CN111753508A - Method and device for generating content of written works and electronic equipment - Google Patents
Method and device for generating content of written works and electronic equipment Download PDFInfo
- Publication number
- CN111753508A CN111753508A CN202010615834.9A CN202010615834A CN111753508A CN 111753508 A CN111753508 A CN 111753508A CN 202010615834 A CN202010615834 A CN 202010615834A CN 111753508 A CN111753508 A CN 111753508A
- Authority
- CN
- China
- Prior art keywords
- content
- target
- authoring
- creative
- auxiliary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 230000004044 response Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 210000000988 bone and bone Anatomy 0.000 description 23
- 230000008569 process Effects 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 102100033814 Alanine aminotransferase 2 Human genes 0.000 description 3
- 101710096000 Alanine aminotransferase 2 Proteins 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013515 script Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000035943 smell Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000008492 tangshen Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a device for generating content of written works and electronic equipment, wherein the method comprises the following steps: acquiring the creation content and the creation target of the target written works; in response to the content auxiliary generation instruction, obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch. In the mode, the creative content and the creative target are used as the creative basis of the target literary work, the target auxiliary creative content associated with the creative target can be obtained, the target auxiliary creative content can assist the user in performing subsequent literary creation, the requirement of the creative literary work on participants is reduced, and the quality and the creative efficiency of the literary work are improved.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a method and a device for generating content of written works and electronic equipment.
Background
In scenes such as games, literary composition and the like, multi-party cooperation is often needed to complete the literary composition; for example, in a game, a plurality of game players write stories together to promote the development of a game scenario together; for another example, a script is written by multiple editions together, and multiple people in the story cooperation community cooperate to complete literary creation and the like. In the related art, the way of completing the literary work by multiple parties in cooperation is generally that one of the participants writes the outline of the beginning, the end and the plot of the work, then all the participants perform content creation in stages, and finally the complete literary work is obtained by combination.
However, the mode of completing the literary works by the cooperation of multiple parties has higher requirements on literary creation mastery, writing styles and the like of participants, and common people are difficult to participate; the problems of inconsistent and inconsistent works and the like easily occur due to multi-party cooperation; interruption of work creation can also result when participants lack inspiration; in a word, the mode of completing the literary works by the cooperation of multiple parties has higher requirements on participants, and the quality and the creation efficiency of the works are difficult to ensure.
Disclosure of Invention
In view of this, the present invention provides a method, an apparatus and an electronic device for generating content of a written work, so as to reduce requirements on participants in a manner of completing the written work in a multi-party collaboration manner, and improve quality and creation efficiency of the written work.
In a first aspect, an embodiment of the present invention provides a method for generating content of a written work, where the method includes: acquiring the creation content and the creation target of the target written works; in response to the content auxiliary generation instruction, obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch.
Further, the authoring goals include: a content summary and/or a content ending of the target written work.
Further, the authoring goals include: the target of creation input by the user, and/or the target of creation preset for the target written work.
Further, the step of obtaining the creative content of the target literary work comprises: acquiring the creative content aiming at the target literary work sent by at least two users; wherein authoring content includes: continuous content of the target written work, and/or discrete content associated with the authoring target.
Further, the step of obtaining the creative content of the target literary work sent by at least two users includes: the method comprises the steps of obtaining first creative content which is sent by a first user and aims at a target literary work, displaying the first creative content on clients of a plurality of designated users including the first user, and enabling the designated users to send subsequent creative content based on the first creative content.
Further, the content auxiliary generation instruction is triggered by the following method: responding to the content auxiliary generation operation input by the user, and triggering a content auxiliary generation instruction; or judging whether a preset condition is met, and if so, triggering a content auxiliary generation instruction; the preset conditions include: authored content that has not been received by user input for a specified period of time.
Further, the step of deriving at least one auxiliary authoring content based on the authoring content and the authoring target includes: inputting the authoring content and the authoring target into a content auxiliary generation model trained in advance, and outputting at least one auxiliary authoring content; wherein at least one type of auxiliary authoring content is associated with an authoring target.
Further, authoring content includes: all contents currently contained in the target written work; the content-assisted generative model is used to: generating at least one intermediate content between the initial content and the ending content by taking the authored content as the initial content and the authored target as the ending content; and taking the intermediate content as auxiliary authoring content.
Further, the content-assisted generation model is trained by the following method: determining sample content based on a preset sample set; wherein the sample content carries a sample target; inputting the sample content into a preset initial model to obtain an output result; if the output result is matched with the sample target, training an initial model based on a preset reward mechanism; if the output result is not matched with the sample target, training an initial model based on a preset punishment mechanism; and determining the trained initial model as a content generation model.
Further, the auxiliary authoring content includes a plurality of types; the step of determining target auxiliary authored content from at least one auxiliary authored content as a subsequent authoring branch of the written work includes: responding to a selection instruction aiming at one auxiliary creative content in the multiple auxiliary creative contents, determining the auxiliary creative content corresponding to the selection instruction as target auxiliary creative content, and taking the target auxiliary creative content as a subsequent creative branch of the literal works.
Further, after the step of determining the target auxiliary authored content from the at least one auxiliary authored content as a subsequent authoring branch of the written work, the method further comprises: judging whether the target written works meet the creation target or not; and if the target writing target is not met, updating the target auxiliary writing content into the writing content of the writing work, and continuing to execute the step of obtaining the writing content and the writing target of the target writing work until the target writing work meets the writing target.
Further, the step of judging whether the target literary work meets the creation target includes: inputting the target written works and the creation targets into a discrimination model to obtain the probability of matching the target written works with the creation targets; determining whether the target literary work meets the authoring target based on the probability.
