CN110782091A - User matching result calculation method and device, computer readable medium and equipment - Google Patents
User matching result calculation method and device, computer readable medium and equipment Download PDFInfo
- Publication number
- CN110782091A CN110782091A CN201911023485.5A CN201911023485A CN110782091A CN 110782091 A CN110782091 A CN 110782091A CN 201911023485 A CN201911023485 A CN 201911023485A CN 110782091 A CN110782091 A CN 110782091A
- Authority
- CN
- China
- Prior art keywords
- user
- matching result
- result
- list
- matching
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000013215 result calculation Methods 0.000 title description 2
- 238000012549 training Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000008030 elimination Effects 0.000 description 4
- 238000003379 elimination reaction Methods 0.000 description 4
- 238000012417 linear regression Methods 0.000 description 3
- 108010001267 Protein Subunits Proteins 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, a computer readable medium and equipment for calculating a user matching result, wherein the method comprises the following steps: acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list; determining a plurality of matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list; for each matching result, predicting the ticket number of each matching result by using a preset prediction model; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result; and taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for calculating a user matching result, a computer-readable medium, and a device.
Background
The elimination competition refers to a competition mode of eliminating the losers among a plurality of competitors by adopting a pairwise competition mode and deciding a winner after one-by-one competition. With the change of computer science, the daily life of people is gradually enriched by the internet, at present, some internet platforms develop innovation, and the elimination competition is introduced to provide the competition of the same race and the competition experience of the same race and the competition of each other.
However, in some obsolete competitions provided by the internet platform, the system works out the matching result of the user according to a fixed ranking relation, usually according to a certain ranking of the user, in a manner that the user matches two by two; this way of formulating the matching results in a fixed ranking lacks flexibility and cannot be guaranteed to be adaptable to users participating in each round of the block.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a computer-readable medium, and a device for calculating a user matching result, so as to provide a flexible user matching result.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the invention provides a method for calculating a user matching result in a first aspect, which comprises the following steps:
acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list;
determining a plurality of matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list;
for each matching result, predicting the ticket number of each matching result by using a preset prediction model; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result;
and taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result.
Optionally, the obtaining the first user list and the second user list includes:
obtaining the result of the previous round of user block; wherein the decision-making result comprises user information of a user winning in the decision-making;
ranking the users in the decision result according to the real force value by using the user information;
and forming the first half of the ranked.
Optionally, before taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result, the method further includes:
comparing the maximum ticket number in the prediction result with the ticket number in the recorded historical matching result;
if the maximum ticket number in the prediction result is not less than the ticket number in the recorded historical matching result, executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result;
and if the maximum ticket number in the prediction result is less than the ticket number in the recorded history matching result, taking the recorded history matching result as the output matching result.
Optionally, the determining multiple matching results of the users in the first user list and the users in the second user list includes:
matching each user in the first user list with each user in the second user list to obtain a matching result; or,
and selecting a preset number of matching results from matching results of one user in the first user list and one user in the second user list.
Optionally, the method for constructing the prediction model includes:
obtaining an initial prediction model;
training the initial prediction model by using a decision result of a historical user decision making as sample data to obtain parameters in the initial prediction model; wherein, the result of the historical user's block includes: the strength value of the users of the two parties of the user's decision making, and the number of tickets brought by the user's decision making;
and taking the initial prediction model of the obtained parameters as the prediction model.
The second aspect of the present invention provides a device for calculating a user matching result, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list;
a determining unit, configured to determine multiple matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list;
the prediction unit is used for predicting the ticket number of each matching result by respectively utilizing a preset prediction model aiming at each matching result; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result;
and the output unit is used for taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result.
Optionally, the obtaining unit includes:
the obtaining subunit is used for obtaining the result of the previous round of user block; wherein the decision-making result comprises user information of a user winning in the decision-making;
the sorting subunit is used for ranking the users in the decision result according to the real force value by using the user information;
and the combining subunit is used for enabling the users to form the first user list by the first half of the ranked checking results and form the second user list by the second half of the ranked checking results.
Optionally, the device for calculating the user matching result further includes:
the comparison unit is used for comparing the maximum ticket number in the prediction result with the ticket number in the recorded historical matching result;
the output unit is used for judging whether the maximum ticket number in the prediction result is less than the ticket number in the recorded historical matching result or not in the comparison unit, and executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result; and the comparison unit is further configured to determine that the maximum number of votes in the prediction result is less than the number of votes in the recorded history matching result, and then use the recorded history matching result as the output matching result.
Optionally, the determining unit includes:
the first determining subunit is configured to match each user in the first user list with each user in the second user list to obtain a matching result;
and the second determining subunit is used for selecting a preset number of matching results from matching results of one user in the first user list and one user in the second user list.
Optionally, the device for calculating the user matching result further includes:
a training unit for obtaining an initial prediction model; training the initial prediction model by using a decision result of a historical user decision making as sample data to obtain parameters in the initial prediction model; wherein, the result of the historical user's block includes: the strength value of the users of the two parties of the user's decision making, and the number of tickets brought by the user's decision making; and taking the initial prediction model of the obtained parameters as the prediction model.
A third aspect of the invention provides a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method as claimed in any one of the preceding claims.
A fourth aspect of the present invention provides an electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method as in any one of the above.
Compared with the prior art, the invention has the following advantages:
in the method for calculating the user matching result, the ticket number of each matching result is predicted by respectively utilizing a preset prediction model aiming at each matching result of the user in the first user list and the user in the second user list; and then, the matching result corresponding to the maximum ticket number in the prediction result is used as the output matching result, so that the matching result of matching can be provided for the users in different user lists by using the prediction model, and the matching result which is flexible and is suitable for different users can be provided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for constructing a prediction model according to an embodiment of the present invention;
FIG. 2a is a flowchart of a method for calculating a user matching result according to another embodiment of the present invention;
FIG. 2b is a page showing diagram of a solution mode according to another embodiment of the present invention;
fig. 3 is a flowchart of an implementation manner of step S201 according to another embodiment of the present invention;
fig. 4 is a flowchart of an implementation manner of step S204 according to another embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a computing device for user matching results according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to another embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It should be noted that, in the research on the prior art, the inventor finds that the current internet platform, such as the live broadcast platform, successively promotes the elimination competition; the matching mode adopted by the user for the block is usually fixed. For example, take the elimination competitive mode-sky circle of one of the live broadcast platforms as an example:
in one inning circle of blocks, 32 contest anchor sons exist in total, and a single winner is generated through five rounds of pairwise block matching. In the five-wheel pairwise decision, the adopted matching modes are all fixed. Taking the first round as an example, of the 32 contest anchor, the anchor in the real value row 1 will match to the anchor in the real value row 17, the anchor in the real value row 2 will match to the anchor … … in the real value row 18, and so on until the live broadcast in the real value row 16 matches to the anchor in the real value row 32. Similarly, the matching results are formulated according to the fixed real force values in the second round, the third round … … and other rounds; it follows that this fixed matching approach lacks flexibility in the circle of life and is not necessarily adequate for users participating in each battle.
For example, user 18 has a lower strength value than user 17, but has a stronger ability to vote fans than user 17; but since user 18 initially decided on user 1 (user 1's ability to vote fans is much greater than user 18's), user 18 may be eliminated in the first round of decision, and cannot enhance the wonderful level of the competition for the next time. It follows that the matching results obtained from fixed matching rules are inherently inflexible and in a sense not universal.
Therefore, the embodiment of the invention constructs a prediction model of the matching method, and the prediction model can be calculated according to different input data to obtain a corresponding matching result.
Specifically, the method for constructing the prediction model, specifically referring to fig. 1, includes:
s101, obtaining an initial prediction model.
In the embodiment of the invention, the initial prediction model can adopt a linear regression model, and the linear regression model has the advantages of simplicity, easy training, less parameters and difficult overfitting. Since the relationship between the number of votes and the strength values of the two users is non-linear, it is necessary to add a second-order feature to input to the linear regression model for training. Therefore, the initial prediction model provided by the embodiment of the invention can be as follows:
y＝w
1x
1+w
2x
2+w
3x
1x
2+w
4x
1 2+w
5x
2 2. Wherein y is the predicted ticket number, x
1，x
2For solving the respective corresponding actual force values of both parties, w
1To w
5Parameters obtained through training are required.
For general purposes, after an initial prediction model is obtained, historical user-oriented data needs to be fed into the initial prediction model to train out a parameter w
1To w
5The value of (c).
S102, training the initial prediction model by using a decision result of a historical user decision making as sample data to obtain parameters in the initial prediction model; wherein, the result of the historical user's block includes: the strength value of the users of the two parties of the block, and the number of tickets brought by the users to the block.
In the embodiment of the invention, the fact that in a historical solution result, the actual force values of two users in the solution are x respectively is assumed to be
1And x
2If the actual number of votes obtained is y, the user's decision data fed into the initial prediction model may be (x)
1，x
2，y)。
Note that the initial prediction model y is w
1x
1+w
2x
2+w
3x
1x
2+w
4x
1 2+w
5x
2 2In parameter w
1To w
5Given an initial value, the user in the feed history checks the data (x)
1，x
2Y) after, by mixing x
1，x
2Substituting into the model to obtain a predicted ticket number
Then based on the predicted ticket number
The difference between the actual number y of votes obtained is used for adjusting the parameter w
1To w
5A value of (d); wherein, the mean square error MSE can be used as a loss function, and the parameter w can be optimized and iterated by a gradient descent method
1To w
5The more the historical sample data of the feeding, the predictionModel y ═ w
1x
1+w
2x
2+w
3x
1x
2+w
4x
1 2+w
5x
2 2Parameter w in
1To w
5The more standard the value of (c) is trained. Thus, after the prediction model is trained, the corresponding number of tickets can be predicted by the prediction model when the strength values of both parties are known.
Based on the above constructed prediction model, the embodiment of the present invention provides a method for calculating a user matching result, as shown in fig. 2a, the specific process includes:
s201, acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list.
In the embodiment of the invention, in the acquired first user list and second user list, each list can comprise a plurality of users, and each user has a corresponding strength value; and the strength value of each user in the first user list is greater than the strength value of each user in the second user list.
It should be noted that the strength value of the user is obtained by comprehensively calculating multiple items of data, and specifically may include a contribution list of the user and a fan amount in a live broadcast room; wherein, the fans can be divided into high-quality fans and common fans, and the weight of the high-quality fans is higher than that of the common fans in the aspect of calculation.
It should be further noted that, the users may be anchor broadcasters, and by taking the above mentioned solution mode named "life circle" as an example, in a life circle, for example, 32 anchor broadcasters participating in the game are included, and in the first wheel solution process, the 32 anchor broadcasters are sorted according to the strength value and divided into a first user list and a second user list with the same number of people; and the strength value of each user in the first user list is greater than that of each user in the second user list, and pairwise talent measures are respectively carried out between the two lists.
It can be concluded that one embodiment of step S201 is:
acquiring a plurality of users, wherein the users are initial users participating in the current round of block;
dividing the plurality of users into a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list.
The winning of the sky circle pattern depends on the voting data of the audience, but the pairwise matching results between the first user list and the second user list are various, so that an optimal scheme needs to be selected as a final matching result, and a fixed matching rule provided by the system cannot obtain the optimal matching result.
Optionally, in another embodiment of the present invention, a manner of acquiring the first user list and the second user list in step S201 may specifically refer to fig. 3, where the method includes:
s301, obtaining a block result of a previous round of user block; wherein the result of the block comprises user information of the user who wins the block.
Taking the above sky ring block as an example, the user in the first user list and the user in the second user list obtained from the second wheel block are from the block result of the previous wheel. For example: the users participating in the second wheel pair block are 16 anchor broadcasters winning the first wheel pair block. Obtaining the user information of the 16 anchor by obtaining the result of the first round of checking; wherein the user information comprises the real force value of the user. By analogy, the users in the third round of the block are 8 anchor broadcasters winning in the second round of the block, the users in the fourth round of the block are 4 anchor broadcasters winning in the third round of the block, and the users in the fifth round of the block are 2 anchor broadcasters winning in the fourth round of the block.
S302, ranking the users in the decision result according to the real force value by using the user information.
Receiving the content in the step S301, and after the first wheel pair block of the sky circle ends, obtaining user information of 16 winning anchor broadcasters, where the user information includes a real force value; thus, the system may perform operations consistent with the first round, ranking the winning 16 anchor by strength value.
In the subsequent third round, fourth round and fifth round, the system also ranks the 8, 4 and 2 winning people according to the strength values, and the ranking from each round to the fifth round is consistent in the executed action.
S303, forming the first half of the ranked users in the decision-making result into the first user list, and forming the second half of the ranked users in the decision-making result into the second user list.
Optionally, taking the first round of the daily life circle as an example, the obtained first user list and the second user list may be shown in table 1 below.
TABLE 1
In table 1, the obtained first user list and the second user list include 32 users in total, the users in each list are sorted according to the real force value, and the real force value of each user in the first user list is greater than the real force value of each user in the second user list. It should be noted that the strength values referred to in table 1 are only for illustrative purposes and do not represent actual strength values.
It should be further noted that, in the life circle with the first user list and the second user list in table 1 as examples, in the subsequent user block, the block result of the user list in the first round will affect the first user list and the second user list acquired in the next round; i.e. the winner of the block will go through the next round of sorting, the rule that the strength value of each user in the first user list is greater than the strength value of each user in the second user list needs to be followed.
S202, determining a plurality of matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list.
In the embodiment of the present invention, after the first user list and the second user list are obtained, it is necessary to determine a plurality of matching results between the users in the first user list and the users in the second user list. Specifically, each user in the first user list and each user in the second user list may be matched one by one to obtain all matching results.
Taking the above table 1 as an example, if a manner of matching each user in the first user list and each user in the second user list in table 1 one by one is adopted, the corresponding matching result should have
And (4) seed preparation. Obviously, the number of all the matching results is too large.
Optionally, in another embodiment of the present invention, a manner of determining multiple matching results of the users in the first user list and the users in the second user list is determined, and in addition to the matching result obtained by matching each user in the first user list and each user in the second user list one by one, a preset number of matching results may be selected from matching results obtained by matching one user in the first user list and one user in the second user list.
In the above, the matching results are common
When the base number is large, the data of the corresponding matching result is too huge; therefore, optionally, a way of randomly drawing 10000 matching results may be adopted as the matching results of the finally determined users in the first user list and the users in the second user list. Of course, embodiments of the present invention include, but are not limited to, randomization10000 matching results are extracted, and the randomly extracted numerical value can be subjected to custom operation.
It should be noted that, in the case that the base number of the users is not large, all matching results are selected, so as to select the matching result with the highest ticket number in the subsequent ticket number prediction.
For example, in an exemplary skyline block, all matches between the first user list and the second user list in the first round block include
All matching results between the first user list and the second user list in the second round of block matching include
Seeds, namely 40320 matching results; by the third round of the decision-making, all the matching results between the first user list and the second user list are
There are only 24 species. Therefore, after the life circle goes to the third round and the fourth round, all matching results can be selected.
S203, aiming at each matching result, predicting the number of tickets of each matching result by using a preset prediction model; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result;
in the embodiment of the present invention, the plurality of matching results obtained in step S202 are received, and for each matching result, the number of votes for each matching result is predicted by using a preset prediction model. The prediction model is obtained through pre-training, and the prediction model comprises the corresponding relation between the real force value and the ticket number; after the strength values of the matched two users are input, the prediction model can predict the total votes of the audience, namely the votes, which can be obtained by the matched two users for the decision.
And S204, taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result.
And predicting the ticket number of each matching result by using the trained prediction model to obtain the predicted ticket number of each matching result. On the basis, the matching result corresponding to the maximum ticket number in the predicted ticket numbers can be selected as the output final matching result.
Taking advantage of the above table 1, for example, in a one-day competition, according to the fixed matching rules provided by the system, the matching results should be from the user 1 to the decision user 17, the user 2 to the decision user 18, the user 3 to the decision user 19 … … to the user 16 to the decision user 32. The matching result provided by the embodiment does not adopt the fixed matching rule; by adopting the method provided by the embodiment of the invention, the prediction model is used for predicting the matching result according to the user strength value, the prediction result with the highest ticket number is used as the final matching result, the flexibility is realized on the matching mode, and the irrationality of the matching result can be reduced.
Optionally, reference may be made to the content in fig. 2b, where the page display diagram is a life circle performed after the calculation method of the user matching result provided by the implementation of the present invention is adopted.
In the figure, the anchor on the left side is one of the users in the first user list, the anchor on the right side is one of the users in the second user list, and both parties are in the fifth round of the daily circle, that is, the final round of the block. The two lines of information at the bottom are the block information of the previous round, namely the fourth round, of the users of both parties.
Optionally, in another embodiment of the present invention, as shown in fig. 4, before performing step S204, the following steps may be performed:
s401, comparing the maximum ticket number in the prediction result with the ticket number in the recorded history matching result.
It should be noted that, by querying the vote data corresponding to the historical matching result and comparing the vote data with the predicted vote data corresponding to the current matching result, it is determined whether the matching result can be directly output.
S402, if the maximum ticket number in the prediction result is not less than the ticket number in the recorded historical matching result, executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result.
And S403, if the maximum ticket number in the prediction result is less than the ticket number in the recorded history matching result, taking the recorded history matching result as the output matching result.
It should be noted that the historical matching result can be selected as the matching result of the previous week and the previous ten block, and the referential value of the matching result is higher in the theoretically closer block number. Of course, all matching results of the history may be selected as comparison objects, which also belongs to the protection scope of the present embodiment.
In the method provided by the embodiment of the invention, the most preferable matching result can be obtained in any one voting mode by taking the highest final vote number as a target. Obtaining a first user list and a second user list; determining a plurality of matching results of the users in the first user list and the users in the second user list; for each matching result, predicting the ticket number of each matching result by using a preset prediction model; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result; and taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result. Therefore, the matching result of the solution mode is calculated by utilizing the strength values of a plurality of users input into the prediction model based on the trained prediction model so as to provide the matching result of the matching, namely the matching result with the highest predicted ticket number, for the users in different user lists; the matching mode has flexibility, and can effectively improve the rationality of the matching result in the solution mode under the condition of taking the number of votes as a target.
Corresponding to fig. 2a, an embodiment of the present invention further provides a computing apparatus for user matching results, where a specific apparatus structure diagram is shown in fig. 5, and includes:
an obtaining unit 501, configured to obtain a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list.
A determining unit 502, configured to determine multiple matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list.
The prediction unit 503 is configured to predict the number of tickets for each matching result by using a preset prediction model for each matching result; and the prediction model is used for predicting the number of votes brought by the user in the matching result by using the real force value of the user in the matching result.
And the output unit 504 is configured to take a matching result corresponding to the maximum ticket number in the prediction results as an output matching result.
In the device for calculating the user matching result provided by the embodiment of the invention, any user can use the highest final number of votes as a target under the decision, and a pre-established prediction model is used for calculating the most preferable matching result, namely the matching result with the largest predicted number of votes. Specifically, a first user list and a second user list are acquired through an acquisition unit 501; a determining unit 502 to determine a plurality of matching results of the users in the first user list and the users in the second user list; the prediction unit 503 predicts the number of votes for each matching result by using a preset prediction model respectively; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result; finally, the output unit 504 takes the matching result corresponding to the maximum ticket number in the prediction results as the output matching result. Therefore, in the user matching result computing device provided by the embodiment of the invention, a flexible solving process is provided for every two matching results of the multi-user block, the purpose is high, the matching result with the highest vote number as the purpose can provide the matching result for the users in different user lists, and the rationality of the matching result in the block matching mode is improved.
In the embodiment of the present invention, specific implementation processes of the obtaining unit 501, the determining unit 502, the predicting unit 503 and the outputting unit 504 may refer to contents in the method embodiment corresponding to fig. 2a, and are not described herein again.
Optionally, in another embodiment of the present invention, the obtaining unit 501 includes:
the obtaining subunit is used for obtaining the result of the previous round of user block; wherein the decision-making result comprises user information of a user winning in the decision-making;
the sorting subunit is used for ranking the users in the decision result according to the real force value by using the user information;
and the combining subunit is used for enabling the users to form the first user list by the first half of the ranked checking results and form the second user list by the second half of the ranked checking results.
In the embodiment of the present invention, the specific execution processes of the obtaining subunit, the sorting subunit, and the combining subunit may refer to the content of the method embodiment corresponding to fig. 3, and are not described herein again.
Optionally, in another embodiment of the present invention, the apparatus for calculating a user matching result further includes:
the comparison unit is used for comparing the maximum ticket number in the prediction result with the ticket number in the recorded historical matching result;
the output unit is used for judging whether the maximum ticket number in the prediction result is less than the ticket number in the recorded historical matching result or not in the comparison unit, and executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result; and the comparison unit is further configured to determine that the maximum number of votes in the prediction result is less than the number of votes in the recorded history matching result, and then use the recorded history matching result as the output matching result.
In the embodiment of the present invention, the specific implementation process of the sub-unit, the first output sub-unit, and the second output sub-unit can be referred to the content of the method embodiment corresponding to fig. 4, and details are not described here.
Optionally, in another embodiment of the present invention, the determining unit 502 includes:
the first determining subunit is configured to match each user in the first user list with each user in the second user list to obtain a matching result;
and the second determining subunit is used for selecting a preset number of matching results from matching results of one user in the first user list and one user in the second user list. In the embodiment of the present invention, the specific execution process of the subunit is determined, which may be referred to in the content of the method embodiment corresponding to fig. 2a and is not described herein again.
Optionally, in another embodiment of the present invention, the apparatus for calculating a user matching result further includes:
a training unit for obtaining an initial prediction model; training the initial prediction model by using a decision result of a historical user decision making as sample data to obtain parameters in the initial prediction model; wherein, the result of the historical user's block includes: the strength value of the users of the two parties of the user's decision making, and the number of tickets brought by the user's decision making; and taking the initial prediction model of the obtained parameters as the prediction model.
In the embodiment of the present invention, for a specific execution process of the training unit, reference may be made to the contents of the method embodiment corresponding to fig. 1, which are not described herein again.
Another embodiment of the invention provides a computer-readable medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the computing method as described in any of the above method embodiments.
Another embodiment of the present invention provides an electronic device, as shown in fig. 6, including:
one or more processors 601;
a storage device 602 on which one or more programs are stored;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a computing method as recited in any of the above method embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Claims (10)
1. A method for calculating a user matching result is characterized by comprising the following steps:
acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list;
determining a plurality of matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list;
for each matching result, predicting the ticket number of each matching result by using a preset prediction model; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result;
and taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result.
2. The computing method of claim 1, wherein obtaining the first list of users and the second list of users comprises:
obtaining the result of the previous round of user block; wherein the decision-making result comprises user information of a user winning in the decision-making;
ranking the users in the decision result according to the real force value by using the user information;
and forming the first half of the ranked.
3. The calculation method according to claim 1, wherein before the step of using the matching result corresponding to the maximum ticket number in the prediction results as the output matching result, the method further comprises:
comparing the maximum ticket number in the prediction result with the ticket number in the recorded historical matching result;
if the maximum ticket number in the prediction result is not less than the ticket number in the recorded historical matching result, executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as an output matching result;
and if the maximum ticket number in the prediction result is less than the ticket number in the recorded history matching result, taking the recorded history matching result as the output matching result.
4. The computing method of claim 1, wherein determining a plurality of matching results for users in the first list of users and users in the second list of users comprises:
matching each user in the first user list with each user in the second user list to obtain a matching result; or,
and selecting a preset number of matching results from matching results of one user in the first user list and one user in the second user list.
5. The computing method according to any one of claims 1 to 4, wherein the method for constructing the prediction model includes:
obtaining an initial prediction model;
training the initial prediction model by using a decision result of a historical user decision making as sample data to obtain parameters in the initial prediction model; wherein, the result of the historical user's block includes: the strength value of the users of the two parties of the user's decision making, and the number of tickets brought by the user's decision making;
and taking the initial prediction model of the obtained parameters as the prediction model.
6. A computing device for user matching results, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first user list and a second user list; wherein the strength value of each user in the first user list is greater than the strength value of each user in the second user list;
a determining unit, configured to determine multiple matching results of the users in the first user list and the users in the second user list; wherein one user in the first user list is matched with only one user in the second user list;
the prediction unit is used for predicting the ticket number of each matching result by respectively utilizing a preset prediction model aiming at each matching result; the prediction model is used for predicting the number of tickets brought by the user to the decision by the user in the matching result by using the real force value of the user in the matching result;
and the output unit is used for taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result.
7. The computing device of claim 6, wherein the obtaining unit comprises:
the obtaining subunit is used for obtaining the result of the previous round of user block; wherein the decision-making result comprises user information of a user winning in the decision-making;
the sorting subunit is used for ranking the users in the decision result according to the real force value by using the user information;
and the combining subunit is used for enabling the users to form the first user list by the first half of the ranked checking results and form the second user list by the second half of the ranked checking results.
8. The computing device of claim 6, further comprising:
the comparison unit is used for comparing the maximum ticket number in the prediction result with the ticket number in the recorded historical matching result;
the output unit is used for judging whether the maximum ticket number in the prediction result is less than the ticket number in the recorded historical matching result or not in the comparison unit, and executing the step of taking the matching result corresponding to the maximum ticket number in the prediction result as the output matching result; and the comparison unit is further configured to determine that the maximum number of votes in the prediction result is less than the number of votes in the recorded history matching result, and then use the recorded history matching result as the output matching result.
9. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1 to 5.
10. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911023485.5A CN110782091B (en) | 2019-10-25 | 2019-10-25 | User matching result calculation method and device, computer readable medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911023485.5A CN110782091B (en) | 2019-10-25 | 2019-10-25 | User matching result calculation method and device, computer readable medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110782091A true CN110782091A (en) | 2020-02-11 |
| CN110782091B CN110782091B (en) | 2021-02-12 |
Family
ID=69386665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911023485.5A Active CN110782091B (en) | 2019-10-25 | 2019-10-25 | User matching result calculation method and device, computer readable medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782091B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881940A (en) * | 2020-06-29 | 2020-11-03 | 广州华多网络科技有限公司 | Live broadcast and live broadcast matching method and device, electronic equipment and storage medium |
| CN112423013A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Online interaction method, client, server, computing device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073659A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of love and marriage object recommendation method and device |
| US20180314880A1 (en) * | 2017-04-26 | 2018-11-01 | Facebook, Inc. | Image based user identification across multiple online systems |
| CN108805598A (en) * | 2017-05-05 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Similarity information determines method, server and computer readable storage medium |
| CN109325883A (en) * | 2017-07-31 | 2019-02-12 | 深圳市珍爱网信息技术有限公司 | A kind of recommended method and device of bi-directional matching |
| CN109513215A (en) * | 2018-11-23 | 2019-03-26 | 腾讯科技（深圳）有限公司 | A kind of object matching method, model training method and server |
-
2019
- 2019-10-25 CN CN201911023485.5A patent/CN110782091B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073659A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of love and marriage object recommendation method and device |
| US20180314880A1 (en) * | 2017-04-26 | 2018-11-01 | Facebook, Inc. | Image based user identification across multiple online systems |
| CN108805598A (en) * | 2017-05-05 | 2018-11-13 | 腾讯科技（深圳）有限公司 | Similarity information determines method, server and computer readable storage medium |
| CN109325883A (en) * | 2017-07-31 | 2019-02-12 | 深圳市珍爱网信息技术有限公司 | A kind of recommended method and device of bi-directional matching |
| CN109513215A (en) * | 2018-11-23 | 2019-03-26 | 腾讯科技（深圳）有限公司 | A kind of object matching method, model training method and server |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881940A (en) * | 2020-06-29 | 2020-11-03 | 广州华多网络科技有限公司 | Live broadcast and live broadcast matching method and device, electronic equipment and storage medium |
| CN111881940B (en) * | 2020-06-29 | 2023-11-24 | 广州方硅信息技术有限公司 | Live broadcast continuous wheat matching method and device, electronic equipment and storage medium |
| CN112423013A (en) * | 2020-11-19 | 2021-02-26 | 腾讯科技（深圳）有限公司 | Online interaction method, client, server, computing device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110782091B (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977411B (en) | Group recommendation method, device, storage medium and server | |
| CN109814955B (en) | Method and device for determining formation capacity and electronic equipment | |
| Veček et al. | Parameter tuning with Chess Rating System (CRS-Tuning) for meta-heuristic algorithms | |
| US20200016457A1 (en) | Virtual interactive fitness platform | |
| CN110782091B (en) | User matching result calculation method and device, computer readable medium and equipment | |
| CN104667511A (en) | Competition ranking promoting system and method based on big data | |
| US20150032235A1 (en) | Systems and methods for automated analysis of fitness data | |
| WO2021229850A1 (en) | Information processing device, information processing method, and program | |
| CN108305005A (en) | Contest object matching method in study competition and device | |
| US20170084108A1 (en) | System and method for sporting event wagering | |
| CN110152302A (en) | The hands of cards game generate and clustering method, equipment and processor | |
| CN110585722A (en) | Block chain-based game time information processing method and device and game control method and device | |
| US20090069089A1 (en) | Method and System For Virtual Competition | |
| Sauer et al. | Improving ranking quality and fairness in Swiss-system chess tournaments | |
| US9352234B2 (en) | Player rankings based on long term opponent activity | |
| KR101614334B1 (en) | Method and apparatus for conducting a tournament for many entries | |
| CN110851661B (en) | User ID mapping relation determination method and device and electronic equipment | |
| KR101723770B1 (en) | Method and system for recommending problems based on player matching technique | |
| EP2503502A1 (en) | Soccer prediction voting system | |
| JP2021089770A5 (en) | ||
| JP2021190064A5 (en) | ||
| JP7393716B2 (en) | Information processing device, information processing method and program | |
| JP5812803B2 (en) | Voting system in public competition | |
| JP6908868B1 (en) | Information processing equipment, information processing methods and programs | |
| KR20170073330A (en) | Online Assessment System Considering Assessor Tendency and Method therefor |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210113 Address after: 510000 3108, 79 Wanbo 2nd Road, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Applicant after: GUANGZHOU CUBESILI INFORMATION TECHNOLOGY Co.,Ltd. Address before: 28th floor, block B1, Wanda Plaza, Nancun Town, Panyu District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU HUADUO NETWORK TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |