Planning information generation method and device, storage medium and electronic equipment

Abstract

This disclosure provides a method, apparatus, storage medium, and electronic device for generating planning information, relating to the field of computer technology. The method includes: acquiring basic planning information, including the theme and novelty index of the activity to be planned; determining a prompt information template matching the theme based on the basic planning information, and replacing keywords in the prompt information template according to the basic planning information to generate target prompt information; inputting the target prompt information into a trained language model, setting a temperature parameter of the language model according to the novelty index, and obtaining the target planning information based on the output of the language model. This disclosure improves planning efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a planning information generation method, planning information generation device, computer-readable storage medium, and electronic device. Background Technology

[0002] In related technologies, event planning heavily relies on manual planning. Furthermore, in game planning, game planning is often a crucial part of game design, enabling more innovative storylines and improved playability. Clearly, this method requires significant human and time resources, resulting in inefficient planning processes. Summary of the Invention

[0003] This disclosure provides a method for generating planning information, a device for generating planning information, a computer-readable storage medium, and an electronic device, thereby improving the problem of low planning efficiency to at least a certain extent.

[0004] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0005] According to a first aspect of this disclosure, a method for generating planning information is provided, comprising: acquiring basic planning information, the basic planning information including the theme and novelty index of the activity to be planned; determining a prompt information template matching the theme based on the basic planning information, and replacing keywords in the prompt information template according to the basic planning information to generate target prompt information; inputting the target prompt information into a trained language model, setting a temperature parameter of the language model according to the novelty index, and acquiring the target planning information based on the output of the language model.

[0006] According to a second aspect of this disclosure, a planning information generation apparatus is provided, comprising: a basic planning information acquisition module configured to acquire basic planning information, the basic planning information including a theme and novelty index of an activity to be planned; a target prompt information acquisition module configured to determine a prompt information template matching the theme based on the basic planning information, and to replace keywords in the prompt information template according to the basic planning information to generate target prompt information; and a target prompt information processing module configured to input the target prompt information into a trained language model, and to set a temperature parameter of the language model according to the novelty index, and to acquire target planning information based on the output result of the language model.

[0007] According to a third aspect of this disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the planning information generation method of the first aspect and its possible implementations.

[0008] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor. The processor is configured to execute the planning information generation method of the first aspect and its possible implementations thereof via executing the executable instructions.

[0009] The technical solution disclosed herein has the following beneficial effects:

[0010] On the one hand, this solution automates the generation of target design information. Compared to existing technologies that heavily rely on manual design, it reduces the manpower and time costs associated with the design process, significantly improving design efficiency. On the other hand, this solution uses a novelty index to set the temperature parameters of the language model and then obtains target design information based on the language model's output. This makes the generated target design information more novel and random. Furthermore, the novelty index can be adjusted to control the novelty of the generated target design information, further enhancing its diversity. Moreover, the solution generates target prompts for inputting into the language model based on basic design information. This alleviates the problem of designers needing to spend considerable time and effort developing prompts for the language model, further improving game design efficiency, effectively reducing the workload of designers, and enhancing the user experience.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0013] Figure 1 This illustrates the system operating architecture of this exemplary embodiment;

[0014] Figure 2 This diagram illustrates a flowchart of a planning information generation method in this exemplary embodiment;

[0015] Figure 3 This exemplary embodiment shows a flowchart of obtaining target planning information based on the output of a language model;

[0016] Figure 4 A flowchart illustrating a method for obtaining target setting information in this exemplary embodiment is shown.

[0017] Figure 5 This exemplary embodiment shows a flowchart of a method for obtaining target planning information based on planning materials;

[0018] Figure 6 This diagram illustrates the structure of a planning information generation device according to this exemplary embodiment.

[0019] Figure 7 A schematic diagram of the structure of an electronic device in this exemplary embodiment is shown. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0021] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0022] In related technologies, the planning and gameplay / story design of games still heavily rely on manual planning by game designers, and automation of the game planning process has not yet been achieved. Clearly, this approach requires significant human and time resources. Furthermore, game designers' innovative thinking is easily limited when designing gameplay / story, leading to low efficiency in conception. Moreover, when game designers collaborate with game developers and testers on game planning, differing perspectives can result in poor communication, further reducing the overall efficiency of event planning.

[0023] In view of one or more of the above-mentioned problems, this disclosure first provides a method for generating planning information through exemplary embodiments. The following is in conjunction with... Figure 1 The system architecture of the operating environment for this exemplary embodiment will be described.

[0024] refer to Figure 1 As shown, the system architecture 100 may include a terminal device 110 and a server 120. The terminal device 110 may be an electronic device such as a tablet computer, laptop computer, or desktop computer, and can be used to obtain basic planning information. The server 120 generally refers to a backend system that provides planning information generation services in this exemplary embodiment, such as a server that implements the planning information generation method. The server 120 may be a single server or a cluster of multiple servers; this disclosure does not limit this. The terminal device 110 and the server 120 can be connected via a wired or wireless communication link for data interaction.

[0025] The planning information generation method in this exemplary embodiment can be executed by the terminal device 110. For example, in a game planning scenario, the terminal device 110 can be a computer used by the planner, and the basic planning information can include the theme and novelty index of the activity that the planner is preparing to plan. The terminal device 110 generates target prompt information based on the basic planning information by executing the planning information generation method, and inputs the target prompt information into a language model to obtain target planning information.

[0026] In one implementation, the terminal device 110 can acquire basic planning information and send it to the server 120. After receiving the basic planning information sent by the terminal device 110, the server 120 determines a prompt information template that matches the theme of the activity to be planned based on the basic planning information, and replaces the keywords in the prompt information template according to the basic planning information to generate target prompt information. Finally, the target prompt information is input into a language model, and the temperature parameter of the language model is set according to the novelty index in the basic planning information. The target planning information is obtained based on the output result of the language model.

[0027] As can be seen from the above, the planning information generation method in this exemplary embodiment can be executed by the terminal device 110 or the server 120.

[0028] The following is combined Figure 2 The method for generating planning information is explained. Figure 2 An exemplary flow of a planning information generation method is shown, including the following steps S210 to S230:

[0029] Step S210: Obtain basic planning information, which includes the theme and novelty index of the activity to be planned;

[0030] Step S220: Based on the basic planning information, determine the prompt information template that matches the theme, and replace the keywords in the prompt information template according to the basic planning information to generate the target prompt information;

[0031] Step S230: Input the target prompt information into the trained language model, set the temperature parameter of the language model according to the novelty index, and obtain the target planning information based on the output of the language model.

[0032] Based on the above method, on the one hand, it achieves automated generation of target design information. Compared with the existing technology that heavily relies on manual design, this reduces the manpower and time costs of the design process and greatly improves design efficiency. On the other hand, this solution sets the temperature parameters of the language model through a novelty index, and then obtains target design information based on the output of the language model. This makes the generated target design information more novel and random. Furthermore, the novelty of the generated target design information can be controlled by adjusting the novelty index, further enhancing the diversity of the target design information. Moreover, target prompts for inputting into the language model can be generated from basic design information. This alleviates the problem of designers needing to spend a lot of energy thinking about the prompts for inputting into the language model, further improving game design efficiency, effectively reducing the workload of designers, and improving the user experience.

[0033] The following is about Figure 2 Each step in the process will be explained in detail.

[0034] refer to Figure 2 In step S210, basic planning information is obtained, which includes the theme and novelty index of the activity to be planned.

[0035] The basic planning information consists of metadata about the activity to be planned. For example, the activity to be planned could be a game with the theme of "space exploration". The basic planning information could include the keyword "space exploration", a novelty index of "0.9", and the total number of candidate setting information to be generated, such as "15". The activity to be planned could include the game or gameplay in the game to be planned by the planner. The novelty index can be used to characterize the relevance of the setting information of the activity to be planned to the theme. The higher the novelty index, the lower the relevance of the setting information of the activity to be planned to the theme. The lower the novelty index, the higher the relevance of the setting information of the activity to be planned to the theme. The setting information of the activity to be planned could include the storyline, gameplay, game context, etc. of the activity to be planned. Candidate setting information refers to the setting information generated in subsequent steps that is related to the theme of the activity to be planned and meets the requirements of the novelty index.

[0036] In one implementation, obtaining basic planning information may include: determining basic planning information based on input data from planners.

[0037] For example, a game designer is planning a game themed around "space exploration." In this game, players take on the role of an astronaut, exploring different planets to acquire resources and complete missions. The designer only needs to provide concise input data such as the number of gameplay modes to be generated, the novelty index of the gameplay modes, and basic gameplay themes and virtual item characteristic keywords, such as "15," "0.9," "space," and "spaceship." Then, "15," "0.9," "space," and "spaceship" can be identified as the basic planning information. Here, "space" and "spaceship" are the themes of the activities to be planned, "0.9" is the novelty index of the activities to be planned, and "15" is the total number of candidate settings.

[0038] By obtaining basic planning information for the activity to be planned through input data from planners, the target planning information intended by the planners can be generated.

[0039] In addition, in one implementation, basic planning information can be generated based on a language model.

[0040] The language model can include a deep learning model capable of handling natural language tasks.

[0041] By automatically generating basic planning information through language models, planners can be provided with references, thereby further reducing the labor and time costs of the planning process and improving planning efficiency.

[0042] After obtaining basic planning information, continue to refer to Figure 2In step S220, a prompt information template matching the theme is determined based on the basic planning information, and the keywords in the prompt information template are replaced according to the basic planning information to generate the target prompt information.

[0043] The prompt template includes keywords and content related to the theme of the event to be planned. Keywords in the prompt template can be used to identify content to be replaced. For example, the keywords can include theme keywords. A prompt template could be something like, "A theme is an endless, mysterious world; planets are the targets of exploration; rockets are the tools of exploration; astronauts are the protagonists of exploration; generate N candidate setting information with a novelty index of K." This prompt template would include the theme keyword "theme," the novelty index keyword "K," and the total number of candidate setting information keywords "N." The target prompt information is a detailed prompt corresponding to the basic planning information. For example, if the basic planning information includes "space," the corresponding target prompt information could include "space is an endless, mysterious world." In other words, the basic planning information can be a brief prompt about the event to be planned, while the target prompt information can be a detailed description or extended description of the basic planning information.

[0044] In one implementation, the above-mentioned determination of a prompt message template matching the theme based on basic planning information may include the following steps:

[0045] In the prompt message template database, the prompt message template with the highest matching degree between basic planning information retrieval and theme is selected.

[0046] The prompt message template database can be a database that stores various types of prompt message templates. For example, basic planning information can be obtained based on the input data of the planners. The basic planning information includes the theme of the event to be planned, the novelty index, etc. The basic planning information can be classified first to identify the information about the theme and the novelty index. Then, based on the information about the theme in the basic planning information, a search can be performed in the prompt message template database to obtain the prompt message template with the highest similarity / matching degree to the theme of the event to be planned.

[0047] By searching the prompt message template database for the prompt message template with the highest matching degree to the theme, the generated target prompt message can be made most relevant to the theme of the event to be planned, thus making the generated target planning information more accurate.

[0048] In one implementation, the above-mentioned prompt message template includes at least topic keywords and novelty index keywords; replacing the keywords in the prompt message template according to the basic planning information may include the following steps:

[0049] In the prompt message template, replace the theme keywords with the theme of the event to be planned, and replace the novelty index keywords with the novelty index of the event to be planned.

[0050] For example, if the basic planning information includes the theme "space" of the event to be planned, then by replacing the theme keywords in the prompt information template, the target prompt information can be "Space is an endless and mysterious universe, without a horizon, without direction, without up, down, left, or right. It is a completely dark world, with only distant stars dotting the sky like scattered stars." If the basic planning information includes the theme "spaceship" of the event to be planned, then the corresponding target prompt information could be "Its streamlined shape is both beautiful and practical, shining with the light of the future."

[0051] By replacing keywords in the prompt information template with basic planning information, the target prompt information can be obtained. This reduces the complexity of obtaining the target prompt information, accelerates the process of obtaining the target prompt information, and further improves planning efficiency.

[0052] After generating the target prompt information, continue to refer to... Figure 2 In step S230, the target prompt information is input into the trained language model, and the temperature parameter of the language model is set according to the novelty index. The target planning information is obtained based on the output of the language model.

[0053] The temperature parameter is used to adjust the randomness and creativity of the language model's output. A higher novelty index results in a higher temperature parameter, leading to greater randomness in the language model's output and a lower similarity between the output and the theme of the planned activity. When the temperature parameter is sufficiently high, the language model's output may contain content unrelated to the theme. Therefore, when setting the temperature parameter of the language model based on the novelty index, it is necessary to adjust it to an appropriate value. This disclosure does not specifically limit the method of setting the temperature parameter of the language model based on the novelty index. For example, a lower limit and an upper limit of the novelty index can be determined in advance. When the novelty index is less than the lower limit, the lower limit is set as the temperature parameter value; when the novelty index is greater than the lower limit but less than the upper limit, the novelty index is set as the temperature parameter value; when the novelty index is greater than the upper limit, the upper limit is used as the temperature parameter value. By adjusting the novelty index, the diversity and novelty of the language model's output can be enhanced, further improving the richness of the generated target planning information.

[0054] In one implementation, the above-mentioned language model-based output results are used to obtain target planning information, which is then referenced. Figure 3 As shown, steps S310 to S330 may be included:

[0055] Step S310: Based on the output of the language model, determine the target setting information for the activity to be planned;

[0056] Among these, the target setting information is the most attractive setting information identified from the candidate setting information. In one implementation, the target setting information for the activity to be planned is determined based on the output results of the language model, with reference to... Figure 4 As shown, steps S410 to S420 may be included:

[0057] Step S410: If the target prompt information includes a total of N candidate setting information, obtain N candidate setting information for the activity to be planned based on the output of the language model, where N is a positive integer; otherwise, obtain a preset number of candidate setting information based on the output of the language model.

[0058] Step S420: In response to the selection operation for N candidate setting information, determine the target setting information from the N candidate setting information; or determine the target setting information from a preset number of candidate setting information.

[0059] The preset quantity is the default value of the total number of candidate setting information. This disclosure does not make any special limitation on the specific value of the preset quantity. For example, the preset quantity can be 1. That is to say, if the target prompt information does not include the total number of candidate setting information, a candidate setting information is generated by default and the candidate setting information is determined as the target setting information.

[0060] For example, the basic design information obtained from the input data of the game designers includes a novelty index of 0.9 and a total of 10 candidate settings. After obtaining the target hint information based on the basic design information, the temperature parameters of the language model are set according to the novelty index, and the target hint information is input into the language model to obtain 10 candidate settings that meet the novelty index. The game designers can then compare these 10 candidate settings and select one as the target setting. For example, among the 10 candidate settings for the event to be planned, the content of candidate setting 1 is: "An astronaut discovers a rare mineral on an unfamiliar planet and then uses a rocket to transport the mineral back to Earth..." If the game designers believe that candidate setting 1 is the most attractive and resonates most with players, then they will select candidate setting 1 as the target setting.

[0061] based on Figure 4The method can determine the target setting information from the candidate setting information, so that the obtained target setting information has a high degree of storytelling and content richness, ensuring the richness and novelty of the generated target planning information.

[0062] In step S320, the target setting information is input into the language model to obtain planning materials, wherein the planning materials include at least the test cases and virtual prop description information corresponding to the target setting information.

[0063] The planning materials should include at least the gameplay story, gameplay script, test cases, and virtual item descriptions corresponding to the goal setting information of the activity to be planned.

[0064] For example, when generating gameplay scripts and test cases, a deep learning model can be used to categorize the target setting information, extract gameplay script requirement prompts and test case requirement prompts from the target setting information, and then generate gameplay script requirement prompts corresponding to the gameplay script requirement prompts and test case requirement prompts corresponding to the test case requirement prompts by replacing the content of the gameplay script prompt templates and test case requirement prompts. Finally, the gameplay script requirement prompts and test case requirement prompts are input into a language model to obtain more accurate gameplay scripts and test cases.

[0065] Continue to refer to Figure 3 After obtaining the planning materials, in step S330, the target planning information can be obtained based on the planning materials.

[0066] In one implementation, the above-mentioned acquisition of target planning information based on planning materials, with reference to... Figure 5 As shown, steps S510 to S530 may be included:

[0067] Step S510: If the planning materials include virtual item description information, determine the virtual item based on the virtual item description information.

[0068] The virtual props include virtual items in the planned event and the resources for generating virtual items. This disclosure does not impose any special limitations on virtual items and the resources for generating virtual items. For example, virtual items may include characters with distinct personalities and the weapons used by the characters, and the resources for generating virtual items may include icons, animations, special effects and models of virtual items.

[0069] For example, you can input the description information of virtual props into a tool that has text-to-image or text-to-effects functions to automatically generate virtual props.

[0070] In step S520, historical usage data of virtual props is obtained, and attribute data of virtual props are determined based on target setting information.

[0071] Historical usage data can be used to characterize the usage of similar virtual products in existing game activities. Attribute data can be the characteristics of virtual items in the target setting information. This disclosure does not specifically limit the content of attribute data; for example, attribute data may include the rarity and usage frequency of virtual items in the target setting information.

[0072] Step S530: Based on the historical usage data and attribute data of virtual props, generate virtual prop evaluation information and add the virtual prop evaluation information to the target planning information.

[0073] The virtual item evaluation information may include the pricing information of the virtual item in the event to be planned.

[0074] For example, virtual item evaluation information can be input into a virtual item valuation model. This model can combine the virtual item's attribute information, its importance in the target setting information, and its historical usage data to evaluate the price of the virtual item and generate pricing information for the virtual item, providing a reference for game designers.

[0075] based on Figure 5 The method obtained virtual item evaluation information and added it to the target planning information, making the generated target planning information more referential.

[0076] In one implementation, after obtaining the target planning information based on the output of the language model, the above method may further include the following steps:

[0077] Insert the target planning information into the corresponding preset planning report template to generate a planning report for the activity to be planned.

[0078] For example, the target planning information may include the target setting information of the activity to be planned, gameplay scripts, test cases, virtual items, and virtual item valuation information. The preset planning report template may include title keywords. Taking the insertion of virtual item valuation information into the preset planning report template as an example, the target planning information can be inserted into the corresponding position of the preset planning report template. For example, if the preset planning report template may include the title keyword "virtual item valuation report", then the insertion position of the virtual item valuation information can be determined by the position of "virtual item valuation report" in the preset planning report template, and the virtual item valuation information in the target planning information can be imported into that insertion position to generate the planning report of the activity to be planned.

[0079] By inserting target planning information into a preset planning report template to generate a planning report, the complexity of the planning report generation process can be reduced, and the efficiency of planning report generation can be further improved.

[0080] In addition, in one implementation, the target planning information can be processed through a planning report generation model to generate a planning report for the activity to be planned.

[0081] The planning report generation model is a deep model that uses Natural Language Generation (NLG) technology.

[0082] By inputting target planning information into the planning report generation model to obtain the planning report, the efficiency of planning report generation can be further improved, thereby enhancing the user experience.

[0083] In one implementation, after generating a planning report for the activity to be planned, the method may further include automatically sending the planning report to the planners.

[0084] After generating the planning report for the event to be planned, the report is immediately sent to the planners. This allows them to view the highly informative report in a timely manner without having to perform data processing and integration, thereby improving planning efficiency and the work efficiency of the planners, and ultimately enhancing the user experience.

[0085] Based on the above methods, the goal planning information is generated automatically, which effectively improves planning efficiency.

[0086] Exemplary embodiments of this disclosure also provide a planning information generation apparatus. For example... Figure 6 As shown, the planning information generation device 600 may include:

[0087] The basic planning information acquisition module 610 is configured to acquire basic planning information, which includes the theme and novelty index of the activity to be planned.

[0088] The target prompt information acquisition module 620 is configured to determine a prompt information template that matches the theme based on the basic planning information, and replace the keywords in the prompt information template according to the basic planning information to generate target prompt information;

[0089] The target prompt information processing module 630 is configured to input target prompt information into the trained language model, set the temperature parameters of the language model according to the novelty index, and obtain target planning information based on the output of the language model.

[0090] In one implementation, obtaining target planning information based on the output of the language model may include:

[0091] Based on the output of the language model, determine the target setting information for the activity to be planned.

[0092] Input the target setting information into the language model to obtain planning materials, wherein the planning materials include at least the test cases and virtual prop description information corresponding to the target setting information;

[0093] Obtain target planning information based on planning materials.

[0094] In one implementation, obtaining target planning information based on planning materials may include:

[0095] When the planning materials include descriptions of virtual items, the virtual items are determined based on those descriptions.

[0096] Obtain historical usage data of virtual items and determine the attribute data of virtual items based on target setting information;

[0097] Based on the historical usage and attribute data of virtual items, virtual item evaluation information is generated and added to the target planning information.

[0098] In one implementation, the above-mentioned output results based on the language model, used to determine the goal setting information of the activity to be planned, may include:

[0099] If the target prompt information includes a total of N candidate setting information, N candidate setting information for the activity to be planned is obtained based on the output of the language model, where N is a positive integer; otherwise, a preset number of candidate setting information is obtained based on the output of the language model.

[0100] In response to a selection operation for N candidate settings, the target settings are determined from the N candidate settings; or the target settings are determined from a preset number of candidate settings.

[0101] In one implementation, the aforementioned prompt message template includes at least topic keywords and novelty index keywords; the replacement of keywords in the prompt message template based on basic planning information may include:

[0102] In the prompt message template, replace the theme keywords with the theme of the event to be planned, and replace the novelty index keywords with the novelty index of the event to be planned.

[0103] In one implementation, the aforementioned prompt message template, which determines the theme matching based on basic planning information, may include:

[0104] In the prompt message template database, the prompt message template with the highest matching degree between basic planning information retrieval and theme is selected.

[0105] In one embodiment, after obtaining the target planning information from the output results based on the language model, the apparatus may further include:

[0106] Insert the target planning information into the corresponding preset planning report template to generate a planning report for the activity to be planned.

[0107] The specific details of each part of the above-mentioned device have been described in detail in the method section of the implementation, and therefore will not be repeated here.

[0108] Exemplary embodiments of this disclosure also provide a computer-readable storage medium that can be implemented as a program product including program code, which, when run on an electronic device, causes the electronic device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. In an alternative embodiment, the program product can be implemented as a portable compact disc read-only memory (CD-ROM) including program code and can run on an electronic device, such as a personal computer. However, the program product of this disclosure is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0109] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0110] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0111] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0112] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0113] Exemplary embodiments of this disclosure also provide an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions for the processor, such as program code. The processor executes the executable instructions to perform the methods of this exemplary embodiment.

[0114] The following is for reference. Figure 7 The electronic device is illustrated by way of a general-purpose computing device. It should be understood that... Figure 7 The electronic device 700 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0115] like Figure 7 As shown, the electronic device 700 may include: a processor 710, a memory 720, a bus 730, an I / O (input / output) interface 740, and a network adapter 750.

[0116] The processor 710 may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a display processing unit (DPU), a graphics processing unit (GPU), an image signal processor (ISP), a controller, an encoder, a decoder, a digital signal processor (DSP), a baseband processor, an artificial intelligence processor, etc. In one embodiment, the artificial intelligence processor can acquire basic planning information; then, based on the basic planning information, it can determine a prompt information template that matches the theme of the activity to be planned, and replace keywords in the prompt information template according to the basic planning information to generate target prompt information; finally, the target prompt information is input into a language model, and the temperature parameters of the language model are set according to the novelty index; the target planning information is obtained based on the output of the language model.

[0117] The memory 720 may include volatile memory, such as RAM 721 and cache unit 722, and may also include non-volatile memory, such as ROM 723. The memory 720 may also include one or more program modules 724, including but not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. For example, program module 724 may include the modules in the aforementioned device 600.

[0118] Bus 730 is used to connect different components of electronic device 700 and may include a data bus, an address bus and a control bus.

[0119] Electronic device 700 can communicate with one or more external devices 800 (such as keyboard, mouse, external controller, etc.) through I / O interface 740.

[0120] Electronic device 700 can communicate with one or more networks via network adapter 750. For example, network adapter 750 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, and near-field communication. Network adapter 750 can communicate with other modules of electronic device 700 via bus 730.

[0121] although Figure 7Other hardware and / or software modules, including but not limited to: displays, microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, may also be configured in electronic device 700.

[0122] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0123] Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be embodied in entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.” Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0124] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is defined only by the appended claims.

Claims

1. A method of generating a plan information, characterized by, include: Obtain basic planning information, which includes the theme and novelty index of the activity to be planned; Based on the basic planning information, a prompt message template matching the theme is determined, and the keywords in the prompt message template are replaced according to the basic planning information to generate the target prompt message; The target prompt information is input into the trained language model, and the temperature parameter of the language model is set according to the novelty index. The target planning information is obtained based on the output of the language model. The step of obtaining target planning information based on the output of the language model includes: Based on the output of the language model, the target setting information of the activity to be planned is determined; The target setting information is input into the language model to obtain planning materials, wherein the planning materials include at least the test cases and virtual prop description information corresponding to the target setting information; When the planning materials include the virtual item description information, the virtual item is determined based on the virtual item description information; Obtain the historical usage data of the virtual item, and determine the attribute data of the virtual item based on the target setting information; Based on the historical usage data and attribute data of the virtual items, virtual item evaluation information is generated and added to the target planning information.

2. The method of claim 1, wherein, The goal setting information for the activity to be planned is determined based on the output of the language model, including: If the target prompt information includes a total of N candidate setting information, N candidate setting information for the activity to be planned is obtained based on the output of the language model, where N is a positive integer; otherwise, a preset number of candidate setting information is obtained based on the output of the language model. In response to a selection operation for the N candidate setting information, the target setting information is determined from the N candidate setting information; or the target setting information is determined from the preset number of candidate setting information.

3. The method of claim 1, wherein, The prompt message template includes at least thematic keywords and novelty index keywords; the replacement of keywords in the prompt message template based on the basic planning information includes: In the prompt message template, the theme keywords are replaced with the theme of the event to be planned, and the novelty index keywords are replaced with the novelty index of the event to be planned.

4. The method of claim 1, wherein, The step of determining a prompt message template that matches the theme based on the basic planning information includes: In the prompt message template database, the prompt message template with the highest matching degree with the theme is retrieved based on the basic planning information.

5. The method of claim 1, wherein, After obtaining the target planning information based on the output of the language model, the method further includes: Insert the target planning information into the corresponding preset planning report template to generate a planning report for the activity to be planned.

6. An information planning generating apparatus characterized by comprising: include: The basic planning information acquisition module is configured to acquire basic planning information, which includes the theme and novelty index of the activity to be planned. The target prompt information acquisition module is configured to determine a prompt information template that matches the theme based on the basic planning information, and replace the keywords in the prompt information template according to the basic planning information to generate target prompt information; The target prompt information processing module is configured to input the target prompt information into the trained language model, set the temperature parameter of the language model according to the novelty index, and obtain target planning information based on the output of the language model; The step of obtaining target planning information based on the output of the language model includes: Based on the output of the language model, the target setting information of the activity to be planned is determined; The target setting information is input into the language model to obtain planning materials, wherein the planning materials include at least the test cases and virtual prop description information corresponding to the target setting information; When the planning materials include the virtual item description information, the virtual item is determined based on the virtual item description information; Obtain the historical usage data of the virtual item, and determine the attribute data of the virtual item based on the target setting information; Based on the historical usage data and attribute data of the virtual items, virtual item evaluation information is generated and added to the target planning information.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 5.

8. An electronic device, comprising: include: processor; Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 5 by executing the executable instructions.

Images