Further, the step of judging whether the target literary work meets the creation target includes: in response to a confirmation instruction that the target written work satisfies the authoring target, determining that the written work satisfies the authoring target.
Further, the target written work comprises a plurality of creation targets arranged according to a preset sequence; the method further comprises the following steps: and executing the steps of acquiring the creative content and the creative target of the target literary works one by one for each creative target based on a preset sequence until the literary works meeting the creative target are obtained.
In a second aspect, an embodiment of the present invention provides a content generating apparatus for a written work, where the apparatus includes: the acquisition module is used for acquiring the creative content and the creative target of the target written works; the content acquisition module is used for responding to the content auxiliary generation instruction and obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and the determining module is used for determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work so as to enable the user to continue to create on the basis of the subsequent creative branch.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a processor and a memory, where the memory stores machine executable instructions that can be executed by the processor, and the processor executes the machine executable instructions to implement the content generation method for a written work according to any one of the first aspect.
In a fourth aspect, embodiments of the present invention provide a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the method for content generation of a written work of any of the first aspects.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides a method and a device for generating content of written works and electronic equipment, wherein the method comprises the following steps: acquiring the creation content and the creation target of the target written works; in response to the content auxiliary generation instruction, obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch. In the mode, the creative content and the creative target are used as the creative basis of the target literary work, the target auxiliary creative content associated with the creative target can be obtained, the target auxiliary creative content can assist the user in performing subsequent literary creation, the requirement of the creative literary work on participants is reduced, and the quality and the creative efficiency of the literary work are improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for generating content of a written work according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for generating content of a written work according to an embodiment of the present invention;
fig. 3 is a flowchart of a content generation method for a specific written work according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a content generating apparatus for literary works according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, in scenes such as games, writing and the like, multi-party cooperation or man-machine cooperation is often needed to complete the creation of written works, for example, in some games, players are needed to write stories together with the games to push a plot or a plurality of people to create stories together; for another example, a movie script is composed of multiple editorial co-drafts, literary composition by multi-user collaboration in a story collaboration community, and so on. With the development of artificial intelligence technology, language generation technology is also continuously improving, and gradually starts to assist human beings in literary creation. In the related art, the way of completing the literature works by multiple parties in cooperation is generally that one of the participants writes the outline of the beginning, the end and the plot of the works, then all the participants perform content creation in stages, and finally the complete literature works are obtained by combination. However, this method has the following problems:
1. each participant has higher requirements, people without writing capability or with low writing capability cannot participate, even the writing style of each participant is different, and the writing styles of all participants also have the requirements;
2. when each participant is independently created, the content created by other participants needs to be considered, and the problems of front-back contradiction, incoherence, mutation and the like are avoided, so that the multi-party collaborative creation difficulty is higher;
3. when a participant has only one general idea and no specific content inspiration, the whole writing process is stopped;
4. since authoring requires a lot of time, the communication cost of multi-party collaboration is high.
In addition, content creation is currently performed by using AI (Artificial Intelligence) techniques, such as GPT-2, CTRL, and other AI techniques, but most of the creation in this manner currently has no outline and no target, and is mainly performed by a single machine (for example, a single-player game). Based on this, the method, the device and the electronic device for generating content of written works provided by the embodiment of the invention can be applied to various game applications and also can be applied to various websites, and particularly can be applied to game applications or websites for writing.
In order to facilitate understanding of the embodiment, a detailed description is first given to a content creation method for text creation disclosed in the embodiment of the present invention, where the method may be applied to a server running a content creation model, and an execution subject is the server; as shown in fig. 1, the method comprises the steps of:
step S102, acquiring the creation content and the creation target of the target written works;
the target written works can be works expressed in the form of characters in the fields of literature, art, science and the like, such as various types of written works including novels with story lines, various types of scripts, poems, prose, lecture manuscripts, news, stories with game scenarios and the like; the created content can be related story line content in the target written works, such as the beginning of a story, subsequent content in the development process of the story and the like; the idea related to the target written work can be a complete word or a simple expression form such as a short sentence or paragraph. Typically, the target written work will include a plurality of storylines, and thus, the authoring target may include a plurality of stage targets, each of which may be a target for a respective stage of the story outline in the target written work.
Specifically, a certain user or a plurality of users (at least two users) can input the creative content and the creative target of the target written work to one or a plurality of clients, and each client is respectively connected with a server running a content generation model of the written work; therefore, the user of each client can input the creative content and the creative target of the target literary work or input the creative content of the target literary work to the model in the server; the server directly obtains the creative content and the creative target of the target literary work or obtains the creative target through the target literary work by receiving the creative content and the creative target of the target literary work or the creative content of the target literary work.
Preferably, the authoring target includes: a content summary and/or a content ending of the target written work.
The content summary generally includes a plurality of stage contents, each stage content having a set stage target; for example, for a target written work with a story line, the content outline can be understood as a story outline, the story outline can include a plurality of stages of story lines, and the story line of each stage is set with a corresponding stage target; the content ending may be an ending of the target written work, for example, for a target written work with a story line, the content ending may be understood as a story ending. The target of creation may include the content summary and the content ending of the target written work, or may include only the content summary of the target written work, or only the content ending of the target written work.
Preferably, the authoring target includes: the target of creation input by the user, and/or the target of creation preset for the target written work.
The target written works can be preset with the creation targets of the works, so that the creation targets can be directly obtained through the preset creation targets of the target written works; if the target written work has no creative target of the work preset, the creative target can be obtained by user input; of course, if the user has his own unique idea for the target written work, or wants to create a multi-level, rich-content work, the above-mentioned creation targets may include: an authoring target input by the user, and an authoring target preset for the target written work.
