CN116510318A - Automatic group office method, system, electronic equipment and storage medium for physical activities - Google Patents
Automatic group office method, system, electronic equipment and storage medium for physical activities Download PDFInfo
- Publication number
- CN116510318A CN116510318A CN202310379213.9A CN202310379213A CN116510318A CN 116510318 A CN116510318 A CN 116510318A CN 202310379213 A CN202310379213 A CN 202310379213A CN 116510318 A CN116510318 A CN 116510318A
- Authority
- CN
- China
- Prior art keywords
- group office
- model
- group
- office
- decision
- 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 56
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000037081 physical activity Effects 0.000 title claims description 4
- 230000000694 effects Effects 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 230000000977 initiatory effect Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 43
- 238000004590 computer program Methods 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 19
- 230000000386 athletic effect Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 13
- 238000013523 data management Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000011156 evaluation Methods 0.000 description 19
- 238000002360 preparation method Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000001737 promoting effect Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction 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
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- 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
- A63F13/70—Game security or game management aspects
- A63F13/79—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories
- A63F13/795—Game security or game management aspects involving player-related data, e.g. identities, accounts, preferences or play histories for finding other players; for building a team; for providing a buddy list
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/50—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game characterized by details of game servers
- A63F2300/55—Details of game data or player data management
- A63F2300/5546—Details of game data or player data management using player registration data, e.g. identification, account, preferences, game history
- A63F2300/5566—Details of game data or player data management using player registration data, e.g. identification, account, preferences, game history by matching opponents or finding partners to build a team, e.g. by skill level, geographical area, background, play style
-
- 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
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/80—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game specially adapted for executing a specific type of game
- A63F2300/8005—Athletics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an automatic grouping method for sports activities, which comprises the following steps: initiating a group office invitation to a user based on the group office decision; monitoring whether the group office task based on the group office invitation is successful; if the group office task is successful, adding 1 to a group office model grading value for generating the group office decision; if the group office task is unsuccessful, subtracting 1 from a group office model score value for generating the group office decision; sorting the plurality of group office models based on the score values of the group office models; the group office model with the scoring value smaller than a preset threshold value is listed as a model to be optimized; and (3) the group office model with the scoring value larger than or equal to the preset threshold value is listed as an available model, and the available model is called to generate the next group office decision. The method, the system, the electronic equipment and the storage medium can bring the artificial intelligence technology into play under the application scene of intelligent sports, and improve the stadium operation performance.
Description
Technical Field
The application relates to the field of intelligent management of sports activities, in particular to an automatic office organization method, an automatic office organization system, electronic equipment and a storage medium for sports activities.
Background
Under the technological explosion wave, the concept of intelligent sports has been developed. The intelligent sports is the intelligent management, flow and operation mode which are realized by integrating advanced technologies into the traditional sports industry. Artificial intelligence, which is a leading-edge technological force, plays a vital role in big data calculation and analysis. However, how to apply artificial intelligence technology to daily operation management of stadiums to improve the operation performance of stadiums has been considered as an important theoretical branch of the performance of artificial intelligence technology in intelligent sports, but has not been effectively implemented.
Disclosure of Invention
Based on the above, the embodiments of the present application provide an automatic office organization method, system, electronic device and storage medium for sports activities, so that the artificial intelligence technology can be used for playing efficacy in the application scenario of intelligent sports, and the stadium operation performance is improved. The technical scheme is as follows:
according to one aspect of embodiments of the present application, there is provided an automated group office method of athletic activity, the method comprising: initiating a group office invitation to a user based on the group office decision; monitoring whether the group office task based on the group office invitation is successful; if the group office task is successful, adding 1 to the group office model grading value for generating the group office decision; if the group office task is unsuccessful, subtracting 1 from the group office model score value for generating the group office decision; sorting the plurality of group office models based on the score values of the group office models; the group office model with the scoring value smaller than a preset threshold value is listed as a model to be optimized; the group office model with the scoring value larger than or equal to the preset threshold value is listed as an available model; and calling the available model to generate a next group office decision.
In an exemplary embodiment, the monitoring is based on whether the group office task invited by the group office is successful, and specifically includes: monitoring whether the user generates a site reservation order based on the group of office invitations; if the site reservation order is generated, judging that the group office task based on the group office invitation is successful; if the site reservation order is not generated, the task of the group office based on the invitation of the group office is judged to be unsuccessful.
In an exemplary embodiment, when the score value of the set of office models is smaller than the preset threshold, after the set of office models are listed as the models to be optimized, the method further includes: analyzing probability distribution of the model to be optimized by a poisson distribution statistical method; based on the probability distribution of the model to be optimized, adjusting the influence factors of each input element of the model to be optimized to form an optimized group office model; and taking the optimized group office model as a group office algorithm model, and obtaining the available model through retraining.
In an exemplary embodiment, the input element includes user data and venue data, and the set of office decision generation method includes: carrying out data management on the user data to obtain a training set of consumption habits of the user on the physical activities; performing data management on the venue data to obtain the venue data training set; inputting the user data training set and the venue data training set into the set of office algorithm models, and training the set of office algorithm models to obtain the trained set of office models; the set of office decisions is generated based on the set of office models.
In an exemplary embodiment, the user data training set and the venue data training set are input into the set of office algorithm models, and the set of office algorithm models are trained to obtain the trained set of office models, which specifically includes: constructing the initialization group office algorithm model based on a fuzzy comprehensive analysis method; configuring the influence factors of the initialized group office algorithm model, wherein the influence factors comprise the influence factors of each input element of the initialized group office algorithm model configured based on expert experience; the user data training set and the venue data training set are input into the set of office algorithm models, and the set of office algorithm models are trained to obtain the trained set of office models.
In an exemplary embodiment, the user data includes one or more of user registration information, user consumption habits, and user interpersonal relationships; the venue data includes one or more of venue operation data, environmental data, price data, and offer data.
In an exemplary embodiment, after sorting the plurality of group office models in order of high and low score values based on the group office models, the method further includes: setting the group office model with the highest scoring value as a default group office model; setting other group office models with the score value higher than the preset threshold value and not the default group office model as strategy group office models; and selecting to generate a group office decision based on the default group office model or generating the group office decision based on the strategy group office model according to the characteristic preference of the user end of the group office invitation to be sent.
According to one aspect of embodiments of the present application, there is provided an automated group office system for sporting activities, comprising: the group office invitation issuing module is used for initiating group office invitation to the user based on the group office decision; the group office task monitoring module is used for monitoring whether the group office task based on the group office invitation is successful or not; if the group office task is successful, adding 1 to the group office model grading value based on the group office decision; if the group office task is unsuccessful, subtracting 1 from the group office model grading value based on the group office decision; the group office effect feedback module is used for sequencing the plurality of group office models based on the score value of the group office models in high-low order; the group office model with the scoring value smaller than or equal to a preset threshold value is listed as a model to be optimized; the group office model with the scoring value larger than the preset threshold value is listed as an available model; and the group office decision generation module is used for preferentially calling the available model to generate the next group office decision.
According to an aspect of an embodiment of the present application, there is provided an electronic device including: at least one processor, at least one memory, and at least one communication bus, wherein the memory stores a computer program thereon, the processor reads the computer program in the memory through the communication bus; the computer program when executed by the processor implements the athletic activity automatic grouping method as described above.
According to an aspect of the embodiments of the present application, there is provided a storage medium including: on which a computer program is stored which, when being executed by a processor, implements the automatic grouping method for sports activities as described above.
The beneficial effects that this application provided technical scheme brought are:
1. according to the technical scheme, the historical data of the user elements and the venue operation elements are trained through analyzing and promoting the elements of the group bureau, including the user elements and the venue operation elements, the group bureau algorithm model is trained to generate the group bureau model, whether the group bureau tasks are successful or not is monitored to serve as scoring basis for the group bureau model performance, the combination of the user elements and the venue operation elements is generated to score a plurality of group bureau models, and therefore an available model is selected, suitable sport partners and suitable venues are searched for users, and venue reservation is facilitated.
2. The method comprises the steps of adjusting influence factors of input elements of a model to be optimized based on probability distribution of the model to be optimized to form an optimized group office model; and taking the optimized group office model as a group office algorithm model, and obtaining a usable model through retraining. Thereby increasing the number of available models to accommodate the diverse contingent conditions contributing group office possibilities.
3. After sorting the plurality of group office models according to the high-low order of the scoring values of the group office models, setting the group office model with the highest scoring value as a default group office model; setting other group office models with scoring values higher than a preset threshold and not the default group office model as strategy group office models; and selecting to generate a group decision based on a default group office model or generating a group decision based on a strategy group office model according to the characteristic preference of the user end of the group office invitation to be sent. Firstly, effectively managing all available models, so as to push out an optimal group office model as a default group office model, thereby improving the generalization capability of the system; further, by scoring each round, the default group office model is iterated continually to obtain the sustainable self-optimizing capability of the system.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a schematic illustration of an environment in which an automated method of organizing athletic activities is performed in accordance with the present application;
FIG. 2 is a flow chart of an automated group office method of athletic activity, according to an example embodiment;
FIG. 3 is a flowchart illustrating a method of retraining a model to be optimized to generate a usable model, according to an example embodiment;
FIG. 4 is a flowchart illustrating a group office decision generation method according to an exemplary embodiment;
FIG. 5 is a flowchart illustrating a method for constructing the initial group office algorithm model using fuzzy comprehensive evaluation and generating a group office model based on the initial group office algorithm model, according to an exemplary embodiment;
FIG. 6 is a schematic diagram of an automated group office system for athletic activity, according to an example embodiment
FIG. 7 is a schematic diagram of a server according to an exemplary embodiment;
fig. 8 is a hardware configuration diagram of an electronic device, which is shown according to an exemplary embodiment.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of illustrating the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
As described above, how to utilize the data analysis capability of the artificial intelligence technology, timely mine the potential team sport demands of the user, and find suitable team teammates for the user, thereby promoting the establishment of the team sport, improving the setting rate for stadium operating the sports, increasing the operation performance, and becoming the technical problem that needs to be solved in the intelligent sports field at present.
For this reason, the automatic grouping method for sports activities provided by the present application can effectively mine the potential requirement of user for grouping sports, and accordingly, the automatic grouping method for sports activities is suitable for an automatic grouping device for sports activities, which can be deployed on an electronic device, and the electronic device can be a computer device configured with von neumann architecture, and the computer device can be a desktop computer, a notebook computer, a server, and the like.
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
FIG. 1 is a schematic diagram of an implementation environment involved in an automated grouping method for athletic activity. It should be noted that this implementation environment is only one example adapted to the present invention and should not be considered as providing any limitation to the scope of use of the present invention.
The implementation environment includes a collection end 110a at the user end, a collection end 110b at the venue end, and a service end 130.
Specifically, the collection terminal 110a of the user terminal may be an electronic device or an embedded program with at least one or more data capabilities of collecting data, audio and video of the user terminal, which is not limited herein. The collection terminal 110b at the venue terminal may be an electronic device or an embedded program with at least one or more data capabilities of collecting the operation data of the venue data center, the files such as the incoming data of the venue environmental sensor, and the audio and video capabilities, which are not particularly limited herein.
The server 130 may be electronic devices such as a desktop computer, a notebook computer, a tablet computer, a server, or a computer device cluster formed by a plurality of servers, or even a cloud computing center formed by a plurality of servers. The service side 130 may be configured to provide services such as AI computation, push messaging, etc., for example, background services including, but not limited to, providing services for training a group office model, optimizing, and providing push group office invitations.
The server 130 establishes network communication connection with the collection end 110a of the user end and the collection end 110b of the venue end in advance in a wired or wireless mode, and data transmission between the server 130 and the collection end 110a of the user end and the collection end 110b of the venue end is realized through the network communication connection. The data transmitted includes, but is not limited to: user terminal data, venue management data, and the like.
Through the interaction between the collection end 110a of the user end and the collection end 110b of the venue end and the server 130, the collection end 110a of the user end and the collection end 110b of the venue end collect data for training the group office model from the user end equipment and the venue data storage equipment and/or the sensor respectively and send the data to the server 130, and the server 130 processes the acquired data for training the group office model to obtain the group office model and generates a group office decision through the group office model.
Referring to fig. 2, an embodiment of the present application provides an automated method for organizing sports activities. The method is suitable for deployment on an electronic device.
In the following method embodiments, for convenience of description, an execution body of each step of the method is taken as an example of a system for executing the method; in addition, in order to facilitate understanding and imagining the application scenario of the present solution by those skilled in the art, the following technical gist will be further described by taking badminton as an example, but this is not a specific limitation.
As shown in fig. 2, the method may include the steps of:
step 710: initiating a group office invitation to a user based on the group office decision;
specifically, the system generates a group decision at the server, wherein the group decision is generated by calling a group model to calculate based on the data to be measured of the system based on the group requirement; the group office decision sends out group office invitation to the user side of registered users in the system according to the number of the demand people of the two opposing sides of the sports. For example, in the case of badminton, the number of people in need of both countermeasures includes: in the case of single-click, two people are involved; in the case of double-click, four people are involved; in the case of mixed double beat: four people, but sex is required as an influencing factor, and in addition, the success of the task of the multi-person group bureau is possibly promoted. Of course, one possible implementation is; in order to improve the success rate of the group office task, the system can send out the group office invitation at the same time by taking the number of people with the highest requirement greater than or equal to the sports as the reference. And judging whether the number of users who accept the invitation of the same group office reaches the group office required number or not according to the minimum required number of the sports. If the number of group office demands is reached, the group office is determined to be a reserved group office for the specific group user, and further, the user can operate on the user side, so as to confirm whether to accept the group office invitation.
Step 720: monitoring whether the group office task based on the group office invitation is successful; if the group office task is successful, adding 1 to the group office model grading value for generating the group office decision; if the group office task is unsuccessful, subtracting 1 from the group office model score value for generating the group office decision;
specifically, for a particular user who has reached a preparation group, the system needs to further monitor whether the group task of the preparation group is ultimately successful, i.e., determine whether the preparation group has translated into offline sports based on participation of a plurality of members of the preparation group. If the system monitors off-line sports which is participated by a plurality of members of the preparation group office, the system judges that the group office task is successful, and the group office model scoring value for generating the group office decision is added with 1. If the system does not monitor the offline sports which is participated by the majority of members of the preparation group office, the group office task is judged to be unsuccessful, and the group office model score value for generating the group office decision is subtracted by 1. For example, if the group office subscriber of the group preparation group office is four; the system continues to monitor whether the four users of the preliminary team are performing the athletic activity based on the time and place team in the team invitation. If only three persons participate in the sports based on the group invitation based on the time and place in the group invitation, the system still judges that the group task is successful. Thereafter, based on this, a score value of 1 is added to the group office model that generated the group office decision. If only less than two users of the four users based on the set of preliminary group bureaus participate in developing the sports based on the time and place group bureaus in the group bureau invitation, the system judges that the task of the group bureau is unsuccessful, and the scoring value of the group bureau model for generating the group bureau decision is subtracted by 1 in view of the fact.
Step 730: sorting the plurality of group office models based on the score values of the group office models;
factors that contribute to success of the group task may be numerous, including user data at the customer site, such as: user basic information, consumption habits of users, interpersonal relationships of users and the like; venue data at venue: for example, marketing strategies for venues (e.g., price premium intervals, time slot premium intervals), venue operational data (e.g., environmental monitoring data for venues), and the like; therefore, firstly, the system needs to collect user data of the user terminal and venue data of the venue terminal as a training set of the group office algorithm model. Generating a plurality of group office models through training of the group office algorithm model; for example, user basic information, user consumption habits, venue marketing strategies, venue operation data may be weighted according to a set of specific weights, thereby obtaining a set of office models; weighting according to another group of specific weights to obtain another group of office models; in addition, other preferential marketing elements can be added to generate other group office models. In an exemplary embodiment, the user data includes one or more of user registration information, user consumption habits, and user interpersonal relationships; the venue data includes one or more of venue operation data, environmental data, price data, and offer data. In addition, the system can also evaluate the data quantity of the user data and the venue data, and judge whether the user data and the venue data need to be subjected to characteristic engineering in advance according to the demand quantity of the training set so as to obtain training data capable of meeting the training and testing demands.
Setting a scoring value attribute for the generated group office model, and scoring the performance of the group office model according to whether the group office decision generated by the group office model each time promotes successful completion of the group office task; and sorting all the group office models according to the score values of the group office models. One possible implementation is to accumulate the scoring values of the group office model through multiple rounds of group office decision pushing so as to observe the performance of the decision computing capacity of the group office model; and sorting the group office models according to the score values of the group office models so as to screen out the group office models with better decision computing capacity and the group office models with poor decision computing capacity.
Step 740, the group office model with the scoring value smaller than the preset threshold value is listed as the model to be optimized; the group office model with the scoring value larger than or equal to the preset threshold value is listed as an available model;
specifically, a scoring value for evaluating the decision expressive force of a group office model to meet the service requirement is preset as a preset threshold according to expert experience; when the scoring value of one group office model is smaller than a preset threshold value, the scoring value is determined as the model to be optimized. The group office model as the model to be optimized is retrained to obtain an optimized group office model. And those group office models with score values greater than or equal to a preset threshold will be identified as available models. The subsequently generated group office decisions will come primarily from these available models. In general, according to the difficulty of the sports office, a proper preset threshold is selected, and on one hand, various office element combinations are provided as far as possible for selection; on the other hand, the generalization capability of each group office model can be ensured. Thus, one possible implementation is to set the preset threshold Th to:
Vmax is the scoring value of the group office model with the highest scoring value;
vmin is the scoring value of the group office model with the lowest scoring value;
g is a value range obtained through expert experience, and can also be a value range obtained through data modeling;
one possible implementation is: g is set to be between 0.4 and 0.6.
Step 750, calling the available model to generate a next group office decision;
specifically, one group office model is selected from all group office models (namely available models) with the grading values larger than a preset threshold value and used for generating the next group office decision. One possible implementation is: and matching all available models according to the consumption preference of the user, so as to select a group office model with the most possibility of successful group office and generate the next group office decision.
In an exemplary embodiment, after sorting the plurality of group office models in order of high and low score values based on the group office models, the method further includes: the group office model with the highest scoring value is set as a default group office model. And setting other group office models with the score value higher than the preset threshold and not the default group office model as strategy group office models. And selecting to generate a group office decision based on the default group office model or generating the group office decision based on the strategy group office model according to the characteristic preference of the user end of the group office invitation to be sent. One possible implementation is: the system judges whether the last office task of the user end is successfully completed, if so, the office model corresponding to the office decision of the last office task is used as the office model which is most likely to be successfully completed, and is used for generating the next office decision; if the system monitors that the user fails to group the office for a plurality of times, the default group office model is selected to generate the next group office decision.
In an exemplary embodiment, the method for monitoring whether the group office task based on the group office invitation is successful specifically comprises the following steps:
step 310: monitoring whether the user generates a site reservation order based on the group of office invitations;
specifically, the system may create a monitoring task at the server. After the group office invitation is accepted by a sufficient number of users, a preparation group office is formed; the system queries whether a venue reservation order is generated for a venue corresponding to the ready group office based on the ready group office. In one possible implementation manner, the system may read the operation data of the venue service end in a manner of periodically polling the venue service end, and query the venue reservation condition based on the time and place of the reserved group office as a query key, so as to determine whether the reserved group office completes the task of the lifetime group office.
Step 320: if the site reservation order is generated, judging that the group office task based on the group office invitation is successful; if the site reservation order is not generated, judging that the group office task based on the group office invitation is unsuccessful;
specifically, if a reservation order of a venue is generated, the achievement of the reservation order transaction of the venue is considered to be facilitated based on the set of office decisions, and therefore, a scoring value of a set office model for generating the set of office decisions is added with 1 to evaluate the accuracy of the decision calculation of the set office model. If the reservation order of the venue is not generated, the reservation order transaction of the venue is considered to be not achieved based on the set of office decisions, and therefore, the scoring value of the set of office models for generating the set of office decisions is subtracted by 1 to evaluate the accuracy of the decision calculation of the set of office models.
Referring to fig. 3, fig. 3 is a flowchart of a method for retraining a model to be optimized to generate a usable model;
when the scoring value of the set of office models is smaller than the preset threshold value, after the set of office models are listed as models to be optimized, the method further comprises:
step 410: analyzing probability distribution of the model to be optimized by a poisson distribution statistical method;
poisson distribution statistics is a method used to count discrete probability distributions. Definition of poisson distribution: if the probability of occurrence of random event A is P, n independent tests are performed, and k times happen to occur, the corresponding probability can be calculated by using the formula:
in the case of the present application, when events of group office success occur randomly and independently at a fixed average rate, then the number or number of occurrences of this time per unit time approximately follows the poisson distribution. Therefore, by collecting the group office decisions generated by the group office model for many times, mathematical modeling is performed on whether the user successfully guides the consumption behavior (namely whether the consumption behavior is converted into a site reservation order) based on the group office decisions through a Poisson distribution algorithm, so that the influence factors of each input element of the model on the occurrence probability of the successful event of the group office are analyzed.
Step 420: based on the probability distribution of the model to be optimized, adjusting the influence factors of each input element of the model to be optimized to form an optimized group office model;
specifically, euclidean distance between the model to be optimized and the available model on probability distribution is analyzed, and each input element of the model to be optimized is adjusted in a data simulation mode. One possible embodiment includes: and finding out key input elements, and performing parameter adjustment on influence factors of the input elements to reduce Euclidean distance between the model to be optimized and the available model, so that probability distribution of the model to be optimized approximates to the available model. Thus, an optimized group office model can be obtained.
Step 430: taking the optimized group office model as a group office algorithm model, and retraining to obtain the available model;
specifically, the optimized group office model adjusted by the poisson distribution statistical method belongs to rough parameter adjustment on the influence factors of all input elements, and a more ideal decision effect cannot be achieved. Therefore, training by machine learning is required to verify the fit of the set of office models. Therefore, the optimized office model is required to be used as an office algorithm model to be trained again so as to accurately adjust the influence factors of the optimized office model, so that the optimized office model becomes a usable model.
Referring to fig. 4, in an exemplary embodiment, the set of office decision generation methods includes:
step 510: performing data management on the user data to obtain a training set of the user data;
step 520: performing data management on venue data to obtain a venue data training set;
of course, if a machine learning algorithm with supervised learning is selected as the set of office algorithm models, then the scoring values of the training set of user data and the training set of venue data need to be annotated.
Step 530: inputting the user data training set and the venue data training set into the set of office algorithm models, and training the set of office algorithm models to obtain the trained set of office models;
step 540: generating the set of office decisions based on the set of office models;
the step 510 and the step 520 have no sequence, and may be performed on user data first or stadium data first; or simultaneously adopting a multithreading parallel processing mode to treat the user data and the venue data. The main tasks of data management here include: data cleaning, feature engineering (optional) and data labeling; the data needs to be cleaned because there may be non-target data, invalid data, and spurious data with respect to the collected data, and thus the original data needs to be filtered. Of course, in addition to filtering the data, denoising, deduplication, etc. are also required to obtain the desired data set.
Of course, if the estimated data amount is insufficient, the data can be subjected to feature engineering, so that a training set of the set of office algorithm models is obtained, and a certain proportion of data is randomly extracted from the training set to serve as a verification set. Feature engineering is able to convert raw data into features.
In addition, referring to fig. 5, in an exemplary embodiment, the initialization cluster algorithm model is constructed based on a fuzzy synthetic analysis method, and a cluster model is generated based on the initialization cluster algorithm model. The fuzzy comprehensive evaluation method is a method of comprehensively determining an event for a certain purpose in consideration of the influence of multiple elements in a fuzzy environment.
Specifically, the method for constructing the initialization group office algorithm model by using the fuzzy comprehensive evaluation method and generating the group office model based on the initialization group office algorithm model comprises the following steps:
step 610: establishing an input element set for comprehensive evaluation;
the input element set is a common set composed of various input elements affecting the evaluation object as elements. Generally denoted by U, u= { undefined U1, U2, … … un }, where element U i represents the i-th input element affecting the evaluation object. Specifically, according to expert experience, the possible elements which promote successful completion of the group task are analyzed, and the possible elements are received into the input element set of the comprehensive evaluation.
Step 620: establishing a scoring set for comprehensive evaluation;
the evaluation set is a set formed by various results possibly made by an evaluator on an evaluation object, and is represented by different grades, comments or numbers according to the needs of actual situations. Generally denoted by V, v= { undefined V1, V2, … … vn }, where the element vj represents the j-th evaluation result. One possible implementation is to represent the performance of each group office model with a score value. Of course, another possible implementation is to represent the performance of each group office model by a best, good, medium, and bad.
Step 630: configuring the influence factors of the initialized group office algorithm model, wherein the influence factors comprise the influence factors of each input element of the initialized group office algorithm model configured based on expert experience;
in the evaluation operation, the importance degree of each input element is different, and for this purpose, each input element ui is given a weight a1, and the fuzzy set of the weight set of each input element is denoted by a: a= { undefined a1, a2, and (3) an. Specifically, a fuzzy set of influence factor sets of each input element is determined, wherein the influence factors can be expressed as weight values of the input elements; in general, in the initialization stage, it is necessary to set the weight value of each input element according to expert experience. And, during subsequent training and verification, the best fit is achieved by debugging. Expert experience as referred to herein includes, but is not limited to, operators who are long-term in stadium operations, administrators who are long-term in sports industry management, marketers who are long-term in sports market business operations, and the like.
Step 640: performing fuzzy evaluation on single input elements to obtain an evaluation matrix;
if the membership degree of the ith element in the input element set U to the 1 st element in the evaluation set V is ri1, the result of evaluating the ith element single input element is represented as a fuzzy set: ri= { undefined Ri1, ri2, the terms, rim, with m single input element evaluation sets R1, R2, rn is a row composition matrix Rn m, which is called a fuzzy comprehensive evaluation matrix. One possible implementation is: and carrying out fuzzy evaluation on the single input element by means of expert experience to form an evaluation matrix.
Step 650: constructing a comprehensive evaluation model, and taking the comprehensive evaluation model as an initialization group bureau algorithm model;
after the single input element judgment matrix R and the input element weight vector a are determined, the blur vector a on U is changed to the blur vector B on V by a blur change, i.e. b=a1n×rnn= { undefinedb1, b2. ·. Bm }.
Step 660: training the set of office algorithm models;
and inputting the user data training set and the venue data training set into the group office algorithm model, and training the group office algorithm model to obtain a trained group office model.
Of course, in another possible implementation, the decision tree-based integrated algorithm GBDT may also be selected as the initializing group office algorithm model for training.
In addition, referring to fig. 6, another embodiment of the present application provides an automated team system for athletic activities, comprising:
group office invitation issuing module 810: for initiating a group office invitation to the user based on the group office decision;
group office task monitoring module 820: for monitoring whether the group office task based on the group office invitation is successful; if the group office task is successful, adding 1 to the group office model grading value based on the group office decision; if the group office task is unsuccessful, subtracting 1 from the group office model grading value based on the group office decision;
the group office effect feedback module 830: the method comprises the steps of sorting a plurality of group office models based on the order of the scoring values of the group office models; the group office model with the scoring value smaller than or equal to a preset threshold value is listed as a model to be optimized; the group office model with the scoring value larger than the preset threshold value is listed as an available model;
the office decision generation module 840 is configured to preferentially invoke the available model to generate a next office decision.
In summary, the beneficial effects brought by the technical solutions provided in the embodiments of the present application include: 1. according to the technical scheme, the historical data of the user elements and the venue operation elements are trained through analyzing and promoting the elements of the group bureau, including the user elements and the venue operation elements, the group bureau algorithm model is trained to generate the group bureau model, whether the group bureau tasks are successful or not is monitored to serve as scoring basis for the group bureau model performance, the combination of the user elements and the venue operation elements is generated to score a plurality of group bureau models, and therefore an available model is selected, suitable sport partners and suitable venues are searched for users, and venue reservation is facilitated. 2. The method comprises the steps of adjusting influence factors of input elements of a model to be optimized based on probability distribution of the model to be optimized to form an optimized group office model; and taking the optimized group office model as a group office algorithm model, and obtaining a usable model through retraining. Thereby increasing the number of available models to accommodate the diverse contingent conditions contributing group office possibilities. 3. After sorting the plurality of group office models according to the high-low order of the scoring values of the group office models, setting the group office model with the highest scoring value as a default group office model; setting other group office models with scoring values higher than a preset threshold and not the default group office model as strategy group office models; and selecting to generate a group decision based on a default group office model or generating a group decision based on a strategy group office model according to the characteristic preference of the user end of the group office invitation to be sent. Firstly, effectively managing all available models, so as to push out an optimal group office model as a default group office model, thereby improving the generalization capability of the system; further, by scoring each round, the default group office model is iterated continually to obtain the sustainable self-optimizing capability of the system.
Fig. 7 is a schematic diagram of a server according to an exemplary embodiment. The server is adapted to store and process an automated grouping method of sports activities according to the above embodiments.
It should be noted that this server is only one example adapted to the present application, and should not be construed as providing any limitation on the scope of use of the present application. Nor should the server be construed as necessarily relying on or necessarily having one or more of the components of the exemplary server 2000 illustrated in fig. 7.
The hardware structure of the server 2000 may vary widely depending on the configuration or performance, as shown in fig. 7, the server 2000 includes: a power supply 210, an interface 230, at least one memory 250, and at least one central processing unit (CPU, central Processing Units) 270.
Specifically, the power supply 210 is configured to provide an operating voltage for each hardware device on the server 2000.
The interface 230 includes at least one wired or wireless network interface 231 for interacting with external devices. Of course, in other examples of adaptation of the present application, the interface 230 may further include at least one serial-parallel conversion interface 233, at least one input-output interface 235, and at least one USB interface 237, as shown in fig. 7, which is not specifically limited herein.
The memory 250 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, where the resources stored include an operating system 251, application programs 253, and data 255, and the storage mode may be transient storage or permanent storage.
The operating system 251 is used for managing and controlling various hardware devices and applications 253 on the server 2000 to implement the operation and processing of the massive data 255 in the memory 250 by the central processing unit 270, which may be Windows server, mac OS XTM, unixTM, linuxTM, freeBSDTM, etc.
The application 253 is a computer program that performs at least one specific task based on the operating system 251, and may include at least one module (not shown in fig. 6), each of which may respectively include a computer program for the server 2000. For example, a sports automatic group office system may be considered an application 253 deployed on server 2000.
The data 255 may be structured data stored on disk, unstructured data, etc., and is stored in the memory 250.
The central processor 270 may include one or more processors and is configured to communicate with the memory 250 via at least one communication bus to read the computer program stored in the memory 250, thereby implementing the operation and processing of the bulk data 255 in the memory 250. For example, an automated grouping method for performing athletic activities by the central processor 270 reading a series of computer programs stored in the memory 250.
Furthermore, the present application can be realized by hardware circuitry or by a combination of hardware circuitry and software, and thus, the implementation of the present application is not limited to any specific hardware circuitry, software, or combination of the two.
Referring to fig. 8, in an embodiment of the present application, an electronic device 4000 is provided, and the electronic device 400 may include: desktop computers, notebook computers, servers, and the like.
In fig. 8, the electronic device 4000 includes at least one processor 4001, at least one communication bus 4002, and at least one memory 4003.
Wherein the processor 4001 is coupled to the memory 4003, such as via a communication bus 4002. Optionally, the electronic device 4000 may further comprise a transceiver 4004, the transceiver 4004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 is not limited to the embodiment of the present application.
The processor 4001 may be a CPU (Central Processing Unit ), general purpose processor, DSP (Digital Signal Processor, data signal processor), ASIC (Application Specific Integrated Circuit ), FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. The processor 4001 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
The communication bus 4002 may include a pathway to transfer information between the aforementioned components. The communication bus 4002 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. The communication bus 4002 can be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 8, but not only one bus or one type of bus.
Memory 4003 may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, EEPROM (Electrically Erasable Programmable Read Only Memory ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 4003 has stored thereon a computer program, and the processor 4001 reads the computer program stored in the memory 4003 through the communication bus 4002.
The computer program, when executed by the processor 4001, implements the athletic activity automatic grouping method in the above embodiments.
Further, in an embodiment of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements an automatic grouping method for sports activities in the above-described embodiments.
In an embodiment of the present application, a computer program product is provided, which includes a computer program stored in a storage medium. The processor of the computer device reads the computer program from the storage medium, and the processor executes the computer program, so that the computer device performs an automatic grouping method of sports activities in the above embodiments.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. An automated method of organizing athletic activity, the method comprising:
initiating a group office invitation to a user based on the group office decision;
monitoring whether the group office task based on the group office invitation is successful;
if the group office task is successful, adding 1 to a group office model grading value for generating the group office decision; if the group office task is unsuccessful, subtracting 1 from a group office model score value for generating the group office decision;
sorting the plurality of group office models based on the score values of the group office models;
the group office model with the scoring value smaller than a preset threshold value is listed as a model to be optimized;
the group office model with the scoring value larger than or equal to the preset threshold value is listed as an available model;
and calling the available model to generate a next group office decision.
2. The method according to claim 1, wherein said monitoring is based on whether the group office task invited by the group office is successful, in particular comprising:
Monitoring whether the user generates a site reservation order based on the group office invitation;
if the site reservation order is generated, judging that the group office task based on the group office invitation is successful;
if the site reservation order is not generated, judging that the group office task based on the group office invitation is unsuccessful.
3. The method of claim 1, wherein when the score value of the group office model is smaller than a preset threshold value, after the group office model is listed as a model to be optimized, further comprising:
analyzing probability distribution of the model to be optimized by a poisson distribution statistical method;
adjusting the influence factors of all input elements of the model to be optimized based on the probability distribution of the model to be optimized to form an optimized group office model;
and taking the optimized group office model as a group office algorithm model, and retraining to obtain the available model.
4. The method of claim 3, wherein the input elements include user data and venue data, and wherein the group office decision generation method comprises:
performing data management on the user data to obtain a training set of consumption habits of the user on the physical activities;
Performing data management on the venue data to obtain the venue data training set;
inputting the user data training set and the venue data training set into the group office algorithm model, and training the group office algorithm model to obtain the trained group office model;
generating the group office decision based on the group office model.
5. The method of claim 4, wherein inputting the user data training set and the venue data training set into the group office algorithm model trains the group office algorithm model to obtain the trained group office model, specifically comprising:
constructing the initialization group office algorithm model based on a fuzzy comprehensive analysis method;
configuring influence factors of the initialized group office algorithm model, wherein the influence factors comprise influence factors of various input elements of the initialized group office algorithm model configured based on expert experience;
inputting the user data training set and the venue data training set into the group office algorithm model, and training the group office algorithm model to obtain the trained group office model.
6. The method of claim 4, wherein the user data includes one or more of user registration information, user consumption habits, user interpersonal relationships; the venue data includes one or more of venue operation data, environmental data, price data, and offer data.
7. The method of claim 1, wherein after ranking the plurality of group office models in order of higher or lower score values based on the group office model, further comprising:
setting the group office model with the highest grading value as a default group office model;
setting other group office models with scoring values higher than the preset threshold and not the default group office model as strategy group office models;
and selecting to generate a group office decision based on the default group office model or generating the group office decision based on the strategy group office model according to the characteristic preference of the user end of the group office invitation to be sent.
8. An automatic athletic activity group bureau system, the apparatus comprising:
the group office invitation issuing module is used for initiating group office invitation to the user based on the group office decision;
the group office task monitoring module is used for monitoring whether the group office task based on the group office invitation is successful or not; if the group office task is successful, adding 1 to a group office model grading value based on the group office decision; if the group office task is unsuccessful, subtracting 1 from a group office model grading value based on the group office decision;
the group office effect feedback module is used for sequencing the plurality of group office models based on the score value of the group office models in high-low order; the group office model with the scoring value smaller than or equal to a preset threshold value is listed as a model to be optimized; the group office model with the scoring value larger than the preset threshold value is listed as the available model;
And the group office decision generation module is used for preferentially calling the available model to generate the next group office decision.
9. An electronic device, comprising: at least one processor, at least one memory, and at least one communication bus, wherein,
the memory stores a computer program, and the processor reads the computer program in the memory through the communication bus;
the computer program, when executed by the processor, implements an automatic athletic activity grouping method as claimed in any one of claims 1 to 7.
10. A storage medium, comprising: on which a computer program is stored which, when being executed by a processor, implements an automatic grouping method for sports activities according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310379213.9A CN116510318A (en) | 2023-04-11 | 2023-04-11 | Automatic group office method, system, electronic equipment and storage medium for physical activities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310379213.9A CN116510318A (en) | 2023-04-11 | 2023-04-11 | Automatic group office method, system, electronic equipment and storage medium for physical activities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116510318A true CN116510318A (en) | 2023-08-01 |
Family
ID=87391304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310379213.9A Pending CN116510318A (en) | 2023-04-11 | 2023-04-11 | Automatic group office method, system, electronic equipment and storage medium for physical activities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116510318A (en) |
-
2023
- 2023-04-11 CN CN202310379213.9A patent/CN116510318A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bifet et al. | New ensemble methods for evolving data streams | |
| US11574202B1 (en) | Data mining technique with distributed novelty search | |
| US11836615B2 (en) | Bayesian nonparametric learning of neural networks | |
| Yu et al. | Challenges and opportunities for trust management in crowdsourcing | |
| CN102075352B (en) | Method and device for predicting network user behavior | |
| Nedić et al. | Dynamic coalitional TU games: Distributed bargaining among players' neighbors | |
| CN114332984B (en) | Training data processing method, device and storage medium | |
| CN110120888B (en) | Cloud crowdsourcing platform mass service resource combination optimization method and system | |
| Unuvar et al. | Selecting optimum cloud availability zones by learning user satisfaction levels | |
| Tahanian et al. | A game-theoretic approach for robust federated learning | |
| Zheng et al. | Analysis and modeling of social influence in high performance computing workloads | |
| Ariu et al. | Regret in online recommendation systems | |
| CN112036831A (en) | Human management system control method and device, readable storage medium and terminal equipment | |
| CN112052399A (en) | Data processing method and device and computer readable storage medium | |
| CN116510318A (en) | Automatic group office method, system, electronic equipment and storage medium for physical activities | |
| Xiao et al. | Efl-wp: Federated learning-based workload prediction in inter-cloud environments | |
| CN112101406A (en) | Intelligent horizontal quantization method of multi-agent network | |
| CN113411405A (en) | Information security processing method for cloud computing environment and artificial intelligence server | |
| CN112818241A (en) | Content promotion method and device, computer equipment and storage medium | |
| Cui et al. | Complex crowdsourcing task allocation strategies employing supervised and reinforcement learning | |
| Unuvar et al. | A predictive method for identifying optimum cloud availability zones | |
| CN111582679A (en) | Processing method, device and equipment for application service partition and storage medium | |
| CN111598390A (en) | Server high availability evaluation method, device, equipment and readable storage medium | |
| CN110163684A (en) | The labeling method and device of a kind of pair of telecommunications affiliate's fraud | |
| CN116384502B (en) | Method, device, equipment and medium for calculating contribution of participant value in federal learning |
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 |