WO2017054582A1 - 一种信息推送方法、装置及电子设备 - Google Patents
一种信息推送方法、装置及电子设备 Download PDFInfo
- Publication number
- WO2017054582A1 WO2017054582A1 PCT/CN2016/095331 CN2016095331W WO2017054582A1 WO 2017054582 A1 WO2017054582 A1 WO 2017054582A1 CN 2016095331 W CN2016095331 W CN 2016095331W WO 2017054582 A1 WO2017054582 A1 WO 2017054582A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- preset
- recommendation degree
- page view
- pushed
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0263—Targeted advertisements based upon Internet or website rating
Definitions
- the present invention relates to the field of Internet technologies, and in particular, to an information push method, device, and electronic device.
- the new merchant will continue to commission the advertisement, and at the same time, the advertisement commissioned by the old merchant will expire.
- the network operator determines the advertisement to be pushed to the user, it is not only necessary to determine the advertisement to be pushed according to the advertisement commissioned by the old merchant, but also needs to determine the advertisement to be pushed according to the advertisement commissioned by the new merchant, usually under the circumstances
- the determination strategy for the above two is different. Specifically, when the advertisement to be pushed by the old merchant is determined, the information about the historical push situation is determined, so in this case, the history of each advertisement can be pushed. Determining the advertisement to be pushed; when determining the advertisement to be pushed for the advertisement commissioned by the new merchant, since there is no relevant information about the history of the push or less information about the history of the push, the random selection is usually adopted from the new merchant. The advertisement to be pushed is determined in the commissioned advertisement.
- the advertisement to be pushed can be determined from the advertisements commissioned by the new merchant, so that the historical push information can be accumulated for the newly commissioned advertisement, but the random selection method is used to determine that the advertisement to be pushed does not consider the user's feeling, and thus the user is likely to be caused. Poor experience.
- the embodiment of the invention discloses an information pushing method, device and electronic device to improve user experience.
- an embodiment of the present invention discloses an information pushing method, where the method includes:
- the obtaining the page view amount in each preset information in the preset information list before the current time is preset, including:
- PV Adi w 1 * PV Adi_f1 + ... + w n * PV Adi_fn ,
- w 1 represents the attenuation coefficient corresponding PV Adi_f1
- PV Adi_fn views showing the page before the current time of the n-th information within the AD i
- w n represents the attenuation coefficient corresponding to PV Adi_fn
- the nth day before the current time is the day when the current time is the longest according to the preset time length
- w 1 ... w n are sequentially decremented according to a preset rule.
- the selecting new information from the preset information list according to the obtained page view amount includes:
- P' ADj1 (target_pv-P ADj1 ) / target_pv,
- P ADj1 represents the page view amount of the information AD j
- P′ ADj1 represents the adjusted page view amount corresponding to P ADj1
- target_pv represents the preset page view amount threshold value
- determining, according to the obtained information recommendation degree, the information to be pushed from the selected information including:
- P' ADq2 (P Adq2 - P min ) / (P max - P min );
- P Adq2 represents the information recommendation degree of the information AD q
- P′ ADq2 represents the adjusted information recommendation degree corresponding to P Adq2
- P min represents the smallest information recommendation degree among the obtained information recommendation degrees
- P max represents the obtained information.
- the information to be pushed is determined from the information that the adjusted information recommendation degree in the selected information satisfies the preset second information selection condition.
- the determining the information to be pushed from the information that the adjusted information recommendation degree in the selected information meets the preset second information selection condition includes:
- P Adr indicates the selection weight of the information AD r
- P ADr1 indicates the adjusted page view amount of the information r
- P Adr2 indicates the adjusted information recommendation degree of the information r
- w r1 and w r2 are P ADr1 and P Adr2 , respectively.
- Selection weight, w r1 +w r2 1;
- the information to be pushed is determined from the information obtained by selecting the weight that satisfies the preset third selection condition.
- the selecting the information that the weight meets the preset third selection condition from the found information, and determining the information to be pushed includes:
- an embodiment of the present invention discloses an information pushing device, where the device includes:
- a page view obtaining module configured to obtain a page view amount of each preset information in the preset information list within a preset time period before the current time
- a new information selection module configured to select new information from the preset information list according to the obtained page view amount, where the new information is information that does not satisfy a preset information display condition
- An information recommendation obtaining module configured to obtain information recommendation degree of the selected information
- a to-be-push information determining module configured to determine, according to the obtained information recommendation degree, a to-be-pushed message from the selected information interest
- the information pushing module is configured to push the determined information to be pushed.
- the page view quantity obtaining module is specifically configured to obtain, according to the following expression, page browsing within a preset time period before any current information AD i in the preset information list The amount of PV ADi ,
- PV Adi w 1 * PV Adi_f1 + ... + w n * PV Adi_fn ,
- w 1 represents the attenuation coefficient corresponding PV Adi_f1
- PV Adi_fn views showing the page before the current time of the n-th information within the AD i
- w n represents the attenuation coefficient corresponding to PV Adi_fn
- the nth day before the current time is the day when the current time is the longest according to the preset time length
- w 1 ... w n are sequentially decremented according to a preset rule.
- the new information selection module includes:
- the page view adjustment sub-module is used to adjust the page views obtained by the following expression.
- P' ADj1 (target_pv-P ADj1 ) / target_pv,
- P ADj1 represents the page view amount of the information AD j
- P′ ADj1 represents the adjusted page view amount corresponding to P ADj1
- target_pv represents the preset page view amount threshold value
- the information selection sub-module is configured to select, from the preset information list, information that the adjusted page view quantity is greater than a preset first probability threshold and less than or equal to a preset second probability threshold.
- the to-be-polished information determining module includes:
- the information recommendation adjustment sub-module is used to adjust the information recommendation degree obtained according to the following expression.
- P' ADq2 (P Adq2 - P min ) / (P max - P min );
- P Adq2 represents the information recommendation degree of the information AD q
- P′ ADq2 represents the adjusted information recommendation degree corresponding to P Adq2
- P min represents the smallest information recommendation degree among the obtained information recommendation degrees
- P max represents the obtained information.
- the to-be-push information determining sub-module is configured to determine the information to be pushed from the information that the adjusted information recommendation degree in the selected information meets the preset second information selection condition.
- the to-be-push information determining sub-module includes:
- An information searching unit configured to search for the adjusted information from the selected information, the degree of recommendation is greater than a preset first recommendation degree a threshold value and less than or equal to a preset second recommendation degree threshold;
- a weight calculation unit is configured to calculate a selection weight of any of the found information according to the following expression.
- P Adr indicates the selection weight of the information AD r
- P ADr1 indicates the adjusted page view amount of the information r
- P Adr2 indicates the adjusted information recommendation degree of the information r
- w r1 and w r2 are P ADr1 and P Adr2 , respectively.
- Selection weight, w r1 +w r2 1;
- the to-be-push information determining unit is configured to determine, from the found information, information that the weight meets the preset third selection condition, and determine the information to be pushed.
- the information to be pushed information determining unit includes:
- the to-be-push information determining sub-unit is configured to determine, from the found information, the information that the weight meets the preset third selection condition according to the obtained random number, and determine the information to be pushed.
- an embodiment of the present invention discloses an electronic device, including: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside a space enclosed by the housing, The processor and the memory are disposed on the circuit board; the power circuit is configured to supply power to each circuit or device of the electronic device; the memory is used to store the executable program code; and the processor operates by reading the executable program code stored in the memory.
- the embodiment of the invention further discloses a computer readable storage medium having instructions stored therein, when the processor of the electronic device executes the instruction, the electronic device performs the information pushing method as described above.
- Embodiments of the present invention also disclose a computer program that, when run on a processor, performs the information as described above Push method.
- the preset information list is obtained according to the obtained page view amount.
- the new information is selected, and then the information recommendation degree of the selected information is obtained, and the information to be pushed is determined from the selected information according to the obtained information recommendation degree, and then the information to be pushed is pushed.
- the selection is not performed randomly, but is performed according to the information recommendation degree of the information, thereby improving the user experience.
- FIG. 1 is a schematic flowchart of a method for pushing information according to an embodiment of the present invention
- FIG. 2 is a schematic flowchart of another information pushing method according to an embodiment of the present invention.
- FIG. 3 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present disclosure.
- FIG. 4 is a schematic structural diagram of another information pushing apparatus according to an embodiment of the present invention.
- FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
- FIG. 1 is a schematic flowchart of a method for pushing information according to an embodiment of the present invention, where the method includes:
- S101 Obtain a page view amount within a preset duration of each information in the preset information list before the current time.
- the preset information list is used to store the identifier of the information, etc., and the above information may be advertisement information, news information, weather forecast, etc., which is not limited in this application.
- the preset duration may be the duration in hours, for example, 12 hours, 6 hours, etc., and may also be the duration in days, for example, 15 days, 20 days, and the like.
- Page View is usually a measure of a network news channel or website or even a network news The main indicator. Page views are one of the most commonly used indicators for evaluating website traffic.
- the page view amount of each information obtained in this step may be one page view amount, or may be multiple, for example, one day time corresponds to one page view amount and the like.
- S102 Select new information from the preset information list according to the obtained page view amount.
- the new information is information that does not satisfy the preset information display condition.
- the preset information display condition may be an information display condition related to the page view amount, and the like, for example, when the page view amount is less than a certain threshold, it is new information or the like.
- the page view amount of a piece of information in a preset time period is usually related to the page view amount in the recent preset time period, but the relationship will become longer as the distance between the two time periods becomes longer.