Step S104, responding to the content auxiliary generation instruction, and obtaining at least one auxiliary authoring content according to the authoring content and the authoring target;
the content auxiliary generation instruction may correspond to an instruction control, and the user may trigger the content auxiliary generation instruction by clicking the instruction control, or may not be a specific instruction control, and the user may trigger the content auxiliary generation instruction by a specified trigger operation, for example, triggering the content auxiliary generation instruction by long-time pressing, double-click and other touch operations, voice control operations, air gesture operations, and other manners; or automatically triggering a content auxiliary generation instruction after receiving the creative content of the target literary work input by the user. A plurality of auxiliary authoring contents are typically obtained according to the authoring content and the authoring target, each auxiliary authoring content including text associated with the authoring content, each auxiliary authoring content being associated with or unrelated to the authoring target.
Specifically, in the process of creating the work, if AI assistance is needed, at least one auxiliary creation content can be obtained in an artificial intelligence manner, such as a text generation model GPT-3 (generic Pre-Training-3), GPT-2, CTRL (directional writing model), and the like, according to the creation content and the story line or the text of the story ending defined by the creation target, so that the story line develops toward the creation target.
The content auxiliary generation instruction is triggered by the following method:
responding to the content auxiliary generation operation input by the user, and triggering a content auxiliary generation instruction;
the user inputs an operation for generating the auxiliary authoring content, which may be an input information, an execution command, or the like, by responding to which the content auxiliary generation instruction is triggered.
Or judging whether a preset condition is met, and if so, triggering a content auxiliary generation instruction; the preset conditions include: authored content that has not been received by user input for a specified period of time.
The specified time can be set according to actual needs, for example, can be set to 1 minute, or 2 minutes, and the like, and is not limited herein; specifically, the user does not input the creative content in a continuous designated time period, and at this time, the user may consider that the input of the current new creative content is completed, and may perform the next operation, that is, trigger the content auxiliary generation instruction to generate the internal auxiliary creative content.
And step S106, determining target auxiliary creative content from at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch.
Since the generated plurality of auxiliary authoring contents may include auxiliary creative contents different from the original creative purpose of the user or auxiliary authoring contents far from the creative target, it is necessary to determine a target auxiliary authoring content (preferably, the target auxiliary authoring content can be selected and determined by the user or automatically selected and determined by the system) from the generated plurality of auxiliary authoring contents, the target auxiliary authoring content is usually one of auxiliary authoring contents most related to the current authoring content and the creative target, the target auxiliary authoring content can be used as a subsequent authoring branch of the written work based on the input authoring content, and the subsequent authoring branch can assist the user to continue completing the work authoring on the basis of the subsequent authoring branch, so that the personalized authoring requirement of the user can be met and the quality of the work can be improved.
The embodiment of the invention provides a method for generating content of a literary work, which is used for acquiring the creation content and the creation target of a target literary work; in response to the content auxiliary generation instruction, obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch. In the mode, the creative content and the creative target are used as the creative basis of the target literary work, the target auxiliary creative content associated with the creative target can be obtained, the target auxiliary creative content can assist the user in performing subsequent literary creation, the requirement of the creative literary work on participants is reduced, and the quality and the creative efficiency of the literary work are improved.
The embodiment also provides another method for generating the content of the literary works, which mainly describes a specific implementation manner of a step of obtaining the creative content of the target literary works, a specific implementation manner of a step of obtaining at least one auxiliary creative content according to the creative content and a creative target, a specific implementation manner of a step of determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the literary works, and method steps included after the step; as shown in fig. 2, the method comprises the steps of:
step S202, acquiring the creative content and the creative target of the target literary work sent by at least two users; wherein authoring content includes: continuous content of the target written work, and/or discrete content associated with the authoring target;
the continuous content of the target literary works can be relatively complete content input by the user, is mostly input by the user with higher writing capability and is expressed in a complete literary description form; the continuous content can be the idea of the user, and can also be the beginning content and the outline of the target written works; the discrete content related to the authoring target can be various ideas related to the authoring target generated by the user according to the authoring target of the target written works, and the ideas are expressed in the form of short sentences or paragraphs, and are mostly input by the user with low writing capability. The authoring content comprises: continuous content of the target written work and discrete content associated with the authoring target; the creative content also comprises continuous content of the target literary works or discrete content associated with the creative target, the degree of freedom is higher, the literary ability requirement on participants can be reduced, and the user experience is improved.
In a preferred embodiment, the step of obtaining at least two user-sent authored contents for a target written work includes: the method comprises the steps of obtaining first creative content which is sent by a first user and aims at a target literary work, displaying the first creative content on clients of a plurality of designated users including the first user, and enabling the designated users to send subsequent creative content based on the first creative content.
The first authored content may be the title, beginning, outline of the target written work, for example, the target written work is a story, and the first authored content may be the title, beginning, and outline of the story, including a plurality of story lines. The first creative content aiming at the target literary work sent to the server by the first user can be displayed through the clients of a plurality of appointed users connected with the server, so that the appointed users can see the first creative content through the corresponding clients; at this time, the designated user may transmit subsequent authoring content to the server based on the first authoring content, the subsequent authoring content being either a completed content associated with the storyline or an idea associated with the first authoring content.
