and acquiring object information of a second participation object aimed at by the document triggering scene information;

2. The method of claim 1, wherein identifying the context trigger context information corresponding to the first participant object comprises:

Responding to a document triggering operation of the first participated object, acquiring operation attribute information corresponding to the document triggering operation, and acquiring an operation scene corresponding to the operation attribute information;

and acquiring a second participation object aimed at by the text triggering operation, and determining text triggering scene information corresponding to the first participation object based on the operation scene and the second participation object.

3. The method of claim 1, wherein the obtaining candidate document data including the target document keyword comprises:

acquiring a first document template corresponding to the document triggering scene information;

and acquiring a second document template comprising the target document keyword from the first document template, and determining the second document template as candidate document data.

4. A method according to claim 3, characterized in that the method further comprises:

acquiring historical document data, and performing data cleaning treatment on the historical document data to obtain conventional document data;

extracting key word characteristics of the conventional text data to obtain text key words;

Identifying composition structure information of the conventional text data, determining to-be-filled information corresponding to the conventional text data and filling position information corresponding to the to-be-filled information based on the composition structure information and the text keywords, and converting the to-be-filled information into filling placeholders;

Based on filling position information corresponding to the information to be filled, combining the text keywords with the filling placeholders to generate a text template corresponding to the conventional text data; the document template includes the first document template;

and detecting trigger scene information corresponding to the conventional text data, associating the text keywords with the trigger scene information, and associating the text templates with the trigger scene information.

5. The method of claim 1, wherein the generating a target document based on the object information of the second participant and the candidate document data comprises:

Determining document parameter information based on the object information of the second participating object; the text parameter information comprises text language and gas and reminding objects;

acquiring a target document conforming to the document parameter information from the candidate document data; the expression mood of the target document is the mood of the document, and the target document aims at the reminding object.

6. The method of claim 1, wherein the generating a target document based on the object information of the second participant and the candidate document data comprises:

determining a target document template from the candidate document data based on the object information of the second participating object;

Acquiring a target filling placeholder in the target document template and target filling position information corresponding to the target filling placeholder;

Determining filling content corresponding to the target filling placeholder based on the object information of the second participation object and the text triggering scene information;

And replacing the filling content with the target filling placeholder in the target document template based on the target filling position information to generate a target document.

7. The method according to claim 1, characterized in that the method further comprises:

Responding to cancel operation aiming at the target document, and acquiring edited document data submitted by an input editing area;

And detecting the edited document data, determining the edited document data passing the detection as an alternative document, and outputting the alternative document.

8.A data processing apparatus, comprising:

The document acquisition module is used for acquiring candidate document data comprising the target document keywords;

9. A computer device, comprising: a processor, a memory, and a network interface;

The processor is connected to a memory, a network interface for providing data communication functions, the memory for storing a computer program, the processor for invoking the computer program to cause the computer device to perform the method of any of claims 1-7.

10. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, which computer program is adapted to be loaded and executed by a processor to cause a computer device with a processor to perform the method of any of claims 1-7.

11. A computer program product, characterized in that the computer program product comprises a computer program stored in a computer readable storage medium, the computer program being adapted to be read and executed by a processor to cause a computer device with a processor to carry out the steps of the method according to any one of claims 1-7.