- Gradually weakening for example, the absolute difference between the page view of an ad today and the page view of the ad yesterday may be less than the absolute difference between the page view of the ad today and the page view of the day before the ad, etc. Wait.
- the page view of a piece of information is gradually reduced, and the probability that the piece of information is new information is low.
- the information recommendation degree of the information may be the popularity of the information obtained by the operation and maintenance personnel through the questionnaire survey or other forms of investigation before the information is delivered, and may be the history of the operation and maintenance personnel combining the information according to the type of the information and other information in the type.
- the popularity of the information predicted by the data can also be the price of the information, etc., for example, the advertisement shows the income eCPM and so on.
- S104 Determine, according to the obtained information recommendation degree, the information to be pushed from the selected information.
- the information recommendation degree can directly affect the user experience or the revenue of the operator, it is determined that the information to be pushed can be performed according to the information recommendation degree of the information.
- the information recommendation degree of the information is the popularity of the information
- information having a high degree of popularity among the selected information may be preferentially determined as the information to be pushed
- the information recommendation degree of the information is the information price
- the information having a high price among the selected information may be preferentially determined as the information to be pushed.
- the degree of recommendation of the information may also be composed of information such as the popularity of the information and the price of the information.
- various factors may be comprehensively considered.
- the preset information list when obtaining a page view amount within a preset duration of each information in the preset information list, the preset information list may be obtained according to the following expression.
- PV Adi w 1 * PV Adi_f1 + ... + w n * PV Adi_fn ,
- w 1 represents the attenuation coefficient corresponding PV Adi_f1
- n represents W
- the attenuation coefficient corresponding to PV Adi_fn the day n before the current time is the longest day of the current time determined according to the preset duration
- w 1 ... w n are sequentially decremented according to a preset rule.
- FIG. 2 a schematic flowchart of another information pushing method is provided.
- S102 Select new information in the preset information list (S102), including:
- S102A Adjust the obtained page views according to the preset expression.
- P' ADj1 (target_pv-P ADj1 ) / target_pv,
- P ADj1 represents the page view amount of the information AD j
- P′ ADj1 represents the adjusted page view amount corresponding to P ADj1
- target_pv represents the preset page view amount threshold value.
- the target_pv when the target_pv is less than or equal to P ADj1 , it can be understood that the page view amount of the information AD j is high.
- the information AD j can generally be regarded as not new information, and vice versa, when the target_pv is greater than P ADj1 , understood as information AD j page views is not very high, and thus can be considered information AD j is information.
- S102B Select, from the preset information list, information that the adjusted page view quantity is greater than a preset first probability threshold and less than or equal to a preset second probability threshold.
- the preset first probability threshold is equal to 0, and the preset second probability threshold is equal to 1.
- the obtained information recommendation degree when the information to be pushed is determined from the selected information according to the obtained information recommendation degree, the obtained information recommendation degree may be adjusted according to the following expression, and from the selected information.
- the adjusted information recommendation degree satisfies the preset second information selection condition information, and determines the information to be pushed,
- P' ADq2 (P Adq2 - P min ) / (P max - P min );
- P Adq2 represents the information recommendation degree of the information AD q
- P′ ADq2 represents the adjusted information recommendation degree corresponding to P Adq2
- P min represents the smallest information recommendation degree among the obtained information recommendation degrees
- P max represents the obtained information. The maximum information recommendation degree in the information recommendation degree.
- the foregoing second information selection condition may be: selecting, from the selected information, that the adjusted information recommendation degree is greater than a preset first threshold and less than or equal to a preset second threshold.
- the second information selection condition may be: selecting information of the adjusted information recommendation degree that is greater than the third threshold from the selected information, and the like, which is not limited in the present application.
- the information recommendation degree of the information may be considered, and the page view amount of the information may also be considered.
- the adjusted information is selected from the selected information.
- the information recommendation degree of the adjusted information may be searched from the selected information for more than the preset first recommendation degree threshold and less than or equal to the preset.
- the information of the second recommendation degree threshold and then, according to the following expression, calculating the selection weight of any of the found information, and selecting from the found information that the weight meets the preset third selection condition, determining Push information,
- P Adr indicates the selection weight of the information AD r
- P ADr1 indicates the adjusted page view amount of the information r
- P Adr2 indicates the adjusted information recommendation degree of the information r
- w r1 and w r2 are P ADr1 and P Adr2 , respectively.
- the choice weight, w r1 + w r2 1.
- w r1 is smaller than w r2 , information with a high degree of information recommendation is preferentially pushed, for example, an advertisement with a high advertisement price is preferentially pushed; and if w r1 is greater than w r2 , information with a high page view amount is preferentially pushed.
- the selected weight of the calculated non-new information is generally large, in order to facilitate determining the information to be pushed, reducing the error, and calculating the selection weight of any information found, Performing information search again according to the preset weight threshold, for example, searching for information that the selection weight is greater than the preset first selection weight and less than or equal to the preset second selection weight from the found information, and then performing subsequent determination.
- the step of pushing the information considering that the selected weight of the calculated non-new information is generally large, in order to facilitate determining the information to be pushed, reducing the error, and calculating the selection weight of any information found.
- the preset first selection weight is equal to 0, and the preset second selection weight is equal to 100.
- the preset third weight threshold if less than, updates the selection weight to a preset third weight threshold.
- the preset four-scatter weight threshold is equal to 20.
- the preset first recommendation degree threshold is equal to 0, and the preset second recommendation degree threshold is equal to 1.
- selecting information from the found information that meets the preset third selection condition, and determining the to-be-pushed information, according to the preset value range, according to the pre-predetermined The random function is obtained to obtain a random number, and according to the obtained random number, selecting information from the found information that the weight meets the preset third selection condition determines the information to be pushed.
- a random number can be selected from the range of (0, 100) by a random function, and then information of the selected weight greater than the random number is selected from the found information as the information to be pushed.
- the preset information list is obtained according to the obtained page view amount.
- the new information is selected, and then the information recommendation degree of the selected information is obtained, and the information to be pushed is determined from the selected information according to the obtained information recommendation degree, and then the information to be pushed is pushed.
- the selection is not performed randomly, but is performed according to the information recommendation degree of the information, thereby improving the user experience.
- an embodiment of the present invention further provides an information pushing device.
- FIG. 3 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present disclosure, where the apparatus includes:
- the page view quantity obtaining module 301 is configured to obtain a page view amount of each preset information in the preset information list within a preset time period before the current time;
- the new information selection module 302 is configured to select new information from the preset information list according to the obtained page view quantity, where the new information is information that does not satisfy the preset information display condition;
- the information recommendation degree obtaining module 303 is configured to obtain an information recommendation degree of the selected information
- the to-be-push information determining module 304 is configured to determine information to be pushed from the selected information according to the obtained information recommendation degree;
- the information pushing module 305 is configured to push the determined information to be pushed.
- the page view quantity obtaining module 301 is configured to obtain, according to the following expression, a page view quantity PV ADi within a preset time period of any information AD i in the preset information list.
- PV Adi w 1 * PV Adi_f1 + ... + w n * PV Adi_fn ,
- w 1 represents the attenuation coefficient corresponding PV Adi_f1
- PV Adi_fn views showing the page before the current time of the n-th information within the AD i
- w n represents the attenuation coefficient corresponding to PV Adi_fn
- the nth day before the current time is the day when the current time is the longest according to the preset time length
- w 1 ... w n are sequentially decremented according to a preset rule.
- the new information selecting module 302 includes:
- the page view amount adjustment sub-module 3021 is configured to adjust the obtained page view amount according to the following expression.
- P' ADj1 (target_pv-P ADj1 ) / target_pv,
- P ADj1 represents the page view amount of the information AD j
- P′ ADj1 represents the adjusted page view amount corresponding to P ADj1
- target_pv represents the preset page view amount threshold value
- the information selection sub-module 3022 is configured to select, from the preset information list, information that the adjusted page view amount is greater than a preset first probability threshold and less than or equal to a preset second probability threshold.
- the to-be-push information determining module 304 may include:
- the information recommendation adjustment sub-module is used to adjust the information recommendation degree obtained according to the following expression.
- P' ADq2 (P Adq2 - P min ) / (P max - P min );
- P Adq2 represents the information recommendation degree of the information AD q
- P′ ADq2 represents the adjusted information recommendation degree corresponding to P Adq2
- P min represents the smallest information recommendation degree among the obtained information recommendation degrees
- P max represents the obtained information.
- the to-be-push information determining sub-module is configured to determine the information to be pushed from the information that the adjusted information recommendation degree in the selected information meets the preset second information selection condition.
- the to-be-push information determining sub-module includes:
- An information searching unit configured to search for the adjusted information from the selected information, the degree of recommendation is greater than a preset first recommendation degree a threshold value and less than or equal to a preset second recommendation degree threshold;
- a weight calculation unit is configured to calculate a selection weight of any of the found information according to the following expression.
- P Adr indicates the selection weight of the information AD r
- P ADr1 indicates the adjusted page view amount of the information r
- P Adr2 indicates the adjusted information recommendation degree of the information r
- w r1 and w r2 are P ADr1 and P Adr2 , respectively.
- Selection weight, w r1 +w r2 1;
- the to-be-push information determining unit is configured to determine, from the found information, information that the weight meets the preset third selection condition, and determine the information to be pushed.
- the to-be-push information determining unit includes:
- the to-be-push information determining sub-unit is configured to determine, from the found information, the information that the weight meets the preset third selection condition according to the obtained random number, and determine the information to be pushed.
- the preset information list is obtained according to the obtained page view amount.
- the new information is selected, and then the information recommendation degree of the selected information is obtained, and the information to be pushed is determined from the selected information according to the obtained information recommendation degree, and then the information to be pushed is pushed.
- the selection is not performed randomly, but is performed according to the information recommendation degree of the information, thereby improving the user experience.
- an embodiment of the present invention further provides an electronic device.
- the electronic device includes a housing 501, a processor 502, a memory 503, a circuit board 504, and a power circuit 505.
- the circuit board 504 is disposed in the housing. Inside the space enclosed by 501, the processor 502 and the memory 503 are disposed on the circuit board 504; the power supply circuit 505 is configured to supply power to various circuits or devices of the electronic device; the memory 503 is configured to store executable program code; the processor 502 passes The executable program code stored in the memory 503 is read to execute a program corresponding to the executable program code for performing the following steps:
- each information in the preset information list is obtained from the preset information list according to the obtained page view amount.
- the new information is selected, and then the information recommendation degree of the selected information is obtained, and the information to be pushed is determined from the selected information according to the obtained information recommendation degree, and then the information to be pushed is pushed.
- the selection is not performed randomly, but is performed according to the information recommendation degree of the information, thereby improving the user experience.
- the electronic device exists in a variety of forms including, but not limited to:
- Mobile communication devices These devices are characterized by mobile communication functions and are mainly aimed at providing voice and data communication.
- Such terminals include: smart phones (such as iPhone), multimedia phones, functional phones, and low-end phones.
- Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has mobile Internet access.
- Such terminals include: PDAs, MIDs, and UMPC devices, such as the iPad.
- Portable entertainment devices These devices can display and play multimedia content. Such devices include: audio, video players (such as iPod), handheld game consoles, e-books, and smart toys and portable car navigation devices.
- the server consists of a processor, a hard disk, a memory, a system bus, etc.
- the server is similar to a general-purpose computer architecture, but because of the need to provide highly reliable services, processing power and stability High reliability in terms of reliability, security, scalability, and manageability.
- the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.
- modules or units in all the embodiments of the present invention may be implemented by a general-purpose integrated circuit, such as a CPU (Central Processing Unit) or an ASIC (Application Specific Integrated Circuit).
- a CPU Central Processing Unit
- ASIC Application Specific Integrated Circuit
- a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
- computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
- the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as may The program is obtained electronically, for example by optical scanning of paper or other medium, followed by editing, interpretation or, if necessary, processing in other suitable manner, and then storing it in a computer memory.
- each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
- the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
- the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
- the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- User Interface Of Digital Computer (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
Claims (15)
- 一种信息推送方法,其特征在于,所述方法包括:获得预设的信息列表中每一信息在当前时刻之前预设时长内的页面浏览量;根据所获得的页面浏览量,从所述预设的信息列表中选择新信息,其中,所述新信息为不满足预设的信息展示条件的信息;获得所选择信息的信息推荐度;根据所获得的信息推荐度,从所选择的信息中确定待推送信息;推送所确定的待推送信息。
- 根据权利要求1所述的方法,其特征在于,所述获得预设的信息列表中每一信息在当前时刻之前预设时长内的页面浏览量,包括:根据以下表达式,获得预设的信息列表中任一信息ADi在当前时刻之前预设时长内的页面浏览量PVADi,PVAdi=w1*PVAdi_f1+……+wn*PVAdi_fn,其中,PVAdi_f1表示当前时刻之前第一天内所述信息ADi的页面浏览量,w1表示PVAdi_f1对应的衰减系数,PVAdi_fn表示当前时刻之前第n天内所述信息ADi的页面浏览量,wn表示PVAdi_fn对应的衰减系数,当前时刻之前第n天为根据预设的时长确定的距离当前时刻时长最长的一天,w1……wn按照预设的规则依次递减。
- 根据权利要求1或2所述的方法,其特征在于,所述根据所获得的页面浏览量,从所述预设的信息列表中选择新信息,包括:按照以下表达式调整所获得的页面浏览量,P'ADj1=(target_pv-PADj1)/target_pv,其中,PADj1表示信息ADj的页面浏览量,P'ADj1表示PADj1对应的调整后的页面浏览量,target_pv表示预设的页面浏览量阈值;从所述预设的信息列表中选择调整后的页面浏览量大于预设的第一概率阈值且小于等于预设的第二概率阈值的信息。
- 根据权利要求1至3中任一项所述的方法,其特征在于,所述根据所获得的信息推荐 度,从所选择的信息中确定待推送信息,包括:按照以下表达式调整所获得的信息推荐度,P'ADq2=(PAdq2-Pmin)/(Pmax-Pmin);其中,PAdq2表示信息ADq的信息推荐度,P'ADq2表示PAdq2对应的调整后的信息推荐度,Pmin表示所获得的信息推荐度中最小的信息推荐度,Pmax表示所获得的信息推荐度中最大的信息推荐度;从所选择的信息中调整后的信息推荐度满足预设的第二信息选择条件的信息中,确定待推送信息。
- 根据权利要求4所述的方法,其特征在于,所述从所选择的信息中调整后的信息推荐度满足预设的第二信息选择条件的信息中,确定待推送信息,包括:从所选择的信息中查找调整后的信息推荐度大于预设的第一推荐度阈值且小于等于预设的第二推荐度阈值的信息;根据以下表达式,计算查找到的任一信息的选择权重,PAdr=wr1*PADr1+wr2*PADr2,其中,PAdr表示信息ADr的选择权重,PADr1表示信息r的调整后的页面浏览量,PAdr2表示信息r的调整后的信息推荐度,wr1和wr2分别为PADr1和PAdr2的选择权重,wr1+wr2=1;从查找到的信息中选择权重满足预设的第三选择条件的信息中,确定待推送信息。
- 根据权利要求5所述的方法,其特征在于,所述从查找到的信息中选择权重满足预设的第三选择条件的信息中,确定待推送信息,包括:根据预先设定的取值范围,根据预设的随机函数获得一个随机数;根据所获得的随机数,从查找到的信息中选择权重满足预设的第三选择条件的信息中,确定待推送信息。
- 一种信息推送装置,其特征在于,所述装置包括:页面浏览量获得模块,用于获得预设的信息列表中每一信息在当前时刻之前预设时长内的页面浏览量;新信息选择模块,用于根据所获得的页面浏览量,从所述预设的信息列表中选择新信息,其中,所述新信息为不满足预设的信息展示条件的信息;信息推荐度获得模块,用于获得所选择信息的信息推荐度;待推送信息确定模块,用于根据所获得的信息推荐度,从所选择的信息中确定待推送信息;信息推送模块,用于推送所确定的待推送信息。
- 根据权利要求7所述的装置,其特征在于,所述页面浏览量获得模块,具体用于根据以下表达式,获得预设的信息列表中任一信息ADi在当前时刻之前预设时长内的页面浏览量PVADi,PVAdi=w1*PVAdi_f1+……+wn*PVAdi_fn,其中,PVAdi_f1表示当前时刻之前第一天内所述信息ADi的页面浏览量,w1表示PVAdi_f1对应的衰减系数,PVAdi_fn表示当前时刻之前第n天内所述信息ADi的页面浏览量,wn表示PVAdi_fn对应的衰减系数,当前时刻之前第n天为根据预设的时长确定的距离当前时刻时长最长的一天,w1……wn按照预设的规则依次递减。
- 根据权利要求7或8所述的装置,其特征在于,所述新信息选择模块,包括:页面浏览量调整子模块,用于按照以下表达式调整所获得的页面浏览量,P'ADj1=(target_pv-PADj1)/target_pv,其中,PADj1表示信息ADj的页面浏览量,P'ADj1表示PADj1对应的调整后的页面浏览量,target_pv表示预设的页面浏览量阈值;信息选择子模块,用于从所述预设的信息列表中选择调整后的页面浏览量大于预设的第一概率阈值且小于等于预设的第二概率阈值的信息。
- 根据权利要求7至9中任一项所述的装置,其特征在于,所述待推送信息确定模块,包括:信息推荐度调整子模块,用于按照以下表达式调整所获得的信息推荐度,P'ADq2=(PAdq2-Pmin)/(Pmax-Pmin);其中,PAdq2表示信息ADq的信息推荐度,P'ADq2表示PAdq2对应的调整后的信息推荐度,Pmin表示所获得的信息推荐度中最小的信息推荐度,Pmax表示所获得的信息推荐度中最大的信息推荐度;待推送信息确定子模块,用于从所选择的信息中调整后的信息推荐度满足预设的第二信 息选择条件的信息中,确定待推送信息。
- 根据权利要求10所述的装置,其特征在于,所述待推送信息确定子模块,包括:信息查找单元,用于从所选择的信息中查找调整后的信息推荐度大于预设的第一推荐度阈值且小于等于预设的第二推荐度阈值的信息;选择权重计算单元,用于根据以下表达式,计算查找到的任一信息的选择权重,PAdr=wr1*PADr1+wr2*PADr2,其中,PAdr表示信息ADr的选择权重,PADr1表示信息r的调整后的页面浏览量,PAdr2表示信息r的调整后的信息推荐度,wr1和wr2分别为PADr1和PAdr2的选择权重,wr1+wr2=1;待推送信息确定单元,用于从查找到的信息中选择权重满足预设的第三选择条件的信息中,确定待推送信息。
- 根据权利要求11所述的装置,其特征在于,所述待推送信息确定单元,包括:随机数获得子单元,用于根据预先设定的取值范围,根据预设的随机函数获得一个随机数;待推送信息确定子单元,用于根据所获得的随机数,从查找到的信息中选择权重满足预设的第三选择条件的信息中,确定待推送信息。
- 一种电子设备,其特征在于,所述电子设备包括:壳体、处理器、存储器、电路板和电源电路,其中,电路板安置在壳体围成的空间内部,处理器和存储器设置在电路板上;电源电路,用于为电子设备的各个电路或器件供电;存储器用于存储可执行程序代码;处理器通过读取存储器中存储的可执行程序代码来运行与可执行程序代码对应的程序,以用于执行以下步骤:获得预设的信息列表中每一信息在当前时刻之前预设时长内的页面浏览量;根据所获得的页面浏览量,从所述预设的信息列表中选择新信息,其中,所述新信息为不满足预设的信息展示条件的信息;获得所选择信息的信息推荐度;根据所获得的信息推荐度,从所选择的信息中确定待推送信息;推送所确定的待推送信息。
- 一种计算机可读存储介质,具有存储于其中的指令,当电子设备的处理器执行所述 指令时,所述电子设备执行如权利要求1-6中任一项所述的信息推送方法。
- 一种计算机程序,当其在处理器上运行时,执行如权利要求1-6中任一项所述的信息推送方法。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/762,012 US10686903B2 (en) | 2015-09-30 | 2016-08-15 | Information push method and electronic device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510641114.9A CN105183904B (zh) | 2015-09-30 | 2015-09-30 | 一种信息推送方法、装置及电子设备 |
CN201510641114.9 | 2015-09-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017054582A1 true WO2017054582A1 (zh) | 2017-04-06 |
Family
ID=54905985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/095331 WO2017054582A1 (zh) | 2015-09-30 | 2016-08-15 | 一种信息推送方法、装置及电子设备 |
Country Status (3)
Country | Link |
---|---|
US (1) | US10686903B2 (zh) |
CN (1) | CN105183904B (zh) |
WO (1) | WO2017054582A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111163152A (zh) * | 2019-12-26 | 2020-05-15 | 中国平安人寿保险股份有限公司 | 信息推送方法及装置 |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105183904B (zh) * | 2015-09-30 | 2020-01-10 | 北京金山安全软件有限公司 | 一种信息推送方法、装置及电子设备 |
CN106777226B (zh) | 2016-12-26 | 2021-05-11 | 腾讯科技(深圳)有限公司 | 一种信息分析方法及电子设备 |
CN108256891A (zh) * | 2016-12-29 | 2018-07-06 | 北京奇虎科技有限公司 | 一种对网页广告的广告展示模板进行测试的方法和装置 |
CN109034965B (zh) * | 2018-07-16 | 2020-12-25 | 深圳美图创新科技有限公司 | 一种产品推荐方法、计算设备及存储介质 |
CN109379410B (zh) * | 2018-09-21 | 2019-11-19 | 北京达佳互联信息技术有限公司 | 信息推送方法、装置、服务器以及存储介质 |
CN109587328B (zh) * | 2018-11-21 | 2021-07-20 | Oppo广东移动通信有限公司 | 消息管理方法和装置、存储介质及电子设备 |
CN110175190B (zh) * | 2019-04-15 | 2024-05-14 | 平安科技(深圳)有限公司 | 房源推荐方法、装置、计算机设备及计算机可读存储介质 |
CN110147496B (zh) * | 2019-05-13 | 2021-06-25 | 百度在线网络技术(北京)有限公司 | 内容推送方法及装置 |
CN110389801B (zh) * | 2019-06-05 | 2022-08-30 | 北京梧桐车联科技有限责任公司 | 一种信息处理方法、装置、车载设备及存储介质 |
CN112291297B (zh) * | 2020-09-04 | 2022-04-26 | 腾讯科技(深圳)有限公司 | 资讯数据的处理方法、装置、存储介质以及电子设备 |
CN112800327A (zh) * | 2021-01-18 | 2021-05-14 | 北京明略软件系统有限公司 | 一种目标媒体信息的确定方法和装置 |
CN112948688A (zh) * | 2021-03-26 | 2021-06-11 | 北京声智科技有限公司 | 信息排序方法、装置、电子设备及计算机可读存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103207876A (zh) * | 2012-01-17 | 2013-07-17 | 阿里巴巴集团控股有限公司 | 一种信息投放的方法及装置 |
CN103714474A (zh) * | 2012-10-08 | 2014-04-09 | 阿里巴巴集团控股有限公司 | 推广信息投放方法及信息服务器 |
CN104834731A (zh) * | 2015-05-15 | 2015-08-12 | 百度在线网络技术(北京)有限公司 | 一种自媒体信息的推荐方法及装置 |
CN105183904A (zh) * | 2015-09-30 | 2015-12-23 | 北京金山安全软件有限公司 | 一种信息推送方法、装置及电子设备 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1394694A4 (en) * | 2001-06-06 | 2006-05-24 | Sony Corp | APPARATUS AND METHOD FOR ADVERTISING SELECTION, STORAGE MEDIUM |
CN103077469A (zh) * | 2011-10-26 | 2013-05-01 | Kddi株式会社 | 推荐装置、推荐系统、推荐方法以及程序 |
US10296948B2 (en) * | 2013-03-15 | 2019-05-21 | Excalibur Ip, Llc | Online digital content real-time update |
CN104102648B (zh) * | 2013-04-07 | 2017-12-01 | 腾讯科技(深圳)有限公司 | 基于用户行为数据的兴趣推荐方法及装置 |
CN103678672B (zh) * | 2013-12-25 | 2017-05-24 | 北京中兴通德网络科技有限公司 | 一种信息推荐方法 |
US20160300265A1 (en) * | 2015-04-09 | 2016-10-13 | Adobe Systems Incorporated | Capping campaign frequency or spend per user across multiple devices or publishers |
CN106445676B (zh) * | 2015-08-05 | 2019-10-22 | 杭州海康威视系统技术有限公司 | 一种分布式数据计算的任务分配方法和任务分配装置 |
-
2015
- 2015-09-30 CN CN201510641114.9A patent/CN105183904B/zh active Active
-
2016
- 2016-08-15 WO PCT/CN2016/095331 patent/WO2017054582A1/zh active Application Filing
- 2016-08-15 US US15/762,012 patent/US10686903B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103207876A (zh) * | 2012-01-17 | 2013-07-17 | 阿里巴巴集团控股有限公司 | 一种信息投放的方法及装置 |
CN103714474A (zh) * | 2012-10-08 | 2014-04-09 | 阿里巴巴集团控股有限公司 | 推广信息投放方法及信息服务器 |
CN104834731A (zh) * | 2015-05-15 | 2015-08-12 | 百度在线网络技术(北京)有限公司 | 一种自媒体信息的推荐方法及装置 |
CN105183904A (zh) * | 2015-09-30 | 2015-12-23 | 北京金山安全软件有限公司 | 一种信息推送方法、装置及电子设备 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111163152A (zh) * | 2019-12-26 | 2020-05-15 | 中国平安人寿保险股份有限公司 | 信息推送方法及装置 |
CN111163152B (zh) * | 2019-12-26 | 2023-08-08 | 中国平安人寿保险股份有限公司 | 信息推送方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
CN105183904A (zh) | 2015-12-23 |
CN105183904B (zh) | 2020-01-10 |
US20180278704A1 (en) | 2018-09-27 |
US10686903B2 (en) | 2020-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017054582A1 (zh) | 一种信息推送方法、装置及电子设备 | |
US20170270189A1 (en) | Selecting content using query-independent scores of query segments | |
US9886705B2 (en) | Advertisement opportunity bidding | |
US20100306049A1 (en) | Method and system for matching advertisements to web feeds | |
US9064264B2 (en) | Predicting visibility of content items | |
US20110184811A1 (en) | Providing contextual advertisements for electronic books | |
US9465881B2 (en) | User displays using N-way paginated merge of information from diverse sources | |
US20190180326A1 (en) | Determining relevant business locations based on travel distances | |
US20160180406A1 (en) | Combined advertisements | |
US11983744B2 (en) | Personalized mobile application re-engagement | |
US20150287096A1 (en) | Bid control through semantic signals expressed in natural language | |
US10796336B1 (en) | Content selection based on connection information | |
US9602563B2 (en) | Selective content delivery in a real-time streaming environment | |
US8856110B2 (en) | Method and apparatus for providing a response to a query | |
WO2017219691A1 (zh) | 页面内容加载方法、装置及电子设备 | |
US20180218395A1 (en) | Advertisements targeting on video playlists | |
US10796345B1 (en) | Offline video advertising | |
US8719259B1 (en) | Providing content based on geographic area | |
US20150332192A1 (en) | Estimating Future Inventory | |
US20200394189A1 (en) | Broad match control | |
US20180343218A1 (en) | Contextual interstitials | |
CN105630793A (zh) | 信息权重的确定方法和装置 | |
US10146778B2 (en) | Determining a lasting value of content items and performers | |
US10049386B1 (en) | Adjusting content selection based on search results | |
US20150370803A1 (en) | Automatic positioning of elements in a computer-based document |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16850206 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15762012 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07.08.2018) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16850206 Country of ref document: EP Kind code of ref document: A1 |