For example, a plurality of users want to cooperate together, a new story is added to the journey to the West, and the story is entitled "three capture three indulge black bone essence", namely the target written work; a first user can write a small segment of content as the beginning of the work, for example, the first user's Tangseng comes to the mountain and heaves a monster in the mountain, which is called black bone sperm', then the outline of the story is set to be put after the black bone sperm is held three times, and finally, the black bone sperm is 30344The Buddha. Then the corresponding phase targets may be: the first time of grasping and placing the black bone essence; the second time of grasping and placing the black bone extract; the black bone essence is grabbed and placed for the third time, and the black bone essence is 30344, Ivermen. Sending the first authored content to a server so that other appointed users can send subsequent authored content based on the first authored content; at this time, any idea of a plurality of designated users for the subsequent content of the target writing "three capture three longitudinal black osseous essence" can be sent to the server through corresponding clients (in the form of a webpage end, a PC end, a mobile end and the like), for example, a certain user has a sense of inspiration, thinks that four people in monk, lead and appreciative province should meet the public land first, but the subsequent content does not know how to write, then he can send "four people in monk, lead and appreciative province meet the public land" to the server, and all users can see the subsequent creative content through the client for use at this time.
Step S204, responding to a content auxiliary generation instruction, inputting the authoring content and the authoring target into a content auxiliary generation model which is trained in advance, and outputting at least one auxiliary authoring content; wherein at least one auxiliary authoring content is associated with an authoring target;
the content auxiliary generation model can be various existing network models, such as GPT-3, GPT-2, CTRL and the like; the model may output at least one auxiliary authoring content, each different but associating the at least one auxiliary authoring content with an authoring target, based on the input first authoring content and subsequent authoring content of the first authoring content.
The authoring content comprises: all contents currently contained in the target written work; all the currently contained contents include the first creative content and the currently acquired subsequent creative content for the target literary work.
The content-assisted generation model is used for: generating at least one intermediate content between the initial content and the ending content by taking the authored content as the initial content and the authored target as the ending content; and taking the intermediate content as auxiliary authoring content.
For example, the creation content is that "four people in a line arrive at a black mountain by the monk tangshen, a goblin is called as a black bone sperm in the listening," the creation target is "the black bone sperm is caught and put for the first time"; based on the starting content and ending content, the content-assisted generation model can output a plurality of different intermediate contents and develop the scenario towards an authoring target of "catching and putting black bone essence for the first time".
The content-assisted generation model is obtained by training in the following way:
step A1, determining sample content based on a preset sample set; wherein the sample content carries a sample target;
the preset sample set can be various types of corpora or various types of literary works; the sample content can be a large amount of corpus works, can also be part or all paragraph characters in the written works, and is not necessarily a complete story; the sample target can be an authoring target of the corpus work and can also be a target corresponding to part or all of paragraph characters in the written work; each sample content may include a plurality of sample objects.
Step A2, inputting sample content into a preset initial model to obtain an output result;
the preset initial model is a model which is not subjected to parameter training; the output result may be the authored content related to the sample content and the sample object, or the authored content unrelated to the sample content and the sample object.
Step A3, if the output result is matched with the sample target, training an initial model based on a preset reward mechanism; if the output result is not matched with the sample target, training an initial model based on a preset punishment mechanism; and determining the trained initial model as a content generation model.
The process of training the model trains the content generation model by a reward and punishment mechanism, so that the model learns to generate the content associated with the target; the method mainly learns the ability of how to write sample content continuously, guides the content generation model to generate content associated with an authoring target, and can improve the quality of the output result of the model.
Step S206, responding to a selection instruction aiming at one auxiliary creative content in the multiple auxiliary creative contents, determining the auxiliary creative content corresponding to the selection instruction as target auxiliary creative content, and taking the target auxiliary creative content as a subsequent creative branch of the literal works;
specifically, the user can select one auxiliary authoring content from multiple auxiliary authoring contents together, the auxiliary authoring content can be selected through the corresponding client, the server can trigger a selection instruction of the auxiliary authoring content according to the selection of each user, the auxiliary authoring content corresponding to the selection instruction is determined as target auxiliary authoring content, and the target auxiliary authoring content is used as a subsequent authoring branch of the written work. In the mode, a plurality of auxiliary creative contents are output by the model, and a user selects an optimal auxiliary creative content as a subsequent creative content (for example, the optimal auxiliary creative content can be selected in a voting mode or one of the users, and the like), so that the personalized creative requirements of the user can be met, and the quality of the work can be improved.
Step S208, judging whether the target written works meet the creation target;
specifically, the judgment can be performed through a user or through a network model, and whether the target written works meet the creation target or not can be judged according to the target auxiliary creation content and the current creation target of the current target written works.
With respect to step S208 above, one possible implementation:
inputting the target written works and the creation targets into a discrimination model to obtain the probability of matching the target written works with the creation targets; determining whether the target literary work meets the authoring target based on the probability.
Judging whether the target written work meets the current creation target or not, wherein the method can be that the target auxiliary creation content of the current target written work and the target in the current stage are input to a high-level judgment model through a judgment model, and the target auxiliary creation content of the current target written work is output as the probability that the target auxiliary creation content of the current target written work is matched with the target in the current stage; the above-mentioned discriminant model can be various network models with classification function, and is equivalent to a classifier, and is used for judging whether the probability meets a preset probability threshold value, and the preset probability threshold value can be set according to actual needs.
In another possible implementation, in response to a confirmation instruction that the target written work satisfies the authoring target, it is determined that the written work satisfies the authoring target.
Judging whether the target written work meets the current creation target or not, and judging whether the target auxiliary creation content of the current target written work meets the current stage target or not by the user; specifically, each user can send a confirmation instruction of the target auxiliary creative content to the server through the corresponding client, and the server responds to the confirmation instruction that the target literary work meets the current creative target and determines that the target auxiliary creative content of the literary work meets the current creative target.
Step S210, if the target writing target is not satisfied, updating the target auxiliary writing content into the writing content of the writing, and continuing to execute the step of obtaining the writing content and the writing target of the target writing until the target writing satisfies the writing target;
through the judgment, if the generated target auxiliary creative content does not meet the current creative target, the target auxiliary creative content can be updated to the creative content of the literary work, namely, the target auxiliary creative content is added into the current creative content, and the step S202 and the subsequent steps are continuously executed based on the updated creative content until the target auxiliary creative content of the current target literary work meets the current creative target.
