CN-122006240-A - Game guiding method and device, computer program product and electronic equipment
Abstract
The disclosure relates to the technical field of games, and provides a game guiding method and device, a computer program product and electronic equipment. The method comprises the steps of obtaining a current characteristic value of a game situation characteristic of a current game at a current moment, inputting the current characteristic value into a pre-trained guiding opportunity prediction model, predicting the probability that a first change value of a fight resource of a fight participant of the current game after a first preset time length passes through based on the guiding opportunity prediction model is larger than a preset threshold value, and determining game guiding opportunity according to the probability so as to conduct game guiding on the fight participant of the current game at the game guiding opportunity. The game guiding accuracy and timeliness can be improved through the scheme.
Inventors
- CAI KANG
Assignees
- 网易(杭州)网络有限公司
Dates
- Publication Date
- 20260512
- Application Date
- 20260319
Claims (10)
- 1. A game guiding method, comprising: Acquiring a current characteristic value of a game situation characteristic of a current game at a current moment; Inputting the current characteristic value into a pre-trained guiding time prediction model, and predicting the probability that a first change value of a fight resource of a fight participant of the current game fight is larger than a preset threshold value after a first preset time length is passed based on the guiding time prediction model; And determining game guiding time according to the probability, so as to guide the game to the fight participants of the current game play at the game guiding time.
- 2. The method of claim 1, wherein the manner of determining the pre-trained guide opportunity prediction model comprises: acquiring historical characteristic values of game situation characteristics of a historical game at each sampling moment so as to obtain sample characteristic data; for each sample characteristic data, determining a second change value of a fight resource of a fight participant of the historical game after a first preset time length passes through a sampling time from the historical game, and generating a sample label corresponding to the sample characteristic data according to whether the second change value is larger than a preset threshold value; Inputting the sample characteristic data into an initial machine learning model, and obtaining a predicted value of a change value of a fight resource of a fight participant of the history game after a first preset time length passes at a sampling time indicated by the sample characteristic data according to the output of the machine learning model; Determining a training loss based on the degree of difference between the variance prediction value and the sample label; And performing iterative training on the machine learning model according to the training loss to obtain the pre-trained guide opportunity prediction model.
- 3. The method of claim 1 or 2, wherein the game play characteristics include game play data for a play participant of a game play, the game play data including one or more of a total virtual economic resources value for the play participant, a number of defensive buildings, a cumulative number of opponent targets for the play participant to defeat, position coordinates of virtual characters controlled by the play participant, remaining cooling time of preset skills, survival status of preset non-player controlled characters, virtual life values for the play participant, virtual economic resources differences for different play participants with the same function for the controlled virtual characters.
- 4. The method of claim 1, wherein determining a game guidance opportunity based on the probabilities comprises: determining the duration of the current moment from the guiding moment corresponding to the latest game guiding moment; Determining the current moment as game guiding time under the condition that the probability is larger than a first preset probability threshold value and the time length is larger than or equal to a second preset time length; And if the probability is greater than a first preset probability threshold and the current game event of the current game pair is detected to be a first preset game event or the probability is greater than a second preset probability threshold, determining that the current moment is a game guiding occasion, wherein the first preset probability threshold is smaller than the second preset probability threshold.
- 5. The method of claim 1, wherein the game directing the opponent of the current game play at the game directing opportunity comprises: Determining a game event of the current game pair at a current guiding moment indicated by the game guiding moment; And matching the game event with a second preset game event in a preset guiding content library, and guiding the game of the fight participant of the current game play according to the matching result.
- 6. The method of claim 5, wherein the game directing the opponent of the current game play based on the matching result comprises: under the condition that the matching is successful, determining preset game guiding content corresponding to a second preset game event which is successfully matched from the preset guiding content library, and guiding the game to the fight participant of the current game play based on the preset game guiding content; Under the condition of failure in matching, current situation information of the current game at the current guiding moment is obtained, the current situation information is input into a pre-trained game guiding content generation model, and current game guiding content is determined according to the output of the game guiding content generation model so as to conduct game guiding on the fight participants of the current game based on the current game guiding content.
- 7. The method of claim 1 or 2, wherein any of the variation values comprises one or more of a variation value of a sum of the combat resources of each combat participant, a variation value of the combat resources of any combat participant, and wherein the combat resources comprise one or more of virtual economic resources and virtual experience values.
- 8. A game guiding device, comprising: the current characteristic value acquisition module is configured to acquire a current characteristic value of a game situation characteristic of a current game at a current moment; The prediction module is configured to input the current characteristic value into a pre-trained guiding opportunity prediction model, and predict the probability that a first change value of a fight resource of a fight participant of the current game fight after a first preset time length passes based on the guiding opportunity prediction model is greater than a preset threshold value; And the guiding occasion determining module is configured to determine whether the current moment is a game guiding occasion according to the probability so as to conduct game guiding on the fight participants of the current game play at the game guiding occasion.
- 9. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the method of any of claims 1 to 7.
- 10. An electronic device, comprising: one or more processors; Storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1 to 7.
Description
Game guiding method and device, computer program product and electronic equipment Technical Field The present disclosure relates to the field of gaming technology, and in particular, to a game guiding method, a game guiding apparatus, a computer program product, and an electronic device. Background The game guiding is carried out on the player in the game, so that the player can be assisted to carry out more accurate game operation, and the game experience of the player is improved. In the related art, an oversized language model can be used for guiding a game for a player, namely, the current game state is described as text input into the oversized language model, the oversized language model automatically judges whether the player needs to be guided currently or not, and specific guiding content is given when the player needs to be guided. However, the large language model is large in calculation overhead, it is difficult to satisfy the real-time requirement, and the large language model may assume a guiding reason to guide when the guiding is not required, resulting in lower accuracy of game guiding. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Disclosure of Invention The present disclosure is directed to a game guiding method and apparatus, a computer program product, and an electronic device, thereby improving game guiding accuracy and guiding efficiency at least to some extent. Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure. According to a first aspect of the present disclosure, a game guiding method is provided, which includes obtaining a current feature value of a game situation feature of a current game at a current moment, inputting the current feature value into a pre-trained guiding opportunity prediction model, predicting a probability that a first change value of an fight resource of a fight participant of the current game after a first preset time period passes through the guiding opportunity prediction model is greater than a preset threshold value, and determining a game guiding opportunity according to the probability, so as to conduct game guiding on the fight participant of the current game at the game guiding opportunity. According to a second aspect of the present disclosure, there is provided a game guiding apparatus including a current feature value obtaining module configured to obtain a current feature value of a game situation feature of a current game at a current time, a prediction module configured to input the current feature value into a pre-trained guiding opportunity prediction model, predict a probability that a first variation value of a fight resource of a fight participant of the current game after a first preset time period passes based on the guiding opportunity prediction model is greater than a preset threshold, and a guiding opportunity determination module configured to determine whether the current time is a game guiding opportunity according to the probability, so as to conduct game guiding on the fight participant of the current game at the game guiding opportunity. According to a third aspect of the present disclosure there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the steps of the game guidance method as described in the first aspect. According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the game guidance method as described in the first aspect of the above embodiments. According to a fifth aspect of the present disclosure, there is provided an electronic device comprising a processor, and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the game guidance method as described in the first aspect of the embodiments described above. As can be seen from the above technical solutions, the game guiding method, the game guiding device, and the computer program product and the electronic device for implementing the game guiding method in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects: In the technical schemes provided by some embodiments of the present disclosure, on one hand, the judgment of the complex game guiding time is converted into a problem of two-class probability prediction through the prediction of the change value of the fight resource, so that the judgment of the guiding time is performed through the light guiding time pred