CN112000812A - Game competition situation scene AI comment base generation method, AI comment method and storage medium - Google Patents
Game competition situation scene AI comment base generation method, AI comment method and storage medium Download PDFInfo
- Publication number
- CN112000812A CN112000812A CN202010865054.XA CN202010865054A CN112000812A CN 112000812 A CN112000812 A CN 112000812A CN 202010865054 A CN202010865054 A CN 202010865054A CN 112000812 A CN112000812 A CN 112000812A
- Authority
- CN
- China
- Prior art keywords
- comment
- game
- commentary
- player
- trigger condition
- 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 30
- 238000004590 computer program Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 24
- 230000000007 visual effect Effects 0.000 description 4
- 238000001356 surgical procedure Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
- G06F16/24565—Triggers; Constraints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a game match situation scene AI comment base generation method, an AI comment method and a storage medium. In the generated game event live AI comment base, the comment packet is stored in association with the corresponding trigger condition, and at least part of the trigger condition of the comment packet contains the body movement data of the player. The invention sets the trigger condition of part of the voice comment packet according to the body movement data of the player in the game process, and then stores the set trigger condition in association with the corresponding comment packet, thereby generating the game situation scene AI comment library. After the game event scene AI comment library is generated, AI comment can be carried out on the game event by using the comment library, and corresponding comment can be carried out according to the body movement data of the player, so that the game event scene AI comment is more vivid.
Description
Technical Field
The invention relates to the technical field of AI comment, in particular to a game match situation scene AI comment library generation method, an AI comment method and a storage medium.
Background
With the development of VR virtual reality technology, the entertainment and comprehensive characteristics of VR sports games are continuously mined and applied, and the VR competition explanation is an indispensable key link. It is often difficult for small offline event sponsors to quickly find suitable commentators, and AI commentary is one solution for solving the problem that suitable commentators cannot be found. The AI commentary at present is just commentary logic applicable to game events of the planar device game. The plane device game only relates to the plane game operation of the two-dimensional game role, when the AI comment is performed, the AI comment is performed according to the plane game operation of the game role, and the comment is not vivid enough. .
Disclosure of Invention
The invention aims to solve the technical problem of enabling the AI commentary on the game situation scene to be more vivid.
The invention provides a method for generating a game match scene AI comment base, which comprises the following steps:
a configuration step: configuring a plurality of comment packages and corresponding trigger conditions for a plurality of game match conditions which can occur;
a generation step: storing each comment packet and the corresponding trigger condition thereof in a database in a correlation manner, thereby forming an AI comment base;
the trigger condition of at least part of the commentary package comprises player body movement data.
Further, at least part of the comment packet contains commentary for embodying player body movement, and the trigger condition corresponding to the part of the comment packet contains player body movement data.
Further, the priority is marked for each comment packet.
The game event scene AI commentary library generated using the above method is stored in a computer-readable storage medium.
After the game situation scene AI comment library is generated, the game situation can be subjected to AI comment in the game rebroadcasting process, and the game situation scene AI comment method provided by the invention comprises the following steps:
and acquiring the game match condition in real time, if the game match condition meets the trigger condition, playing an explanation packet corresponding to the trigger condition, extracting the body movement data of the player contained in the game match condition, and comparing whether the game match condition meets the trigger condition or not.
Further, at least part of the commentary package contains commentary which embodies the physical movement of the player.
Further, if the game match conditions meet a plurality of trigger conditions, and the trigger conditions respectively correspond to the comment packages, the comment package with the highest priority is played.
The above-described game situation live AI commentary method is stored in a computer-readable storage medium in the form of a computer program.
The invention sets the trigger condition of part of the voice comment packet according to the body movement data of the player in the game process, and then stores the set trigger condition in association with the corresponding comment packet, thereby generating the game situation scene AI comment library. After the game event scene AI comment library is generated, AI comment can be carried out on the game event by using the comment library, and corresponding comment can be carried out according to the body movement data of the player, so that the game event scene AI comment is more vivid.
Detailed Description
The embodiment needs to relay a shooting VR game match. As shown in table 1, in this embodiment, various game events that may occur during a game process are marked as events, the event types include a warm-up event, a killing event, a blood volume event, a scene event, a body surgery event, a strategy event, a ratio event, and a time event, and then a corresponding voice comment packet and a corresponding trigger condition are configured for each event, specifically, the trigger condition is as shown in table 1, and the voice comment packet is as shown in table 2. In the configuration process of the voice commentary package, the audience attention of each event needs to be evaluated, and corresponding priority is set for the corresponding voice commentary package according to the audience attention of each event, wherein the higher the audience attention is, the higher the priority is, and the smaller the corresponding priority value is. And storing the voice comment packet, the trigger condition and the priority corresponding to each event in a correlated manner to generate a game situation scene AI comment library.
After generating the game event scene AI comment library, we can perform AI comment on the game event scene during the game rebroadcasting process, store the generated AI comment library in the memory of the rebroadcasting client by using the memory of the rebroadcasting client as a computer readable storage medium, store the game event scene AI comment method in the memory in the form of a computer program, and then execute the method by a processor of the rebroadcasting client, where the specific comment flow is illustrated as follows:
before the game rebroadcasting starts, the staff makes the rebroadcasting client start an AI comment mode. After the game is rebroadcast, the rebroadcast client acquires game conditions in real time, and judges whether the currently acquired game conditions meet triggering conditions, for example, the currently acquired game conditions are that "both parties enter a game virtual space", and "if the currently acquired game conditions meet the triggering conditions", a game starts in a game play and a game turn is reset for the first time under the condition of any rebroadcast view angle, and then a corresponding voice comment package "both parties have all entered the game virtual space and are ready to start the game" is played. If the currently acquired game match conditions are as follows: "the blue team 2 player shoots when the height of the head display is reduced more than 1/2" and extracts the body movement data of the player included in the game situation "the blue team 2 player has the height of the head display reduced 1/2" and compares the game situation with the trigger condition, and after the comparison, the trigger condition is met "when the following/player perspective is met, the shooting is performed when the height of the head display of the character locked by the current camera is changed (reduced) more than 1/2 and the current event is triggered", and the corresponding voice comment packet is played "which is a body art type player". If the currently acquired game conditions meet a plurality of trigger conditions, for example, the currently acquired game conditions are that "a blue team 3 player continuously kills two enemy players, and a blue team 3 player is a last player", the game conditions meet the trigger conditions that firstly "in the case of any rebroadcasting visual angle, someone kills and triggers a current event", and secondly "in the case of any rebroadcasting visual angle, someone kills and judges whether the game is the last player of the team, if so, the current event is triggered", the priority values of the voice comment packets corresponding to the two trigger conditions are respectively 3 and 2, and the priority value is higher as the priority value is smaller, so that the playing trigger condition that the voice packet "[ team color ] team [ number ] number player corresponding to the trigger condition has tried to be! ". In order to play the voice comment packet, the team color and the number of the double players are acquired, and then the voice comment packet is played according to the acquired team color and the number of the player. In a special case, the priority values of the voice comment packets corresponding to the plurality of trigger conditions that are met by the currently acquired game situation are the same, and in this case, one of the voice comment packets is played randomly. The playing of the voice commentary package is not interrupted due to the resetting of the game in the playing process, and the playing is not interrupted due to the fact that a new game match condition meets the trigger condition.
In this embodiment, the voice commentary package corresponding to the body surgery type event includes commentary that reflects the body movement of the player, and the trigger condition corresponding to the voice commentary package includes body movement data of the player, and the body movement data of the player is specifically height information of a VR head display worn by the player. In other embodiments, an aggressive type event may be increased or replaced by an aggressive type event. The voice explanation package corresponding to the opponent's event includes the commentary embodying the player's opponent's mouth, such as the player of the [ team color ] team [ gate ] number sends the opposite declaration: let your experience what is a sudden hit, the corresponding trigger condition can be "if the current camera-locked character presses the opponent awakening key of the handle and draws out the action track of shooting with the handle, then trigger the current event" following the visual angle/player visual angle. Furthermore, events of player status class can be added, the corresponding voice commentary package contains commentary which reflects the status of the player, for example, the current status of the [ number bit ] player of the [ team color ] team is excited, and how to perform the subsequent representation is not known, and the corresponding triggering condition can be set as "triggering the current event if the character locked by the current camera swings the handle up and down more than n times under the following view angle/player view angle". In the event of the player state class, the trigger condition is set by the handle motion track (namely the player hand motion track belonging to the player body motion data), but the corresponding voice commentary package does not contain commentary representing the player body motion, but other types of conventional commentary.
TABLE 1
Table 2.
Claims (10)
1. A computer-readable storage medium on which a library of game event scene AI commentary is stored, in which commentary packages are stored in association with corresponding trigger conditions, characterized in that: the trigger condition of at least part of the commentary package comprises player body movement data.
2. The computer-readable storage medium of claim 1, wherein: at least part of the comment packet contains commentary for embodying player body movement, and the trigger condition corresponding to the part of the comment packet contains player body movement data.
3. The computer-readable storage medium of claim 1 or 2, wherein: the comment packet is marked with a priority.
4. The game match situation scene AI comment library generation method comprises the following steps:
a configuration step: configuring a plurality of comment packages and corresponding trigger conditions for a plurality of game match conditions which can occur;
a generation step: storing each comment packet and the corresponding trigger condition thereof in a database in a correlation manner, thereby forming an AI comment base;
the method is characterized in that: the trigger condition of at least part of the commentary package comprises player body movement data.
5. The game situation scene AI commentary library creation method of claim 4, wherein: at least part of the comment packet contains commentary for embodying player body movement, and the trigger condition corresponding to the part of the comment packet contains player body movement data.
6. The game situation live AI commentary library creation method according to claim 4 or 5, wherein: the priority is marked for each explanation packet.
7. The game match situation on-site AI comment method is characterized in that the game match situation is obtained in real time, and if the game match situation meets the trigger condition, a comment packet corresponding to the trigger condition is played, and the method comprises the following steps: and extracting the body movement data of the player contained in the game match condition, and comparing whether the game match condition meets the triggering condition or not.
8. The AI commentary method for game situation scene as claimed in claim 7, wherein: at least part of the commentary package contains commentary which embodies the physical movement of the player.
9. The AI commentary method for game situation scene as claimed in claim 7, wherein: and if the game match conditions meet a plurality of trigger conditions, and the trigger conditions respectively correspond to a plurality of comment packets, playing the comment packet with the highest priority.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements a game situation live AI narration method as claimed in any one of claims 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010865054.XA CN112000812A (en) | 2020-08-25 | 2020-08-25 | Game competition situation scene AI comment base generation method, AI comment method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010865054.XA CN112000812A (en) | 2020-08-25 | 2020-08-25 | Game competition situation scene AI comment base generation method, AI comment method and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112000812A true CN112000812A (en) | 2020-11-27 |
Family
ID=73471209
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010865054.XA Pending CN112000812A (en) | 2020-08-25 | 2020-08-25 | Game competition situation scene AI comment base generation method, AI comment method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112000812A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113209640A (en) * | 2021-07-09 | 2021-08-06 | 腾讯科技（深圳）有限公司 | Comment generation method, device, equipment and computer-readable storage medium |
| WO2022134943A1 (en) * | 2020-12-25 | 2022-06-30 | 腾讯科技（深圳）有限公司 | Explanation video generation method and apparatus, and server and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009125107A (en) * | 2007-11-20 | 2009-06-11 | Nhn Corp | Multiplayer online game system and play-by-play game commentary control method |
| CN109011588A (en) * | 2018-10-16 | 2018-12-18 | 杭州电魂网络科技股份有限公司 | Scene of game exchange method and device |
| CN110971964A (en) * | 2019-12-12 | 2020-04-07 | 腾讯科技（深圳）有限公司 | Intelligent comment generation and playing method, device, equipment and storage medium |
-
2020
- 2020-08-25 CN CN202010865054.XA patent/CN112000812A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009125107A (en) * | 2007-11-20 | 2009-06-11 | Nhn Corp | Multiplayer online game system and play-by-play game commentary control method |
| CN109011588A (en) * | 2018-10-16 | 2018-12-18 | 杭州电魂网络科技股份有限公司 | Scene of game exchange method and device |
| CN110971964A (en) * | 2019-12-12 | 2020-04-07 | 腾讯科技（深圳）有限公司 | Intelligent comment generation and playing method, device, equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022134943A1 (en) * | 2020-12-25 | 2022-06-30 | 腾讯科技（深圳）有限公司 | Explanation video generation method and apparatus, and server and storage medium |
| CN113209640A (en) * | 2021-07-09 | 2021-08-06 | 腾讯科技（深圳）有限公司 | Comment generation method, device, equipment and computer-readable storage medium |
| CN113209640B (en) * | 2021-07-09 | 2021-09-24 | 腾讯科技（深圳）有限公司 | Comment generation method, device, equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10835825B2 (en) | Distributed ledger tracking of event data | |
| CN109499068B (en) | Object control method and device, storage medium and electronic device | |
| CN108491930B (en) | Sample data processing method and data processing device | |
| US20190224568A1 (en) | Prompt method and related apparatus in virtual scene, and computer storage medium | |
| CN112000812A (en) | Game competition situation scene AI comment base generation method, AI comment method and storage medium | |
| CN103838982B (en) | Virtual game object generating method and device | |
| WO2019105240A1 (en) | Method and apparatus for determining resource acquisition probability, storage medium, and electronic device | |
| TW200821021A (en) | Team-based networked video gaming and automatic event management | |
| US11395971B2 (en) | Auto harassment monitoring system | |
| WO2022028135A1 (en) | Method and apparatus for holding online motion-sensing dance competition, computer device, and storage medium | |
| CN111841018A (en) | Model training method, model using method, computer device and storage medium | |
| JP2002239237A (en) | Game system and game reward distributing program | |
| US20160023118A1 (en) | Method and system for live action sports game | |
| CN111773702A (en) | Control method and device for live game | |
| CN107930113A (en) | A kind of Xbox platform multiplayer connection control methods based on client synchronization | |
| CN110267056A (en) | Live broadcasting method, apparatus system and computer storage medium | |
| WO2022062146A1 (en) | Game instance display method and apparatus, and storage medium | |
| CN106362395A (en) | Quick completing method for game duplicate | |
| CN111957044A (en) | Role control method and device of multi-player confrontation game and electronic equipment | |
| KR100841069B1 (en) | System and method of managing an identification tag for team play on the online first person shooting game | |
| CN111298432B (en) | Virtual object information acquisition method and device, server and readable storage medium | |
| JP2019141265A (en) | Game system, game device, and program | |
| CN106254520B (en) | A kind of resource competition method and server | |
| TW201012511A (en) | Boxing game method in a versus mode | |
| JP6081638B1 (en) | GAME CONTROL METHOD AND GAME PROGRAM |
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 |