Step S212, judging whether the target written works are completely created; if not, go to step S214; if so, obtaining the written works meeting the creation target, and ending the creation;
after the target auxiliary creative content of the current target written work meets the creative target, it is first required to determine whether the target written work has been completed or not, and specifically, it is possible to determine whether all the creative targets of the target written work generate corresponding creative content and auxiliary content.
Step S214, updating the authoring content and the authoring target based on the preset sequence; step S202 is performed for each authoring target pair by pair.
The target written works comprise a plurality of creation targets which are arranged according to a preset sequence; if the target written work is not created, the current creation target can be updated to the next creation target with the created target being completed according to the preset sequence; specifically, when generating the target of the target written work, only one creation target is input at a time according to a preset sequence; in addition, after the current authoring target is completed, when the next authoring target is performed, all the authoring contents and target auxiliary authoring contents generated before need to be input into the content generation model, and the step of acquiring the authoring contents and the authoring target of the target literary work is executed; for example, after the creation target of "catching and putting black bone essence for the first time" is completed, the current creation target is updated to "catching and putting black bone essence for the second time", and the previous creation content and the target auxiliary creation content are input into the content generation model, and the above step S202 is repeated until the literary work meeting the creation target is obtained, and finally the target sitter work is created completely. In the method, when the plot of the product is more, a plurality of creation targets can be divided in advance, and each creation target is reached one by one, so that a high-quality work with rich content and more plots can be obtained.
In the method, the beginning and the stage outline or the target of the target written work are input by the user as the initial input of the content generation model, and then the interaction between the users is realized through the server and the client connected with the server, so that the users are assisted to collaboratively perform literature creation; when the method is used, users can think and benefit freely according to the creative content in the works like daily creation, but when the creation is difficult due to various reasons (such as no inspiration thought, only trivial character thought, only no writing ability of the thought, the creative content can not be connected with the existing content, and the like), continuous creative content or inspiration discrete content can be input into the content generation model, the content generation model is utilized to assist the users in character creation, a plurality of auxiliary contents can be generated, whether the generated auxiliary content meets the creative target or not is determined through the users or the judgment model until the character works meeting the creative target are obtained.
Because the generation speed of the content generation model is very high and the generation quality is also guaranteed, the time required by thinking and creation of human users can be greatly reduced, and the efficiency of collaboration is greatly improved. The difficulty of literary work creation can be reduced, common people can participate in the literary work creation, and when a participant lacks inspiration, related content can be generated by the content generation model only by providing a creation target, so that the quality and the efficiency of the literary work creation are improved. In addition, the threshold of multi-person cooperation for literary creation is greatly reduced, and common persons without cooperation ability can also perform cooperation creation; meanwhile, the communication cost among collaborators is reduced, and the creation efficiency is improved.
Referring to fig. 3, a specific method for generating content of a written work, first, the beginning and stage targets of a story correspond to the created content and created targets; the language generation model corresponds to the content generation model; the subsequent content corresponds to the auxiliary authoring content.
Specifically, firstly, one user writes the beginning and the outline of the story, sets stage targets for each stage of the outline of the story, and inputs the beginning and the current stage targets of the story into a language generation model; any user can write out the idea in the form of complete text description or short sentence or paragraph when having any idea on the subsequent content of the story; the contents created by the users can be all input into the language generation model; judging whether AI assistance is needed by users to generate subsequent contents; if not, at least one user creates the subsequent content of the work, and then judges whether the target subsequent content achieves the target of the current stage through a judgment model or the user; if necessary, generating a plurality of subsequent contents according to the input story beginning and stage targets through a language generation model, and promoting the plot to develop towards the targets; the users select a most suitable subsequent content as a target subsequent content according to the target at the current stage, the beginning of the story and the generated plurality of subsequent contents; judging whether the target subsequent content achieves the target of the current stage or not through a judgment model or a user; if yes, judging whether the story is completely authored; if not, inputting the subsequent content of the target and the target of the next stage into the language generation model, and continuing to execute the following steps; in addition, whether the story is completely authored is judged, and the authoring is finished if the story is completely authored.
Take a specific story creation as an example: suppose that several people want to cooperate together to add a new story segment for the journey to the West, for example, to be defined as "three capture three indulge black bone essence". Then they first need to write a small segment of content as the beginning of the story, for example, "the monk tang went to the black mountain in four people, and listen and hear a monster inside, which is called black bone sperm", then set the outline of the story to be three times, and all three times, and finally, black bone sperm 30344yi Buddha. Then the corresponding phase targets may be: the first time of grasping and placing the black bone essence; the second time of grasping and placing the black bone extract; the black bone essence is grabbed and placed for the third time, and the black bone essence is 30344, Ivermen.
The user inputs the language generation model of ' three capture three vertical black osseous sperms ' and ' four people in one line with the monk tang ' to the black mountain, listens and smells a monster in the model called black osseous sperms ' and the current stage target ' catching and putting the black osseous sperms for the first time ', and then people start to collaborate to create. No matter who creates what content, the content can be input into the model, and when the user needs the model to be busy, the model generates new story content according to the previously input content. For example, the user has a sense of inspiration, thinks that four people in monk and monk should meet the public land first, but then does not know how to write, so he can input the model that four people in monk and monk meet the public land, and requires the model to output the subsequent content, the model can output a plurality of different subsequent contents and develop the plot into the plot that the black bone essence is caught and put for the first time, the user can select any content that the user is satisfied with, and then the process is repeated until the goal that the black bone essence is caught and put for the first time is achieved.
And then updating the target of the current stage to be 'catching and putting the black bone essence for the second time' and repeating the process until the whole story is completely authored.
The specific method for generating the content of the written works provided by the embodiment has the same technical characteristics as the method of the embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
Corresponding to the above method embodiment, referring to fig. 4, a schematic structural diagram of a content generating device for a written work, the device includes:
an obtaining module 41, configured to obtain the creative content and the creative target of the target written work;
a content acquisition module 42, configured to obtain at least one auxiliary authoring content according to the authoring content and the authoring target in response to the content auxiliary generation instruction;
and a determining module 43, for determining the target auxiliary authored content from the at least one auxiliary authored content as a subsequent authoring branch of the written work, so that the user continues to author on the basis of the subsequent authoring branch.
The embodiment of the invention provides a content generation device of a literary work, which comprises: acquiring the creation content and the creation target of the target written works; in response to the content auxiliary generation instruction, obtaining at least one auxiliary authoring content according to the authoring content and the authoring target; and determining the target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to create on the basis of the subsequent creative branch. In the mode, the creative content and the creative target are used as the creative basis of the target literary work, the target auxiliary creative content associated with the creative target can be obtained, the target auxiliary creative content can assist the user in performing subsequent literary creation, the requirement of the creative literary work on participants is reduced, and the quality and the creative efficiency of the literary work are improved.
The above authoring targets include: a content summary and/or a content ending of the target written work.
The above authoring targets include: the target of creation input by the user, and/or the target of creation preset for the target written work.
The obtaining module is further configured to: acquiring the creative content aiming at the target literary work sent by at least two users; wherein authoring content includes: continuous content of the target written work, and/or discrete content associated with the authoring target.
The obtaining module is further configured to: the method comprises the steps of obtaining first creative content which is sent by a first user and aims at a target literary work, displaying the first creative content on clients of a plurality of designated users including the first user, and enabling the designated users to send subsequent creative content based on the first creative content.
The content auxiliary generation instruction is triggered by the following method: responding to the content auxiliary generation operation input by the user, and triggering a content auxiliary generation instruction; or judging whether a preset condition is met, and if so, triggering a content auxiliary generation instruction; the preset conditions include: authored content that has not been received by user input for a specified period of time.
The content acquisition module is further configured to: inputting the authoring content and the authoring target into a content auxiliary generation model trained in advance, and outputting at least one auxiliary authoring content; wherein at least one type of auxiliary authoring content is associated with an authoring target.
The authoring content comprises: all contents currently contained in the target written work; the content-assisted generation model is used for: generating at least one intermediate content between the initial content and the ending content by taking the authored content as the initial content and the authored target as the ending content; and taking the intermediate content as auxiliary authoring content.
The content-assisted generation model is obtained by training in the following way: determining sample content based on a preset sample set; wherein the sample content carries a sample target; inputting the sample content into a preset initial model to obtain an output result; if the output result is matched with the sample target, training an initial model based on a preset reward mechanism; if the output result is not matched with the sample target, training an initial model based on a preset punishment mechanism; and determining the trained initial model as a content generation model.
The auxiliary creation content comprises a plurality of types; the determining module is further configured to: responding to a selection instruction aiming at one auxiliary creative content in the multiple auxiliary creative contents, determining the auxiliary creative content corresponding to the selection instruction as target auxiliary creative content, and taking the target auxiliary creative content as a subsequent creative branch of the literal works.
The above apparatus is also for: judging whether the target written works meet the creation target or not; and if the target writing target is not met, updating the target auxiliary writing content into the writing content of the writing work, and continuing to execute the step of obtaining the writing content and the writing target of the target writing work until the target writing work meets the writing target.
The above apparatus is also for: inputting the target written works and the creation targets into a discrimination model to obtain the probability of matching the target written works with the creation targets; determining whether the target literary work meets the authoring target based on the probability.
The above apparatus is also for: in response to a confirmation instruction that the target written work satisfies the authoring target, determining that the written work satisfies the authoring target.
The target written works comprise a plurality of creation targets which are arranged according to a preset sequence; the above apparatus is also for: and executing the steps of acquiring the creative content and the creative target of the target literary works one by one for each creative target based on a preset sequence until the literary works meeting the creative target are obtained.
The content generating device of the written works provided by the embodiment of the invention has the same technical characteristics as the content generating method of the written works provided by the embodiment, so the same technical problems can be solved, and the same technical effects can be achieved.
The embodiment also provides an electronic device, which comprises a processor and a memory, wherein the memory stores machine executable instructions capable of being executed by the processor, and the processor executes the machine executable instructions to realize the content generation method of the literary work.
Referring to fig. 5, the electronic device includes a processor 100 and a memory 101, the memory 101 stores machine executable instructions capable of being executed by the processor 100, and the processor 100 executes the machine executable instructions to implement the content generation method of the written work.
Further, the electronic device shown in fig. 5 further includes a bus 102 and a communication interface 103, and the processor 100, the communication interface 103, and the memory 101 are connected through the bus 102.
The Memory 101 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 103 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used. The bus 102 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
The present embodiments also provide a machine-readable storage medium storing machine-executable instructions that, when invoked and executed by a processor, cause the processor to implement the above-described method for content generation of a written work.
The method and the device for generating content of written works and the computer program product of the electronic device provided by the embodiment of the invention comprise a computer readable storage medium storing program codes, wherein instructions included in the program codes can be used for executing the method described in the previous method embodiment, and specific implementation can refer to the method embodiment, which is not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood in specific cases for those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that the following embodiments are merely illustrative of the present invention, and not restrictive, and the scope of the present invention is not limited thereto: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (17)
1. A method for generating content of a written work, the method comprising:
acquiring the creation content and the creation target of the target written works;
responding to a content auxiliary generation instruction, and obtaining at least one auxiliary authoring content according to the authoring content and the authoring target;
and determining target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the written work, so that the user continues to compose on the basis of the subsequent creative branch.
2. The method of claim 1, wherein the authoring target comprises: the content summary and/or the content ending of the target written work.
3. The method of claim 1, wherein the authoring target comprises: the target of creation input by the user, and/or the target of creation preset by the target work of writing.
4. The method of claim 1, wherein the step of obtaining the authored content of the target written work comprises:
acquiring the creative content aiming at the target literary work sent by at least two users; wherein the authoring content comprises: continuous content of the target written work, and/or discrete content associated with the authoring target.
5. The method of claim 4, wherein the step of obtaining authored content for the target written work sent by at least two users comprises:
the method comprises the steps of obtaining first creative content aiming at the target literary composition sent by a first user, and displaying the first creative content on clients of a plurality of designated users including the first user, so that the designated users send subsequent creative content based on the first creative content.
6. The method of claim 1, wherein the content-assisted generation of the instruction is triggered by:
responding to a content auxiliary generation operation input by a user, and triggering the content auxiliary generation instruction;
or judging whether a preset condition is met, and if so, triggering the content auxiliary generation instruction; the preset conditions include: authored content that has not been received by user input for a specified period of time.
7. The method of claim 1, wherein the step of deriving at least one auxiliary authoring content based on the authoring content and the authoring target comprises:
inputting the authoring content and the authoring target into a content auxiliary generation model trained in advance, and outputting at least one auxiliary authoring content; wherein the at least one auxiliary authoring content is associated with the authoring target.
8. The method of claim 7, wherein authoring content comprises: all the contents currently contained in the target written work;
the content-assisted generative model is to: generating at least one intermediate content between the initial content and the ending content by taking the authored content as the initial content and the authored target as the ending content; and taking the intermediate content as auxiliary authoring content.
9. The method of claim 7, wherein the content-assisted generation model is trained by:
determining sample content based on a preset sample set; wherein the sample content carries a sample target;
inputting the sample content into a preset initial model to obtain an output result;
if the output result is matched with the sample target, training the initial model based on a preset reward mechanism; if the output result is not matched with the sample target, training the initial model based on a preset punishment mechanism; and determining the trained initial model as a content generation model.
10. The method of claim 1, wherein the auxiliary authoring content comprises a plurality of types; the step of determining a target auxiliary authored content from the at least one auxiliary authored content as a subsequent authoring branch of the written work comprises:
responding to a selection instruction aiming at one auxiliary creative content in the multiple auxiliary creative contents, determining the auxiliary creative content corresponding to the selection instruction as target auxiliary creative content, and taking the target auxiliary creative content as a subsequent creative branch of the literal work.
11. The method of claim 1, wherein after the step of determining the targeted auxiliary authoring content from the at least one auxiliary authoring content as a subsequent authoring branch of the written work, the method further comprises:
judging whether the target written works meet the creation target or not;
and if the target writing target is not met, updating the target auxiliary authoring content into the authoring content of the writing work, and continuing to execute the step of obtaining the authoring content and the authoring target of the target writing work until the target writing work meets the authoring target.
12. The method of claim 11, wherein determining whether the target written work satisfies the authoring target comprises:
inputting the target written works and the creation targets into a discrimination model to obtain the probability that the target written works are matched with the creation targets;
determining whether the target written work meets the authoring target based on the probability.
13. The method of claim 11, wherein determining whether the target written work satisfies the authoring target comprises:
in response to a confirmation instruction that the target written work satisfies the authoring target, determining that the written work satisfies the authoring target.
14. The method of claim 11, wherein the target written work includes a plurality of creative targets arranged in a predetermined order; the method further comprises the following steps:
and executing the step of acquiring the creative content and the creative target of the target literary works for each creative target one by one based on the preset sequence until the literary works meeting the creative target are obtained.
15. An apparatus for generating content of a written work, the apparatus comprising:
the acquisition module is used for acquiring the creative content and the creative target of the target written works;
the content acquisition module is used for responding to a content auxiliary generation instruction and obtaining at least one auxiliary authoring content according to the authoring content and the authoring target;
and the determining module is used for determining target auxiliary creative content from the at least one auxiliary creative content as a subsequent creative branch of the literal work so as to enable the user to continue to compose on the basis of the subsequent creative branch.
16. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor, the processor executing the machine executable instructions to implement the method of content generation of a written work of any of claims 1-14.
17. A machine-readable storage medium having stored thereon machine-executable instructions which, when invoked and executed by a processor, cause the processor to implement the method of content generation for a written work of any of claims 1-14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010615834.9A CN111753508A (en) | 2020-06-29 | 2020-06-29 | Method and device for generating content of written works and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010615834.9A CN111753508A (en) | 2020-06-29 | 2020-06-29 | Method and device for generating content of written works and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111753508A true CN111753508A (en) | 2020-10-09 |
Family
ID=72676838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010615834.9A Pending CN111753508A (en) | 2020-06-29 | 2020-06-29 | Method and device for generating content of written works and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111753508A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112667774A (en) * | 2020-12-23 | 2021-04-16 | 上海掌门科技有限公司 | Method and equipment for providing creative help information in work creation process |
| CN112685534A (en) * | 2020-12-23 | 2021-04-20 | 上海掌门科技有限公司 | Method and apparatus for generating context information of authored content during authoring process |
| CN112966479A (en) * | 2021-03-02 | 2021-06-15 | 北京彩彻区明科技有限公司 | Language model-based auxiliary writing method, device and system |
| CN113033182A (en) * | 2021-03-25 | 2021-06-25 | 网易（杭州）网络有限公司 | Text creation auxiliary method and device and server |
| CN114139524A (en) * | 2021-11-29 | 2022-03-04 | 浙江大学 | Method and device for predicting story text and electronic equipment |
| CN115630640A (en) * | 2022-12-23 | 2023-01-20 | 苏州浪潮智能科技有限公司 | Intelligent writing method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271491A (en) * | 2008-04-25 | 2008-09-24 | 上海虹栋软件科技有限公司 | Implementing method and system for user to create contents in network game |
| CN105955964A (en) * | 2016-06-13 | 2016-09-21 | 北京百度网讯科技有限公司 | Method and apparatus for automatically generating poem |
| CN109492982A (en) * | 2018-09-18 | 2019-03-19 | 平安科技（深圳）有限公司 | Collaborative authoring method, apparatus and electronic equipment based on block chain |
| CN110134968A (en) * | 2019-05-22 | 2019-08-16 | 网易（杭州）网络有限公司 | Poem generation method, device, equipment and storage medium based on deep learning |
| CN110782900A (en) * | 2018-07-12 | 2020-02-11 | 迪斯尼企业公司 | Collaborative AI storytelling |
-
2020
- 2020-06-29 CN CN202010615834.9A patent/CN111753508A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101271491A (en) * | 2008-04-25 | 2008-09-24 | 上海虹栋软件科技有限公司 | Implementing method and system for user to create contents in network game |
| CN105955964A (en) * | 2016-06-13 | 2016-09-21 | 北京百度网讯科技有限公司 | Method and apparatus for automatically generating poem |
| CN110782900A (en) * | 2018-07-12 | 2020-02-11 | 迪斯尼企业公司 | Collaborative AI storytelling |
| CN109492982A (en) * | 2018-09-18 | 2019-03-19 | 平安科技（深圳）有限公司 | Collaborative authoring method, apparatus and electronic equipment based on block chain |
| CN110134968A (en) * | 2019-05-22 | 2019-08-16 | 网易（杭州）网络有限公司 | Poem generation method, device, equipment and storage medium based on deep learning |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112667774A (en) * | 2020-12-23 | 2021-04-16 | 上海掌门科技有限公司 | Method and equipment for providing creative help information in work creation process |
| CN112685534A (en) * | 2020-12-23 | 2021-04-20 | 上海掌门科技有限公司 | Method and apparatus for generating context information of authored content during authoring process |
| CN112667774B (en) * | 2020-12-23 | 2023-12-15 | 上海掌门科技有限公司 | Method and equipment for providing creation help information in work creation process |
| CN112966479A (en) * | 2021-03-02 | 2021-06-15 | 北京彩彻区明科技有限公司 | Language model-based auxiliary writing method, device and system |
| CN113033182A (en) * | 2021-03-25 | 2021-06-25 | 网易（杭州）网络有限公司 | Text creation auxiliary method and device and server |
| CN113033182B (en) * | 2021-03-25 | 2024-03-01 | 网易（杭州）网络有限公司 | Text creation assisting method, device and server |
| CN114139524A (en) * | 2021-11-29 | 2022-03-04 | 浙江大学 | Method and device for predicting story text and electronic equipment |
| CN115630640A (en) * | 2022-12-23 | 2023-01-20 | 苏州浪潮智能科技有限公司 | Intelligent writing method, device, equipment and medium |
| CN115630640B (en) * | 2022-12-23 | 2023-03-10 | 苏州浪潮智能科技有限公司 | Intelligent writing method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111753508A (en) | Method and device for generating content of written works and electronic equipment | |
| US20240168933A1 (en) | Ai story platform with customizable personality for education, entertainment, and therapy | |
| Sagolla | 140 characters: A style guide for the short form | |
| US11267121B2 (en) | Conversation output system, conversation output method, and non-transitory recording medium | |
| CN109154948B (en) | Method and apparatus for providing content | |
| CN113748425A (en) | Auto-completion for content expressed in video data | |
| CN112015852A (en) | Providing responses in a session about an event | |
| CN114125492A (en) | Live content generation method and device | |
| CN115445211A (en) | Processing method for calling back round game old player through telephone and related product | |
| CN111553138A (en) | Auxiliary writing method and device for standardizing content structure document | |
| CN113617036A (en) | Game dialogue processing method, device, equipment and storage medium | |
| CN111767386A (en) | Conversation processing method and device, electronic equipment and computer readable storage medium | |
| CN116860924A (en) | Processing method for generating simulated personality AI based on preset prompt word data | |
| CN115963963A (en) | Interactive novel generation method, presentation method, device, equipment and medium | |
| CN110516043B (en) | Answer generation method and device for question-answering system | |
| US12002470B1 (en) | Multi-source based knowledge data for artificial intelligence characters | |
| US11960983B1 (en) | Pre-fetching results from large language models | |
| CN115052194B (en) | Learning report generation method, device, electronic equipment and storage medium | |
| CN116226411B (en) | Interactive information processing method and device for interactive project based on animation | |
| Makini | PictureBlocks: constructing and deconstructing picture-driven literacy development | |
| CN118304657A (en) | Game dialogue generation method and device, electronic equipment and storage medium | |
| WO2024131414A1 (en) | Method and apparatus for displaying interactive information, electronic device, and storage medium | |
| TWI643080B (en) | A method to parse network data and simulate specific objects accordingly | |
| Tran et al. | PLATICA: Personalized Language Acquisition Training & Instruction Chatbot Assistant | |
| CN116434750A (en) | User portrait construction and man-machine interaction methods, devices, equipment and media |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |