CN112100045A - Method and equipment for identifying game similarity - Google Patents
Method and equipment for identifying game similarity Download PDFInfo
- Publication number
- CN112100045A CN112100045A CN202010904428.4A CN202010904428A CN112100045A CN 112100045 A CN112100045 A CN 112100045A CN 202010904428 A CN202010904428 A CN 202010904428A CN 112100045 A CN112100045 A CN 112100045A
- Authority
- CN
- China
- Prior art keywords
- word
- word vector
- game application
- words
- target game
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Machine Translation (AREA)
Abstract
The application provides a method and equipment for identifying game similarity, which can automatically acquire a description text corresponding to a target game application, generate a word vector corresponding to the target game application according to the corresponding description text, and finally compare the word vector with a word vector corresponding to a game application to be compared to obtain the similarity between the word vector and the word vector, so that the automatic comparison between the target game application and the game application to be compared is realized, competing products do not need to be searched manually, the searching efficiency and the coverage range of the competing products are improved, the similarity between the word vector and the word vector is quantized, and the accuracy of the similarity judgment of the competing products is improved.
Description
Technical Field
The present application relates to the field of games, and in particular, to a method and device for identifying game similarity.
Background
Currently, game manufacturers often need to know which competing products of their game applications are, so that marketing and expansion of game clients can be performed in a targeted manner, and income of the game applications is further increased. At present, relevant competitive products for searching game applications are mainly searched in a manual mode, for example, searching in an application market according to manual experience, the manual mode searching has the defects of low efficiency, poor accuracy, low coverage rate and the like, and even if similar competitive products are found, the similarity degree of the competitive products and the game applications of the competitive products is difficult to quantify.
Disclosure of Invention
An object of the present application is to provide a method for identifying game similarity, so as to solve the problems of the prior art that it is difficult to find competing products in an automated manner and the similarity cannot be quantified.
To achieve the above object, the present application provides a method of identifying a similarity degree of a game, wherein the method includes:
obtaining a description text corresponding to a target game application;
generating a word vector corresponding to the target game application according to the description text corresponding to the target game application;
and comparing the word vector with the word vector corresponding to the game application to be compared, and determining the similarity between the word vector and the word vector.
Further, acquiring a description text corresponding to the target game application includes:
and acquiring a description text corresponding to the target game application from the Internet by using an automatic network information acquisition technology.
Further, generating a word vector corresponding to the target game application according to the description text corresponding to the target game application includes:
segmenting words of a description text corresponding to the target game application to obtain words in the description text;
performing vector conversion on the words to generate word vectors corresponding to the words;
and generating a word vector corresponding to the target game application according to the word vector.
Further, performing vector conversion on the word to generate a word vector corresponding to the word, including:
determining adjacent word pairs corresponding to the words according to a preset window size;
encoding words in the adjacent word pairs;
training a neural network model according to the coded adjacent word pair, wherein the neural network model comprises an input layer and a hidden layer, and the number of neurons in the hidden layer is a preset value;
and generating a word vector corresponding to the word according to the weight between the input layer and the hidden layer in the trained neural network model.
Further, encoding a word in the pair of contiguous words includes:
words in the pairs of contiguous words are encoded using one-hot encoding.
Further, generating a word vector corresponding to the word according to the weight between the input layer and the hidden layer in the trained neural network model, including:
combining a plurality of weights between input layer neurons and all hidden layer neurons in the trained neural network model into word vectors corresponding to the words, wherein the input layer neurons correspond to the coding valid bits of the words.
Further, generating a word vector corresponding to the target game application according to the word vector includes:
compressing the word vector to obtain a vector value corresponding to the word;
and combining vector values corresponding to all words obtained by word segmentation of the description text into a word vector corresponding to the target game application.
Further, comparing the word vector with a word vector corresponding to the game application to be compared, and determining the similarity between the word vector and the word vector, including:
and calculating the cosine value of an included angle between the word vector and the word vector corresponding to the game application to be compared, and taking the obtained cosine value as the similarity degree between the two.
Based on another aspect of the present application, the present application further provides an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform the aforementioned method of identifying game likeness.
The present application also provides a computer readable medium having computer readable instructions stored thereon that are executable by a processor to implement the aforementioned method of identifying game likeness.
Compared with the prior art, the scheme provided by the application can automatically acquire the description text corresponding to the target game application, then generate the word vector corresponding to the target game application according to the corresponding description text, and finally compare the word vector with the word vector corresponding to the game application to be compared to obtain the similarity degree between the word vector and the word vector, so that the automatic comparison between the target game application and the game application to be compared is realized, a competitive product does not need to be searched manually, the searching efficiency and the coverage range of the competitive product are improved, the similarity degree between the word vector and the word vector is quantized, and the accuracy of the similarity judgment of the competitive product is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method of identifying game likeness provided by some embodiments of the present application;
figure 2 is a schematic illustration of a similarity score for a game application for an auction provided by some preferred embodiments of the present application.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
The present application is described in further detail below with reference to the attached figures.
In a typical configuration of the present application, the terminal and the network device each include one or more processors (CPUs), input/output interfaces, network interfaces, and memories.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.
Some embodiments of the present application provide a method of identifying game likeness, as shown in fig. 1, the method comprising the steps of:
step S101, obtaining a description text corresponding to a target game application;
step S102, generating a word vector corresponding to the target game application according to the description text corresponding to the target game application;
and step S103, comparing the word vector with a word vector corresponding to the game application to be compared, and determining the similarity between the word vector and the word vector.
The scheme is particularly suitable for scenes in which competing products of game applications to be compared are expected to be compared, the description text corresponding to the target game application can be automatically acquired, the word vector corresponding to the target game application is generated according to the corresponding description text, and finally the word vector is compared with the word vector corresponding to the game applications to be compared to obtain the similarity between the word vector and the word vector.
In step S101, a description text corresponding to the target game application is first acquired. Here, the target game application is a competitive product application that needs to be compared, and the game facilitator wants to evaluate the degree of similarity between the target game application and the game application itself, and then determines what kind of subsequent processing is performed according to the obtained degree of similarity, for example, if the degree of similarity is high, the relevant client group, marketing mode, etc. of the target game application may be further analyzed, so as to provide relevant references for the game application itself; if the degree of similarity is not high, the target game application may be directly ignored, and so on.
In addition, when the target game application is popularized in an application market or a website, a corresponding game content introduction is usually provided, and the game content introduction is generally described in a text form, that is, a description text corresponding to the target game application. For example, the description text corresponding to the target game application "royal glory" may be: "Rong Yao of Wang" is the first 5V5 hero fair combat tour and Teng Xuan MOBA tour in the world! As a MOBA game, Wang Zhen Rong Yao has many characteristics, and the game of the same kind is a unique and full-range of beauty. 5V5 Wang canyon, 5V5 deep Yuan big battle, 3V3, 1V1 and other various modes of one-key experience, and the pleasure of hot blood competition! "
In some embodiments of the present application, the description text corresponding to the target game application is obtained, and specifically, the description text corresponding to the target game application may be obtained from the internet through an automatic network information obtaining technology. Preferably, the network information automatic acquisition technology may be a web crawler technology, that is, a description text corresponding to a target game application is automatically acquired from a game-related website or an application market through the web crawler, where the application market refers to a centralized display and download platform of multiple applications, and a user may search and download an application required by the user in the application market and install the downloaded application on a terminal device of the user. Examples of the application market include pea pods, appliques, huashi application markets, and the like, and examples of the game-related website include a taptap, a first hand net, and the like. Description texts corresponding to a plurality of target game applications can be generally obtained through web crawler technology.
In step S102, a word vector corresponding to the target game application is generated according to the description text corresponding to the target game application. The description texts corresponding to the target game application are described in a text form, and because the expression of the text has limitations and ambiguity and uncertainty exist, the comparison result is inevitably inaccurate by directly comparing the description texts, so that the comparison between the description texts is converted into the comparison between vectors with more accurate description, and the accuracy of the comparison result can be improved.
In some embodiments of the present application, generating a word vector corresponding to the target game application according to the description text corresponding to the target game application may specifically include the following steps:
1) segmenting words of a description text corresponding to the target game application to obtain words in the description text;
2) carrying out vector conversion on the word to generate a word vector corresponding to the word;
3) and generating a word vector corresponding to the target game application according to the word vector.
Here, the description text may be segmented using a variety of segmentation methods, such as a character string matching-based segmentation method, an understanding-based segmentation method, a statistics-based segmentation method, and the like. The word segmentation tools used specifically may be ansj word segmenters, jieba word segmentation tools, stanford word segmenters, etc., and are not specifically limited herein.
In some embodiments of the present application, performing vector transformation on the term to generate a term vector corresponding to the term may specifically include the following steps:
1) determining an adjacent word pair corresponding to the word according to the preset window size;
2) encoding words in the adjacent word pair;
3) training a neural network model according to the coded adjacent word pair, wherein the neural network model comprises an input layer and a hidden layer, and the number of neurons in the hidden layer is a preset value;
4) and generating a word vector corresponding to the word according to the weight between the input layer and the hidden layer in the trained neural network model.
Here, the window size may be set according to the user's needs, and the window size is used to determine the adjacent terms of the selected term, and the adjacent term of one term is a set composed of all terms that are separated from the front and back of the term by the window size with the term as the center. For example, the sentence "royal glory" is the first global 5V5 hero fair battle hand trip "and the result is" royal glory global hero fair hand trip ", the word of the adjacent word is determined to be" global ", and if the window size is 2, the adjacent word is" royal "," glory "," hero "," fair ".
The pair of adjacent words to which a word corresponds is a pair of words composed of a word and its adjacent words, and in the above example, the resulting plurality of pairs of adjacent words are ("global", "queen"), ("global", "glory"), ("global", "hero"), ("global", "fair").
In some embodiments of the present application, the words in adjacent word pairs are encoded, and particularly, the words in adjacent word pairs may be encoded using one-hot encoding. One-Hot Encoding (One-Hot Encoding), also known as One-bit-efficient Encoding, uses an N-bit status register to encode N states, each with its own independent register bit, and only One of which is active at any One time.
The game application comprises a word list of a game application, the word list comprises a plurality of words in the target game application, the words in adjacent word pairs can be found in the word list, the words in the adjacent word pairs can generate corresponding one-hot codes according to the word list, and the dimension of the generated codes is the same as the number of the words in the word list.
The method comprises the steps of training a plurality of codes of adjacent word pairs into a neural network model, wherein the neural network model comprises an input layer and a hidden layer, for example, one adjacent word pair is (global and king) and is coded as (10000000 and 01000000), the training is carried out by taking the code (10000000) corresponding to the word (global) as the input of the neural network model, and the code (01000000) corresponding to the word (king) as the training label. Here, the number of neurons in the hidden layer in the neural network model is a preset value, and the user can set the number of neurons according to the user's own needs, for example, if the user wants to convert each word into a vector of 100 dimensions, the number of neurons in the hidden layer can be set to 100. In addition, other common network settings of the neural network model, such as a loss function, a parameter optimization method and the like, can be set by adopting common settings, such as a square error loss function, a gradient descent method and the like.
In some embodiments of the present application, a word vector corresponding to a word is generated according to a weight between an input layer and a hidden layer in a trained neural network model, which may specifically use the following method: combining a plurality of weights between the input layer neurons and all hidden layer neurons in the trained neural network model into word vectors corresponding to the words, wherein the input layer neurons correspond to the coding valid bits of the words. Here, the number of input layer neurons in the neural network model is the same as the number of dimensions of the input word code, each input layer neuron receives only one digit in the word code, only one significant bit in the one-hot code of the word, that is, the digit of "1" in the code, connections exist between the input layer neuron receiving the digit and all hidden layer neurons, each connection corresponds to one weight, and therefore, a plurality of weights correspond to all hidden layer neurons between the input layer neuron and all hidden layer neurons, and the weights are combined into one vector, which is the word vector corresponding to the word.
In some embodiments of the present application, generating a word vector corresponding to the target game application according to the word vector may specifically include the following steps: compressing the word vector to obtain a vector value corresponding to the word; and combining vector values corresponding to all the words obtained by word segmentation of the description text into a word vector corresponding to the target game application. Here, the word vector is a multi-dimensional vector, and compressing the word vector into a vector value with a dimension of 1 can reduce the later comparison calculation amount and improve the comparison efficiency. Preferably, the word vector is compressed by calculating an average value, that is, calculating an average value of values of all dimensions of the word vector, and using the obtained average value as a vector value of the word vector. For example, the word "king" may obtain a 100-dimensional word vector by the above method, and the vector value obtained by compressing the word vector may be-0.08977831074752021.
The above description text "" Rong Yao "is preferably available via the ansj tool as the global capital 5V5 hero fair battle tour, Tencent MOBA tour great job! As a MOBA game, Wang Zhen Rong Yao has many characteristics, and the game of the same kind is a unique and full-range of beauty. 5V5 Wang canyon, 5V5 deep Yuan big battle, 3V3, 1V1 and other various modes of one-key experience, and the pleasure of hot blood competition! "carry out word segmentation to obtain the corresponding word segmentation result: "the king glory the global hero official trip Tengchan Moba …", then use skip-gram method in word2vector tool to convert the word segmentation result into vector and compress it into vector value, the obtained word vector can be [ -0.08977831074752021, -0.1161408931442091,0.2592430370207426,0.12981394762600712, … ].
In step S103, the word vector is compared with the word vector corresponding to the game application to be compared, and the similarity between the two is determined. Here, the game application to be compared is a game application that the game facilitator provides a service by itself, and the found competitive game application is compared with the game application by itself, and the competitive game application having a higher threat to the game application by itself is determined according to the degree of similarity. The method of obtaining the word vector corresponding to the game application to be compared is the same as the method of obtaining the word vector corresponding to the target game application.
In some embodiments of the present application, the word vector is compared with the word vector corresponding to the game application to be compared, and the similarity between the word vector and the word vector corresponding to the game application to be compared is determined. Here, the cosine value of the included angle between two vectors in the vector space is used as a measure of the difference between two individuals, and the closer the cosine value is to 1, the closer the included angle is to 0 degree, i.e., the more similar the two vectors are, i.e., the cosine similarity. Fig. 2 illustrates the cosine similarity score ranking of a plurality of auction game applications provided in some preferred embodiments of the present application, from which it can be seen that the "second-degree major combat" of the auction game application is most similar to the cosine of the game application to be compared, which is the most threatening auction game application to be compared.
Some embodiments of the present application also provide an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform the aforementioned method of identifying a game likeness.
Some embodiments of the present application also provide a computer readable medium having computer readable instructions stored thereon, the computer readable instructions being executable by a processor to implement the aforementioned method of identifying a degree of game similarity.
To sum up, the scheme provided by the application can automatically acquire the description text corresponding to the target game application, then generate the word vector corresponding to the target game application according to the corresponding description text, and finally compare the word vector with the word vector corresponding to the game application to be compared to obtain the similarity between the word vector and the word vector, so that the automatic comparison between the target game application and the game application to be compared is realized, a competitive product does not need to be searched manually, the searching efficiency and the coverage range of the competitive product are improved, the similarity between the word vector and the game application to be compared is quantized, and the accuracy of the similarity judgment of the competitive product is improved.
It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including associated data structures) of the present application may be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Program instructions which invoke the methods of the present application may be stored on a fixed or removable recording medium and/or transmitted via a data stream on a broadcast or other signal-bearing medium and/or stored within a working memory of a computer device operating in accordance with the program instructions. An embodiment according to the present application comprises a device comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the device to perform a method and/or a solution according to the aforementioned embodiments of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (10)
1. A method of identifying game likeness, wherein the method comprises:
obtaining a description text corresponding to a target game application;
generating a word vector corresponding to the target game application according to the description text corresponding to the target game application;
and comparing the word vector with the word vector corresponding to the game application to be compared, and determining the similarity between the word vector and the word vector.
2. The method of claim 1, wherein obtaining the description text corresponding to the target game application comprises:
and acquiring a description text corresponding to the target game application from the Internet by using an automatic network information acquisition technology.
3. The method of claim 1, wherein generating a word vector corresponding to the target game application according to the description text corresponding to the target game application comprises:
segmenting words of a description text corresponding to the target game application to obtain words in the description text;
performing vector conversion on the words to generate word vectors corresponding to the words;
and generating a word vector corresponding to the target game application according to the word vector.
4. The method of claim 3, wherein vector converting the words to generate word vectors corresponding to the words comprises:
determining adjacent word pairs corresponding to the words according to a preset window size;
encoding words in the adjacent word pairs;
training a neural network model according to the coded adjacent word pair, wherein the neural network model comprises an input layer and a hidden layer, and the number of neurons in the hidden layer is a preset value;
and generating a word vector corresponding to the word according to the weight between the input layer and the hidden layer in the trained neural network model.
5. The method of claim 4, wherein encoding a word in the pair of contiguous words comprises:
words in the pairs of contiguous words are encoded using one-hot encoding.
6. The method of claim 5, wherein generating a word vector corresponding to the word according to the weight between the input layer and the hidden layer in the trained neural network model comprises:
combining a plurality of weights between input layer neurons and all hidden layer neurons in the trained neural network model into word vectors corresponding to the words, wherein the input layer neurons correspond to the coding valid bits of the words.
7. The method of claim 3, wherein generating a word vector corresponding to the target gaming application from the word vector comprises:
compressing the word vector to obtain a vector value corresponding to the word;
and combining vector values corresponding to all words obtained by word segmentation of the description text into a word vector corresponding to the target game application.
8. The method of claim 1, wherein comparing the word vector with a word vector corresponding to a game application to be compared to determine a degree of similarity between the two comprises:
and calculating the cosine value of an included angle between the word vector and the word vector corresponding to the game application to be compared, and taking the obtained cosine value as the similarity degree between the two.
9. An apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform the method of any of claims 1 to 8.
10. A computer readable medium having computer readable instructions stored thereon which are executable by a processor to implement the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010904428.4A CN112100045A (en) | 2020-09-01 | 2020-09-01 | Method and equipment for identifying game similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010904428.4A CN112100045A (en) | 2020-09-01 | 2020-09-01 | Method and equipment for identifying game similarity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112100045A true CN112100045A (en) | 2020-12-18 |
Family
ID=73757422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010904428.4A Pending CN112100045A (en) | 2020-09-01 | 2020-09-01 | Method and equipment for identifying game similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112100045A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355446A (en) * | 2016-08-31 | 2017-01-25 | 镇江乐游网络科技有限公司 | Online and mobile game advertising recommending system |
| CN108228845A (en) * | 2018-01-09 | 2018-06-29 | 华南理工大学 | A kind of mobile phone games sorting algorithm |
| CN108304853A (en) * | 2017-10-10 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Acquisition methods, device, storage medium and the electronic device for the degree of correlation of playing |
| CN109589603A (en) * | 2018-11-30 | 2019-04-09 | 广州要玩娱乐网络技术股份有限公司 | Game operation control method, device, medium and computer equipment |
-
2020
- 2020-09-01 CN CN202010904428.4A patent/CN112100045A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355446A (en) * | 2016-08-31 | 2017-01-25 | 镇江乐游网络科技有限公司 | Online and mobile game advertising recommending system |
| CN108304853A (en) * | 2017-10-10 | 2018-07-20 | 腾讯科技（深圳）有限公司 | Acquisition methods, device, storage medium and the electronic device for the degree of correlation of playing |
| CN108228845A (en) * | 2018-01-09 | 2018-06-29 | 华南理工大学 | A kind of mobile phone games sorting algorithm |
| CN109589603A (en) * | 2018-11-30 | 2019-04-09 | 广州要玩娱乐网络技术股份有限公司 | Game operation control method, device, medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658455B (en) | Image processing method and processing apparatus | |
| Alzu'bi et al. | Content-based image retrieval with compact deep convolutional features | |
| CN110059198B (en) | Discrete hash retrieval method of cross-modal data based on similarity maintenance | |
| CN106445939B (en) | Image retrieval, image information acquisition and image identification method, device and system | |
| CN104376003A (en) | Video retrieval method and device | |
| CN106776849A (en) | A kind of method and guide system to scheme quick-searching sight spot | |
| CN113159056A (en) | Image segmentation method, device, equipment and storage medium | |
| US20170193987A1 (en) | Speech recognition method and device | |
| CN112182167B (en) | Text matching method and device, terminal equipment and storage medium | |
| CN114462570A (en) | Training method of text generation model, target corpus expansion method and related device | |
| CN113656613A (en) | Method for training image-text retrieval model, multi-mode image retrieval method and device | |
| CN115984874A (en) | Text generation method and device, electronic equipment and storage medium | |
| Wang et al. | From low-cost depth sensors to cad: Cross-domain 3d shape retrieval via regression tree fields | |
| CN104142978B (en) | A kind of image indexing system and method based on multiple features and rarefaction representation | |
| CN112100045A (en) | Method and equipment for identifying game similarity | |
| CN109902162B (en) | Text similarity identification method based on digital fingerprints, storage medium and device | |
| CN114580354B (en) | Information coding method, device, equipment and storage medium based on synonym | |
| CN115687625B (en) | Text classification method, device, equipment and medium | |
| CN111008294B (en) | Traffic image processing and image retrieval method and device | |
| CN110852066B (en) | Multi-language entity relation extraction method and system based on confrontation training mechanism | |
| CN116662538A (en) | Text abstract generation method, device, equipment and medium based on multitask learning | |
| CN112100044B (en) | Method and equipment for identifying game similarity | |
| CN109657034A (en) | Address similarity calculating method and its system | |
| CN114288674A (en) | VR skiing control method and system | |
| CN114241361A (en) | Video gene extraction and video matching method and device based on video gene |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201218 |