CN114445542B - Game role model mapping processing method and system based on big data - Google Patents
Game role model mapping processing method and system based on big data Download PDFInfo
- Publication number
- CN114445542B CN114445542B CN202210049671.1A CN202210049671A CN114445542B CN 114445542 B CN114445542 B CN 114445542B CN 202210049671 A CN202210049671 A CN 202210049671A CN 114445542 B CN114445542 B CN 114445542B
- Authority
- CN
- China
- Prior art keywords
- event
- mapping
- map
- performance feedback
- use event
- 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.)
- Active
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 228
- 238000003672 processing method Methods 0.000 title abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 79
- 238000012545 processing Methods 0.000 claims description 75
- 238000000034 method Methods 0.000 claims description 38
- 230000008569 process Effects 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 12
- 238000005065 mining Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 6
- 230000014509 gene expression Effects 0.000 claims description 6
- 238000003491 array Methods 0.000 claims description 5
- 230000006835 compression Effects 0.000 claims description 4
- 238000007906 compression Methods 0.000 claims description 4
- 230000004807 localization Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 70
- 238000013461 design Methods 0.000 description 17
- 238000012360 testing method Methods 0.000 description 11
- 239000013598 vector Substances 0.000 description 9
- 238000013139 quantization Methods 0.000 description 6
- 238000007635 classification algorithm Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- YREOLPGEVLLKMB-UHFFFAOYSA-N 3-methylpyridin-1-ium-2-amine bromide hydrate Chemical compound O.[Br-].Cc1ccc[nH+]c1N YREOLPGEVLLKMB-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000002346 layers by function Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/50—Controlling the output signals based on the game progress
- A63F13/52—Controlling the output signals based on the game progress involving aspects of the displayed game scene
-
- 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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Graphics (AREA)
- Probability & Statistics with Applications (AREA)
- Fuzzy Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a game character model mapping processing method and system based on big data, which can intelligently and accurately create related game performance feedback sets, and can accurately and orderly sort game performance feedback contents corresponding to different mapping using events, so that needed game performance feedback contents can be conveniently and rapidly positioned from the game performance feedback sets.
Description
Technical Field
The invention relates to the technical field of big data and games, in particular to a game role model mapping processing method and system based on big data.
Background
The development of scientific and technological interest has been spread across all industries, and the gaming industry is no exception. From traditional black and white gaming machines to current 3D game frames and even VR feel experience, game players have increasingly high requirements for game frames and game performance, which also puts significant strain on game service providers. In the game development process, the game picture is critical to the expression of the game quality, and the game characters play important roles in the game picture, and whether the game characters act to change or the game characters skill to release, the game picture can intuitively reflect the game quality. Therefore, one important link for guaranteeing the game quality during the mapping processing of the game roles. However, the actual game character mapping technique still stays in the "mapping-modification-mapping-modification" vicious circle of low efficiency and low quality.
Disclosure of Invention
The application provides a game role model mapping processing method and system based on big data.
A first aspect is a game character model mapping processing method based on big data, applied to a game mapping processing system, the method at least comprising:
Determining, in response to a mapping process request for a target game character model, a set of mapping usage events that match the target game character model; wherein the mapping event group covers X mapping event groups, and X is an integer greater than or equal to 2;
determining a model deployment compliance index between each map use event in the set of map use events and the target game character model; utilizing the matched model application fitting index of each mapping use event and the differentiated description of each mapping use event to adjust each mapping use event so as to obtain a corresponding mapping event adjustment list;
A target game performance feedback set is created via the mapping event adjustment list that matches the target game character model, the target game performance feedback set encompassing X target game performance feedback content.
In some alternative designs, the applying the matching index with the model matched by each of the map usage events and the differential description of each of the map usage events adjusts each of the map usage events to obtain a corresponding map event adjustment list, including:
Utilizing the matched model application fitting index of each mapping use event and the differentiated description of each mapping use event to carry out localized processing on each mapping use event so as to obtain X staged use event sets;
and adjusting each staged use event set and adjusting each mapping use event in each staged use event set respectively to obtain the mapping event adjustment list.
In some optional designs, the applying the matching index with the model matched by each map use event and the differential description of each map use event perform a localization process on each map use event to obtain X staged use event sets, including:
Respectively utilizing a model matched with each mapping use event to apply a fitting index to carry out fusion processing on the differential description of each mapping use event so as to obtain a key differential description of each mapping use event;
and carrying out classification processing based on a description level on each mapping use event by utilizing the key differential description of each mapping use event to obtain X staged use event sets.
In some optional designs, the adjusting the each staged usage event set and adjusting each map usage event in the each staged usage event set respectively, to obtain the map event adjustment list includes:
According to the statistical result of the mapping use event covered by each staged use event set, adjusting each staged use event set;
For each set of staged usage events: adjusting each map use event in the staged use event set by utilizing the differentiated description of each map use event in the staged use event set and the binding weight of the staged use event set; the mapping event adjustment list is created via the event adjustment records between each set of staged usage events and the event adjustment records for each mapping usage event in each set of staged usage events.
In some alternative designs, the determining a model deployment compliance index between each of the set of map use events and the target game character model includes: loading each map use event into a performance feedback analysis network which is completed with configuration one by one, carrying out key content mining on each map use event through a compliance resolution layer of a game operation scene dimension in the performance feedback analysis network which is completed with configuration, and determining a model application compliance index matched with each map use event derived by the compliance resolution layer;
The matching module uses the matching index and the differential description of each mapping event, and adjusts each mapping event to obtain a corresponding mapping event adjustment list, including: loading each mapping use event and a model matched with each mapping use event into a multifunctional event processing layer in the configured performance feedback analysis network by using a fitting index, performing classification processing and adjustment based on a description level on each mapping use event through the multifunctional event processing layer, and determining a first combined event feature of a game operation node dimension derived by the multifunctional event processing layer, wherein each mapping use event label in the first combined event feature jointly forms a mapping event adjustment list;
The creating, via the mapping event adjustment list, a target game performance feedback set that matches the target game character model, comprising: loading the combined event features to a performance feedback analysis layer in the configured performance feedback analysis network, performing targeted description mining through the performance feedback analysis layer, and determining the target game performance feedback set derived by the performance feedback analysis layer; the performance feedback analysis network after completing configuration is configured based on an authentication example set, wherein the authentication examples in the authentication example set cover authentication type mapping use events of adding processing of target notes which are completed before, and the target notes reflect whether the authentication type mapping use events are matched with an authentication game role model or not.
In some optional designs, the loading each map usage event into the configured performance feedback analysis network one by one, determining, via a compliance resolution layer of a game operation scene dimension in the configured performance feedback analysis network, a model application compliance index matched by each authentication type map usage event derived by the compliance resolution layer includes:
Loading each map use event to the fitness resolution layer one by one, and transferring each map use event to a transitional characteristic list through a set network unit in the fitness resolution layer to obtain personalized characteristics of each map use event;
Updating the personalized features of each map using event one by one into a matched distinguishing array through a derivative analysis strategy;
digging the pertinence expression between the differential array of each map use event and the differential arrays of the rest map use events except for the map use event one by one through the fit resolution layer;
determining a model deployment compliance index between the each map use event and the target game character model via the matched targeted representation of the each map use event.
In some optional designs, the classifying and adjusting the using event based on the description level by the multifunctional event processing layer on each map, determining a first combined event feature of the game operation node dimension derived by the multifunctional event processing layer includes:
Transforming each map use event migration to a transitional feature list through a multifunctional event processing layer in the configured performance feedback analysis network to obtain a use behavior feature cluster matched with each map use event;
performing feature compression processing on the matched usage behavior feature clusters of each mapping usage event by setting a feature compression strategy to obtain the differentiated personalized features of each mapping usage event;
Respectively utilizing a model matched with each mapping use event to apply a fitting index, and carrying out fusion processing on the distinguishing personalized features of each mapping use event to obtain key personalized features of each mapping use event;
Carrying out classification processing based on a description level through key personalized features of each map using event to obtain X staged using event sets;
And after all the staged use event sets are adjusted and each map use event in each staged use event set is adjusted, combining key personalized features of each map use event and updating the dimensions of the game operation nodes to obtain the first combined event features.
In some optional designs, the loading the first combined event feature into a performance feedback analysis layer in the configured performance feedback analysis network, performing targeted description mining via the performance feedback analysis layer, determining the target game performance feedback set derived by the performance feedback analysis layer includes: setting processing strategies to establish each game performance feedback content in the target game performance feedback set one by one, wherein one performance theme in the target game performance feedback set at least comprises one game performance feedback content;
Each round of processing under the set processing strategy comprises:
Loading target game performance feedback content derived from the previous round into the performance feedback analysis layer, wherein the initial round is the default guiding information loaded into the performance feedback analysis layer;
Analyzing pairing degree of each mapping usage event tag in the previous round of derived target game performance feedback content and the example set through a local focusing strategy, wherein the pairing degree reflects a focusing coefficient between the mapping usage event tag and the previous round of derived game performance feedback content;
Fusing the pairing degree and the distinct array set of the mapping use event labels in the mapping event adjustment list, loading the fused mapping event adjustment list into a long-short-period memory network, and determining target distinct personalized features of the mapping event adjustment list derived in the current round;
And establishing the target game performance feedback content derived by the current round through the target game performance feedback content derived by the previous round and the target distinguishing type personalized characteristic.
In some alternative designs, prior to said analyzing the pairing degree of the target game performance feedback content derived from the previous round and each map usage event tag in the example set by the local focus strategy, further comprising: taking the target phased use event set of the round of positioning and the associated event set of the target phased use event set as the focused phased use event set, and taking the rest phased use event sets as non-focused phased use event sets, wherein the target phased use event set of each round of positioning is determined based on the precedence relationship among each phased use event set; adding a first pairing description for the mapping use event labels in the focused staged use event set in the mapping event adjustment list, adding a second pairing description for the mapping use event labels in the non-focused staged use event set in the mapping event adjustment list, and obtaining a first paired distinctive array matched by each mapping use event label in the example set; adding the first pairing description to the target game performance feedback content derived from the previous round to obtain a matched second paired distinctive array;
The analyzing, by the local focus strategy, the pairing degree of the target game performance feedback content derived from the previous round and each map usage event tag in the example set, comprising: and analyzing the pairing degree of the target game performance feedback content exported in the previous round and each mapping usage event label in the example set based on the local focusing strategy.
In some independently implementable designs, the performance feedback analysis network is configured by:
Determining the set of authentication examples for Y authenticated game character models; wherein Y is an integer of 1 or more;
Performing feedback configuration on the original performance feedback analysis network by using the authentication examples in the authentication example set to determine the configured performance feedback analysis network;
Wherein each round of feedback configuration comprises:
Screening a group of authentication examples pointing to the same authentication game role model from the authentication example set, loading authentication type mapping usage events carried by each positioned authentication example into a compliance resolution layer of game operation scene dimension in the original performance feedback analysis network one by one, and determining a model application compliance index matched with each authentication type mapping usage event derived by the compliance resolution layer;
Obtaining a first network quality index by using a model matched by the event through each authentication map and utilizing a quantization difference between a fitting index and a matched target annotation;
Loading the positioned authentication type mapping use events in each authentication example and a model matched with each authentication type mapping use event into a multifunctional event processing layer in the original performance feedback analysis network by using a fitting index one by one, and performing classification processing based on a description layer on each authentication type mapping use event through the multifunctional event processing layer to determine X staged use event sets;
adjusting each staged usage event set via the multi-functional event processing layer, determining a second combined event feature of a game operation node dimension derived by the multi-functional event processing layer;
Loading the second combined event feature to a performance feedback analysis layer in the original performance feedback analysis network, performing targeted description mining through the performance feedback analysis layer, and determining a group of test game performance feedback sets derived by the performance feedback analysis layer, wherein the test game performance feedback sets cover X test game performance feedback contents;
Obtaining a second network quality index via a quantitative difference of the relative relationship between the test-type game performance feedback content in the test-type game performance feedback set and the authenticated game performance feedback content in the authenticated game performance feedback set;
obtaining a third network quality index based on the attention coefficient of the event label used by each staged use event concentration mapping;
and optimizing the network variable of the original performance feedback analysis network by utilizing the first network quality index, the second network quality index and the third network quality index.
In some designs that may be implemented independently, the obtaining the second network quality indicator via a quantitative difference in a relative relationship between the test game performance feedback content in the test game performance feedback set and the authenticated game performance feedback content in the authenticated game performance feedback set specifically includes:
Determining, for one of the test-type game performance feedback contents, a relative relationship quantization difference of the test-type game performance feedback content in the test-type game performance feedback set and the authenticated game performance feedback content in the authenticated game performance feedback set via a position tag of the test-type game performance feedback content in the designated game performance feedback content set and a position tag of the test-type game performance feedback content in the map use event group;
and obtaining the second network quality index based on the determined relative relationship quantization difference.
A second aspect is a game map processing system comprising a memory and a processor; the memory is coupled to the processor; the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; wherein the computer instructions, when executed by the processor, cause the game map processing system to perform the method of the first aspect.
A third aspect is a computer readable storage medium having stored thereon a computer program which, when run, performs the method of the first aspect.
In view of the embodiment of the invention, the thought of creating the game performance feedback set based on the related map use events is shown, on the premise of obtaining the map processing request, the map processing request can be used for intelligently creating the game performance feedback set corresponding to the target game role model and having a sequence through the map event adjustment list having the sequence by applying the fitting index between the model between each map use event and the target game role model and the differential description of each map use event. By the embodiment of the invention, the related game performance feedback sets can be intelligently and accurately created, and game performance feedback contents corresponding to different mapping use events can be accurately and orderly arranged, so that the required game performance feedback contents can be conveniently and rapidly and accurately positioned from the game performance feedback sets.
Drawings
FIG. 1 is a flow chart of a method for mapping a character model of a game based on big data according to an embodiment of the present invention.
FIG. 2 is a block diagram of a big data based game character model map processing device according to an embodiment of the present invention.
Detailed Description
Hereinafter, the terms "first," "second," and "third," etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", or "a third", etc., may explicitly or implicitly include one or more such feature.
FIG. 1 is a flow diagram of a big data based game character model mapping method provided by an embodiment of the present invention, which may be implemented by a game mapping processing system, which may include a memory and a processor; the memory is coupled to the processor; the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; wherein the computer instructions, when executed by the processor, cause the game map processing system to perform the technical scheme described in the following steps.
Step 21: in response to a mapping process request for a target game character model, a set of mapping usage events that match the target game character model is determined.
For the embodiment of the present invention, the map use event group covers X map use events, where X is an integer greater than or equal to 2. Further, the X map usage events covered in the set of map usage events may originate from different game editing clients, but are all map usage events that are directed to the same target game character model. Further, the target game character model may be a 3D character model of the game character, a face-piece model of the game character, or other types of digital models of the game character, and embodiments of the present invention are not limited.
Further, the mapping usage event may be understood as a series of behavior events in the process of applying different mapping to the target game character model, including an operation editing event of a game editing client, a mapping result debugging event, and the like.
Step 22: a model deployment compliance index is determined between each of the set of map use events and the target game character model.
For the embodiment of the present invention, the model application compliance index may be understood as the degree of adaptation between the mapping event and the target game character model, where the higher the model application compliance index, the higher the mapping result corresponding to the mapping event corresponds to the application quality of the target game character model (for example, having smoother character action transformation, game skill release, for example, having fewer rendering vulnerability problems, etc.). In general, the value range of the model application fitting index may be 0 to 1, and of course, the model application fitting index may also be adaptively adjusted according to the actual situation, which is not limited in the embodiment of the present invention.
Step 23: and adjusting each mapping use event according to the matching model of each mapping use event by applying the fit index and the distinguishing description of each mapping use event to obtain a matching mapping event adjustment list.
For the embodiment of the invention, the differentiated description of each mapping use event can be understood as the semantic feature of each mapping use event, so as to distinguish the mapping use events, and the adjustment of each mapping use event can be understood as the arrangement (such as sorting) of different mapping use events, so that a mapping event adjustment list with a sequence identifier can be obtained. For example, a mapping event adjustment list may be understood as a mapping event queue.
Step 24: a set of target game performance feedback sets is created that match the target game character model based on the mapping event adjustment list.
For the embodiments of the present application, the target game performance feedback set encompasses X target game performance feedback content. Different game performance feedback content can reflect the game play quality of different map use events after application to the target game character model, and the game performance feedback content can relate to different types of game performance such as game picture performance, game delay performance or hardware heating performance.
It will be appreciated that there may be different requirements for mapping processes for the same target game character model, and for this reason, a complete, accurate and ordered target game performance feedback set can be output based on the mapping process request for the target game character model, so that a reference basis can be provided for the subsequent mapping process, and the subsequent mapping process can select the mapping mode with the highest adaptation degree to perform the mapping process of the game character model.
In view of the embodiment of the invention, the thought of creating the game performance feedback set based on the related map use events is shown, on the premise of obtaining the map processing request, the map processing request can be used for intelligently creating the game performance feedback set corresponding to the target game role model and having a sequence through the map event adjustment list having the sequence by applying the fitting index between the model between each map use event and the target game role model and the differential description of each map use event. By the embodiment of the invention, the related game performance feedback sets can be intelligently and accurately created, and game performance feedback contents corresponding to different mapping use events can be accurately and orderly arranged, so that the required game performance feedback contents can be conveniently and rapidly and accurately positioned from the game performance feedback sets.
For some possible design ideas, according to the model application fit index between each map use event and the target game character model and the differential description of each map use event, the map use event localization (such as disassembly) can be processed into multiple staged use event sets (which can be understood as a subset of map events later), so that the discrimination of each map use event in the same staged use event set is smaller, and the difference of the model application fit indexes between the map use events and the target game character model is smaller. And then after the staged use event sets are disassembled to obtain, each staged use event set is adjusted, each mapping use event in each staged use event set is respectively adjusted to obtain a mapping event adjustment list, and a game performance feedback set with accurate sequence is created based on the mapping event adjustment list with accurate sequence.
For the embodiment of the present invention, if the mapping event group localization process is performed for multiple staged event sets, when creating the target game performance feedback content based on the mapping event adjustment list, one staged event set may be used to create one target game performance feedback content, or multiple staged event sets may be used to create one target game performance feedback content, or one staged event set may be used to create multiple target game performance feedback content. In some possible cases, if the map usage events in the map usage event group may be more, but the finally created target game performance feedback set will typically cover several target game performance feedback contents, so that one target game performance feedback content can be created for multiple staged usage event sets.
For some possible design ideas, when the event is used for each map to be processed locally, the implementation may be based on the classification processing of the description level, and an exemplary implementation may be: respectively applying a fitting index according to a model matched with each mapping use event, and carrying out fusion processing on the differential description of each mapping use event to obtain a key differential description of each mapping use event; and classifying each mapping use event based on a description level according to the key differential description of each mapping use event to obtain X staged use event sets.
In view of the fact that the model application fit index can be understood as the game performance quality index, the differentiated description of the mapping use events is fused based on the model application fit index, the content with the characteristic recognition degree of the mapping use events and the target game role model can be determined, the effect of interference filtering on a plurality of mapping use events is achieved, the key and popular mapping use events can be positioned accurately, and the mapping use events of the cooling doors and which are not commonly used are limited to a certain extent.
In addition, there may be many ideas, such as multidimensional feature classification algorithms (also known as K-means clustering), when performing a description-level based classification process on each map-use event according to its key discriminative description. For example, a key discriminative description of all map use events is processed using a multidimensional feature classification algorithm, dividing all map use events into several (typically K) staged use event sets.
For the embodiment of the invention, after the mapping event group is locally processed into a plurality of staged event sets based on the multidimensional feature classification algorithm, the staged event sets and mapping event in the staged event sets can be adjusted to generate a mapping event adjustment list.
For some possible design ideas, the adjustment between each staged usage event set and the adjustment for each map usage event in each staged usage event set respectively, to obtain a set of map event adjustment lists may include the following contents: according to the statistical result of the mapping use event covered by each staged use event set, adjusting each staged use event set; and aiming at each staged use event set, according to the differentiated description of each map use event in the staged use event set and the binding weight of the staged use event set, adjusting each map use event in the staged use event set.
Further, the staged use event sets are adjusted, and after the staged use event sets are also adjusted, a staged event adjustment list is created based on event adjustment records between each staged use event set and event adjustment records of each staged use event in each staged use event set.
For example, a total of 4 staged usage event sets are obtained by a total of disassembly, and the 4 staged usage event sets are recorded as case_set_1, case_set_2, case_set_3 and case_set_4 in sequence. Wherein, there are 3 map use events in case_set_1, 5 map use events in case_set_2, 7 map use events in case_set_3, and 3 map use events in case_set_4. In this case, by counting the number of map use events in each of the staged use event sets, the adjustment is performed between each staged use event set, and assuming that the larger the map use event count is, the more front the arrangement is, the event adjustment is recorded as: case_set_3, case_set_2, case_set_1, and case_set_4 (or case_set_3, case_set_2, case_set_4, and case_set_1). The statistics of the map usage events covered by case_set_1 and case_set_4 are consistent, because the two staged usage event sets can be dynamically adjusted or adjusted by combining other conditions.
For the embodiment of the present invention, after the adjustment between each staged usage event set, each map usage event in each staged usage event set may be further adjusted, or before the adjustment between each staged usage event set, each map usage event in each staged usage event set may be adjusted, or adjusted simultaneously, etc., the embodiment of the present invention is not limited. Illustratively, when each map use event in the staged use event set is adjusted, the binding weight (which may be understood as an association weight or an association degree) of each map use event in the staged use event set is generally described by the distinction type of each map use event in the staged use event set, for example, the greater the binding weight, the more forward the position after adjustment, the less the binding weight, and the more backward the position after adjustment.
In some design considerations that may be implemented independently, the big data based game character model mapping method of the embodiments of the present invention may also be implemented by AI technology, such as through a related neural network model, with exemplary steps including: loading each map use event into the performance feedback analysis network after completing configuration one by one, mining key contents of each map use event based on a fitness analysis layer of a game operation scene dimension in the performance feedback analysis network after completing configuration, and determining a model application fitness index matched with each map use event derived by the fitness analysis layer.
Further, each mapping use event and a model matched by each mapping use event are loaded to a multifunctional event processing layer in the configured performance feedback analysis network by using a fitting index one by one, classification processing and adjustment based on a description layer are performed on each mapping use event based on the multifunctional event processing layer, a first combined event feature of a game operation node dimension derived by the multifunctional event processing layer is determined, and each mapping use event label in the first combined event feature jointly forms a mapping event adjustment list.
Furthermore, the first combined event feature is loaded to a performance feedback analysis layer in the configured performance feedback analysis network, targeted description mining is performed based on the performance feedback analysis layer, and a target game performance feedback set derived by the performance feedback analysis layer is determined.
For the embodiment of the present invention, the performance feedback analysis network (which may be understood as a neural network model, and is not limited in type) may include a fitness resolution layer including a game operation scene dimension, a multifunctional event processing layer, and a performance feedback resolution layer. These functional layers can be understood as local models/sets of model elements/model components, etc. Further, the game operation scene dimension is used for distinguishing with the subsequent game operation node dimension, the game operation scene expression which can be the mapping use event is obtained in the matching resolution layer, the first combined event feature finally obtained in the multifunctional event processing layer is the game operation node dimension, and the feature vector of each mapping use event in the mapping event adjustment list can be understood to be updated into the feature vector obtained in the game operation node dimension after the feature vector of each mapping use event is combined according to rules.
Further, the performance feedback analysis network is configured based on an authentication example set (training sample set), wherein the authentication example in the authentication example set covers authentication type mapping usage event of which the adding process of the target annotation is completed before, and the target annotation indicates whether the authentication type mapping usage event is matched with the authentication game role model or not, and can be a 2-class tag. It may be understood that, in the authentication examples covered in the authentication example set in the embodiment of the present invention, the authentication type map usage event may be directed to the same authentication game role model, or may be directed to a plurality of authentication game role models, and generally, the same authentication game role model corresponds to a plurality of authentication type map usage events.
First, a set of map usage events loaded into a game character model may be passed through a compliance resolution layer of the game operational scenario dimension, and each map usage event may be resolved to data related to the game model using an event test type game performance quality index for each map, such as a model exercise compliance index to which the map usage event matches.
For embodiments of the present invention, the function of the fitness resolution layer of the game operation scene dimension is to determine a quantized score for each map using an event. First, each map-using event migration can be transformed into a transitional feature list (such as continuous space) by means of a related neural network model, so as to obtain personalized features of each map-using event, and the personalized features are updated into a distinguishing array (which can be understood as semantic vectors) through a derivative analysis strategy. Illustratively, an active local focus strategy (self-attention mechanism) of the game operation scene dimension is adopted to mine the distinctive arrays of each map use event one by one and the targeted expressions (attention features) between the distinctive arrays of the remaining map use events except for the map use event, and a model application fit index between each map use event and the target game role model is determined based on the targeted expressions matched by each map use event, so that a game performance quality index (such as the quantized score can be understood as the above) is determined for each map use event.
It can be understood that BRNN may be used as the setting network element in the above-mentioned fitness resolution layer, and embodiments of the present invention are not limited.
After determining that the game performance quality index matched with each map use event is obtained based on the fit resolution layer, the classification processing adjustment based on the description level can be carried out on each map use event based on the multifunctional event processing layer in the configured performance feedback analysis network, and the multifunctional event processing layer provided by the invention can absorb and analyze the precedence relation of the map use events by optimizing the map use events into the map event subset which is as orderly as possible, which is the key of accurately and completely creating the game performance feedback set, based on the fact, the exemplary design thought can be as follows: the method comprises the steps of obtaining a usage behavior feature cluster matched with each mapping usage event by transferring and transforming each mapping usage event to a transitional feature list through an encoder, and then respectively applying a fitting index according to a model matched with each mapping usage event to fuse distinguishing personalized features of each mapping usage event to obtain key_ indiv _feature of each mapping usage event.
Further, a multi-dimensional feature classification algorithm can be applied to key personalized features of all map use events to perform classification processing based on a description level, and all map use events are divided into a plurality of map event subsets; and arranging all the map event subsets in descending order according to the covered map use event statistics, and arranging each map event subset in ascending order according to the distance from the map use event to a reference event (such as a clustering center), so as to obtain a map event adjustment list with sequence. After feature vectors are obtained by using event according to rule combination mapping, the embodiment of the invention updates the dimension of the game operation node and adjusts the dimension of the game operation node into a first combination type event feature of the dimension of the game operation node
Based on the above, for the performance feedback analysis layer with enhanced functions, by means of different matching constraints, namely pairing description and matching deviation (matching loss), the performance feedback analysis network can create a game performance feedback set with a sequence according to the distinctive personalized features of the map usage event, and based on this, the following technical schemes can be exemplarily included: and setting up each game performance feedback content in the target game performance feedback set one by using a set processing strategy (such as loop processing), wherein one performance theme in the target game performance feedback set at least comprises one game performance feedback content.
By way of example, a round-robin process may be understood as every time a game performance feedback is created. Please combine the following, the following relevant steps can be implemented during a round of processing.
Step 51: and loading the target game performance feedback content derived from the previous round to a performance feedback analysis layer.
For the embodiment of the present invention, the first round of boot information (such as indication information that can be understood as start) is loaded to the performance feedback parsing layer as default.
Step 52: and taking the target mapping event subset positioned in the round and the associated event set of the target mapping event subset as the mapping event subset concerned, and taking the rest mapping event subsets as the mapping event subset not concerned, wherein the target mapping event subset positioned in each round is determined based on the precedence relationship among each mapping event subset.
For the embodiments of the present invention, the associated event set may be understood as a neighbor set of the target map event subset, the concerned map event subset may be understood as a map event subset having a certain value, and the non-concerned map event subset may be understood as a map event subset of the edge. Illustratively, this step may be implemented using a sliding window technique.
Step 53: adding a first pairing description for the map use event labels in the map event subset concerned in the map event adjustment list, and adding a second pairing description for the map use event labels in the map event subset not concerned in the map event adjustment list, so as to obtain a first paired distinctive array matched by each map use event label in the example set; and adding the first pairing description to the target game performance feedback content derived from the previous round to obtain a matched second paired distinctive type array.
For example, a paired description may be understood as an alignment feature, and a paired discriminating array may be understood as an aligned semantic vector.
Step 54: and analyzing the pairing degree of the target game performance feedback content exported in the previous round and the event label used by each map in the example set based on the local focusing strategy by combining the first paired array matched by the event label and the second paired distinctive array matched by the target game performance feedback content exported in the previous round, wherein the pairing degree represents the attention coefficient between the event label used by the map and the game performance feedback content exported in the previous round.
For example, a local focus strategy may be understood as an attention mechanism and, correspondingly, a focus factor may be understood as an attention value.
Step 55: and fusing the pairing degree and the mapping in the mapping event adjustment list by using a differential array set of event labels, loading the fusion processing into a long-period and short-period memory network, and determining target differential personalized features of the mapping event adjustment list derived in the round.
In some alternative design concepts, a forward neural network may also be used in place of the long and short term memory network. Further, a distinguishing personalized feature may be understood as a feature vector with a greater degree of feature recognition.
Step 56: and based on the target game performance feedback content derived from the previous round and the target distinguishing type personalized characteristics, creating target game performance feedback content derived from the current round.
It can be understood that the performance feedback parsing layer in the embodiment of the present invention is exemplified by a feature translation thread (such as a decoder), and of course, the function of the performance feedback parsing layer may also be implemented by other functional modules. .
For some design considerations that may be implemented independently, the performance feedback analysis network in embodiments of the present invention is configured by way of several examples of authentication. Further, the configuring step with respect to the performance feedback analysis network may include the following.
An authentication example set for Y authentication game character models is determined, and based on the authentication examples in the authentication example set, a feedback type configuration is performed on the original performance feedback analysis network to determine a configured performance feedback analysis network. For example, Y is an integer of 1 or more.
Further, each round of feedback configuration includes: firstly, screening a group of authentication examples which point to the same authentication game role model from an authentication example set, taking the group of authentication examples as a mapping use event group, and referring to the related examples, loading authentication mapping use events carried by each positioned authentication example into a compliance resolution layer of a game operation scene dimension in an original performance feedback analysis network one by one, and determining a model operation compliance index matched with each authentication mapping use event derived by the compliance resolution layer; a first network quality indicator is then obtained based on the model matched by each certification type map using the event using the quantized difference between the fitting index and the matched target annotation.
For example, the matching resolution layer of the dimension of the game operation scene analyzes the association degree between each mapping event and other mapping events by means of the interactions between the mapping event distinguishing arrays, determines the content with characteristic recognition degree, related to the game role model, of each mapping event, and further achieves the effect of interference filtering on a plurality of mapping events, preferably popular mapping events, and marginalizes the popular mapping events to a certain extent.
Based on the above, the authentication type mapping use events in each authentication example are located one by one, and a model matched by each authentication type mapping use event is loaded to a multifunctional event processing layer in the original performance feedback analysis network by using a fitting index, the classifying processing based on the description level is performed on each authentication type mapping use event based on the multifunctional event processing layer, after X mapping event subsets are determined, each mapping event subset is adjusted, and a second combined event feature of the game operation node dimension derived by the multifunctional event processing layer is determined. And then, loading the second combined event characteristic to a performance feedback analysis layer in the original performance feedback analysis network, performing targeted description mining based on the performance feedback analysis layer, and determining a group of test game performance feedback sets derived by the performance feedback analysis layer, wherein the test game performance feedback sets cover X test game performance feedback contents.
The method mainly comprises the steps of obtaining a second network quality index based on the relative relation quantification difference between test game performance feedback content in a test game performance feedback set and authenticated game performance feedback content in an authenticated game performance feedback set in terms of a multifunctional event processing layer and a performance feedback analysis layer; a third network quality indicator is obtained based on the attention coefficients of the mapping using the event tags in each subset of mapping events.
In some possible embodiments, the second network quality indicator may be obtained based on a match offset. For one of the test-type game performance feedback contents, determining a relative relationship quantization difference between the test-type game performance feedback content in the test-type game performance feedback set and the authenticated game performance feedback content in the authenticated game performance feedback set based on the position label of the test-type game performance feedback content in the designated game performance feedback content set and the position label of the test-type game performance feedback content in the mapping use event group; and obtaining a second network quality index based on the determined relative relationship quantization difference.
Illustratively, the relative relationship quantization difference can be understood as a distribution loss.
For one of the test-type game performance feedback contents, the test-type game performance feedback content is taken as target game performance feedback content, the feature vector of the target game performance feedback content is updated through a feature translation thread, and the recording condition of the game performance feedback content related to the feature vector is determined. In some examples, the game performance feedback content record may be represented in the form of a probability distribution.
In view of the above three functional layers included in the performance feedback analysis network according to the embodiment of the present invention, the performance feedback analysis network can be implemented through collaborative configuration when the network is configured. By combining the matching resolution layer, the multifunctional event processing layer and the performance feedback resolution layer of the game operation scene dimension, the global network quality index l_whole can be determined by combining the first network quality index loss1, the second network quality index loss2 and the third network quality index loss3, for example, corresponding weight coefficients a1, a2 and a3 are configured for the first network quality index loss1, the second network quality index loss2 and the third network quality index loss3, and then l_whole is obtained in a weighted manner. Further, the network variable is continuously optimized for the performance feedback analysis network through the L_whole until the configuration requirement is met (such as the convergence of the L_whole or the requirement of the number of times of circulation is met), so as to obtain the configured performance feedback analysis network.
After the configuration of the performance feedback analysis network is completed, a game performance feedback set can be established through the performance feedback analysis network, so that a reference basis is provided for the subsequent game role model mapping processing.
Based on the same inventive concept, fig. 2 shows a block diagram of a big data based game character model mapping processing apparatus according to an embodiment of the present invention, which may include modules for implementing the relevant method steps shown in fig. 1.
A mapping event determining module 21 for determining a set of mapping usage events matched with a target game character model in response to a mapping processing request of the target game character model; the mapping event group covers X mapping event groups, and X is an integer greater than or equal to 2.
A mapping event adjustment module 22 for determining a model deployment compliance index between each mapping use event in the set of mapping use events and the target game character model; and adjusting each mapping use event by utilizing the matched model application fitting index of each mapping use event and the differentiated description of each mapping use event so as to obtain a corresponding mapping event adjustment list.
A performance feedback determination module 23 for creating a target game performance feedback set matching the target game character model via the map event adjustment list, the target game performance feedback set covering X target game performance feedback contents
The related embodiments applied to the present invention can achieve the following technical effects: in view of the embodiment of the invention, the thought of creating the game performance feedback set based on the related map use events is shown, on the premise of obtaining the map processing request, the map processing request can be used for intelligently creating the game performance feedback set corresponding to the target game role model and having a sequence through the map event adjustment list having the sequence by applying the fitting index between the model between each map use event and the target game role model and the differential description of each map use event. By the embodiment of the invention, the related game performance feedback sets can be intelligently and accurately created, and game performance feedback contents corresponding to different mapping use events can be accurately and orderly arranged, so that the required game performance feedback contents can be conveniently and rapidly and accurately positioned from the game performance feedback sets.
The foregoing is only a specific embodiment of the present application. Variations and alternatives will occur to those skilled in the art based on the detailed description provided herein and are intended to be included within the scope of the application.
Claims (10)
1. A method for processing a game character model map based on big data, which is applied to a game map processing system, the method at least comprises:
Determining, in response to a mapping process request for a target game character model, a set of mapping usage events that match the target game character model; wherein the mapping event group covers X mapping event groups, and X is an integer greater than or equal to 2;
determining a model deployment compliance index between each map use event in the set of map use events and the target game character model; utilizing the matched model application fitting index of each mapping use event and the differentiated description of each mapping use event to adjust each mapping use event so as to obtain a corresponding mapping event adjustment list;
A target game performance feedback set is created via the mapping event adjustment list that matches the target game character model, the target game performance feedback set encompassing X target game performance feedback content.
2. The method of claim 1, wherein the determining a model exercise fit index between each map use event in the set of map use events and the target game character model comprises: loading each map use event into a performance feedback analysis network which is completed with configuration one by one, carrying out key content mining on each map use event through a compliance resolution layer of a game operation scene dimension in the performance feedback analysis network which is completed with configuration, and determining a model application compliance index matched with each map use event derived by the compliance resolution layer;
The matching module uses the matching index and the differential description of each mapping event, and adjusts each mapping event to obtain a corresponding mapping event adjustment list, including: loading each mapping use event and a model matched with each mapping use event into a multifunctional event processing layer in the configured performance feedback analysis network by using a fitting index, performing classification processing and adjustment based on a description level on each mapping use event through the multifunctional event processing layer, and determining a first combined event feature of a game operation node dimension derived by the multifunctional event processing layer, wherein each mapping use event label in the first combined event feature jointly forms a mapping event adjustment list;
The creating, via the mapping event adjustment list, a target game performance feedback set that matches the target game character model, comprising: loading the combined event features to a performance feedback analysis layer in the configured performance feedback analysis network, performing targeted description mining through the performance feedback analysis layer, and determining the target game performance feedback set derived by the performance feedback analysis layer; the performance feedback analysis network after completing configuration is configured based on an authentication example set, wherein the authentication examples in the authentication example set cover authentication type mapping use events of adding processing of target notes which are completed before, and the target notes reflect whether the authentication type mapping use events are matched with an authentication game role model or not.
3. The method of claim 2, wherein loading each map usage event into a fully configured performance feedback analysis network one by one, determining a model exertion compliance index for each authenticated map usage event that the compliance resolution layer derives via a compliance resolution layer of a game operation scene dimension in the fully configured performance feedback analysis network, comprises:
Loading each map use event to the fitness resolution layer one by one, and transferring each map use event to a transitional characteristic list through a set network unit in the fitness resolution layer to obtain personalized characteristics of each map use event;
Updating the personalized features of each map using event one by one into a matched distinguishing array through a derivative analysis strategy;
digging the pertinence expression between the differential array of each map use event and the differential arrays of the rest map use events except for the map use event one by one through the fit resolution layer;
determining a model deployment compliance index between the each map use event and the target game character model via the matched targeted representation of the each map use event.
4. The method of claim 2, wherein said classifying and adjusting the usage events of each map based on the description level via the multi-function event processing layer, determining a first combined event feature of the game operation node dimension derived by the multi-function event processing layer, comprises:
Transforming each map use event migration to a transitional feature list through a multifunctional event processing layer in the configured performance feedback analysis network to obtain a use behavior feature cluster matched with each map use event;
performing feature compression processing on the matched usage behavior feature clusters of each mapping usage event by setting a feature compression strategy to obtain the differentiated personalized features of each mapping usage event;
Respectively utilizing a model matched with each mapping use event to apply a fitting index, and carrying out fusion processing on the distinguishing personalized features of each mapping use event to obtain key personalized features of each mapping use event;
Carrying out classification processing based on a description level through key personalized features of each map using event to obtain X staged using event sets;
And after all the staged use event sets are adjusted and each map use event in each staged use event set is adjusted, combining key personalized features of each map use event and updating the dimensions of the game operation nodes to obtain the first combined event features.
5. The method of claim 2, wherein loading the first combined event feature into a performance feedback analysis layer in the configured performance feedback analysis network, performing targeted description mining via the performance feedback analysis layer, determining the target game performance feedback set derived by the performance feedback analysis layer, comprises: setting processing strategies to establish each game performance feedback content in the target game performance feedback set one by one, wherein one performance theme in the target game performance feedback set at least comprises one game performance feedback content;
Each round of processing under the set processing strategy comprises:
Loading target game performance feedback content derived from the previous round into the performance feedback analysis layer, wherein the initial round is the default guiding information loaded into the performance feedback analysis layer;
Analyzing pairing degree of each mapping usage event tag in the previous round of derived target game performance feedback content and the example set through a local focusing strategy, wherein the pairing degree reflects a focusing coefficient between the mapping usage event tag and the previous round of derived game performance feedback content;
Fusing the pairing degree and the distinct array set of the mapping use event labels in the mapping event adjustment list, loading the fused mapping event adjustment list into a long-short-period memory network, and determining target distinct personalized features of the mapping event adjustment list derived in the current round;
And establishing the target game performance feedback content derived by the current round through the target game performance feedback content derived by the previous round and the target distinguishing type personalized characteristic.
6. The method of claim 5, further comprising, prior to said analyzing the pairing degree of the target game performance feedback content derived from the previous round and each map usage event tag in the example set by the local focus strategy: taking the target phased use event set of the round of positioning and the associated event set of the target phased use event set as the focused phased use event set, and taking the rest phased use event sets as non-focused phased use event sets, wherein the target phased use event set of each round of positioning is determined based on the precedence relationship among each phased use event set; adding a first pairing description for the mapping use event labels in the focused staged use event set in the mapping event adjustment list, adding a second pairing description for the mapping use event labels in the non-focused staged use event set in the mapping event adjustment list, and obtaining a first paired distinctive array matched by each mapping use event label in the example set; adding the first pairing description to the target game performance feedback content derived from the previous round to obtain a matched second paired distinctive array;
The analyzing, by the local focus strategy, the pairing degree of the target game performance feedback content derived from the previous round and each map usage event tag in the example set, comprising: and analyzing the pairing degree of the target game performance feedback content exported in the previous round and each mapping usage event label in the example set based on the local focusing strategy.
7. The method of claim 1, wherein said adapting said each map use event to obtain a corresponding map event adaptation list using said model matched by said each map use event using a fit index and said differentiated description of said each map use event comprises:
Utilizing the matched model application fitting index of each mapping use event and the differentiated description of each mapping use event to carry out localized processing on each mapping use event so as to obtain X staged use event sets;
and adjusting each staged use event set and adjusting each mapping use event in each staged use event set respectively to obtain the mapping event adjustment list.
8. The method of claim 7, wherein using the model matched by each of the map use events to apply a fit index and a discriminative description of each of the map use events, performing a localization process on each of the map use events to obtain X staged use event sets, comprises:
Respectively utilizing a model matched with each mapping use event to apply a fitting index to carry out fusion processing on the differential description of each mapping use event so as to obtain a key differential description of each mapping use event;
and carrying out classification processing based on a description level on each mapping use event by utilizing the key differential description of each mapping use event to obtain X staged use event sets.
9. The method of claim 7, wherein said adjusting between each set of staged usage events and each map usage event in each set of staged usage events respectively, to obtain said map event adjustment list, comprises:
According to the statistical result of the mapping use event covered by each staged use event set, adjusting each staged use event set;
For each set of staged usage events: adjusting each map use event in the staged use event set by utilizing the differentiated description of each map use event in the staged use event set and the binding weight of the staged use event set; the mapping event adjustment list is created via the event adjustment records between each set of staged usage events and the event adjustment records for each mapping usage event in each set of staged usage events.
10. A game map processing system, comprising: a memory and a processor; the memory is coupled to the processor; the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; wherein the computer instructions, when executed by the processor, cause the game map processing system to perform the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210049671.1A CN114445542B (en) | 2022-01-17 | 2022-01-17 | Game role model mapping processing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210049671.1A CN114445542B (en) | 2022-01-17 | 2022-01-17 | Game role model mapping processing method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114445542A CN114445542A (en) | 2022-05-06 |
| CN114445542B true CN114445542B (en) | 2024-05-28 |
Family
ID=81368612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210049671.1A Active CN114445542B (en) | 2022-01-17 | 2022-01-17 | Game role model mapping processing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445542B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069075A (en) * | 2020-09-09 | 2020-12-11 | 网易（杭州）网络有限公司 | Fashion testing method and device for game role and game client |
| CN113304485A (en) * | 2021-05-31 | 2021-08-27 | 创联无忧(广州)信息科技有限公司 | Operation data processing method of big data cloud game, server and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2937062A1 (en) * | 2016-07-25 | 2018-01-25 | 9203-4776 Quebec Inc. (Djeanius Divertissement) | Method and system for theme or role-play games on a mobile device |
| US20210283505A1 (en) * | 2020-03-10 | 2021-09-16 | Electronic Arts Inc. | Video Game Content Provision System and Method |
-
2022
- 2022-01-17 CN CN202210049671.1A patent/CN114445542B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112069075A (en) * | 2020-09-09 | 2020-12-11 | 网易（杭州）网络有限公司 | Fashion testing method and device for game role and game client |
| CN113304485A (en) * | 2021-05-31 | 2021-08-27 | 创联无忧(广州)信息科技有限公司 | Operation data processing method of big data cloud game, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114445542A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180300535A1 (en) | Media content enrichment using an adapted object detector | |
| CN110188829B (en) | Neural network training method, target recognition method and related products | |
| CN113128369A (en) | Lightweight network facial expression recognition method fusing balance loss | |
| CN111479130A (en) | Video positioning method and device, electronic equipment and storage medium | |
| CN111695824B (en) | Method, device, equipment and computer storage medium for analyzing risk tail end customer | |
| CN109033833B (en) | Malicious code classification method based on multiple features and feature selection | |
| CN111310918B (en) | Data processing method, device, computer equipment and storage medium | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| Ong et al. | Deep architectures and ensembles for semantic video classification | |
| KR102501575B1 (en) | Method and apparatus for transmitting a video text list to a user terminal using a plurality of neural networks by a server | |
| CN114969504A (en) | Big data processing method and system combining user interest analysis | |
| CN115203393A (en) | Dialogue response method and system, electronic equipment and storage medium | |
| CN116415647A (en) | Method, device, equipment and storage medium for searching neural network architecture | |
| WO2023047162A1 (en) | Object sequence recognition method, network training method, apparatuses, device, and medium | |
| CN117196000A (en) | Edge side model reasoning acceleration method for containerized deployment | |
| CN114445542B (en) | Game role model mapping processing method and system based on big data | |
| CN114664401A (en) | User demand analysis method and system serving intelligent medical big data | |
| Kim et al. | Explicit performance metric optimization for fusion-based video retrieval | |
| CN115408617B (en) | Internet user integration method based on artificial intelligence and big data service system | |
| CN111597361A (en) | Multimedia data processing method, device, storage medium and equipment | |
| CN117011751A (en) | Segmentation of video image sequences using a transformer network | |
| CN114697127B (en) | Service session risk processing method based on cloud computing and server | |
| US20230368038A1 (en) | Improved fine-tuning strategy for few shot learning | |
| CN111523308B (en) | Chinese word segmentation method and device and computer equipment | |
| CN112190926B (en) | Data traffic processing method in online game scene and online game server |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |