CN116595398A - Resource intelligent matching method and related device based on meta universe - Google Patents
Resource intelligent matching method and related device based on meta universe Download PDFInfo
- Publication number
- CN116595398A CN116595398A CN202310689139.0A CN202310689139A CN116595398A CN 116595398 A CN116595398 A CN 116595398A CN 202310689139 A CN202310689139 A CN 202310689139A CN 116595398 A CN116595398 A CN 116595398A
- Authority
- CN
- China
- Prior art keywords
- resource
- user
- data
- universe
- meta
- 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 78
- 238000013468 resource allocation Methods 0.000 claims abstract description 92
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000009826 distribution Methods 0.000 claims abstract description 46
- 238000010276 construction Methods 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 86
- 238000004422 calculation algorithm Methods 0.000 claims description 46
- 238000013075 data extraction Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 16
- 238000007621 cluster analysis Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 239000000284 extract Substances 0.000 description 12
- 238000010801 machine learning Methods 0.000 description 11
- 238000003058 natural language processing Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000005065 mining Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000007418 data mining Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000003997 social interaction Effects 0.000 description 4
- 238000007635 classification algorithm Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000009561 snack bars Nutrition 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention relates to the technical field of metauniverse, and discloses a resource intelligent matching method and a related device based on metauniverse, which are used for improving the efficiency and accuracy of resource intelligent matching in metauniverse. The method comprises the following steps: acquiring initial user information of a target user in a meta universe, and generating a user interest distribution field set; acquiring online behavior data, and performing virtual entity matching on the online behavior data to generate a plurality of virtual entities; extracting resource data from a plurality of virtual entities to obtain a resource data set; classifying the resource data set, determining the resource data type set, extracting resource configuration information from the meta universe, and generating target resource configuration information; performing model construction through the historical transaction data set to generate a target resource allocation model; and inputting the target resource configuration data information and the user interest distribution field set into a target resource configuration model to perform resource configuration analysis, and generating a resource configuration analysis result.
Description
Technical Field
The invention relates to the technical field of metauniverse, in particular to a resource intelligent matching method and a related device based on metauniverse.
Background
With the continuous maturation and development of virtual reality technology, the metauniverse has become a new application scene. By utilizing the virtual reality equipment and the sensor, the behavior data of the user in the meta universe can be obtained, so that more intelligent and personalized resource allocation is realized.
However, the prior art still has some drawbacks, and in order to obtain more accurate user behavior data, a large amount of sensitive information needs to be collected, for example, the user position, the physiological state, etc., which causes problems of privacy disclosure, data abuse, etc., and a data protection mechanism needs to be enhanced. In the analysis of resource allocation, the accuracy and the precision of the algorithm have great influence on the quality of the result, and the existing algorithm still has the problem of insufficient accuracy and precision.
Disclosure of Invention
The invention provides a resource intelligent matching method and a related device based on a meta universe, which are used for improving the efficiency and accuracy of resource intelligent matching in the meta universe.
The first aspect of the invention provides a resource intelligent matching method based on a meta universe, which comprises the following steps: acquiring initial user information of a target user in a meta universe, and generating a user interest distribution field set through the initial user information;
Acquiring online behavior data of the target user in the meta universe, and performing virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
extracting resource data from a plurality of virtual entities to obtain a resource data set;
classifying the resource data sets, determining corresponding resource data type sets, extracting resource configuration information from the meta universe based on the resource data type sets, and generating target resource configuration information;
acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model;
and inputting the target resource configuration data information and the user interest distribution field set into the target resource configuration model to perform resource configuration analysis, and generating a corresponding resource configuration analysis result.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the obtaining initial user information of the target user in the meta-universe, and generating the user interest distribution domain set according to the initial user information includes:
Acquiring initial user information of a target user in a meta universe, and carrying out information coding on the initial user information to generate a corresponding user code;
and carrying out user interest field matching on the user codes to obtain corresponding user interest distribution field sets.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the collecting online behavior data of the target user in the meta-universe, and performing virtual entity matching on the online behavior data, to generate a plurality of corresponding virtual entities, includes:
acquiring online behavior data of the target user in the meta universe, and performing behavior cluster analysis on the online behavior data to generate a behavior cluster analysis result;
performing behavior region analysis on the meta-universe through the behavior cluster analysis result to generate a plurality of corresponding target meta-universe regions;
and respectively carrying out virtual entity matching on each target meta-universe area to generate a plurality of corresponding virtual entities.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the extracting resource data from the plurality of virtual entities to obtain a resource data set includes:
Extracting resource types from a plurality of virtual entities based on the user interest distribution field set to obtain a plurality of corresponding resource types;
and extracting resource data from the metauniverse based on the plurality of resource types, and generating a corresponding resource data set.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the classifying the resource data set, determining a corresponding resource data type set, and extracting resource configuration information from the meta space based on the resource data type set, to generate target resource configuration information includes:
carrying out semantic analysis on the resource data set to obtain a plurality of semantic identification information;
performing data type matching through a plurality of semantic identification information to generate a resource data type set;
performing data extraction algorithm matching on the resource data type set, and determining an initial data extraction algorithm;
performing rule configuration on the initial data extraction algorithm to generate a target data extraction algorithm;
and extracting resource configuration information from the metauniverse through the target data extraction algorithm to generate target resource configuration information.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the obtaining a historical transaction data set of a plurality of historical users in the meta universe, and performing model construction through the historical transaction data set, generating a target resource configuration model includes:
acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing user types for the plurality of historical users to generate a plurality of user types;
performing resource allocation weight matching on a plurality of historical users through the historical transaction data based on a plurality of user types, and generating resource allocation weights corresponding to each historical user;
and constructing a resource allocation model through the resource allocation weight corresponding to each historical user and the historical transaction data set, and generating a target resource allocation model.
With reference to the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect of the present invention, the generating, based on the plurality of user types, resource configuration weights for a plurality of historical users through the historical transaction data, the resource configuration weights corresponding to each historical user includes:
Extracting user characteristics from a plurality of user types to generate a plurality of user characteristics;
performing data set division on the historical transaction data based on a plurality of user characteristics to generate a plurality of sub-transaction data sets;
and respectively carrying out resource allocation weight calculation on each historical user through each sub-transaction data set to generate resource allocation weights corresponding to each historical user.
The second aspect of the present invention provides a resource intelligent matching system based on a meta universe, the resource intelligent matching system based on the meta universe includes:
the acquisition module is used for acquiring initial user information of a target user in the meta universe and generating a user interest distribution field set through the initial user information;
the matching module is used for collecting online behavior data of the target user in the meta universe, and carrying out virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
the extraction module is used for extracting the resource data of the plurality of virtual entities to obtain a resource data set;
the classification module is used for classifying the resource data sets, determining corresponding resource data type sets, extracting resource configuration information from the meta universe based on the resource data type sets and generating target resource configuration information;
The construction module is used for acquiring historical transaction data sets of a plurality of historical users in the meta universe, constructing a model through the historical transaction data sets and generating a target resource configuration model;
and the analysis module is used for inputting the target resource configuration data information and the user interest distribution field set into the target resource configuration model to carry out resource configuration analysis and generating a corresponding resource configuration analysis result.
The third aspect of the present invention provides a resource intelligent matching device based on meta-universe, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the metauniverse-based resource intelligent matching device to execute the metauniverse-based resource intelligent matching method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein that, when executed on a computer, cause the computer to perform the meta-universe based resource intelligent matching method described above.
In the technical scheme provided by the invention, initial user information of a target user in a meta universe is acquired, and a user interest distribution field set is generated; acquiring online behavior data of a target user, and performing virtual entity matching on the online behavior data to generate a plurality of virtual entities; extracting resource data from a plurality of virtual entities to obtain a resource data set; classifying the resource data set, determining the resource data type set, extracting resource configuration information from the meta universe, and generating target resource configuration information; acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model; and inputting the target resource configuration data information and the user interest distribution field set into a target resource configuration model to perform resource configuration analysis, and generating a resource configuration analysis result. According to the invention, the user requirements and the behavior mode can be better known by acquiring the initial user information of the user and acquiring the online behavior data of the user in the meta universe, so that a more personalized and optimized resource allocation scheme is provided, the user experience and satisfaction are improved, an automatic resource allocation can be realized by constructing a target resource allocation model based on historical transaction data and carrying out resource allocation analysis by utilizing a user interest distribution field set, the complicated and wrong manual intervention is avoided, and the resource allocation information is extracted for the meta universe by carrying out resource data extraction on a plurality of virtual entities and carrying out resource allocation information extraction for the meta universe based on a resource data type set, so that more intelligent and efficient resource allocation can be realized, the resource utilization rate is optimized, and the resource efficiency is improved.
Drawings
FIG. 1 is a diagram of one embodiment of a meta-universe based resource intelligent matching method in an embodiment of the present invention;
FIG. 2 is a flow chart of performing virtual entity matching on online behavior data in an embodiment of the invention;
FIG. 3 is a flowchart of extracting resource data from a plurality of virtual entities according to an embodiment of the present invention;
FIG. 4 is a flow chart of classifying a resource data set in an embodiment of the invention;
FIG. 5 is a diagram of one embodiment of a metauniverse-based resource intelligent matching system in an embodiment of the invention;
FIG. 6 is a diagram of one embodiment of a metauniverse-based resource intelligent matching device in an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a resource intelligent matching method and a related device based on a meta universe, which are used for improving the efficiency and accuracy of resource intelligent matching in the meta universe.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of a meta-universe-based resource intelligent matching method in an embodiment of the present invention includes:
s101, acquiring initial user information of a target user in a meta universe, and generating a user interest distribution field set through the initial user information;
it can be understood that the execution subject of the present invention may be a resource intelligent matching system based on metauniverse, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, initial user information of the target user in the meta universe is obtained, and common modes include user registration information, user behavior tracks, user social relations and the like. The user registration information may include information such as user's basic profile, preference settings, etc., and may be obtained through a registration page or third party authorization, etc. The user behavior track is used for recording activities such as browsing, searching and purchasing of the user by monitoring the game, social entertainment and consumption behaviors of the user in the meta universe by the server, so that a user behavior data set is generated. The social relationship of the users can acquire social network data, such as information of friends, attention, groups and the like, among the users by monitoring social interactions of the users in the meta universe. Based on the initial user information obtained, a set of user interest distribution fields may be generated using a variety of methods. One common method is to analyze and mine user behavior data by using a machine learning algorithm, and extract interest distribution characteristics of users in different fields from the user behavior data. For example, the rules and patterns in the user behavior data can be found out by using methods such as cluster analysis, classification algorithm and the like, and the fields and topics of interest to the user can be found out. Meanwhile, the user behavior data and the user social relationship data can be combined for analysis, and the interpersonal interest relationship of the user can be deduced. For some target users, the server calculates the possible interest direction through calculation by data research of groups. For example, taking a travel application as an example, behavior data such as a user browsing record, a search record, a comment record and the like can be utilized to mine aspects such as a favorite destination, a travel mode, a restaurant, a scenic spot and the like of the user. In addition, the social relationship data of the user can be combined to infer which interest points related to travel exist in the social network where the user is located.
S102, acquiring online behavior data of a target user in a meta universe, and performing virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
specifically, the collection of online behavior data of the target user in the meta universe can be achieved through various approaches. The game log, the network flow monitor and other tools are adopted to monitor the behavior and interaction data of the user in the meta universe, and the activity track of the user in the game or social media is recorded. Such data may include user behavior, actions, operational records, interactive behavior, etc., and may be stored in text, image, or other various data formats. Through the data, the server further knows the behavior characteristics of the user, so that the user demand is better understood, and better service is provided for the user. And the server needs to perform virtual entity matching on the collected online behavior data to generate a plurality of corresponding virtual entities. This requires the use of various techniques and means such as natural language processing, machine learning, etc. The virtual entity may be an object, character, event, etc., which is a virtual object created from user behavior data, representing the true identity of the user in the meta-universe. The generation process server of the virtual entity is used for identifying the behavior characteristics of the user by extracting key behaviors of the user in the meta universe and researching the behavior characteristics of the user, and the technologies of machine learning algorithm, natural language processing and the like, and generating a plurality of corresponding virtual entities by utilizing analysis and mining technologies, so that better service is provided for the user. For example, taking a social media application as an example, by collecting actions such as praise, forwarding, comment, private chat and the like of a user, social behavior characteristics of the user can be identified, and interests and demands of the user can be deduced. The server discovers a social circle in which the user is located by researching a social relation network of the user, and analyzes similar characteristics and interaction behaviors of each user in the circle. According to the data, corresponding virtual roles and scenes can be constructed, so that users can interact and communicate better, and more personified services can be provided.
S103, extracting resource data of a plurality of virtual entities to obtain a resource data set;
specifically, before extracting resource data from a plurality of virtual entities, the server classifies the virtual entities according to the types of the virtual entities. This is accomplished by analyzing and classifying the attributes, features of the virtual entities. For example, in a social media application, virtual entities may include users, posts, comments, etc., which may be categorized according to their attributes and characteristics. After classification is completed, different data extraction methods and algorithms can be adopted for different virtual entity types. The server may employ a variety of data extraction methods and techniques for different types of virtual entities. For example, for text-type entities, natural language processing techniques may be utilized to analyze and extract their content. Specifically, information such as a topic, a keyword, an entity, and the like can be extracted from the text using techniques such as keyword extraction, entity recognition, emotion analysis, and the like. For example, in a book e-commerce application, information about the author, publisher, date of publication, abstract, etc. of the book may be extracted. For image-type entities, virtual entity images may be analyzed and extracted using image processing and computer vision techniques. For example, in a clothing e-commerce application, processing such as target detection, image classification, color extraction and the like can be performed on clothing images to achieve image recognition and automatic classification of clothing, so that clothing types available for user selection are generated. For video type entities, video content of the virtual entity may be analyzed and extracted using video processing and camera computing techniques. For example, in gaming applications, video processing techniques may be utilized to analyze and extract pictures of a game, thereby providing a better gaming experience.
S104, classifying the resource data sets, determining corresponding resource data type sets, extracting resource configuration information from the meta universe based on the resource data type sets, and generating target resource configuration information;
specifically, the resource data set is classified, and the resource data set needs to be analyzed and classified according to the type and the attribute of the resource. This requires the use of a variety of algorithms and techniques such as machine learning, data mining, natural language processing, etc. By the method, different kinds of resources such as music, video, pictures, texts and the like can be extracted from the resource data set, and each type of resources is classified to determine the attribute and the characteristic of the resources. After the server determines the corresponding resource data type set, the server extracts resource configuration information of the metauniverse based on the resource data type set. This requires analysis of its distribution in the meta-universe, usage, popularity and other relevant information for each resource type. Through the analysis, the requirements and preferences of the user on different resource types can be known, and then a more personalized resource allocation scheme meeting the requirements of the user is designed according to the information. For example, in a music application, different types of music, such as popular songs, classical music, national music, etc., may be categorized. By analyzing the user's preferences for different music types, the user's musical interests and needs can be known. Meanwhile, popularity analysis can be performed on different types of music, and popularity of the different types of music is known. Based on the information, the music resource which meets the requirements and interests of the user can be provided for the user in a targeted manner, and the service with better quality can be provided. Finally, extracting the resource configuration information based on the resource data type set, and generating target resource configuration information. The server combines the resource data type set with information such as resource distribution conditions, use conditions, user demands and the like in the metauniverse to generate a personalized resource allocation scheme. In this embodiment, special algorithms and techniques, such as optimization algorithms, multi-objective decisions, etc., are typically required. Meanwhile, real-time updating and analysis are needed to be carried out on resources in the meta universe so as to ensure the high efficiency and practicability of the resource allocation scheme.
S105, acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model;
in particular, obtaining a historical transaction data set of a historical user in the meta universe generally requires passing through transaction logs, transaction data analysis tools, and the like. Such data typically includes a user's purchase record, transaction price, time of purchase, place of transaction, and the like. From this data we can learn about the user's consumption behavior, purchasing power, transaction habits, etc. in the meta universe. The server performs model construction based on a historical transaction data set, typically requiring the selection of appropriate algorithms and techniques. The process is mainly divided into two phases: data preprocessing and model construction. In the data preprocessing stage, the transaction data needs to be subjected to cleaning, extraction, normalization and other processes so as to facilitate subsequent analysis and model construction. In the model building stage, various algorithms and techniques may be used to build models, such as classification models, cluster models, association rule models, and the like. For example, in a gaming application, our server analyzes the sales of a user's game characters, game props, game accessories, etc. through historical user transaction records, and observes the user's consumption preferences and purchase strength. A resource allocation model based on user consumption habits and preferences can be constructed through which virtual resource allocation and sales are performed to better accommodate the needs and interests of the user. Finally, performing model construction based on the historical transaction data set, and generating a target resource allocation model. This requires the discovery of potential patterns and rules from historical data, and the construction of corresponding resource allocation models based on the user's needs and preferences.
S106, inputting the target resource configuration data information and the user interest distribution field set into a target resource configuration model to perform resource configuration analysis, and generating a corresponding resource configuration analysis result.
Specifically, the target resource configuration data information and the user interest distribution field set are input into a resource configuration model, and the server performs preprocessing and feature extraction on the data information. For example, text information may be analyzed and extracted using natural language processing techniques and picture information may be analyzed and extracted using computer vision techniques. And inputting the processed data into the model, and carrying out resource configuration analysis to provide a resource configuration result corresponding to the user. After input, the server may analyze the target resource configuration using a variety of algorithms and techniques. For example, a cluster analysis algorithm may be used to cluster the set of user interest distribution areas, and each user may be grouped according to the clustering result, so as to better provide a corresponding resource allocation suggestion for each user. Meanwhile, an association rule mining algorithm can be used for mining the situation that the user purchases different types of resources, so that a better resource combination scheme is provided for the user. For example, in the application of virtual forests, the interest set of a user can be divided into different fields of culture, entertainment, science and technology, etc. The interests of each user can be clustered by using a cluster analysis algorithm, and the interest distribution situation of the users is determined. After the interests of the user are clustered, corresponding virtual environment configuration suggestions can be provided for the user so as to meet the requirements and interests of the user. And finally, based on the input target resource configuration data information and the user interest distribution field set, a corresponding resource configuration analysis result can be generated. This requires processing and analyzing the input data through a resource allocation model containing a plurality of algorithms and methods, and finally obtaining a resource allocation result suitable for the user. When the result is generated, the consideration can be carried out according to different factors such as interest distribution, historical transaction records and the like of the user.
In the embodiment of the invention, initial user information of a target user in a meta universe is acquired, and a user interest distribution field set is generated; acquiring online behavior data of a target user, and performing virtual entity matching on the online behavior data to generate a plurality of virtual entities; extracting resource data from a plurality of virtual entities to obtain a resource data set; classifying the resource data set, determining the resource data type set, extracting resource configuration information from the meta universe, and generating target resource configuration information; acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model; and inputting the target resource configuration data information and the user interest distribution field set into a target resource configuration model to perform resource configuration analysis, and generating a resource configuration analysis result. According to the invention, the user requirements and the behavior mode can be better known by acquiring the initial user information of the user and acquiring the online behavior data of the user in the meta universe, so that a more personalized and optimized resource allocation scheme is provided, the user experience and satisfaction are improved, an automatic resource allocation can be realized by constructing a target resource allocation model based on historical transaction data and carrying out resource allocation analysis by utilizing a user interest distribution field set, the complicated and wrong manual intervention is avoided, and the resource allocation information is extracted for the meta universe by carrying out resource data extraction on a plurality of virtual entities and carrying out resource allocation information extraction for the meta universe based on a resource data type set, so that more intelligent and efficient resource allocation can be realized, the resource utilization rate is optimized, and the resource efficiency is improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Acquiring initial user information of a target user in a meta universe, and performing information coding on the initial user information to generate a corresponding user code;
(2) And carrying out user interest field matching on the user codes to obtain corresponding user interest distribution field sets.
Specifically, the server obtains initial user information of the target user in the meta universe, and needs to pass through various channels and tools. For example, the user's basic information such as name, sex, age, etc. may be acquired using registration information of a game or application. Meanwhile, the server discovers the interests of the user by using the interaction behaviors of the virtual worlds in the meta-universe, and knows the purchase behaviors of the user, such as purchased virtual articles or transferred virtual currency. The server encodes the information to generate a corresponding user code. The server performs user interest field matching on the user codes, and the server performs feature extraction and pattern recognition on the codes. For example, text information may be supervised and extracted using natural language processing techniques, with machine learning algorithms being utilized to construct text classification models. Meanwhile, a computer vision technology can be used for analyzing and decoding the user name and the user head portrait to obtain richer user information. By the method, the user codes and the interest fields thereof in the meta universe can be matched to obtain corresponding user interest distribution field sets. For example, in card game application, the server analyzes the collection condition of the current game prop and card of the user and the card group structure and fight record of the user in the game through the user recharging record and the transaction record, matches the user codes with the user interest field according to the information, obtains the interest distribution of the user in the fields of role playing game, strategic card game, chat social interaction and the like, and further provides personalized game configuration, game commodity, social interaction and other schemes for the user.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, acquiring online behavior data of a target user in a meta universe, and performing behavior cluster analysis on the online behavior data to generate a behavior cluster analysis result;
s202, performing behavior region analysis on the meta-universe through a behavior cluster analysis result to generate a plurality of corresponding target meta-universe regions;
s203, performing virtual entity matching on each target meta-universe area respectively to generate a plurality of corresponding virtual entities.
Specifically, the server needs to use corresponding tools and platforms to collect online behavior data of the target user in the meta-universe. For example, a game application, a social network platform, a smart home device, etc. may be used to gather behavior data of a user in a meta-universe, such as a browsing record of the user in the meta-universe, game behavior, social interactions, etc. The collected behavior data needs to be preprocessed, and behavior characteristics such as time stamps, behavior types, behavior places and the like are extracted. And finally, analyzing the behavior data through a clustering algorithm to generate a behavior clustering analysis result. The server analyzes the behavior region of the meta universe through the behavior cluster analysis result, and needs to consider factors such as geographic position, time distribution and the like of the behavior region. On the basis, behavioral region analysis can be performed according to the clustering result, and a plurality of target meta-universe regions are partitioned, so that virtual services and configuration resources can be better provided for users. For example, in a virtual city application, a server analyzes the behavior of a user in a virtual city, such as virtual shopping, virtual travel, virtual social contact, etc., through a clustering algorithm. Multiple target virtual city areas can be divided, the virtual city is divided into different areas such as business areas, recreation areas, social areas and the like according to the clustering analysis result, and when elements are configured for the different areas, the interests and the purposes of users can be better converted and met. Finally, in the process of matching the virtual entity for each target element universe region, the region can be matched with a proper virtual entity according to specific rules and description information in the region. For example, in a business area of a city center, corresponding virtual entities can be matched into high-grade brand shops, people stream interaction areas, restaurant bars and the like; in suburban amusement areas, corresponding virtual entities may be matched as theme parks, amusement rides, snack bars, etc.
In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:
s301, extracting resource types of a plurality of virtual entities based on a user interest distribution field set to obtain a plurality of corresponding resource types;
s302, extracting resource data from the meta universe based on a plurality of resource types, and generating a corresponding resource data set.
Specifically, the server extracts resource types from the plurality of virtual entities based on the user interest distribution field set, and may use a natural language processing technology and a data mining technology. Specifically, the user interest distribution field set may be first clustered, and classified into different interest fields. And extracting and matching the interest fields of the virtual entities by carrying out semantic analysis and text mining on the plurality of virtual entities. On this basis, a corresponding plurality of resource types can be obtained. For example, in a virtual forest application, a set of user interest distribution areas are clustered into three areas of interest, cultural, recreational, and scientific. The corresponding virtual entity may be a museum, theme park, smart show, etc. Through semantic analysis and text mining, the corresponding resource types can be obtained as cultural arts, recreation facilities and scientific and technological display. More virtual services and resource configurations may be provided to users depending on the type of resource. The server extracts resource data of the meta universe according to a plurality of resource types to generate a corresponding resource data set, and various technologies and means are required to be applied. For example, various data related to the resource type, such as pictures, videos, texts, etc., may be extracted from the virtual entity using computer vision techniques and data mining techniques. Meanwhile, the data can be analyzed and the characteristics are extracted by utilizing a machine learning algorithm and a deep learning algorithm, so that a corresponding resource data set is generated. For example, in a film application in a meta-universe, film data may be extracted based on a plurality of resource types. For cultural artistic movies, related information such as movie names, directors, actors and the like can be extracted; for science and technology movies, related information such as movie topics, science and technology elements and the like can be extracted; for action adventure movies, related information such as movie names, main angles, dramas and the like can be extracted. According to the information, the extraction and configuration of the movie data set can be carried out on the meta universe, and movie services which are more in line with the interests and demands of users can be provided for the users.
In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:
s401, carrying out semantic analysis on a resource data set to obtain a plurality of semantic identification information;
s402, performing data type matching through a plurality of semantic identification information to generate a resource data type set;
s403, performing data extraction algorithm matching on the resource data type set, and determining an initial data extraction algorithm;
s404, performing rule configuration on the initial data extraction algorithm to generate a target data extraction algorithm;
s405, extracting resource configuration information of the metauniverse through a target data extraction algorithm, and generating target resource configuration information.
Specifically, the server performs semantic analysis on the resource data set, and natural language processing technology or computer vision technology can be used. Specifically, text, pictures, videos and other contents in the resource data set can be extracted and converted into semantic tags through natural language understanding or image recognition technology. For example, for a movie data set, director, actors, scenario, etc. content may be extracted and semantically identified. The server performs data type matching through a plurality of semantic identification information, and can convert the semantic identification information into a corresponding resource data type set. For example, in movie data, semantic identifiers of directors, actors, drama, and the like extracted through semantic analysis may be converted into resource data types of director types, actor types, drama types, and the like. The server performs data extraction algorithm matching on the resource data type set, and needs to select according to factors such as data type characteristics and data sources. For example, an image classification algorithm may be selected to analyze and extract features from the picture data; a text classification algorithm can be selected to extract and classify the characteristics of the text data; the neural network algorithm can be selected to comprehensively analyze and analyze various data. The server performs rule configuration on the initial data extraction algorithm to generate a target data extraction algorithm. In this process, factors such as frequency and occurrence rule of various data types need to be considered, so as to extract relevant data information more accurately. The server extracts resource configuration information of the meta universe through a target data extraction algorithm, and generates target resource configuration information. For example, in a movie repository application, the server analyzes and extracts features from movie data via semantic identification information. According to semantic identification information such as movie names, directors and actors, the server extracts related data information such as movie duration, scores and ticket houses through a data extraction algorithm. By the method, the target resource configuration information can be obtained, and movie resource service which meets the requirements of users can be provided for the users.
In a specific embodiment, the process of executing step S105 may specifically include the following steps:
(1) Acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing user types of the historical users to generate a plurality of user types;
(2) Performing resource allocation weight matching on a plurality of historical users through historical transaction data based on a plurality of user types to generate resource allocation weights corresponding to each historical user;
(3) And constructing a resource allocation model through the resource allocation weight corresponding to each historical user and the historical transaction data set, and generating a target resource allocation model.
It should be noted that, the historical transaction data sets of a plurality of historical users in the meta universe are acquired, and the server is acquired by providing a program interface or directly acquiring the related transaction data on the blockchain. The user type construction is carried out on a plurality of historical users, and the server divides the historical users into different user types such as collectors, investors, tourists and the like through analysis of transaction behaviors of the historical users in metauniverse and through an algorithm or machine learning mode, so that guidance is provided for subsequent resource allocation weight matching. The method comprises the steps of carrying out resource allocation weight matching on a plurality of historical users through historical transaction data, firstly, corresponding a plurality of transaction data corresponding to each historical user to different user types, then carrying out weighting and normalization on the transaction data of the different user types through a certain algorithm to obtain the weight of each user type on various resource allocation items, and then calculating the resource allocation weight corresponding to each historical user through a weight allocation mode. The resource allocation model is constructed through the resource allocation weight corresponding to each historical user and the historical transaction data set, the historical transaction data and the resource allocation weight can be processed and trained by using machine learning and other technologies, a target resource allocation model is finally obtained, and testing and optimizing are carried out in the meta universe. For example, a server may have a plurality of historical users in a metauniverse, and may first obtain a historical transaction data set of the relevant users in the metauniverse through an interface or directly. We divide these historical users algorithmically into different user types, such as investors, collectors, etc. The server performs weight matching on the historical transactions of each type of user in the meta universe to obtain weights of different user types on various resource allocation items, and calculates the resource allocation weight corresponding to each historical user in a weight allocation mode. By taking the historical transaction data and the weights as training data, an asset configuration model can be constructed, and the asset configuration model is finally obtained by testing and optimizing in the meta universe to guide the asset configuration of different historical users. Data is collected from transaction records of the metauniverse platform, including transaction records between users and transaction records with the platform. In addition, records of digital money transactions may be obtained from blockchain or the like. After the historical user transaction data set is acquired, user type construction needs to be performed on a plurality of historical users. This server derives from analysis of the transaction actions of the historic user, such as transaction frequency, transaction amount, transaction variety, etc. By these features, users can be classified into different types. Historical transaction data is used for resource configuration weight matching. This is accomplished by classifying historical transaction data and matching it to a particular user type. By associating a particular transaction with a particular user type, a corresponding resource allocation weight for each user may be obtained. And constructing a resource allocation model based on the resource allocation weight corresponding to each historical user. This server proceeds in a number of ways, for example using machine learning algorithms and statistical models. Different methods will produce different analysis results, and the user can select the most suitable method according to the actual situation. And constructing a target resource allocation model by generating resource allocation weights corresponding to each historical user and a historical transaction data set. By analyzing the target resource allocation model, the user can learn the advantages and disadvantages of the resource allocation and make meaningful improvements thereto. For example, a social media platform may use the above-described methods to analyze its historical user data to determine different needs of different types of users for resource configurations. By identifying these needs and adjusting the configuration targeted, user satisfaction and platform performance may be improved.
In a specific embodiment, the process of performing the step of matching the resource configuration weights of the plurality of historical users through the historical transaction data may specifically include the steps of:
(1) Extracting user characteristics of a plurality of user types to generate a plurality of user characteristics;
(2) Performing data set division on historical transaction data based on a plurality of user features to generate a plurality of sub-transaction data sets;
(3) And respectively carrying out resource allocation weight calculation on each historical user through each sub-transaction data set, and generating the resource allocation weight corresponding to each historical user.
Specifically, user feature extraction is performed on multiple user types, and multiple normalization and feature extraction techniques may be employed. For example, principal component analysis and factor analysis techniques may be used to reduce and extract representative features. At the same time, data mining and machine learning algorithms may also be used to analyze useful information in the user data. After extracting the plurality of user features, the server divides the historical transaction data into a plurality of sub-transaction data sets. This server is divided in various ways, for example by time, transaction type and transaction amount. And respectively carrying out resource allocation weight calculation on each sub-transaction data set to obtain the resource allocation weight corresponding to each historical user. The particular method of calculating the resource allocation weights may be determined according to particular needs. For example, a linear regression model or a non-linear regression model based on historical transaction data and user characteristics may be used to calculate the corresponding resource allocation weights for each historical user. Meanwhile, a machine learning algorithm can be used for predicting the resource allocation weight corresponding to each historical user. For example, an e-commerce platform may use the above-described method to analyze its historical user data to determine different needs for resource configurations for different types of users. The server divides the historical transaction data into a plurality of sub-transaction data sets, for example by different commodity categories, and then calculates a resource allocation weight corresponding to each historical user for each sub-transaction data set. In this way, the user's needs can be better understood and resource allocation optimized. Behavioral characteristics such as transaction frequency and amount are extracted from transaction records, and attribute characteristics such as geographic position and age are extracted from personal information of users. By analyzing these features, users can be classified into different types, such as high-consumption users and low-consumption users. The server performs data set partitioning on the historical transaction data. This server divides the historical transaction data into a plurality of sub-transaction data sets, each sub-transaction data set containing a particular type of transaction record. For example, the transaction records of high-consumption users are divided into one sub-transaction data set and the transaction records of low-consumption users are divided into another sub-transaction data set. The server calculates the resource allocation weight of each historical user through each sub-transaction data set. This server derives from an analysis of each user's transaction record in a particular sub-transaction data set, for example by calculating the ratio of each user's transaction amount to frequency in the sub-transaction data set and taking it as the resource allocation weight for that user in that sub-transaction data set. In this way, a corresponding resource allocation weight may be generated for each user. And integrating the resource allocation weights corresponding to each historical user by the server to generate final resource allocation weights. This server is performed by means of a weighted average method or the like. For example, an e-commerce platform may use the above-described methods to analyze historical user data. For example, the users are classified into high-consumption users and low-consumption users according to the characteristics of consumption amount, consumption frequency and the like, and by analyzing each sub-transaction data set, corresponding resource allocation weights can be generated for each historical user. In this way, the e-commerce platform can provide more personalized services and recommendations for each user, thereby improving user satisfaction and platform performance.
The above describes the resource intelligent matching method based on the metauniverse in the embodiment of the present invention, and the following describes the resource intelligent matching system based on the metauniverse in the embodiment of the present invention, referring to fig. 5, an embodiment of the resource intelligent matching system based on the metauniverse in the embodiment of the present invention includes:
the acquisition module 501 is configured to acquire initial user information of a target user in a meta universe, and generate a user interest distribution field set according to the initial user information;
the matching module 502 is configured to collect online behavior data of the target user in the meta universe, and perform virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
an extracting module 503, configured to extract resource data from a plurality of virtual entities, to obtain a resource data set;
the classification module 504 is configured to classify the resource data set, determine a corresponding resource data type set, and extract resource configuration information of the meta universe based on the resource data type set, so as to generate target resource configuration information;
the construction module 505 is configured to acquire historical transaction data sets of a plurality of historical users in the meta universe, and perform model construction through the historical transaction data sets to generate a target resource configuration model;
The analysis module 506 is configured to input the target resource configuration data information and the user interest distribution field set into the target resource configuration model to perform resource configuration analysis, and generate a corresponding resource configuration analysis result.
Acquiring initial user information of a target user in a meta universe through cooperative cooperation of the components, and generating a user interest distribution field set; acquiring online behavior data of a target user, and performing virtual entity matching on the online behavior data to generate a plurality of virtual entities; extracting resource data from a plurality of virtual entities to obtain a resource data set; classifying the resource data set, determining the resource data type set, extracting resource configuration information from the meta universe, and generating target resource configuration information; acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model; and inputting the target resource configuration data information and the user interest distribution field set into a target resource configuration model to perform resource configuration analysis, and generating a resource configuration analysis result. According to the invention, the user requirements and the behavior mode can be better known by acquiring the initial user information of the user and acquiring the online behavior data of the user in the meta universe, so that a more personalized and optimized resource allocation scheme is provided, the user experience and satisfaction are improved, an automatic resource allocation can be realized by constructing a target resource allocation model based on historical transaction data and carrying out resource allocation analysis by utilizing a user interest distribution field set, the complicated and wrong manual intervention is avoided, and the resource allocation information is extracted for the meta universe by carrying out resource data extraction on a plurality of virtual entities and carrying out resource allocation information extraction for the meta universe based on a resource data type set, so that more intelligent and efficient resource allocation can be realized, the resource utilization rate is optimized, and the resource efficiency is improved.
The above fig. 5 describes the meta-universe-based resource intelligent matching system in the embodiment of the present invention in detail from the point of view of the modularized functional entity, and the following describes the meta-universe-based resource intelligent matching device in the embodiment of the present invention in detail from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of a metauniverse-based resource intelligent matching device 600 according to an embodiment of the present invention, where the metauniverse-based resource intelligent matching device 600 may generate relatively large differences due to configuration or performance, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations on the metauniverse-based resource intelligent matching device 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the metauniverse-based resource intelligent matching device 600.
The meta-universe based resource intelligent matching device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Serve, macOS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the metauniverse-based resource intelligent matching device structure shown in fig. 6 does not constitute a limitation of a metauniverse-based resource intelligent matching device, and may include more or fewer components than illustrated, or may combine certain components, or a different arrangement of components.
The invention also provides a resource intelligent matching device based on the metauniverse, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the resource intelligent matching method based on the metauniverse in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, where the instructions, when executed on a computer, cause the computer to perform the steps of the meta-universe based resource intelligent matching method.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (randomacceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments is still modified or some technical features thereof are replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The resource intelligent matching method based on the metauniverse is characterized by comprising the following steps of:
acquiring initial user information of a target user in a meta universe, and generating a user interest distribution field set through the initial user information;
acquiring online behavior data of the target user in the meta universe, and performing virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
extracting resource data from a plurality of virtual entities to obtain a resource data set;
classifying the resource data sets, determining corresponding resource data type sets, extracting resource configuration information from the meta universe based on the resource data type sets, and generating target resource configuration information;
Acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing a model through the historical transaction data sets to generate a target resource allocation model;
and inputting the target resource configuration data information and the user interest distribution field set into the target resource configuration model to perform resource configuration analysis, and generating a corresponding resource configuration analysis result.
2. The meta-universe-based resource intelligent matching method according to claim 1, wherein the obtaining initial user information of a target user in a meta-universe and generating a user interest distribution field set through the initial user information includes:
acquiring initial user information of a target user in a meta universe, and carrying out information coding on the initial user information to generate a corresponding user code;
and carrying out user interest field matching on the user codes to obtain corresponding user interest distribution field sets.
3. The meta-universe-based resource intelligent matching method of claim 1, wherein the collecting online behavior data of the target user in the meta-universe and performing virtual entity matching on the online behavior data, generating a plurality of corresponding virtual entities, comprises:
Acquiring online behavior data of the target user in the meta universe, and performing behavior cluster analysis on the online behavior data to generate a behavior cluster analysis result;
performing behavior region analysis on the meta-universe through the behavior cluster analysis result to generate a plurality of corresponding target meta-universe regions;
and respectively carrying out virtual entity matching on each target meta-universe area to generate a plurality of corresponding virtual entities.
4. The meta-universe-based resource intelligent matching method of claim 1, wherein the extracting the resource data from the plurality of virtual entities to obtain the resource data set includes:
extracting resource types from a plurality of virtual entities based on the user interest distribution field set to obtain a plurality of corresponding resource types;
and extracting resource data from the metauniverse based on the plurality of resource types, and generating a corresponding resource data set.
5. The method for intelligent matching of resources based on metauniverse according to claim 1, wherein the classifying the resource data sets, determining a corresponding resource data type set, and extracting resource configuration information of the metauniverse based on the resource data type set, generating target resource configuration information includes:
Carrying out semantic analysis on the resource data set to obtain a plurality of semantic identification information;
performing data type matching through a plurality of semantic identification information to generate a resource data type set;
performing data extraction algorithm matching on the resource data type set, and determining an initial data extraction algorithm;
performing rule configuration on the initial data extraction algorithm to generate a target data extraction algorithm;
and extracting resource configuration information from the metauniverse through the target data extraction algorithm to generate target resource configuration information.
6. The meta-universe-based resource intelligent matching method of claim 1, wherein the obtaining a historical transaction data set of a plurality of historical users in the meta-universe, and performing model construction through the historical transaction data set, generating a target resource configuration model comprises:
acquiring historical transaction data sets of a plurality of historical users in the meta universe, and constructing user types for the plurality of historical users to generate a plurality of user types;
performing resource allocation weight matching on a plurality of historical users through the historical transaction data based on a plurality of user types, and generating resource allocation weights corresponding to each historical user;
And constructing a resource allocation model through the resource allocation weight corresponding to each historical user and the historical transaction data set, and generating a target resource allocation model.
7. The meta-universe-based resource intelligent matching method according to claim 6, wherein the generating the resource allocation weight corresponding to each historical user by performing resource allocation weight matching on a plurality of historical users through the historical transaction data based on a plurality of user types comprises:
extracting user characteristics from a plurality of user types to generate a plurality of user characteristics;
performing data set division on the historical transaction data based on a plurality of user characteristics to generate a plurality of sub-transaction data sets;
and respectively carrying out resource allocation weight calculation on each historical user through each sub-transaction data set to generate resource allocation weights corresponding to each historical user.
8. The resource intelligent matching system based on the metauniverse is characterized by comprising:
the acquisition module is used for acquiring initial user information of a target user in the meta universe and generating a user interest distribution field set through the initial user information;
The matching module is used for collecting online behavior data of the target user in the meta universe, and carrying out virtual entity matching on the online behavior data to generate a plurality of corresponding virtual entities;
the extraction module is used for extracting the resource data of the plurality of virtual entities to obtain a resource data set;
the classification module is used for classifying the resource data sets, determining corresponding resource data type sets, extracting resource configuration information from the meta universe based on the resource data type sets and generating target resource configuration information;
the construction module is used for acquiring historical transaction data sets of a plurality of historical users in the meta universe, constructing a model through the historical transaction data sets and generating a target resource configuration model;
and the analysis module is used for inputting the target resource configuration data information and the user interest distribution field set into the target resource configuration model to carry out resource configuration analysis and generating a corresponding resource configuration analysis result.
9. The resource intelligent matching device based on the metauniverse is characterized by comprising: a memory and at least one processor, the memory having instructions stored therein;
The at least one processor invoking the instructions in the memory to cause the metauniverse-based resource intelligent matching device to perform the metauniverse-based resource intelligent matching method of any one of claims 1-7.
10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the meta-universe based resource intelligent matching method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310689139.0A CN116595398A (en) | 2023-06-12 | 2023-06-12 | Resource intelligent matching method and related device based on meta universe |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310689139.0A CN116595398A (en) | 2023-06-12 | 2023-06-12 | Resource intelligent matching method and related device based on meta universe |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595398A true CN116595398A (en) | 2023-08-15 |
Family
ID=87606333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310689139.0A Pending CN116595398A (en) | 2023-06-12 | 2023-06-12 | Resource intelligent matching method and related device based on meta universe |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595398A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349484A (en) * | 2023-12-06 | 2024-01-05 | 四川物通科技有限公司 | Virtual-real fusion method and system based on meta universe |
| CN117392352A (en) * | 2023-12-11 | 2024-01-12 | 南京市文化投资控股集团有限责任公司 | Model modeling operation management system and method for meta universe |
| CN117519486A (en) * | 2024-01-02 | 2024-02-06 | 虚拟现实(深圳)智能科技有限公司 | Meta-universe digital person interaction method, device, equipment and storage medium |
-
2023
- 2023-06-12 CN CN202310689139.0A patent/CN116595398A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117349484A (en) * | 2023-12-06 | 2024-01-05 | 四川物通科技有限公司 | Virtual-real fusion method and system based on meta universe |
| CN117349484B (en) * | 2023-12-06 | 2024-02-27 | 四川物通科技有限公司 | Virtual-real fusion method and system based on meta universe |
| CN117392352A (en) * | 2023-12-11 | 2024-01-12 | 南京市文化投资控股集团有限责任公司 | Model modeling operation management system and method for meta universe |
| CN117392352B (en) * | 2023-12-11 | 2024-02-13 | 南京市文化投资控股集团有限责任公司 | Model modeling operation management system and method for meta universe |
| CN117519486A (en) * | 2024-01-02 | 2024-02-06 | 虚拟现实(深圳)智能科技有限公司 | Meta-universe digital person interaction method, device, equipment and storage medium |
| CN117519486B (en) * | 2024-01-02 | 2024-03-29 | 虚拟现实(深圳)智能科技有限公司 | Meta-universe digital person interaction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210157869A1 (en) | Information sending method, apparatus and system, and computer-readable storage medium | |
| CN116595398A (en) | Resource intelligent matching method and related device based on meta universe | |
| CN103038769B (en) | System and method for content to be directed into social network engine user | |
| Isson | Unstructured data analytics: how to improve customer acquisition, customer retention, and fraud detection and prevention | |
| Selke et al. | Pushing the boundaries of crowd-enabled databases with query-driven schema expansion | |
| US20230153870A1 (en) | Unsupervised embeddings disentanglement using a gan for merchant recommendations | |
| CN106062730A (en) | Systems and methods for actively composing content for use in continuous social communication | |
| Suh et al. | A prediction model for the purchase probability of anonymous customers to support real time web marketing: a case study | |
| CN109785064A (en) | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion | |
| Sohrabi et al. | A predictive model of tourist destinations based on tourists' comments and interests using text analytics | |
| Bhattacharjee et al. | Identifying the causal relationship between social media content of a Bollywood movie and its box-office success-a text mining approach | |
| Jia et al. | Multi-modal learning for video recommendation based on mobile application usage | |
| US20210103925A1 (en) | Feature subspace isolation and disentanglement in merchant embeddings | |
| KR20170107868A (en) | Method and system to recommend music contents by database composed of user's context, recommended music and use pattern | |
| Liu et al. | Building effective short video recommendation | |
| Kang et al. | A personalized point-of-interest recommendation system for O2O commerce | |
| CN112036987B (en) | Method and device for determining recommended commodity | |
| KR102119518B1 (en) | Method and system for recommending product based style space created using artificial intelligence | |
| KR102449602B1 (en) | Apparatus and method for processing information related to product in multimedia contents | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device | |
| Sun | Music Individualization Recommendation System Based on Big Data Analysis | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN112035740A (en) | Project use duration prediction method, device, equipment and storage medium | |
| Gonçalves et al. | Improving the tourists’ experience | |
| Sowmya et al. | A Brief Survey on Recommendation System for a Gradient Classifier based Inadequate Approach System |
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 |