CN110163460B - Method and equipment for determining application score - Google Patents
Method and equipment for determining application score Download PDFInfo
- Publication number
- CN110163460B CN110163460B CN201810293738.XA CN201810293738A CN110163460B CN 110163460 B CN110163460 B CN 110163460B CN 201810293738 A CN201810293738 A CN 201810293738A CN 110163460 B CN110163460 B CN 110163460B
- Authority
- CN
- China
- Prior art keywords
- feature
- characteristic
- sub
- score
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Abstract
The embodiment of the application discloses a method and equipment for determining scores. The method of the embodiment of the application comprises the following steps: obtaining a target application of a score to be predicted; determining a feature index set corresponding to the target application, the feature index set comprising a plurality of feature indexes for predicting a score of the target application; acquiring a set of feature information corresponding to the target application from the internet data according to the plurality of feature indexes, wherein the set of feature information comprises feature information corresponding to each of the plurality of feature indexes; and taking the set of the characteristic information as input of a score prediction model, and running the score prediction model to obtain a target score corresponding to the target application. The embodiment of the application also provides equipment for determining the application score, which is used for saving the labor cost for evaluating the target application score and improving the efficiency of evaluating the target application.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a method and apparatus for determining an application score.
Background
With the development of intelligent terminals, various applications are dazzled, users often need to find better applications in the applications of the same category, the score is often used as one of the common means for evaluating whether things are good or bad, and of course, the score is also applied to the current evaluation of various applications, taking game applications as an example, and the users judge whether the game is interesting or not through the score of the current game.
The game score is simply that through testing, analyzing, playing and the like of a certain game, an evaluation score is given on a plurality of characteristic indexes (such as pictures, music and drama), and finally, the score of each index is integrated to give an overall evaluation score, so that the game playability is described.
There are many methods of game scoring, such as expert evaluation and player trial play, but most of the above methods are implemented by relying on human labor, which results in high cost and inefficiency of game scoring work.
Disclosure of Invention
The embodiment of the application provides a method and equipment for determining an application score, which are used for improving the evaluation efficiency of target applications.
In a first aspect, an embodiment of the present application provides a method for determining an application score, including:
obtaining a target application of a score to be predicted;
determining a set of feature indicators corresponding to the target application, the set of feature indicators including a plurality of feature indicators for predicting the target application score;
acquiring a set of characteristic information of the target application from internet data according to the plurality of characteristic indexes, wherein the set of characteristic information comprises characteristic information corresponding to each characteristic index in the plurality of characteristic indexes;
And taking the set of the characteristic information as input of a score prediction model, and operating the score prediction model to obtain a target score corresponding to the target application.
In a second aspect, an embodiment of the present application provides an apparatus for determining an application score, including:
the first acquisition module acquires a target application of a score to be predicted;
a first determining module that determines a set of feature indicators corresponding to the target application, the set of feature indicators including a plurality of feature indicators for predicting the target application score;
the second acquisition module is used for acquiring a set of characteristic information of the target application from internet data according to the plurality of characteristic indexes determined by the first determination module, wherein the set of characteristic information comprises characteristic information corresponding to each characteristic index in the plurality of characteristic indexes;
and the score prediction module is used for taking the set of the characteristic information acquired by the second acquisition module as input of a score prediction model, and running the score prediction model to obtain a target score corresponding to the target application.
In a third aspect, an embodiment of the present application provides an apparatus for determining an application score, including:
A memory for storing computer executable program code;
network interface, and
a processor coupled with the memory and the network interface;
wherein the program code comprises instructions which, when executed by the processor, cause the apparatus to perform the method of the first aspect described above.
In a fourth aspect, embodiments of the present application provide a computer storage medium containing computer software instructions for use in an apparatus for storing a determined score, for performing the method of the first aspect.
In the embodiment of the application, equipment determines a target application of a score to be predicted; acquiring a characteristic index set corresponding to the target application, wherein the characteristic index is used for describing from which aspects the target application is evaluated, and the characteristic index set can comprise a plurality of characteristic indexes; acquiring a set of feature information, wherein the set of feature information comprises feature information corresponding to the target application under each of the plurality of feature indexes; and then, taking the set of the characteristic information as input of a score prediction model, and operating the score prediction model to obtain a target score corresponding to the target application. The target score is the evaluation score of the target application, the target application is not required to be scored by manpower, the labor cost is saved, the scoring time of the target application is shortened, and the evaluation efficiency of the target application is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings to those skilled in the art.
FIG. 1 is a flowchart illustrating steps of one embodiment of a method for determining an application score in accordance with an embodiment of the present application;
FIG. 2 is an exemplary diagram of a feature index in an embodiment of the present application;
FIG. 3 is a diagram illustrating quantization of feature information according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating an architecture of an embodiment of a system for determining an application score in accordance with an embodiment of the present application;
FIG. 5 is a flowchart illustrating steps of another embodiment of a method for determining an application score according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating one embodiment of an apparatus for determining an application score in accordance with an embodiment of the present application;
FIG. 7 is a schematic diagram of another embodiment of an apparatus for determining an application score according to an embodiment of the present application;
FIG. 8 is a schematic diagram illustrating another embodiment of an apparatus for determining an application score according to an embodiment of the present application;
FIG. 9 is a schematic diagram illustrating another embodiment of an apparatus for determining an application score according to an embodiment of the present application;
FIG. 10 is a schematic diagram illustrating another embodiment of an apparatus for determining an application score according to an embodiment of the present application;
fig. 11 is a schematic structural view of another embodiment of an apparatus for determining an application score according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a method for determining an application score, which is used for saving labor cost for evaluating a target application score and improving efficiency of evaluating the target application.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, shall fall within the scope of protection of the application.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the application provides a method for determining scores, which can be applied to the evaluation of various types of applications, for example, the applications can be applications of living types, applications of games and the like, the method can be used for scoring the applications, and a user can compare the advantages and disadvantages of the applications in the same type through the scores.
For example, the application may be a life-type application, the three applications of 'beauty drawing show', 'day P drawing', 'shadow magic hand' can be scored by the method in the embodiment of the application, the user can select the application with high score through the score; the application may also be a game application, by which a designated game may be scored, and a player may select a game with a high score by scoring.
The method for determining the score provided by the embodiment of the application can be applied to a system for determining the score, and the system can comprise 3 servers with different functions. In practical application, the 3 servers may be integrated into a device for determining scores to deploy, and a specific deployment architecture is not limited in the embodiment of the present application, and the device may be a server.
In the embodiment of the application, the score of the application is predicted by a pre-trained score prediction model, and the application is described by two parts, namely, the first part describes the training of the score prediction model and the second part describes the scoring process of the target application by the score prediction model.
Referring now to FIG. 1, FIG. 1 is a flowchart illustrating steps of one embodiment of a method for determining an application score according to an embodiment of the present application. In this embodiment, the device side for determining the score will be described.
Training of a score prediction model:
step 101, determining a plurality of applications.
The plurality of applications may be a specified plurality of games that may be stored in a list, for example, as shown in table 1 below:
TABLE 1
| Name of the name | |
| 1 | Switch version My world |
| 2 | Flame hank Zhang Huisheng: another hero |
| 3 | Iron boxing 7 |
| 4 | Limit racing: horizon 3 wind-fire wheel |
| 5 | Soul of Taitan |
It should be noted that the games shown in table 1 are only examples, and in practical applications, more games may be included in the list, and the games in the game list are samples of the training score prediction model.
Step 102, acquiring a characteristic information data set according to the characteristic index set, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications under the plurality of characteristic indexes.
The set of characteristic indicators includes a plurality of characteristic indicators that are used to represent specific aspects of the assessment.
It should be noted that, in this example, a game application is taken as an example, and the feature index is further described, and as will be understood with reference to fig. 2, fig. 2 is a schematic diagram of the feature index in an embodiment of the present application.
For a player, which aspects affect the player's assessment of the game, then starting from this aspect, for example, the core aspects of the game assessment may include: 1. storyline of the game; 2. initial experience; 3. designing a game; 4. experience evaluation; 5. game expressive force. Further, the evaluating core is subdivided conveniently to obtain specific characteristic indexes, wherein the feature indexes obtained by subdividing the story aspect of the game include: materials, story audiences, script documents, task targets, etc.; subdividing the initial experience aspect, wherein the obtained characteristic indexes comprise: media evaluation, player evaluation, professional evaluation, etc.; subdividing the aspect of game design, wherein the obtained characteristic indexes comprise: core play, player type, innovation points, mission systems, team members, historical works, and so forth; subdividing game expressive force includes: player interaction capability, visual presentation, sound effects, 2D/3D/VR, etc. In the embodiment of the present application, the feature indexes of the game may take 18 feature indexes shown in fig. 2 as an example, and it should be noted that the feature indexes in the present application are also only illustrative and not limiting the present application, and the feature indexes are different in different types of applications, such as scoring for life-class applications, and the determination of the feature indexes is the feature indexes capable of reflecting the advantages and disadvantages of the application.
In one implementation, a set of information for each of a plurality of applications is crawled from internet data. The information set of each application is crawled according to the name of each application. In the embodiment of the application, the Internet data comprises data issued by an application developer and data generated by a user using the Internet. For example: game data posted by game developers, data posted by users of game comment websites, game comments posted by users in game forums, game data generated by users playing games, and the like. In order to improve the efficiency of crawling content, in this example, a theme crawler may be used to crawl an information set of each application, and a corresponding theme may be predefined, where the theme may be a name of each game, so that web content related to the game may be selectively crawled.
The theme crawler judges whether a page is related to a certain characteristic theme (such as the name of one game) in advance, and when the page is downloaded, the crawler uses a classifier to determine whether the page is related to the theme; if relevant, the hyperlinks in the page are retained and used to search for other relevant sites. When accessing hyperlinks contained in a page, the crawler continues to determine whether the page content needs to be downloaded according to and by determining the topic relevance of the page.
For example, according to the content in table 1, an information set of the game in table 1 is obtained, where the information set includes information related to the application, for example, information possibly including a feature index of the application, and includes installation package information, a profile, and the like of the application, of course, the installation package information is not required in the data set, and then, further, the information set is classified according to a plurality of feature indexes to obtain a set of feature information under each feature index, that is, the information in the information set is classified according to the above feature index, for example, including the following information in the information set: the game experience of the 'nintendo switch' is presented, portability and control feel of entity keys are brought to players, no voice chat is regrettable, the mode of multiple persons who play the game is not as happy as other versions, and therefore the scene which is most suitable for the switch board 'My world' is the scene which is in the same room as a small partner. The above information may be classified under the characteristic index of "player evaluation". The above-described information on player evaluation is merely an example for convenience of explanation, and does not limit the present application.
The feature information dataset includes a set of feature information corresponding to each of a plurality of applications. An example of this feature information dataset is shown in table 2 below:
TABLE 2
It should be noted that, the set of feature information corresponding to each game in table 2 above includes the first feature information, the second feature information, the third feature information, and so on, and in table 2, only illustrative examples are given for easy understanding, and do not limit the description of the present application.
In another implementation manner, the server may crawl the feature information of each application under each feature index from the internet data directly according to the feature indexes, and crawl the corresponding feature information from some game comment websites by taking the name and the feature index of the game as the subject, for example, crawl the feature information related to the sound effect from the game comment websites according to the soul and the sound effect of taitan. For each game, each feature index corresponds to the feature information under that feature index, and a general game may be analyzed from 18 feature indexes as in fig. 2, in this example, the feature information data set includes a set of feature information of 5 games, and the set of feature information of each game includes feature information corresponding to 18 feature indexes.
Further, the characteristic index further comprises a plurality of sub-characteristic indexes, and for each application in the plurality of applications, target information corresponding to each characteristic information in the set of characteristic information under each sub-characteristic index is determined; and quantizing the target information to obtain quantized characteristic values.
As will be understood with reference to fig. 3, in the example of fig. 3, the feature information of each feature index is quantized, and in the example of fig. 3, the feature index of "core play" is taken as an example, and the feature index of "core play" includes a plurality of sub-feature indexes, for example, the sub-feature indexes include: player against player (player versus player, PVP), player versus environment (play VS environment, PVE), collaboration (Co-op), value growth, capacity growth, collection, and the like.
For each game, the obtained feature information is quantized, and the feature information can be classified according to sub-feature indexes, for example, taking the "Don't star" game as an example, the feature information of the core playing method of the game includes: the game is PVEs and is a cooperative game, the virtual character can perform collection equipment, numerical growth and capability growth are performed, and the game is not PVP type; through the characteristic information, the sub-characteristic index PVP is corresponding to the target information which is not PVP type, the target information which is not PVP type is quantized, the sub-characteristic index PVP is assigned to be 0, and the characteristic value corresponding to the sub-characteristic index is obtained; similarly, if the game is of the PVE type, the game corresponds to the sub-feature index PVE and is assigned a value of 1; the game is a cooperation type game, corresponds to a sub-feature index Co-op and is assigned as 1, and is a numerical growth type game, corresponds to a sub-feature index numerical growth and is assigned as 1; the game is a capability growth type game, and corresponds to a sub-feature index "capability growth", and assigns a value of "1", etc., and it should be noted that, for a plurality of applications in fig. 3, feature information of one game is quantized and described in this example, and other games are not repeated.
The equipment determines a set of sub-feature indexes and feature values corresponding to the set of feature information in all games; the sub-feature indexes and the feature values are training sample data and are used for training a score prediction model.
The feature information data set is training sample data, and is used for training to obtain a score prediction model.
In another possible implementation, the feature information dataset may be divided into several sub-datasets, each for training one sub-model, as understood with reference to fig. 2, the sub-model may be trained according to several different aspects of the game evaluation core, e.g., a first sub-dataset for the "game story" aspect, a second sub-dataset for the "initial experience" aspect, a third sub-dataset for the "game design" aspect, a fourth sub-dataset for the "experience evaluation" aspect, respectively; a fifth sub-data set concerning the "game expressive force" aspect.
Referring to fig. 2, a first sub-data set is taken as an example to illustrate, where the first sub-data set includes feature information corresponding to each of the 4 feature indexes, for example, feature information in the aspect of "game story nature" includes feature information corresponding to "subject material", feature information corresponding to "story audience", feature information corresponding to "play text" and feature information corresponding to "task objective", and in this example, only the first sub-data set is taken as an example to illustrate, and other sub-data sets may be understood with reference to the first sub-data set, which is not repeated herein.
Further, the characteristic information in each sub-data set is quantized to obtain sub-characteristic indexes and corresponding characteristic values in each sub-data set.
And 103, learning and training the characteristic information data set to obtain a score prediction model.
In one possible implementation, the feature information dataset is used as training data to learn and train a set of sub-feature indexes and feature values in a plurality of games to obtain a score prediction model. The score prediction model comprises a corresponding relation between a characteristic value and a score, and is used for predicting the score of the game.
In another implementation, the score prediction model may include a plurality of sub-models, which may be trained according to several different aspects of the game evaluation core, and learned and trained from sub-data sets to obtain the sub-models. For example, training the first sub-data set to obtain a first sub-model regarding the "game storyline" aspect; learning and training the second sub-data set to obtain a second sub-model related to the 'initial experience' aspect; learning and training the third sub-data set to obtain a third sub-model concerning the aspect of 'game design'; learning and training the fourth sub-data set to obtain a fourth sub-model related to the 'experience evaluation' aspect; the fifth sub-data set is learned and trained to obtain a fifth sub-model regarding the aspect of "game expressivity", and it should be noted that, in the embodiment of the present application, the sub-model is an exemplary description, and does not constitute a limiting description of the present application. Each sub-model may predict a relevant portion of the game, e.g., a first sub-model may predict a "game storyline" aspect of the game, yielding a score for that portion.
The relative effect of each sub-model is evaluated, weight distribution is carried out on each sub-model, and the product of the predicted value of each model and the weight is taken as the final value of the game. In this example, several parts of the core evaluation of the game can be respectively predicted by several sub-models to obtain scores of different aspects, further, the product of the predicted score and the weight of each sub-model is used as a final score, so that a player can select the game according to the scores of the concerned aspects, for example, the player can compare the story of the game when playing the game, consider that as long as the story of the game is better, other aspects can be selected with less scores, the player can select the application according to the scores of the single evaluation aspect, and the game can also be selected through the total score of the game.
The score prediction model can be a logistic regression score prediction model, a Bayesian Internet data score prediction model, a support vector machine (support vector machine, SVM) score prediction model, deep neural Internet data, recursive Internet data, convolutional neural Internet data and the like.
It should be noted that, steps 101 to 103 are optional steps, may be performed off-line, or may be performed on-line, and steps 101 to 103 are steps for training the score prediction model, and after the score prediction model training is completed, step 104 may be directly performed without performing steps 101 to 103.
The following describes the score prediction of a target game using a score prediction model:
and 104, obtaining target application of the score to be predicted.
The target application for determining the predictive value is not limited to the category of the target application, and for example, the target application may be a life-class application or a game-class application.
For example, the target application is "game a".
Step 105, determining a feature index set corresponding to the target application, wherein the feature index set comprises a plurality of feature indexes for predicting the target application score.
Obtaining a preset characteristic index set according to the target application, wherein the category of the target application is a game, and obtaining the preset characteristic index set of the game, as shown in fig. 2, wherein the preset characteristic index set comprises: subject matter, story audience, script, task objective; media ratings, player ratings, professional ratings, core play, player types, innovation points, mission systems, team members, historical works, and so forth.
In this example, the feature index set is merely illustrative, and is not meant to be a limiting illustration of the present application, and in this example, the target application is a game, and the feature index set is a feature index for analyzing a core aspect of game evaluation. It should be noted that, if the target application is a living application (such as a mei xiu), the obtained feature index is a feature index corresponding to the application, which is not illustrated here.
And 106, acquiring a set of characteristic information of the target application from the internet data according to the plurality of characteristic indexes, wherein the set of characteristic information comprises characteristic information corresponding to each characteristic index in the plurality of characteristic indexes.
Specifically, in one implementation, the server crawls feature information of the target application under each feature index from the internet data according to the plurality of feature indexes, and the set of feature information includes feature information under each feature index corresponding to the plurality of feature indexes.
Taking the name and the characteristic index of the game A as a theme, adopting a theme crawler to crawl the characteristic information of the game A under each characteristic index from Internet data, for example, crawling the characteristic information of the game A under the characteristic index of 'subject', the characteristic information of the game A under the characteristic index of 'media evaluation', and the like. Referring to fig. 2, a set of feature information of game a under 13 feature indexes may be acquired. In the embodiment of the present application, in one implementation manner, the feature information of the target application corresponding to each feature index may be periodically crawled from the internet data, the feature information is stored locally, and then the set of feature information is read locally, where the set of feature information is used as input of a score prediction model, or the set of feature information of the target application obtained from the internet data is directly used as input of the score prediction model.
Further, each feature index further includes a plurality of sub-feature indexes, as shown in fig. 3, and corresponding target information under each sub-feature index in the feature information is determined.
For example, under the characteristic index of "core playing method", the characteristic index further includes sub-characteristic indexes such as "PVP", and the corresponding target information under the sub-characteristic indexes of "PVP" is: the method comprises the steps of non-PVP type, quantization of target information, value assignment of quantized characteristic values, and value assignment of PVP corresponding characteristic values of 0, wherein in the example, if the PVP corresponds to the sub-characteristic indexes, the PVP is assigned to 1, and if the PVP does not correspond to the sub-characteristic indexes, the PVP is assigned to 0; in this example, assignment of other sub-feature indexes is not described in detail.
And determining a sub-feature index and a set of feature values corresponding to each feature information in the set of feature information.
In another implementation, the set of feature information may be classified to obtain N subsets, where N is a positive integer greater than or equal to 1, and the feature information in each subset is used as an input to a correlation submodel to obtain a predictive score. For example, the feature information is classified according to the core aspect as shown in FIG. 3, and the feature information is classified into a subset of feature information on the aspect of "game story" including, for example, feature information on a subject, feature information on a story audience, feature information on a scenario, and feature information on a task objective, a subset of feature information on the aspect of "initial experience", a subset of feature information on the aspect of "game design", and a subset of feature information on the aspect of "experience evaluation".
Further, the information in each feature information subset is quantized, for example, the feature information of the "game design" aspect includes feature information of the "core play", feature information of the "play type", and the like, and each feature information in the subset is quantized to obtain a feature value of the feature information quantized, so as to obtain a feature value of the feature information subset of each aspect.
And 107, taking the set of the characteristic information as input of a score prediction model, and running the score prediction model to obtain a target score corresponding to the target application.
In one possible implementation, the set of sub-feature indicators and feature values of the target application as shown in fig. 3 is used as input to a score prediction model, which outputs the target score of the target application.
In another possible implementation manner, N sub-model combinations may be used to predict the target score of the target application, and the feature information in each sub-set is used as an input of the related sub-model to obtain the predicted score. For example, a first sub-model is used to predict the value of the characteristic value of the first sub-set of characteristic information in the aspect of "game story", a first score is output, the first score is the value of the characteristic value of the game a in the aspect of "game story", a second sub-model is used to predict the value of the characteristic value of the second sub-set of characteristic information in the aspect of "game design", a second score is output, the second score is the value of the characteristic value of the game a in the aspect of "game design", and the like, and then the product of the predicted value and the weight of each model is used as the final score of the game. In this example, several parts of the core evaluation of the game may be respectively predicted by several sub-models to obtain scores in different aspects, further, the product of the predicted score and the weight of each sub-model is used as a final score, so that the player may select the game according to the scores of the concerned aspects, for example, the player may pay attention to the story nature of the game when playing the game, consider that as long as the story nature of the game is better, other aspects have less scores and may also be selected, the player may select the application according to the score of a single evaluation aspect, and may also select the game according to the total score of the game, thereby improving the application flexibility of the target application.
In the embodiment of the application, the target application of the score to be predicted is determined; acquiring a preset characteristic index set, wherein the characteristic index set comprises a plurality of characteristic indexes; acquiring a set of feature information, wherein the set of feature information comprises feature information corresponding to each feature index of the plurality of feature indexes of the target application; and then, predicting according to the set of the characteristic information by adopting a score prediction model to obtain a target score corresponding to the target application. The target score is the evaluation score of the target application, the target application is not required to be scored by manpower, the labor cost is saved, the scoring time of the target application is shortened, and the evaluation efficiency of the target application is improved.
The embodiment of the application provides a system for determining scores, referring to fig. 4, fig. 4 is a schematic diagram of a structure of the system for determining applied scores. In this embodiment, the functions of the servers in the embodiment corresponding to fig. 1 may be performed by 3 servers, where the 3 servers are respectively a crawler server, an algorithm server and a feature database.
The crawler server is responsible for crawling feature information of the specified game from the Internet, quantifying the feature information, and storing the quantified feature value into a game feature library.
The game feature library is responsible for storing feature information of a plurality of applications (such as games) and feature values corresponding to the feature information.
The algorithm server is responsible for pulling feature information of a plurality of applications from the game feature library, training the feature information to obtain a score prediction model, and then determining a target score of a target application (such as a designated game) by using the score prediction model.
Specifically, referring to fig. 5, fig. 5 is a flowchart illustrating steps of an embodiment of a method for determining an application score. In one application scenario, each server performs the following steps:
step 501, a crawler server acquires a game list including a plurality of games from a feature database.
Specifically, referring to step 101 in the corresponding embodiment of fig. 1, details are omitted here.
Step 502, the crawler server crawls the feature information set of each game from the internet data.
Specifically, referring to step 102 in the corresponding embodiment of fig. 1, details are omitted here.
Step 503, the crawler server stores the set of the feature information of each game into a feature database;
step 504, the algorithm server requests feature information data sets corresponding to a plurality of games from the feature database.
Step 505, the feature database feeds back feature information data sets corresponding to the games to the algorithm server.
And step 506, training by the algorithm server according to the feature information data sets corresponding to the games to obtain a score prediction model, wherein the score prediction model comprises the corresponding relation between the feature information and the score.
Specifically, referring to step 103 in the corresponding embodiment of fig. 1, details are omitted here.
And 507, predicting the score of the target application by using the score prediction model by the algorithm server to obtain the target score of the target application.
Specifically, refer to steps 104-107 in the corresponding embodiment of fig. 1, which are not repeated here.
In the embodiment of the application, the characteristic information of the game is acquired in an automatic crawler mode, the characteristic information is trained by using a machine learning algorithm to obtain the score prediction model, and the score prediction model is used for predicting the evaluation score of the target game, so that the labor cost of evaluating the target game by manpower is saved, and the game evaluation efficiency is improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of an apparatus for determining an application score according to an embodiment of the present application, and an embodiment of an apparatus 600 for determining an application score according to an embodiment of the present application includes:
A first obtaining module 601, which obtains a target application of a score to be predicted;
a first determining module 602 that determines a set of feature indicators corresponding to the target application, the set of feature indicators including a plurality of feature indicators for predicting a score of the target application;
a second obtaining module 603, configured to obtain, from the internet data, a set of feature information corresponding to the target application according to the plurality of feature indexes determined by the first determining module 602, where the set of feature information includes feature information corresponding to each of the plurality of feature indexes;
and a score prediction module 604, configured to take the set of the feature information acquired by the second acquisition module 603 as an input of a score prediction model, and operate the score prediction model to obtain a target score corresponding to the target application.
Referring to fig. 7, another embodiment of an apparatus 700 for determining an application score is provided in an embodiment of the present application based on the corresponding embodiment of fig. 6;
the second acquisition module 603 includes a crawling unit 6031;
the crawling unit 6031 is configured to crawl, from the internet data, feature information corresponding to each feature index according to each feature index of the plurality of feature indexes acquired by the first determining module 602, where a set of feature information includes feature information under each feature index corresponding to the plurality of feature indexes.
Based on the corresponding embodiment of fig. 7, referring to fig. 8, another embodiment of an apparatus 800 for determining a score is provided in an embodiment of the present application;
each feature index further includes a plurality of sub-feature indexes, and the second acquisition module 603 further includes a first determination unit 6032, a quantization unit 6033, and a second determination unit 6034;
a first determining unit 6032 for determining target information corresponding to each sub-feature index in the feature information crawled by the crawling unit 6031;
a quantization unit 6033, configured to quantize the target information determined by the first determination unit 6032, to obtain a quantized feature value;
a second determining unit 6034 for determining a set of sub-feature indexes and feature values corresponding to the set of feature information quantized by the quantizing unit 6033;
the score prediction module 604 is further configured to use the set of the sub-feature indexes and the feature values determined by the second determining unit 6034 as an input of the score prediction model, and operate the score prediction model to obtain a target score corresponding to the target application.
In a possible implementation manner, the score prediction module 604 is further configured to use each subset of the N subsets as an input of a corresponding sub-model of the N sub-models, and operate the N sub-models to obtain N sub-scores; and obtaining the target score corresponding to the target application according to the weight corresponding to each sub-model and the N sub-scores.
Referring to fig. 9, another embodiment of an apparatus 900 for determining an application score is provided in an embodiment of the present application based on the corresponding embodiment of fig. 6;
the apparatus further comprises a second determination module 605, a third acquisition module 606 and a training module 607;
a second determining module 605 for determining a plurality of applications;
a third obtaining module 606, configured to obtain a feature information data set according to the feature index set, where the feature information data set includes a set of feature information corresponding to each of the plurality of applications determined by the second determining module 605 under the plurality of feature indexes;
the training module 607 is configured to learn and train the feature information dataset acquired by the third acquiring module 606 to obtain a score prediction model.
In one possible implementation, the third obtaining module 606 is further configured to crawl an information set of each of the plurality of applications from the internet data; classifying the information sets according to the plurality of characteristic indexes to obtain a set of characteristic information under each characteristic index, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications.
In a possible implementation manner, the third obtaining module 606 is further configured to crawl, from the internet data, feature information of each application in the plurality of applications under each feature index according to the plurality of feature indexes, where the feature information dataset includes a set of feature information corresponding to each application in the plurality of applications.
Referring to fig. 10, another embodiment of an apparatus 1000 for determining an application score is provided in an embodiment of the present application based on the corresponding embodiment of fig. 9;
the feature indicators further comprise a plurality of sub-feature indicators, the apparatus further comprising a third determination module 608;
a third determining module 608, configured to determine, for each application in the plurality of applications, target information corresponding to each feature information in the set of feature information acquired by the third acquiring module 606 under each sub-feature index;
quantizing the target information to obtain quantized characteristic values;
determining a sub-feature index corresponding to the feature information set and a feature value set;
the training module 607 is further configured to learn and train the sub-feature indexes and the set of feature values determined by the third determining module 608 to obtain a score prediction model.
Further, the devices of FIGS. 6-10 that determine application scores are presented in the form of functional modules. "module" herein may refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that execute one or more software or firmware programs, an integrated logic circuit, and/or other devices that can provide the described functionality. In a simple embodiment, the apparatus of fig. 6-10 may take the form shown in fig. 11. The modules may be implemented by the processor, transceiver, and memory of fig. 11.
FIG. 11 is a schematic diagram of a device for determining an application score, where the device 1100 for determining the score may vary widely depending on configuration or performance, and may include one or more processors 1122 and memory 1132, one or more storage mediums 1130 (e.g., one or more mass storage devices) storing applications 1142 or data 1144, according to an embodiment of the present application. Wherein the memory 1132 and the storage medium 1130 may be transitory or persistent. The program stored on the storage medium 1130 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, a processor 1122 may be provided in communication with the storage medium 1130, executing a series of instruction operations in the storage medium 1130 on the server 1100.
The apparatus 1100 for determining a score may also include one or more power supplies 1126, one or more wired or wireless network interfaces 1150, one or more input-output interfaces 1158, and/or one or more operating systems 1141.
The steps performed by the score determining device in the above embodiment may be based on the score determining device structure shown in fig. 11. Processor 1122 causes the device to perform the steps performed by the device to determine scores in the embodiment corresponding to fig. 1 and the steps performed by the crawler server, algorithm server and feature database in the embodiment corresponding to fig. 5.
Specifically, the processor 1122 is configured to cause the device to specifically perform the following steps:
determining target application of the score to be predicted;
acquiring a preset characteristic index set, wherein the characteristic index set comprises a plurality of characteristic indexes;
acquiring a set of feature information, wherein the set of feature information comprises feature information corresponding to each feature index of the plurality of feature indexes of the target application;
and predicting according to the set of the characteristic information by adopting a score prediction model to obtain a target score corresponding to the target application.
In one possible implementation, the processor 1122 is further configured to crawl, from the internet data, feature information of the target application under each feature index according to a plurality of feature indexes, where the set of feature information includes feature information under each feature index corresponding to the plurality of feature indexes.
In one possible implementation, each feature indicator further includes a plurality of sub-feature indicators, and the processor 1122 is further configured to determine target information corresponding to each sub-feature indicator in the feature information; quantizing the target information to obtain quantized characteristic values; determining a sub-feature index corresponding to the feature information set and a feature value set; and predicting the score by adopting a score prediction model according to the sub-characteristic indexes and the set of characteristic values to obtain a target score corresponding to the target application.
In one possible implementation, the score prediction model includes N sub-models, the set of feature information includes N sub-sets, and the processor 1122 is further configured to predict a corresponding subset of the N sub-sets by using each of the N sub-models to obtain N sub-scores; and obtaining a target score corresponding to the target application according to the weight corresponding to each sub-model and the N sub-scores.
In one possible implementation, the processor 1122 is also used to determine a number of applications; acquiring a characteristic information data set according to the characteristic index set, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications under the plurality of characteristic indexes; and learning and training the characteristic information data set to obtain a score prediction model.
In one possible implementation, the processor 1122 is further configured to crawl an information set for each of a plurality of applications from the internet data; classifying the information sets according to the plurality of characteristic indexes to obtain a set of characteristic information under each characteristic index, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications.
In one possible implementation, the processor 1122 is further configured to crawl, from the internet data, feature information for each of the plurality of applications under each feature indicator according to the plurality of feature indicators, wherein the feature information data set includes a set of feature information corresponding to each of the plurality of applications.
In one possible implementation, the feature information further includes a plurality of sub-feature indicators, and the processor 1122 is further configured to determine, for each of the plurality of applications, target information corresponding to each of the feature information in the set of feature information under each of the sub-feature indicators; quantizing the target information to obtain quantized characteristic values; determining a sub-feature index corresponding to the feature information set and a feature value set; and carrying out learning training on the sub-characteristic indexes and the characteristic value sets to obtain a score prediction model.
The present application also provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of the above-described method embodiments.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (11)
1. A method of determining an application score, comprising:
obtaining a target application of a score to be predicted;
determining a set of feature indicators corresponding to the target application, the set of feature indicators including a plurality of feature indicators for predicting the target application score;
acquiring a set of feature information corresponding to the target application from internet data according to the plurality of feature indexes, wherein the set of feature information comprises feature information corresponding to each of the plurality of feature indexes; the set of the characteristic information comprises N subsets, and the N subsets respectively correspond to characteristic information of the target application in different aspects;
The feature information collection is used as input of a score prediction model, the score prediction model is operated, and the target score corresponding to the target application is obtained, specifically comprising the following steps: each subset of the N subsets is used as input of a corresponding sub-model of N sub-models of the score prediction model, the N sub-models are operated to obtain N sub-scores, and a target score corresponding to the target application is obtained according to the weight corresponding to each sub-model and the N sub-scores; the N sub-scores each correspond to a predicted score of the target application in a different aspect; the N sub-scores are used for enabling a user to select the target application according to the sub-scores corresponding to the target application in a single aspect;
the training process of the score prediction model comprises the following steps: determining a plurality of applications; acquiring a characteristic information data set according to a characteristic index set, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications under a plurality of characteristic indexes; learning and training the characteristic information data set to obtain the score prediction model; the feature information dataset includes a plurality of sub-datasets; the plurality of sub-data sets each correspond to characteristic information of the plurality of applications in different aspects; each of the plurality of sub-data sets is used to train a sub-model.
2. The method according to claim 1, wherein the obtaining the set of feature information of the target application from internet data according to the plurality of feature indicators comprises:
and crawling the corresponding characteristic information of each characteristic index from the internet data according to each characteristic index in the plurality of characteristic indexes, wherein the set of the characteristic information comprises the characteristic information under each characteristic index corresponding to the plurality of characteristic indexes.
3. The method of claim 2, wherein each of the characteristic metrics further comprises a plurality of sub-characteristic metrics, the method further comprising:
determining corresponding target information under each sub-characteristic index in the characteristic information;
quantizing the target information to obtain quantized characteristic values;
determining a set of sub-feature indexes and feature values corresponding to the set of feature information;
the feature information collection is used as input of a score prediction model, the score prediction model is operated, and the target score corresponding to the target application is obtained, and the feature information collection comprises the following steps:
and taking the collection of the sub-characteristic indexes and the characteristic values as the input of the score prediction model, and operating the score prediction model to obtain the target score corresponding to the target application.
4. The method of claim 1, wherein the obtaining a feature information dataset from a feature index set comprises:
crawling an information set of each application in the plurality of applications from internet data;
classifying the information sets according to the plurality of characteristic indexes to obtain a set of characteristic information under each characteristic index, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in a plurality of applications.
5. The method of claim 1, wherein the obtaining a feature information dataset from a feature index set comprises:
and crawling the characteristic information of each application in the plurality of applications under each characteristic index from the internet data according to the plurality of characteristic indexes, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications.
6. The method of claim 4 or 5, wherein the characteristic index further comprises a plurality of sub-characteristic indexes, the method further comprising:
for each application in the plurality of applications, determining target information corresponding to each piece of characteristic information in the set of characteristic information under each piece of sub-characteristic index;
Quantizing the target information to obtain quantized characteristic values;
determining a set of sub-feature indexes and feature values corresponding to the set of feature information;
the learning and training of the characteristic information data set to obtain the score prediction model comprises the following steps:
and carrying out learning training on the sub-characteristic indexes and the characteristic value sets to obtain the score prediction model.
7. An apparatus for determining an application score, comprising:
the first acquisition module acquires a target application of a score to be predicted;
a first determining module that determines a set of feature indicators corresponding to the target application, the set of feature indicators including a plurality of feature indicators for predicting the target application score;
the second acquisition module is used for acquiring a set of characteristic information corresponding to the target application from internet data according to the plurality of characteristic indexes determined by the first determination module, wherein the set of characteristic information comprises characteristic information corresponding to each characteristic index in the plurality of characteristic indexes; the set of the characteristic information comprises N subsets, and the N subsets respectively correspond to characteristic information of the target application in different aspects;
The score prediction module is configured to use the set of the feature information acquired by the second acquisition module as an input of a score prediction model, and operate the score prediction model to obtain a target score corresponding to the target application, where the score prediction module specifically includes: each subset of the N subsets is used as input of a corresponding sub-model of N sub-models of the score prediction model, the N sub-models are operated to obtain N sub-scores, and a target score corresponding to the target application is obtained according to the weight corresponding to each sub-model and the N sub-scores; the N sub-scores each correspond to a predicted score of the target application in a different aspect; the N sub-scores are used for enabling a user to select the target application according to the sub-scores corresponding to the target application in a single aspect;
a second determining module for determining a plurality of applications;
the third acquisition module is used for acquiring a characteristic information data set according to the characteristic index set, wherein the characteristic information data set comprises a set of characteristic information corresponding to each application in the plurality of applications under the plurality of characteristic indexes;
the training module is used for learning and training the characteristic information data set to obtain the score prediction model; the feature information dataset includes a plurality of sub-datasets; the plurality of sub-data sets each correspond to characteristic information of the plurality of applications in different aspects; each of the plurality of sub-data sets is used to train a sub-model.
8. The apparatus of claim 7, wherein the second acquisition module comprises a crawling unit;
the crawling unit is configured to crawl, from internet data, feature information corresponding to each feature index according to each feature index in the plurality of feature indexes determined by the first determining module, where the set of feature information includes feature information under each feature index corresponding to the plurality of feature indexes.
9. The apparatus of claim 8, wherein each of the characteristic indicators further comprises a plurality of sub-characteristic indicators, and the second acquisition module further comprises a first determination unit, a quantization unit, and a second determination unit;
the first determining unit is used for determining corresponding target information under each sub-characteristic index in the characteristic information crawled by the crawling unit;
the quantization unit is used for quantizing the target information determined by the first determination unit to obtain a quantized characteristic value;
the second determining unit is used for determining a set of sub-feature indexes and feature values corresponding to the set of the feature information quantized by the quantizing unit;
the score prediction module is further configured to use the set of the sub-feature indexes and the feature values as input of the score prediction model, and operate the score prediction model to obtain a target score corresponding to the target application.
10. An apparatus for determining an application score, comprising:
a memory for storing computer executable program code;
network interface, and
a processor coupled with the memory and the network interface;
wherein the program code comprises instructions which, when executed by the processor, cause the apparatus to perform the method of any of claims 1-6.
11. A computer storage medium, characterized by computer software instructions for a device for storing a determined application score, comprising instructions for performing the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293738.XA CN110163460B (en) | 2018-03-30 | 2018-03-30 | Method and equipment for determining application score |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293738.XA CN110163460B (en) | 2018-03-30 | 2018-03-30 | Method and equipment for determining application score |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110163460A CN110163460A (en) | 2019-08-23 |
| CN110163460B true CN110163460B (en) | 2023-09-19 |
Family
ID=67636593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810293738.XA Active CN110163460B (en) | 2018-03-30 | 2018-03-30 | Method and equipment for determining application score |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110163460B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115738285A (en) * | 2023-01-08 | 2023-03-07 | 深圳市乐讯科技有限公司 | Game quality evaluation feedback method and system |
Citations (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634356A (en) * | 2012-08-24 | 2014-03-12 | 百度在线网络技术（北京）有限公司 | Method and system for packing downloading of a plurality of application programs, and apparatuses |
| CN104679852A (en) * | 2015-02-12 | 2015-06-03 | 广东欧珀移动通信有限公司 | Method and device for recommending application software |
| CN104750538A (en) * | 2013-12-27 | 2015-07-01 | 伊姆西公司 | Virtual storage pool providing method and system for target application |
| CN105096058A (en) * | 2015-08-20 | 2015-11-25 | 北京中电普华信息技术有限公司 | Data processing method and device for customer service staff scoring system |
| CN105160418A (en) * | 2015-08-05 | 2015-12-16 | 国家电网公司 | Charging distribution predication method based on electric vehicle application features |
| CN105354092A (en) * | 2015-11-19 | 2016-02-24 | 东软集团股份有限公司 | Method, device and system for predicting application performance risk |
| CN105516247A (en) * | 2015-11-25 | 2016-04-20 | 小米科技有限责任公司 | Information recommendation method and apparatus for communication application |
| CN105679324A (en) * | 2015-12-29 | 2016-06-15 | 福建星网视易信息系统有限公司 | Voiceprint identification similarity scoring method and apparatus |
| CN106066754A (en) * | 2016-05-26 | 2016-11-02 | 北京金山安全软件有限公司 | Method and device for guiding user to score application program |
| CN106156941A (en) * | 2016-06-06 | 2016-11-23 | 腾讯科技（深圳）有限公司 | A kind of user credit scoring optimization method and device |
| CN106202242A (en) * | 2016-06-28 | 2016-12-07 | 青岛海信传媒网络技术有限公司 | A kind of application program recommends method and apparatus |
| CN106294788A (en) * | 2016-08-11 | 2017-01-04 | 湖南警察学院 | The recommendation method of Android application |
| EP3128451A1 (en) * | 2015-08-07 | 2017-02-08 | Molomics Biotech, S.L. | Method, computer program, video game and system for optimizing a molecule for medical applications |
| CN106445710A (en) * | 2016-10-26 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Method for determining interactive type object and equipment thereof |
| CN106503787A (en) * | 2016-10-26 | 2017-03-15 | 腾讯科技（深圳）有限公司 | A kind of method for obtaining game data and electronic equipment |
| CN106599623A (en) * | 2016-12-09 | 2017-04-26 | 江苏通付盾科技有限公司 | Method and device for calculating application similarity |
| CN106682809A (en) * | 2016-11-16 | 2017-05-17 | 上海建工集团股份有限公司 | Enterprise BIM technology application capability quantification assessment method |
| CN106682056A (en) * | 2016-07-15 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Method, device and system for determining correlation among different application software |
| CN106875206A (en) * | 2016-07-18 | 2017-06-20 | 阿里巴巴集团控股有限公司 | Acquisition of information, assessment, questionnaire method, device and server |
| CN106897412A (en) * | 2017-02-20 | 2017-06-27 | 广州优视网络科技有限公司 | A kind of method and apparatus for recommending associated application based on intended application |
| CN107045693A (en) * | 2017-05-05 | 2017-08-15 | 北京媒立方传媒科技有限公司 | Media characteristic determination, Media Recommendation Method and device |
| CN107092678A (en) * | 2017-04-20 | 2017-08-25 | 腾讯科技（深圳）有限公司 | A kind of method, device and equipment for obtaining application active degree |
| CN107169650A (en) * | 2017-05-11 | 2017-09-15 | 安徽谦通信息科技有限公司 | It is a kind of to be applied to the sincere toolization methods of marking that bid is assessed |
| CN107179930A (en) * | 2017-06-12 | 2017-09-19 | 广东小天才科技有限公司 | Method and device is recommended in one kind application unloading |
| CN107220303A (en) * | 2017-05-10 | 2017-09-29 | 努比亚技术有限公司 | Recommendation method, device and the computer-readable medium of a kind of application |
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN107292463A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of method and system that the project evaluation is carried out to application program |
| CN107391548A (en) * | 2017-04-06 | 2017-11-24 | 华东师范大学 | A kind of Mobile solution market brush list user's group detection method and its system |
| CN107507036A (en) * | 2017-08-28 | 2017-12-22 | 深圳市诚壹科技有限公司 | The method and terminal of a kind of data prediction |
| CN107563630A (en) * | 2017-08-25 | 2018-01-09 | 前海梧桐（深圳）数据有限公司 | Enterprise's methods of marking and its system based on various dimensions |
| CN107609130A (en) * | 2017-09-18 | 2018-01-19 | 链家网（北京）科技有限公司 | A kind of method and server for selecting data query engine |
| CN107622326A (en) * | 2017-09-13 | 2018-01-23 | 阿里巴巴集团控股有限公司 | User's classification, available resources Forecasting Methodology, device and equipment |
| CN107678845A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Application program management-control method, device, storage medium and electronic equipment |
| CN107730083A (en) * | 2017-09-18 | 2018-02-23 | 上海量明科技发展有限公司 | The ability quantization method and device of object |
| CN107844865A (en) * | 2017-11-20 | 2018-03-27 | 天津科技大学 | Feature based parameter chooses the stock index prediction method with LSTM models |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8321357B2 (en) * | 2009-09-30 | 2012-11-27 | Lapir Gennady | Method and system for extraction |
| US9558455B2 (en) * | 2014-07-11 | 2017-01-31 | Microsoft Technology Licensing, Llc | Touch classification |
| US20160042146A1 (en) * | 2014-08-07 | 2016-02-11 | Practice Fusion, Inc. | Recommending medical applications based on a physician's electronic medical records system |
| AU2017208994B2 (en) * | 2016-01-19 | 2022-01-20 | Magic Leap, Inc. | Eye image collection, selection, and combination |
| US9876825B2 (en) * | 2016-02-04 | 2018-01-23 | Amadeus S.A.S. | Monitoring user authenticity |
| US11800978B2 (en) * | 2016-08-05 | 2023-10-31 | Siemens Healthcare Gmbh | Deep learning based isocenter positioning and fully automated cardiac MR exam planning |
-
2018
- 2018-03-30 CN CN201810293738.XA patent/CN110163460B/en active Active
Patent Citations (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103634356A (en) * | 2012-08-24 | 2014-03-12 | 百度在线网络技术（北京）有限公司 | Method and system for packing downloading of a plurality of application programs, and apparatuses |
| CN104750538A (en) * | 2013-12-27 | 2015-07-01 | 伊姆西公司 | Virtual storage pool providing method and system for target application |
| CN104679852A (en) * | 2015-02-12 | 2015-06-03 | 广东欧珀移动通信有限公司 | Method and device for recommending application software |
| CN105160418A (en) * | 2015-08-05 | 2015-12-16 | 国家电网公司 | Charging distribution predication method based on electric vehicle application features |
| EP3128451A1 (en) * | 2015-08-07 | 2017-02-08 | Molomics Biotech, S.L. | Method, computer program, video game and system for optimizing a molecule for medical applications |
| CN105096058A (en) * | 2015-08-20 | 2015-11-25 | 北京中电普华信息技术有限公司 | Data processing method and device for customer service staff scoring system |
| CN105354092A (en) * | 2015-11-19 | 2016-02-24 | 东软集团股份有限公司 | Method, device and system for predicting application performance risk |
| CN105516247A (en) * | 2015-11-25 | 2016-04-20 | 小米科技有限责任公司 | Information recommendation method and apparatus for communication application |
| CN105679324A (en) * | 2015-12-29 | 2016-06-15 | 福建星网视易信息系统有限公司 | Voiceprint identification similarity scoring method and apparatus |
| CN107292463A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of method and system that the project evaluation is carried out to application program |
| CN106066754A (en) * | 2016-05-26 | 2016-11-02 | 北京金山安全软件有限公司 | Method and device for guiding user to score application program |
| CN106156941A (en) * | 2016-06-06 | 2016-11-23 | 腾讯科技（深圳）有限公司 | A kind of user credit scoring optimization method and device |
| CN106202242A (en) * | 2016-06-28 | 2016-12-07 | 青岛海信传媒网络技术有限公司 | A kind of application program recommends method and apparatus |
| CN106682056A (en) * | 2016-07-15 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Method, device and system for determining correlation among different application software |
| CN106875206A (en) * | 2016-07-18 | 2017-06-20 | 阿里巴巴集团控股有限公司 | Acquisition of information, assessment, questionnaire method, device and server |
| CN106294788A (en) * | 2016-08-11 | 2017-01-04 | 湖南警察学院 | The recommendation method of Android application |
| CN106503787A (en) * | 2016-10-26 | 2017-03-15 | 腾讯科技（深圳）有限公司 | A kind of method for obtaining game data and electronic equipment |
| CN106445710A (en) * | 2016-10-26 | 2017-02-22 | 腾讯科技（深圳）有限公司 | Method for determining interactive type object and equipment thereof |
| CN106682809A (en) * | 2016-11-16 | 2017-05-17 | 上海建工集团股份有限公司 | Enterprise BIM technology application capability quantification assessment method |
| CN106599623A (en) * | 2016-12-09 | 2017-04-26 | 江苏通付盾科技有限公司 | Method and device for calculating application similarity |
| CN106897412A (en) * | 2017-02-20 | 2017-06-27 | 广州优视网络科技有限公司 | A kind of method and apparatus for recommending associated application based on intended application |
| CN107391548A (en) * | 2017-04-06 | 2017-11-24 | 华东师范大学 | A kind of Mobile solution market brush list user's group detection method and its system |
| CN107092678A (en) * | 2017-04-20 | 2017-08-25 | 腾讯科技（深圳）有限公司 | A kind of method, device and equipment for obtaining application active degree |
| CN107045693A (en) * | 2017-05-05 | 2017-08-15 | 北京媒立方传媒科技有限公司 | Media characteristic determination, Media Recommendation Method and device |
| CN107220303A (en) * | 2017-05-10 | 2017-09-29 | 努比亚技术有限公司 | Recommendation method, device and the computer-readable medium of a kind of application |
| CN107247961A (en) * | 2017-05-10 | 2017-10-13 | 西安交通大学 | A kind of trajectory predictions method of application blurring trajectorie sequence |
| CN107169650A (en) * | 2017-05-11 | 2017-09-15 | 安徽谦通信息科技有限公司 | It is a kind of to be applied to the sincere toolization methods of marking that bid is assessed |
| CN107179930A (en) * | 2017-06-12 | 2017-09-19 | 广东小天才科技有限公司 | Method and device is recommended in one kind application unloading |
| CN107563630A (en) * | 2017-08-25 | 2018-01-09 | 前海梧桐（深圳）数据有限公司 | Enterprise's methods of marking and its system based on various dimensions |
| CN107507036A (en) * | 2017-08-28 | 2017-12-22 | 深圳市诚壹科技有限公司 | The method and terminal of a kind of data prediction |
| CN107622326A (en) * | 2017-09-13 | 2018-01-23 | 阿里巴巴集团控股有限公司 | User's classification, available resources Forecasting Methodology, device and equipment |
| CN107609130A (en) * | 2017-09-18 | 2018-01-19 | 链家网（北京）科技有限公司 | A kind of method and server for selecting data query engine |
| CN107730083A (en) * | 2017-09-18 | 2018-02-23 | 上海量明科技发展有限公司 | The ability quantization method and device of object |
| CN107678845A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Application program management-control method, device, storage medium and electronic equipment |
| CN107844865A (en) * | 2017-11-20 | 2018-03-27 | 天津科技大学 | Feature based parameter chooses the stock index prediction method with LSTM models |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110163460A (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Drachen et al. | Game data mining | |
| Drachen et al. | Game analytics–the basics | |
| CN108304853B (en) | Game correlation obtaining method and device, storage medium and electronic device | |
| KR101291333B1 (en) | learning system based on game dynamics and method for the same | |
| Canossa | Meaning in gameplay: Filtering variables, defining metrics, extracting features and creating models for gameplay analysis | |
| CN110516164B (en) | Information recommendation method, device, equipment and storage medium | |
| WO2015014260A1 (en) | Data processing method and server therefor | |
| CN110163460B (en) | Method and equipment for determining application score | |
| US9323643B1 (en) | Method and system for analyzing mobile apps | |
| Hyrynsalmi et al. | What is a minimum viable (video) game? towards a research agenda | |
| CN111652673B (en) | Intelligent recommendation method, device, server and storage medium | |
| Hiraoka et al. | Construction and analysis of a persuasive dialogue corpus | |
| CN110347916B (en) | Cross-scene item recommendation method and device, electronic equipment and storage medium | |
| KR101745874B1 (en) | System and method for a learning course automatic generation | |
| US20160271500A1 (en) | System and Method for Analyzing Data Associated with Electronic Games | |
| CN114556331A (en) | New frame for less-lens time action positioning | |
| Abou-Zleikha et al. | Evolving random forest for preference learning | |
| Tamla et al. | What Do Serious Games Developers Search Online? A Study of GameDev StackExchange. | |
| Alomari et al. | Predicting success of a mobile game: A proposed data analytics-based prediction model | |
| Budden et al. | Simulation leagues: Analysis of competition formats | |
| CN113886697A (en) | Clustering algorithm based activity recommendation method, device, equipment and storage medium | |
| Bogers et al. | “Looking for an amazing game I can relax and sink hours into...”: A Study of Relevance Aspects in Video Game Discovery | |
| KR20210024755A (en) | Lottery purchase supporting apparatus and method thereof | |
| WO2008115234A1 (en) | A system and method for control and training of avatars in an interactive environment | |
| Notten | Improving Performance for the Steam Recommender System using Achievement Data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |