CN114372831A - Method and system for realizing content reward calculation based on Sigmoid function - Google Patents
Method and system for realizing content reward calculation based on Sigmoid function Download PDFInfo
- Publication number
- CN114372831A CN114372831A CN202210039716.7A CN202210039716A CN114372831A CN 114372831 A CN114372831 A CN 114372831A CN 202210039716 A CN202210039716 A CN 202210039716A CN 114372831 A CN114372831 A CN 114372831A
- Authority
- CN
- China
- Prior art keywords
- factor
- content
- conversion
- value
- reward
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000006243 chemical reaction Methods 0.000 claims abstract description 37
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010606 normalization Methods 0.000 abstract description 6
- 230000001737 promoting effect Effects 0.000 abstract description 3
- 230000005284 excitation Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 19
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0208—Trade or exchange of goods or services in exchange for incentives or rewards
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Mathematical Optimization (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method and a system for realizing content reward calculation based on a Sigmoid function. The method comprises the following steps: determining a heat degree model according to factors influencing the heat degree of the content; calculating factor values of all factors accumulated in a certain time of each piece of content; respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value; determining the weight of each factor; and performing weighted calculation according to the conversion value and the weight of each factor to obtain the reward result of the content. The invention carries out Sigmoid conversion on the factor values of each factor influencing the heat degree and then carries out reward calculation with each weight, thereby realizing effective distribution of rewards, exciting the rewards on intermediate strength, avoiding the consumption of considerable rewards by tail scale effect, simultaneously realizing the normalization of each factor value, saving normalization operation steps, leading the reward calculation result to be clear and easy to understand, increasing the excitation of the supported intermediate content object, leading the reward to be more reasonable to use, and achieving a benign operation effect of promoting the upward conversion of users.
Description
Technical Field
The invention belongs to the field of content processing and analysis, and particularly relates to a method and a system for realizing content reward calculation based on a Sigmoid function.
Background
For a content platform, the vast majority are content consumers, and only a small percentage are content producers (UGC users). How to promote UGC users to continuously contribute content by using a good reward mechanism and accurately support users with authoring capability and growth space is an indispensable ring of each content platform at present. For example, Bilibili, small red book and buffalo all have respective calculation models and calculation formulas on content rewards and author rewards.
The common calculation model calculates the reward according to factors such as content flow, content interaction, content duration, content value and the like, and in this regard, each large company model is designed according to the actual business of the company model, and most of the large company models are universal; in the calculation formula, a linear weighting method is usually adopted, the weight of each factor needs to be calculated in advance, and corresponding standardization operation needs to be performed on factors of different orders, for example, logarithm is adopted, z-score standardization is adopted to remove dimension, and the model is prevented from being excessively dependent on the change of an index of a certain order. The model and formula are generally as follows:
the above prior art has the following disadvantages:
the first disadvantage is that: because the reward influence factors are different in magnitude, the reward influence factors generally need to be standardized or normalized firstly;
the second disadvantage is that: the reward formula describes a linear relationship between the reward and the factor. But generally in the reward system setting, the reward designer does not give the reward indefinitely (the linear relation is usually the same), and does not want to pay the higher reward for the long-tailed low-quality content (the logarithm of ln can bring about the result); but the content with interaction and flow at the middle waist part is rewarded more, and the conversion of the content to the head part is promoted; the tail content does not share out a considerable reward due to its scale effect. The purpose of the reward set is to "enrich" most of the reward, rather than "enrich" the head.
Therefore, the current formula, even the time attenuation factor of the superposition, can not meet the original intention of the rewarding system designer.
Disclosure of Invention
In order to overcome the problems in the related art, the invention provides a method and a system for realizing content reward calculation based on a Sigmoid function.
According to a first aspect of the embodiments of the present invention, there is provided a method for implementing content reward calculation based on a Sigmoid function, including:
determining a heat degree model according to factors influencing the heat degree of the content;
calculating factor values of all factors accumulated in a certain time of each piece of content;
respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
determining the weight of each factor;
and performing weighted calculation according to the conversion value and the weight of each factor to obtain the reward result of the content.
According to a second aspect of the embodiments of the present invention, there is provided a system for implementing content reward calculation based on Sigmoid function, including:
the model determining module is used for determining a heat degree model according to the factors influencing the heat degree of the content;
the factor value calculating module is used for calculating the factor value of each factor accumulated in a certain time of each content;
the factor conversion module is used for respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
the weight determining module is used for determining the weight of each factor;
and the reward calculation module is used for carrying out weighting calculation according to the conversion value and the weight of each factor to obtain a reward result of the content.
According to the technical scheme provided by the embodiment of the invention, the reward calculation is carried out on the factors influencing the heat degree after the factor values of the factors are subjected to Sigmoid conversion, so that the effective distribution of the reward is realized, the reward is stimulated on the intermediate strength, the consumption of considerable reward by the tail scale effect is avoided, the normalization of the factor values is realized, the normalization operation steps are saved, the reward calculation result is clear and easy to understand, the stimulation to the supported intermediate content object is increased, the reward is more reasonably used, and a benign operation effect of promoting the upward conversion of the user is achieved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts throughout.
Fig. 1 is a flowchart illustrating a method for implementing content reward calculation based on a Sigmoid function according to an exemplary embodiment of the present invention;
fig. 2 is a schematic graph of Sigmoid function curves under different values of a and b.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that, although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The technical solutions of the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Example 1:
fig. 1 is a flowchart illustrating a method for implementing content reward calculation based on a Sigmoid function according to an exemplary embodiment of the present invention.
Referring to fig. 1, the method includes:
110. determining a heat degree model according to factors influencing the heat degree of the content;
in this embodiment, the step lists the service factors that affect the popularity of the content, and the number of the factors is not limited, and it should be noted that the popularity model needs to be uniformly applied to the calculation process of the rewards that need to be issued for all the content, so as to ensure fairness.
Optionally, in this embodiment, in order to facilitate subsequent removal of the influence caused by different magnitudes of the factor values, clustering may be further performed by units of the factors, such as a duration class, an interaction number class, a browsing number class, and the like.
120. Calculating factor values of all factors accumulated in a certain time of each piece of content;
130. respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
in this embodiment, factor values such as interaction, flow rate, value and the like obtained by UGC content are converted by a Sigmoid function, and the Sigmoid function used in this embodiment is as follows:
wherein, a is the ascending slope of the middle part of the control S curve, a & ltb & gt is the displacement of the control S curve on the x coordinate axis, and b represents the mean value or median of the array.
In general, the slope a can be given in advance, a can be selected to be a number in the range of 0-1, the larger the number is, the steeper the middle part of the curve is, the head and tail are more smoothly close to 1 and 0, i.e. the middle content is less. For the purpose of encouraging intermediate content, the slope a may be tapered, such as 0.05 or 0.005.
b is the median or the mean of the whole content, specifically, the median or the mean can be selected according to the data distribution condition of each factor, and if the data dispersion degree is higher, the median mode is suggested; if the data distribution is sparse, it is suggested that higher quantiles can be used, such as 3/4 quantiles, 0.9 quantiles, etc.; the higher b, the more right the curve is shifted on the coordinate axis, the less the head content and the more the tail content.
Fig. 2 is a schematic graph of the Sigmoid function under different values of a and b. As shown in fig. 2, in the left part of the abscissa value 150, the values of a and b of the three curves from top to bottom are: a is 0.03, b is 150; a is 0.05, b is 150; a equals 0.05 and b equals 200.
140. Determining the weight of each factor;
specifically, the weight W of each factor may be determined by a regression equation, or may be determined by using an expert delphi method. The specific method belongs to the prior art, and this embodiment will not be described in detail.
150. And performing weighted calculation according to the conversion value and the weight of each factor to obtain the reward result of the content.
Specifically, the calculation formula of the reward is as follows:
y=∑Wi*Si
wherein y is a reward; w is the weight, i.e. the maximum reward upper limit value for each factor; s is the result of Sigmoid [0, 1] of each factor, i.e., the conversion value.
In the above calculation formula, the weight is a fixed value, so the reward y obtained by the content depends on the conversion value of the factor after Sigmoid conversion, and as can be seen from the curve trend of the Sigmoid function shown in fig. 2, the growth trend of the function value at the head and tail is slow, and the growth at the middle waist is fast, so that by adopting the reward calculation method provided by this embodiment, an ideal state that the reward coefficient of the low-quality content at the long tail becomes slow, the reward coefficient at the middle waist is high, and the reward coefficient at the head becomes slow can be realized. In addition, the Sigmoid function is a standardized method, and an array can be compressed into data between 0 and 1, so that the problem of different magnitude of influence factors is solved.
The method for realizing the content reward calculation based on the Sigmoid function provided by the embodiment of the invention realizes the effective distribution of the reward by carrying out the Sigmoid conversion on the factor values of all factors influencing the heat degree and then carrying out the reward calculation with all weights, and encourages the reward on the intermediate strength, thereby avoiding consuming considerable reward by the tail scale effect, simultaneously realizing the normalization of all factor values, saving the normalization operation steps, leading the reward calculation result to be clear and understandable, increasing the incentive to the supported intermediate content object, leading the reward to be more reasonably used, and achieving a good operation effect of promoting the upward conversion of a user.
Example 2:
corresponding to the above method embodiments, this embodiment provides a system for implementing content reward calculation based on Sigmoid function, and the functional principle of each functional module in the system may refer to the above description, and will not be described again below. The system comprises:
the model determining module is used for determining a heat degree model according to the factors influencing the heat degree of the content;
the factor value calculating module is used for calculating the factor value of each factor accumulated in a certain time of each content;
the factor conversion module is used for respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
the weight determining module is used for determining the weight of each factor;
and the reward calculation module is used for carrying out weighting calculation according to the conversion value and the weight of each factor to obtain a reward result of the content.
The method according to the invention may be implemented as a computing device comprising a memory and a processor.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include various types of storage units such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are required by the processor or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory may comprise any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, the memory may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-dense optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory has stored thereon executable code which, when processed by the processor, causes the processor to perform some or all of the methods described above.
Furthermore, the method according to the invention may also be implemented as a computer program or computer program product comprising computer program code instructions for carrying out some or all of the steps of the above-described method of the invention.
Alternatively, the invention may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or computing device, server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the invention.
The aspects of the invention have been described in detail hereinabove with reference to the drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required by the invention. In addition, it can be understood that the steps in the method according to the embodiment of the present invention may be sequentially adjusted, combined, and deleted according to actual needs, and the modules in the device according to the embodiment of the present invention may be combined, divided, and deleted according to actual needs.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A method for realizing content reward calculation based on a Sigmoid function is characterized by comprising the following steps:
determining a heat degree model according to factors influencing the heat degree of the content;
calculating factor values of all factors accumulated in a certain time of each piece of content;
respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
determining the weight of each factor;
and performing weighted calculation according to the conversion value and the weight of each factor to obtain the reward result of the content.
2. The method according to claim 1, wherein determining the heat model according to factors that affect the heat of the content comprises:
and listing factors influencing the content heat, and clustering by the unit of the factors.
3. The method according to claim 2, wherein the Sigmoid conversion is performed on each factor value to obtain a converted value, and specifically comprises:
and respectively converting the different clustering factors according to a Sigmoid function to obtain conversion values.
4. Method according to claim 3, characterized in that the Sigmoid function is as follows:
wherein, a is the ascending slope of the middle part of the control S curve, a & ltb & gt is the displacement of the control S curve on the x coordinate axis, and b represents the mean value or median of the array.
5. The method according to any one of claims 1 to 4, wherein determining the weight of each factor comprises:
the weights of the individual factors are determined by regression equations or using expert delphi.
6. A system for realizing content reward calculation based on Sigmoid function is characterized by comprising:
the model determining module is used for determining a heat degree model according to the factors influencing the heat degree of the content;
the factor value calculating module is used for calculating the factor value of each factor accumulated in a certain time of each content;
the factor conversion module is used for respectively carrying out Sigmoid conversion on each factor value to obtain a conversion value;
the weight determining module is used for determining the weight of each factor;
and the reward calculation module is used for carrying out weighting calculation according to the conversion value and the weight of each factor to obtain a reward result of the content.
7. The system of claim 6, wherein the model determination module is configured to list factors that affect the heat of the content, and wherein the clustering is performed in units of the factors.
8. The system according to claim 7, wherein the factor conversion module is specifically configured to convert the different clustering factors according to a Sigmoid function to obtain converted values.
10. The system according to any of claims 6 to 9, wherein the weight determination module is configured to determine the weight of each factor by means of a regression equation or by using expert delphi.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210039716.7A CN114372831A (en) | 2022-01-10 | 2022-01-10 | Method and system for realizing content reward calculation based on Sigmoid function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210039716.7A CN114372831A (en) | 2022-01-10 | 2022-01-10 | Method and system for realizing content reward calculation based on Sigmoid function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114372831A true CN114372831A (en) | 2022-04-19 |
Family
ID=81143892
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210039716.7A Pending CN114372831A (en) | 2022-01-10 | 2022-01-10 | Method and system for realizing content reward calculation based on Sigmoid function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114372831A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090111589A (en) * | 2008-04-22 | 2009-10-27 | (주)인스비젼아이넷 | System and method for providing contents creator with remuneration |
US8554601B1 (en) * | 2003-08-22 | 2013-10-08 | Amazon Technologies, Inc. | Managing content based on reputation |
CN110175786A (en) * | 2019-05-30 | 2019-08-27 | 浪潮卓数大数据产业发展有限公司 | A kind of content value evaluation method based on block chain |
KR20200052680A (en) * | 2018-11-07 | 2020-05-15 | 주식회사 제이씨이노베이션 | Commerce platform system using the analysis of big data |
CN112232706A (en) * | 2020-11-06 | 2021-01-15 | 四川大汇大数据服务有限公司 | Capability evaluation method, system, terminal and medium based on behavior and capability dimension |
-
2022
- 2022-01-10 CN CN202210039716.7A patent/CN114372831A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8554601B1 (en) * | 2003-08-22 | 2013-10-08 | Amazon Technologies, Inc. | Managing content based on reputation |
KR20090111589A (en) * | 2008-04-22 | 2009-10-27 | (주)인스비젼아이넷 | System and method for providing contents creator with remuneration |
KR20200052680A (en) * | 2018-11-07 | 2020-05-15 | 주식회사 제이씨이노베이션 | Commerce platform system using the analysis of big data |
CN110175786A (en) * | 2019-05-30 | 2019-08-27 | 浪潮卓数大数据产业发展有限公司 | A kind of content value evaluation method based on block chain |
CN112232706A (en) * | 2020-11-06 | 2021-01-15 | 四川大汇大数据服务有限公司 | Capability evaluation method, system, terminal and medium based on behavior and capability dimension |
Non-Patent Citations (2)
Title |
---|
楼文高: "《基于群智能最优化算法的投影寻踪理论 新进展、应用及软件》", 31 December 2021, 复旦大学出版社, pages: 64 * |
陈明等: "《高速切削技术基础与应用》", 31 October 2012, 上海科学技术出版社, pages: 146 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10977338B1 (en) | Reduced-area circuit for dot product computation | |
US8296274B2 (en) | Considering multiple lookups in bloom filter decision making | |
CN111061979B (en) | User tag pushing method and device, electronic equipment and medium | |
CN106779050A (en) | The optimization method and device of a kind of convolutional neural networks | |
CN110084629A (en) | System and method for promotional media in online distribution platform | |
CN113643119A (en) | Model training method, business wind control method and business wind control device | |
CN114764768A (en) | Defect detection and classification method and device, electronic equipment and storage medium | |
CN111291894A (en) | Resource scheduling method, device, equipment and medium in hyper-parameter optimization process | |
CN111539765A (en) | Commodity price data processing method, device and equipment | |
CN103688290A (en) | Image processing device, image processing method, control program, and recording medium | |
CN109582741A (en) | Characteristic treating method and apparatus | |
CN110750530A (en) | Service system and data checking method thereof | |
CN112434884A (en) | Method and device for establishing supplier classified portrait | |
CN111695941A (en) | Commodity transaction website data analysis method and device and electronic equipment | |
CN114372831A (en) | Method and system for realizing content reward calculation based on Sigmoid function | |
US20110191258A1 (en) | Method and apparatus for processing logistic information | |
CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
CN113643100A (en) | Commodity similarity judgment module contribution quantification method and system | |
US7107192B1 (en) | Method for computing models based on attributes selected by entropy | |
CN116091111A (en) | Product demand prediction method and device, electronic equipment and storage medium | |
CN113722440B (en) | Significance analysis method based on keyword recognition and related products | |
CN111080067A (en) | Speaker commercial value evaluation method, storage medium and device | |
CN116777226B (en) | Information display system based on quantization processing model | |
CN112684972B (en) | Data storage method and device based on distributed block storage | |
JP7057332B2 (en) | Decision device, decision method and decision program |
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 |