WO2019019396A1 - 推送结果预测方法、装置、计算机设备和存储介质 - Google Patents

推送结果预测方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2019019396A1
WO2019019396A1 PCT/CN2017/104871 CN2017104871W WO2019019396A1 WO 2019019396 A1 WO2019019396 A1 WO 2019019396A1 CN 2017104871 W CN2017104871 W CN 2017104871W WO 2019019396 A1 WO2019019396 A1 WO 2019019396A1
Authority
WO
WIPO (PCT)
Prior art keywords
user account
account set
click
predicted
information
Prior art date
Application number
PCT/CN2017/104871
Other languages
English (en)
French (fr)
Inventor
王强
Original Assignee
上海壹账通金融科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海壹账通金融科技有限公司 filed Critical 上海壹账通金融科技有限公司
Publication of WO2019019396A1 publication Critical patent/WO2019019396A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/55Push-based network services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/535Tracking the activity of the user

Definitions

  • the present application relates to the field of information processing technologies, and in particular, to a push result prediction method, apparatus, computer device, and storage medium.
  • the information is pushed according to the preset push parameters, and the information is pushed according to the preset target user account.
  • some target user accounts are unavailable, and the information cannot be pushed to the target user account, which reduces the success rate of information push.
  • a push result prediction method is provided.
  • a method for predicting push results including:
  • a push result prediction device includes:
  • a push task acquisition module configured to obtain an information push task
  • a user account extraction module configured to extract a target user account in the information push task, and obtain a target user account set
  • the historical information obtaining module is configured to obtain historical online information corresponding to each user account in the target user account set;
  • the online account selection module is configured to select an online user account from the set of target user accounts according to the obtained historical online information, and obtain a predicted arrival user account set;
  • a tag information obtaining module configured to acquire a user interest tag and historical click information corresponding to each user account in the predicted user account set
  • Clicking an account selection module configured to extract a predicted click user account set from the predicted arrival user account set according to the obtained user interest tag and historical click information
  • the prediction result generating module is configured to generate a push prediction result according to the predicted arrival user account set and the predicted click user account set.
  • a computer device comprising a memory and a processor, wherein the memory stores computer executable instructions that, when executed by the processor, cause the processor to perform the following steps:
  • One or more storage media storing computer executable instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps:
  • 1 is an application environment diagram of a method for predicting a push result in an embodiment
  • FIG. 2 is a structural block diagram of a server in a push result prediction system in an embodiment
  • FIG. 3 is a schematic flow chart of a method for predicting a push result in an embodiment
  • FIG. 4 is a schematic flowchart of a step of obtaining a predicted arrival user account set in an embodiment
  • FIG. 5 is a schematic flowchart of a step of extracting a predicted click user account set in an embodiment
  • FIG. 6 is a schematic flowchart of a step of extracting a user account according to a click prediction value in an embodiment
  • Figure 7 is a block diagram showing the structure of a push result prediction apparatus in an embodiment
  • FIG. 8 is a structural block diagram of an online account selection module in an embodiment
  • FIG. 9 is a structural block diagram of a click account selection module in an embodiment
  • Figure 10 is a block diagram showing the structure of a push result prediction apparatus in another embodiment.
  • FIG. 1 is an application environment diagram of a method for predicting a push result in an embodiment.
  • the push result prediction method is applied to a push result prediction system.
  • the push result prediction system includes a terminal 110 and a server 120, wherein the terminal 110 is connected to the server 120 through a network.
  • the terminal 110 may be a fixed terminal or a mobile terminal, and the fixed terminal may specifically be at least one of a printer, a scanner, and a monitor, and the mobile terminal may specifically be at least one of a tablet computer, a smart phone, a personal data assistant, and a digital camera.
  • Server 120 can be a single server or a cluster of servers with multiple servers.
  • the server 120 includes a processor, a non-volatile storage medium, an internal memory, and a network interface connected by a system bus.
  • the processor of server 120 is used to provide computing and control capabilities to support the operation of the entire server 120, the memory for storing data, code instructions, etc., and the network interface for network communication with terminal 110.
  • At least one computer executable instruction is stored on the memory, and the computer executable instructions are executable by the processor to implement the push result prediction method applicable to the server 120 provided in the embodiment of the present application.
  • the memory may include a non-volatile storage medium such as a magnetic disk, an optical disk, or a read-only memory (ROM).
  • a non-volatile storage medium such as a magnetic disk, an optical disk, or a read-only memory (ROM).
  • the memory includes a non-volatile storage medium and an internal memory; the non-volatile storage medium stores an operating system, a database, and computer-executable instructions, and the database stores historical online information corresponding to each user account, History click information and user interest tags, the computer executable instructions executable by the processor to implement the push result prediction method described above; the internal memory provides cached operation for operating systems and computer executable instructions in the non-volatile storage medium surroundings.
  • FIG. 2 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the server to which the solution of the present application is applied.
  • the specific server may include a ratio. More or fewer components are shown in Figure 2, or some components are combined, or have different component arrangements.
  • a method for predicting a push result is provided.
  • This embodiment is exemplified by the method applied to the server 120 in FIG. 1, and the method specifically includes the following content:
  • the terminal 110 acquires an operator account input by the push operator, generates a push prediction page request according to the acquired operator account, and sends a push prediction page request to the server 120.
  • the server 120 receives the push prediction page request sent by the terminal 110, parses the push prediction page request, and analyzes and extracts the operator account number in the push prediction page request, and verifies whether the extracted operator account has the right to access the push prediction page. After verifying that the extracted operator account has the right to access the push prediction page, the server 120 acquires the push prediction page data, and returns the obtained push prediction page data to the terminal 110 corresponding to the push prediction page request.
  • the terminal 110 receives the push prediction page data returned by the server 120, and displays the push prediction page based on the push prediction page data.
  • the terminal 110 detects that the push operator touches the push prediction page.
  • the pushed push result prediction command acquires the information push task input by the push operator on the push prediction page according to the push result prediction command, and transmits the acquired information push task to the server 120.
  • the server 120 receives the information push task sent by the terminal 110.
  • the information push task includes a target user account, and the target user account is a user account corresponding to the target user.
  • the server 120 parses the information push task, and analyzes and extracts the target user account in the information push task, so that the extracted target user account constitutes the target user account set.
  • the historical online information corresponding to each user account is stored in the database of the server 120.
  • Historical online information includes online time information and user accounts.
  • the server 120 extracts the user account in the target user account set, and queries historical online information corresponding to the extracted user account in the historical online information in the database.
  • the server 120 detects whether the user account corresponding to the historical online information is online according to the historical online information corresponding to each user account.
  • the server 120 detects the online user account in the target user account set, extracts the online user account, and constructs a predicted arrival user account set according to the extracted user account.
  • the server 120 detects an offline user account in the target user account set, deletes the offline user account from the target user account set, and deletes the target user account set after the offline user account as a prediction. Reach the user account collection.
  • the user interest tag and the historical click information corresponding to each user account are stored in the database in the server 120.
  • the user interest tag is a user's favorite identifier corresponding to the user account.
  • the user interest tag corresponding to the user account of the user who likes the soccer ball is a favorite football.
  • the history click information includes the click time information and the user account of the user clicking the push message.
  • the server 120 predicts each of the predicted user account sets.
  • the user account extracts user interest tags and historical click information corresponding to each user account from the database.
  • the server 120 obtains the information to be pushed corresponding to the information push task, and calculates the degree of interest according to the user interest tag corresponding to each user account in the predicted user account set and the acquired information to be pushed.
  • the server 120 counts the historical click rate corresponding to each user account according to the historical click information corresponding to each user account predicted to reach the user account set.
  • the server 120 extracts, from the predicted arrival user account set, a user account whose interest degree is higher than the preset interest degree and whose historical click rate is higher than the preset click rate threshold, and constructs a predicted click user account set according to the extracted user account.
  • the server 120 generates a push prediction result corresponding to the information push task based on the predicted arrival user account set and the predicted click user account set.
  • the server 120 counts the total number of user accounts in the target user account set to obtain the total amount of information push; the server 120 statistically predicts the total number of user accounts in the set of user accounts to obtain the predicted total amount of information arrival; Click the total number of user accounts in the user account collection to get the total amount of information click prediction.
  • the server 120 obtains the information predicted arrival rate by dividing the statistical information arrival prediction total amount by the statistical information push total amount, and divides the statistical information click prediction total amount by the statistical information click prediction total amount to obtain the information prediction click rate. .
  • the server 120 generates a push prediction result corresponding to the information push target based on the statistically predicted information prediction rate and the information predicted click rate.
  • the method further includes: extracting a predicted arrival user account set in the push prediction result; and generating a target user account adjustment suggestion corresponding to the information push task according to the extracted predicted arrival user account set.
  • the server 120 transmits the generated push prediction result to the terminal 110 corresponding to the information push task, causing the terminal 110 to display the push prediction result in the push prediction page.
  • the push operator clicks the account adjustment suggestion generation button in the push prediction page through the input device of the terminal 110.
  • the terminal 110 detects that the account adjustment suggestion generation button is clicked, triggering the account adjustment suggestion
  • the instruction is generated, and the account adjustment suggestion generation instruction is sent to the server 120.
  • the server 120 After receiving the account adjustment suggestion generation instruction sent by the terminal 110, the server 120 extracts the predicted arrival user account set in the push prediction result, and generates a target user account adjustment suggestion corresponding to the information push task according to the predicted user account in the user account set. The server 120 sends the generated target user account adjustment proposal to the terminal 110, so that the terminal 110 displays the account adjustment suggestion on the push prediction page.
  • the terminal 110 detects that the push operator clicks the account adjustment confirmation button in the push prediction page through the input device, and the terminal 110 extracts the user account in the account adjustment proposal to obtain the predicted arrival user account set, and predicts the arrival of the user account set as the target of the information push task. User account collection.
  • the target user account in the information push task is extracted, and the target user account set is obtained.
  • the accuracy of predicting the arrival of the user account set and the predicted click user account set is ensured, thereby ensuring the generated push prediction result.
  • the target user account in the information push task can be adjusted according to the push prediction result, thereby ensuring that the arrival amount and the click amount corresponding to the information push task can be improved, thereby improving the push success rate of the information push task.
  • S308 specifically includes the step of acquiring a predicted arrival user account set, and the step specifically includes the following:
  • the user account marked as invalid in the obtained historical online information is deleted from the target user account set, and the user account marked as invalid is deleted, and a valid user account set is obtained.
  • the server 120 collects, according to historical online information corresponding to each user account, a user account that does not have historical online information within a preset time period, and marks a user account that does not have historical online information within a preset time period as Invalid user account.
  • the server 120 queries the target user account set for the user account marked as invalid, deletes the queried user account from the target user account set, and forms a valid user account set according to the remaining user accounts in the target user account set.
  • the preset time period can be the most recent month, two months or three months.
  • the server 120 extracts valid users from the acquired historical online information.
  • the account collects historical online information corresponding to each user account in China, and counts the number of online times corresponding to each user account in the preset time period according to the extracted historical online information.
  • the server 120 compares the online number of the preset time period corresponding to each user account in the valid user account set with the preset number of times, and determines the user account whose online number is higher than the preset number of times in the preset time period. Extracting the determined user account from the set of valid user accounts, and obtaining the predicted arrival user account set.
  • the user account marked as invalid is deleted from the target user account set to obtain a valid user account set, and then the predicted arrival user account set is extracted from the valid user account set according to the historical online information.
  • the utilization of historical online information is improved, and the accuracy of selecting the predicted arrival user account set is also improved.
  • S312 specifically includes the step of extracting a predicted click user account set, and the step specifically includes the following content:
  • the server 120 parses the information push task by parsing the message to be pushed in the extracted information task.
  • the message to be pushed is a message to be pushed to the user corresponding to the user account in the target user account set.
  • the server 120 analyzes the push information by using the keyword extraction software, and extracts the message keyword from the information to be pushed by analyzing.
  • the database of servers 120 stores message keywords corresponding to the messages to be pushed. After obtaining the message to be pushed, the server 120 queries the database for the message keyword corresponding to the obtained to-be-push message.
  • the server 120 calculates the similarity between the user interest tag corresponding to each user account and the extracted message keyword, and the calculated similarity is respectively corresponding to the user account. Degree of interest.
  • the historical click rate corresponding to each user account in the user account set is predicted and predicted.
  • the server 120 statistically predicts the number of push message receptions and the number of push message clicks of each user account in the user account set according to the historical click information, and calculates the number of push messages received and the number of push message clicks.
  • the historical click rate corresponding to the user account is obtained, that is, the server 120 divides the number of push message clicks by the number of push message receptions to obtain a historical click rate.
  • the server 120 compares the degree of interest corresponding to each user account with a preset degree of interest, and compares the historical click rate corresponding to each user account with a preset click rate.
  • the server 120 compares the user accounts whose interest degree is higher than the preset interest degree and the historical click rate is higher than the preset click rate from the predicted arrival user set, and constructs a predicted click user account set according to the extracted user account.
  • the interest degree corresponding to the user account is calculated according to the user interest tag and the message keyword corresponding to the user account
  • the historical click rate of the user account is calculated according to the historical click information
  • the user account is extracted according to the degree of interest and the historical click rate.
  • S510 specifically includes the step of extracting a user account according to the click prediction value, and the step specifically includes the following content:
  • the server 120 obtains the weight corresponding to each of the interest degree and the historical click rate, according to the interest degree corresponding to each user account, the historical click rate, the weight corresponding to the degree of interest, and the right corresponding to the historical click rate.
  • the value is weighted and calculated to obtain a click prediction value corresponding to each user account.
  • the server 120 will predict the arrival of each user account pair in the set of user accounts.
  • the predicted click value is compared with the preset threshold, and the user account whose click predicted value exceeds the preset threshold is selected from the predicted arrival user account set, and the predicted click user account set is formed according to the selected user account.
  • the click prediction value corresponding to each user account is calculated according to the calculated interest degree and the historical click rate, and the predicted click user value is extracted from the predicted arrival user set by the calculated click prediction value, thereby greatly improving the prediction. Clicking on the extraction accuracy in the user account improves the prediction accuracy of the prediction results.
  • a push result prediction apparatus 700 is extracted, and the apparatus specifically includes the following: a push task acquisition module 702, a user account extraction module 704, a history information acquisition module 706, and an online account selection module. 708.
  • the push task obtaining module 702 is configured to obtain an information push task.
  • the user account extraction module 704 is configured to extract a target user account in the information push task, and obtain a target user account set.
  • the history information obtaining module 706 is configured to obtain historical online information corresponding to each user account in the target user account set.
  • the online account selection module 708 is configured to select an online user account from the target user account set according to the obtained historical online information, and obtain a predicted arrival user account set.
  • the tag information obtaining module 710 is configured to obtain a user interest tag and historical click information corresponding to each user account in the predicted user account set.
  • the account selection module 712 is configured to extract a predicted click user account set from the predicted arrival user account set according to the obtained user interest tag and historical click information.
  • the prediction result generating module 714 is configured to generate a push prediction result according to the predicted arrival user account set and the predicted click user account set.
  • the target user account in the information push task is extracted, and the target user account set is obtained.
  • the accuracy of predicting the arrival of the user account set and the predicted click user account set is ensured, thereby ensuring the generated push prediction result.
  • the accuracy. And can root According to the push prediction result, the target user account in the information push task is adjusted, thereby ensuring that the amount of arrival and the amount of clicks corresponding to the information push task can be improved, thereby improving the push success rate of the information push task.
  • the online account selection module 708 specifically includes the following: an effective account obtaining module 708a, an online number counting module 708b, and an online number comparison module 708c.
  • the valid account obtaining module 708a is configured to delete the user account marked as invalid in the obtained historical online information from the target user account set to obtain a valid user account set.
  • the online number statistics module 708b is configured to count the number of online times in the preset time period corresponding to each user account in the valid user account set according to the obtained historical online information.
  • the online number comparison module 708c is configured to select, from the valid user account set, a user account whose online number is higher than the preset number of times in the preset time period, and obtain a predicted arrival user account set.
  • the user account marked as invalid is deleted from the target user account set to obtain a valid user account set, and then the predicted arrival user account set is extracted from the valid user account set according to the historical online information.
  • the utilization of historical online information is improved, and the accuracy of selecting the predicted arrival user account set is also improved.
  • the click account selection module 712 specifically includes the following contents: a push message acquisition module 712a, a keyword extraction module 712b, a degree of interest calculation module 712c, a click rate statistics module 712d, and a click set extraction. Module 712e.
  • the push message obtaining module 712a is configured to obtain a to-be-pushed message corresponding to the information push task.
  • the keyword extraction module 712b is configured to extract a message keyword from the acquired message to be pushed.
  • the interest degree calculation module 712c is configured to calculate, according to the acquired user interest tag and the extracted message keyword, the degree of interest corresponding to each user account in the predicted arrival user account set.
  • the click rate statistics module 712d is configured to perform statistical prediction on the historical click rate corresponding to each user account in the user account set according to the obtained historical click information.
  • the click collection extraction module 712e is configured to extract a predicted click user account set from the predicted arrival user account set according to the calculated interest degree and the statistical historical click rate.
  • the click set extraction module 712e is also used to calculate the interest based on Degree and statistical history click rate, calculate the predicted click value corresponding to each user account in the user account set; from the predicted arrival user account set, select the user account whose click prediction value exceeds the preset threshold, and obtain the predicted click user account. set.
  • the interest degree corresponding to the user account is calculated according to the user interest tag and the message keyword corresponding to the user account
  • the historical click rate of the user account is calculated according to the historical click information
  • the user account is extracted according to the degree of interest and the historical click rate.
  • the push result prediction apparatus 700 specifically includes an adjustment suggestion generation module 716.
  • the adjustment suggestion generating module 716 extracts the predicted arrival user account set in the push prediction result, and generates a target user account adjustment suggestion corresponding to the information push task according to the extracted predicted arrival user account set.
  • the target user account adjustment proposal is generated according to the predicted arrival user account set in the push prediction result, and the user performing the information push task in the adjusted target user account set is adjusted according to the target user account, thereby ensuring that the message arrival amount can be improved.
  • Each of the above-described push result prediction devices may be implemented in whole or in part by software, hardware, and a combination thereof.
  • the network interface may be an Ethernet or a wireless network card.
  • Each of the above modules may be embedded in a hardware form or independent of a processor in the server, or may be stored in a memory of the server in a software form, so that the processor calls to perform operations corresponding to the above modules.
  • the processor can be a central processing unit (CPU), a microprocessor, a microcontroller, or the like.
  • a computer device comprising a memory and a processor, wherein the memory stores computer executable instructions, the computer executable instructions being executed by the processor, such that the processor performs the step of: acquiring an information push task Extracting the target user account in the information push task, obtaining the target user account set; obtaining the historical online information corresponding to each user account in the target user account set; and selecting the online user account from the target user account set according to the obtained historical online information.
  • the online user account is selected from the target user account set according to the obtained historical online information, and the predicted arrival user account set is obtained, including: the user account marked as invalid in the obtained historical online information, Deleting the user account marked as invalid from the target user account set to obtain a valid user account set; and collecting the online number of the preset time period corresponding to each user account in the valid user account set according to the obtained historical online information; In the user account set, the user account whose online number is higher than the preset number of times in the preset time period is selected, and the predicted arrival user account set is obtained.
  • extracting the predicted click user account set from the predicted arrival user account set according to the obtained user interest tag and the historical click information including: obtaining the to-be-push message corresponding to the information push task; and obtaining the to-be-pushed message Extracting a message keyword from the message; calculating, according to the obtained user interest tag and the extracted message keyword, the degree of interest corresponding to each user account in the predicted arrival user account set; and statistically predicting the arrival according to the obtained historical click information
  • the historical click rate corresponding to each user account in the user account set; and the predicted click user account set is extracted from the predicted arrival user account set according to the calculated interest degree and the statistical historical click rate.
  • the predicted click user account set is extracted from the predicted arrival user account set according to the calculated interest degree and the statistical historical click rate, including: the calculated interest degree and the statistical history click. Rate, calculate the predicted click value corresponding to each user account in the set of user accounts; from the predicted arrival user account set, select a user account whose click prediction value exceeds a preset threshold, and obtain a predicted click user account set.
  • the processor after generating the push prediction result according to the predicted arrival user account set and the predicted click user account set, performs the following steps: extracting the predicted arrival user account set in the push prediction result; and reaching the user according to the extracted prediction.
  • the account set generates a target user account adjustment suggestion corresponding to the information push task.
  • the target user account in the information push task is extracted, and the target user account set is obtained.
  • the accuracy of predicting the arrival of the user account set and the predicted click user account set is ensured, thereby ensuring the generated push prediction result.
  • the target user account in the information push task can be adjusted according to the push prediction result, thereby ensuring that the amount of arrival and the amount of clicks corresponding to the information push task can be improved, thereby improving the push of the information push task. power.
  • One or more storage media storing computer-executable instructions that, when executed by one or more processors, cause one or more processors to perform the steps of: obtaining an information push task; extracting information in a push task
  • the target user account obtains the target user account set; obtains the historical online information corresponding to each user account in the target user account set; and selects the online user account from the target user account set according to the obtained historical online information, and obtains the predicted arrival user account set.
  • the user account set and the predicted click user account set generate a push prediction result.
  • the online user account is selected from the target user account set according to the obtained historical online information, and the predicted arrival user account set is obtained, including: the user account marked as invalid in the obtained historical online information, Deleting the user account marked as invalid from the target user account set to obtain a valid user account set; and collecting the online number of the preset time period corresponding to each user account in the valid user account set according to the obtained historical online information; In the user account set, the user account whose online number is higher than the preset number of times in the preset time period is selected, and the predicted arrival user account set is obtained.
  • extracting the predicted click user account set from the predicted arrival user account set according to the obtained user interest tag and the historical click information including: obtaining the to-be-push message corresponding to the information push task; and obtaining the to-be-pushed message Extracting a message keyword from the message; calculating, according to the obtained user interest tag and the extracted message keyword, the degree of interest corresponding to each user account in the predicted arrival user account set; and statistically predicting the arrival according to the obtained historical click information
  • the historical click rate corresponding to each user account in the user account set; and the predicted click user account set is extracted from the predicted arrival user account set according to the calculated interest degree and the statistical historical click rate.
  • the predicted click user account set is extracted from the predicted arrival user account set according to the calculated interest degree and the statistical historical click rate, including: the calculated interest degree and the statistical history click. Rate, calculate the predicted click value corresponding to each user account in the user account set; from the predicted arrival user account set, select the click predicted value to exceed the pre- Set a threshold user account to get a predicted click user account set.
  • the processor after generating the push prediction result according to the predicted arrival user account set and the predicted click user account set, the processor further performs the steps of: extracting the predicted arrival user account set in the push prediction result; and arriving according to the extracted prediction.
  • the user account set generates a target user account adjustment suggestion corresponding to the information push task.
  • the target user account in the information push task is extracted, and the target user account set is obtained.
  • the accuracy of predicting the arrival of the user account set and the predicted click user account set is ensured, thereby ensuring the generated push prediction result.
  • the target user account in the information push task can be adjusted according to the push prediction result, thereby ensuring that the arrival amount and the click amount corresponding to the information push task can be improved, thereby improving the push success rate of the information push task.
  • all or part of the processes in the foregoing embodiment may be completed by instructing related hardware by computer executable instructions, which may be stored in a computer readable storage medium.
  • the program may be stored in a storage medium of the computer system and executed by at least one processor in the computer system to implement a flow including an embodiment of the methods as described above.
  • the storage medium includes, but is not limited to, a magnetic disk, a USB flash drive, an optical disk, a read-only memory (ROM), and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Information Transfer Between Computers (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种推送结果预测方法,所述方法包括:获取信息推送任务(S302);提取信息推送任务中的目标用户账号,得到目标用户账号集合(S304);获取目标用户账号集合中各用户账号对应的历史在线信息(S306);根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合(S308);获取预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息(S310);根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合(S312);根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果(S314)。

Description

推送结果预测方法、装置、计算机设备和存储介质
本申请要求于2017年7月24日提交中国专利局,申请号为2017106080944,发明名称为“推送结果预测方法、装置、计算机设备和存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息处理技术领域,特别是涉及一种推送结果预测方法、装置、计算机设备和存储介质。
背景技术
随着互联网技术的迅猛发展,各种信息可以通过互联网向用户推送,以便用户可以及时获取到相关的信息。随着消息推送需求的不断增加,通过互联网进行信息推送的任务量也不断增加。
传统的推送过程,都是根据预设推送参数对信息进行推送,根据预设的目标用户账号进行信息推送。然而,在推送信息时,某些目标用户账号不可用,导致信息无法推送至目标用户账号,降低了信息推送成功率。
发明内容
根据本申请公开的各种实施例,提供一种推送结果预测方法、装置、计算机设备和存储介质。
一种推送结果预测方法,包括:
获取信息推送任务;
提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
获取所述目标用户账号集合中各用户账号对应的历史在线信息;
根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历 史点击信息;
根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
一种推送结果预测装置,包括:
推送任务获取模块,用于获取信息推送任务;
用户账号提取模块,用于提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
历史信息获取模块,用于获取所述目标用户账号集合中各用户账号对应的历史在线信息;
在线账号选取模块,用于根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
标签信息获取模块,用于获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
点击账号选取模块,用于根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
预测结果生成模块,用于根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可执行指令,所述计算机可执行指令被所述处理器执行时,可使得所述处理器执行以下步骤:
获取信息推送任务;
提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
获取所述目标用户账号集合中各用户账号对应的历史在线信息;
根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
一个或多个存储有计算机可执行指令的存储介质,所述计算机可执行指令被一个或多个处理器执行时,使得所述一个或多个处理器执行以下步骤:
获取信息推送任务;
提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
获取所述目标用户账号集合中各用户账号对应的历史在线信息;
根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其它的附图。
图1为一个实施例中推送结果预测方法的应用环境图;
图2为一个实施例中推送结果预测***中的服务器的结构框图;
图3为一个实施例中推送结果预测方法的流程示意图;
图4为一个实施例中获取预测到达用户账号集合的步骤的流程示意图;
图5为一个实施例中提取预测点击用户账号集合的步骤的流程示意图;
图6为一个实施例中根据点击预测值提取用户账号的步骤的流程示意图;
图7为一个实施例中推送结果预测装置的结构框图;
图8为一个实施例中在线账号选取模块的结构框图;
图9为一个实施例中点击账号选取模块的结构框图;
图10为另一个实施例中推送结果预测装置的结构框图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
图1为一个实施例中推送结果预测方法的应用环境图。参照图1,该推送结果预测方法应用于推送结果预测***。推送结果预测***包括终端110和服务器120,其中终端110通过网络与服务器120连接。终端110可以是固定终端或移动终端,固定终端具体可以是打印机、扫描仪和监控器中的至少一种,移动终端具体可以是平板电脑、智能手机、个人数据助理和数码相机中的至少一种。服务器120可以是单个服务器,也可以是有多个服务器组成的服务器集群。
图2为一个实施例中图1推送结果预测***中的服务器120的内部结构 示意图。如图2所示,该服务器120包括通过***总线连接的处理器、非易失性存储介质、内存储器和网络接口。服务器120的处理器用于提供计算和控制能力,支撑整个服务器120的运行,存储器用于存储数据、代码指令等,网络接口用于与终端110进行网络通信。存储器上存储有至少一个计算机可执行指令,该计算机可执行指令可被处理器执行,以实现本申请实施例中提供的适用于服务器120的推送结果预测方法。存储器可包括磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)等非易失性存储介质。例如,在一个实施例中,存储器包括非易失性存储介质及内存储器;非易失性存储介质存储有操作***、数据库和计算机可执行指令,数据库存储着各用户账号对应的历史在线信息、历史点击信息和用户兴趣标签,该计算机可执行指令可被处理器执行以实现上述的推送结果预测方法;内存储器为非易失性存储介质中的操作***及计算机可执行指令提供高速缓存的运行环境。
本领域技术人员可以理解,图2中示出的结构,仅仅是与本申请方案相关的部分结构的框图,并不构成对本申请方案所应用于其上的服务器的限定,具体的服务器可以包括比图2中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
如图3所示,在一个实施例中,提供一种推送结果预测方法,本实施例以该方法应用于图1中的服务器120来举例说明,该方法具体包括以下内容:
S302,获取信息推送任务。
在一个实施例中,终端110获取推送运营人员输入的运营人员账号,根据获取到的运营人员账号生成推送预测页面请求,将推送预测页面请求发送至服务器120。
服务器120接收终端110发送的推送预测页面请求,对推送预测页面请求进行解析,通过解析提取推送预测页面请求中的运营人员账号,验证提取到的运营人员账号是否有访问推送预测页面的权限。服务器120在验证提取到的运营人员账号有访问推送预测页面的权限后,获取推送预测页面数据,将获取到的推送预测页面数据返回至推送预测页面请求对应的终端110。
终端110接收到服务器120返回的推送预测页面数据,根据推送预测页面数据显示推送预测页面。终端110检测到推送运营人员在推送预测页面触 发的推送结果预测指令,根据推送结果预测指令获取推送运营人员在推送预测页面中输入的信息推送任务,将获取的信息推送任务发送至服务器120。服务器120接收终端110发送的信息推送任务。
S304,提取信息推送任务中的目标用户账号,得到目标用户账号集合。
在一个实施例中,信息推送任务中包括目标用户账号,目标用户账号为将信息推送至目标用户所对应的用户账号。服务器120在获取到信息推送任务后,对信息推送任务进行解析,通过解析提取信息推送任务中的目标用户账号,以提取到的目标用户账号构成目标用户账号集合。
S306,获取目标用户账号集合中各用户账号对应的历史在线信息。
在一个实施例中,服务器120的数据库中存储着各用户账号对应的历史在线信息。历史在线信息包括在线时间信息和用户账号。服务器120提取目标用户账号集合中的用户账号,在数据库中的历史在线信息中查询与提取到的用户账号对应的历史在线信息。
S308,根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合。
在一个实施例中,服务器120获取到各用户账号对应的历史在线信息后,根据各用户账号对应的历史在线信息检测历史在线信息对应的用户账号是否在线。服务器120在目标用户账号集合中检测到在线的用户账号,提取在线的用户账号,根据提取到的用户账号构成预测到达用户账号集合。
在一个实施例中,服务器120在目标用户账号集合中检测到不在线的用户账号,将不在线的用户账号从目标用户账号集合中删除,删除不在线的用户账号后的目标用户账号集合为预测到达用户账号集合。
S310,获取预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息。
在一个实施例中,服务器120中的数据库中存储着各用户账号对应的用户兴趣标签和历史点击信息。用户兴趣标签为用户账号对应的用户的喜好标识,例如,喜好足球的用户的用户账号所对应的用户兴趣标签为喜好足球。历史点击信息中包括用户点击推送消息的点击时间信息和用户账号。服务器120在得到预测到达用户账号集合后,对于预测到达用户账号集合中的每个 用户账号,从数据库中提取各用户账号对应的用户兴趣标签和历史点击信息。
S312,根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合。
在一个实施例中,服务器120获取信息推送任务对应的待推送信息,根据预测到达用户账号集合中的各用户账号对应的用户兴趣标签和获取到的待推送信息计算感兴趣度。服务器120根据预测到达用户账号集合中的各用户账号对应的历史点击信息,统计各用户账号对应的历史点击率。服务器120从预测到达用户账号集合中提取感兴趣度高于预设感兴趣度,且历史点击率高于预设点击率阈值的用户账号,根据提取到的用户账号构成预测点击用户账号集合。
S314,根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果。
在一个实施例中,服务器120根据预测到达用户账号集合和预测点击用户账号集合,生成与信息推送任务对应的推送预测结果。
在一个实施例中,服务器120统计目标用户账号集合中的用户账号总数量得到信息推送总量;服务器120统计预测到达用户账号集合中的用户账号总数量得到信息到达预测总量;服务器120统计预测点击用户账号集合中的用户账号总数量得到信息点击预测总量。服务器120将统计到的信息到达预测总量除以统计到的信息推送总量得到信息预测到达率,将统计到的信息点击预测总量除以统计到的信息点击预测总量得到信息预测点击率。服务器120根据统计到的信息预测到达率和信息预测点击率生成信息推送任务对应的推送预测结果。
在一个实施例中,S314之后具体还包括以下内容:提取推送预测结果中的预测到达用户账号集合;根据提取到的预测到达用户账号集合,生成与信息推送任务对应的目标用户账号调整建议。
在一个实施例中,服务器120将生成的推送预测结果发送至信息推送任务对应的终端110,使终端110将推送预测结果展示在推送预测页面中。推送运营人员通过终端110的输入设备点击推送预测页面中的账号调整建议生成按钮。终端110检测到账号调整建议生成按钮被点击时,触发账号调整建议 生成指令,将账号调整建议生成指令发送至服务器120。
服务器120接收到终端110发送的账号调整建议生成指令后,提取推送预测结果中的预测到达用户账号集合,根据预测到达用户账号集合中的用户账号生成与信息推送任务对应的目标用户账号调整建议。服务器120将生成的目标用户账号调整建议发送至终端110,使终端110将账号调整建议展示在推送预测页面。
终端110检测到推送运营人员通过输入设备点击推送预测页面中的账号调整确认按钮,终端110提取账号调整建议中的用户账号得到预测到达用户账号集合,将预测到达用户账号集合作为信息推送任务的目标用户账号集合。
本实施例中,提取信息推送任务中的目标用户账号,得到目标用户账号集合。通过对目标用户账号集合中各用户账号对应的历史在线信息、用户兴趣标签和历史点击信息进行分析,保证了预测到达用户账号集合和预测点击用户账号集合的准确性,从而保证生成的推送预测结果的准确性。并可以根据推送预测结果对信息推送任务中的目标用户账号进行调整,从而确保可以提高信息推送任务对应的到达量和点击量,从而提高信息推送任务的推送成功率。
如图4所示,在一个实施例中,S308具体包括获取预测到达用户账号集合的步骤,该步骤具体包括以下内容:
S402,将获取到的历史在线信息中被标记为无效的用户账号,从所述目标用户账号集合中删除被标记为无效的用户账号,得到有效用户账号集合。
在一个实施例中,服务器120根据各用户账号对应的历史在线信息统计在预设时间段内不存在历史在线信息的用户账号,将在预设时间段内不存在历史在线信息的用户账号标记为无效的用户账号。服务器120在目标用户账号集合中查询被标记为无效的用户账号,从目标用户账号集合中将查询到的用户账号删除,根据目标用户账号集合中剩下的用户账号构成有效用户账号集合。预设时间段内可以是最近一个月、二个月或三个月等。
S404,根据获取到的历史在线信息,统计有效用户账号集合中各用户账号对应的预设时间段内在线次数。
在一个实施例中,服务器120在获取到的历史在线信息中提取有效用户 账号集合中国各用户账号对应的历史在线信息,根据提取到的历史在线信息统计预设时间段内各用户账号对应的在线次数。
S406,从有效用户账号集合中,选取预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
在一个实施例中,服务器120将有效用户账号集合中各用户账号对应的预设时间段内在线次数与预设次数进行比较,确定预设时间段内在线次数高于预设次数的用户账号,从有效用户账号集合中提取确定的用户账号,得到预测到达用户账号集合。
本实施例中,根据历史在线信息,先从目标用户账号集合中删除被标记为失效的用户账号,得到有效用户账号集合,再根据历史在线信息从有效用户账号集合中提取预测到达用户账号集合。根据历史在线信息获取预测到达用户账号集合,提高了历史在线信息的利用率,同时也提高了选取预测到达用户账号集合的准确性。
如图5所示,在一个实施例中,S312具体包括提取预测点击用户账号集合的步骤,该步骤具体包括以下内容:
S502,获取信息推送任务对应的待推送消息。
在一个实施例中,服务器120对信息推送任务进行解析,通过解析提取信息任务中的待推送消息。待推送消息为将要推送给目标用户账号集合中用户账号对应的用户的消息。
S504,从获取到的待推送消息中提取消息关键词。
在一个实施例中,服务器120在获取待推送信息后,利用关键词提取软件对待推送信息进行分析,通过分析从待推送信息中提取消息关键词。
在一个实施例中,服务器120的数据库中存储着与待推送消息对应的消息关键词。服务器120在获取到待推送消息后,从数据库中查询与获取到的待推送消息对应的消息关键词。
S506,根据获取到的用户兴趣标签和提取到的消息关键词,分别计算预测到达用户账号集合中各用户账号对应的感兴趣度。
在一个实施例中,服务器120计算各用户账号对应的用户兴趣标签与提取到的消息关键词的相似度,以计算到的相似度分别作为个用户账号对应的 感兴趣度。
S508,根据获取到的历史点击信息,统计预测到达用户账号集合中各用户账号对应的历史点击率。
在一个实施例中,服务器120根据到的历史点击信息,统计预测到达用户账号集合中各用户账号的推送消息接收次数和推送消息点击次数,根据统计到的推送消息接收次数和推送消息点击次数计算得到用户账号对应的历史点击率,即服务器120将推送消息点击次数除以推送消息接收次数得到历史点击率。
S510,根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合。
在一个实施例中,服务器120将各用户账号对应的感兴趣度与预设感兴趣度进行比较,并将各用户账号对应的历史点击率与预设点击率进行比较。服务器120通过比较从预测到达用户集合中提取感兴趣度高于预设感兴趣度和历史点击率高于预设点击率的用户账号,根据提取到的用户账号构成预测点击用户账号集合。
本实施例中,根据用户账号对应的用户兴趣标签和消息关键词计算用户账号对应的感兴趣度,根据历史点击信息计算用户账号的历史点击率,根据感兴趣度和历史点击率提取用户账号,得到预测点击用户账号集合,大大提高了预测准确率。
如图6所示,在一个实施例中,S510具体包括根据点击预测值提取用户账号的步骤,该步骤具体包括以下内容:
S602,根据计算得到的感兴趣度和统计到的历史点击率,计算预测到达用户账号集合中各用户账号对应的点击预测值。
在一个实施例中,服务器120获取感兴趣度和历史点击率各自对应的权值,根据各用户账号对应的感兴趣度、历史点击率、感兴趣度对应的权值和历史点击率对应的权值进行加权和计算得到各用户账号对应的点击预测值。
S604,从预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
在一个实施例中,服务器120将预测到达用户账号集合中各用户账号对 应的点击预测值与预设阈值进行比较,从预测到达用户账号集合中选取点击预测值超过预设阈值的用户账号,根据选取的用户账号构成预测点击用户账号集合。
本实施例中,根据计算得到的感兴趣度和历史点击率计算各用户账号对应的点击预测值,通过计算得到的点击预测值从预测到达用户集合中提取预测点击用户账号集合,大大提高了预测点击用户账号中的提取准确度,提高了预测结果的预测准确率。
如图7所示,在一个实施例中,提取一种推送结果预测装置700,该装置具体包括以下内容:推送任务获取模块702、用户账号提取模块704、历史信息获取模块706、在线账号选取模块708、标签信息获取模块710、点击账号选取模块712和预测结果生成模块714。
推送任务获取模块702,用于获取信息推送任务。
用户账号提取模块704,用于提取信息推送任务中的目标用户账号,得到目标用户账号集合。
历史信息获取模块706,用于获取目标用户账号集合中各用户账号对应的历史在线信息。
在线账号选取模块708,用于根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合。
标签信息获取模块710,用于获取预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息。
点击账号选取模块712,用于根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合。
预测结果生成模块714,用于根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果。
本实施例中,提取信息推送任务中的目标用户账号,得到目标用户账号集合。通过对目标用户账号集合中各用户账号对应的历史在线信息、用户兴趣标签和历史点击信息进行分析,保证了预测到达用户账号集合和预测点击用户账号集合的准确性,从而保证生成的推送预测结果的准确性。并可以根 据推送预测结果对信息推送任务中的目标用户账号进行调整,从而确保可以提高信息推送任务对应的到达量和点击量,从而提高信息推送任务的推送成功率。
如图8所示,在一个实施例中,在线账号选取模块708具体包括以下内容:有效账号获得模块708a、在线次数统计模块708b和在线次数比较模块708c。
有效账号获得模块708a,用于将获取到的历史在线信息中被标记为无效的用户账号,从目标用户账号集合中删除,得到有效用户账号集合。
在线次数统计模块708b,用于根据获取到的历史在线信息,统计有效用户账号集合中各用户账号对应的预设时间段内在线次数。
在线次数比较模块708c,用于从有效用户账号集合中,选取预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
本实施例中,根据历史在线信息,先从目标用户账号集合中删除被标记为失效的用户账号,得到有效用户账号集合,再根据历史在线信息从有效用户账号集合中提取预测到达用户账号集合。根据历史在线信息获取预测到达用户账号集合,提高了历史在线信息的利用率,同时也提高了选取预测到达用户账号集合的准确性。
如图9所示,在一个实施例中,点击账号选取模块712具体包括以下内容:推送消息获取模块712a、关键词提取模块712b、感兴趣度计算模块712c、点击率统计模块712d和点击集合提取模块712e。
推送消息获取模块712a,用于获取信息推送任务对应的待推送消息。
关键词提取模块712b,用于从获取到的待推送消息中提取消息关键词。
感兴趣度计算模块712c,用于根据获取到的用户兴趣标签和提取到的消息关键词,分别计算预测到达用户账号集合中各用户账号对应的感兴趣度。
点击率统计模块712d,用于根据获取到的历史点击信息,统计预测到达用户账号集合中各用户账号对应的历史点击率。
点击集合提取模块712e,用于根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合。
在一个实施例中,点击集合提取模块712e还用于根据计算得到的感兴趣 度和统计到的历史点击率,计算预测到达用户账号集合中各用户账号对应的点击预测值;从预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
本实施例中,根据用户账号对应的用户兴趣标签和消息关键词计算用户账号对应的感兴趣度,根据历史点击信息计算用户账号的历史点击率,根据感兴趣度和历史点击率提取用户账号,得到预测点击用户账号集合,大大提高了预测准确率。
如图10所示,在一个实施例中,推送结果预测装置700具体还包括:调整建议生成模块716。
调整建议生成模块716,提取推送预测结果中的预测到达用户账号集合;根据提取到的预测到达用户账号集合,生成与信息推送任务对应的目标用户账号调整建议。
本实施例中,根据推送预测结果中的预测到达用户账号集合生成目标用户账号调整建议,根据目标用户账号调整建议调整后的目标用户账号集合中的用户执行信息推送任务,保证可以提高消息到达量。
上述推送结果预测装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。其中,网络接口可以是以太网或无线网卡等。上述各模块可以硬件形式内嵌于或独立于服务器中的处理器中,也可以以软件形式存储于服务器的存储器中,以便于处理器调用执行以上各个模块对应的操作。该处理器可以为中央处理单元(CPU)、微处理器、单片机等。
一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可执行指令,所述计算机可执行指令被所述处理器执行时,使得所述处理器执行以下步骤::获取信息推送任务;提取信息推送任务中的目标用户账号,得到目标用户账号集合;获取目标用户账号集合中各用户账号对应的历史在线信息;根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;获取预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合;根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果。
在一个实施例中,根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合,包括:将获取到的历史在线信息中被标记为无效的用户账号,从目标用户账号集合中删除被标记为无效的用户账号,得到有效用户账号集合;根据获取到的历史在线信息,统计有效用户账号集合中各用户账号对应的预设时间段内在线次数;从有效用户账号集合中,选取预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
在一个实施例中,根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合,包括:获取信息推送任务对应的待推送消息;从获取到的待推送消息中提取消息关键词;根据获取到的用户兴趣标签和提取到的消息关键词,分别计算预测到达用户账号集合中各用户账号对应的感兴趣度;根据获取到的历史点击信息,统计预测到达用户账号集合中各用户账号对应的历史点击率;根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合。
在一个实施例中,根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合,包括:根据计算得到的感兴趣度和统计到的历史点击率,计算预测到达用户账号集合中各用户账号对应的点击预测值;从预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
在一个实施例中,根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果之后,处理器执行以下步骤:提取推送预测结果中的预测到达用户账号集合;根据提取到的预测到达用户账号集合,生成与信息推送任务对应的目标用户账号调整建议。
本实施例中,提取信息推送任务中的目标用户账号,得到目标用户账号集合。通过对目标用户账号集合中各用户账号对应的历史在线信息、用户兴趣标签和历史点击信息进行分析,保证了预测到达用户账号集合和预测点击用户账号集合的准确性,从而保证生成的推送预测结果的准确性。并可以根据推送预测结果对信息推送任务中的目标用户账号进行调整,从而确保可以提高信息推送任务对应的到达量和点击量,从而提高信息推送任务的推送成 功率。
一个或多个存储有计算机可执行指令的存储介质,计算机可执行指令被一个或多个处理器执行时,使得一个或多个处理器执行以下步骤:获取信息推送任务;提取信息推送任务中的目标用户账号,得到目标用户账号集合;获取目标用户账号集合中各用户账号对应的历史在线信息;根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;获取预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合;根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果。
在一个实施例中,根据获取到的历史在线信息,从目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合,包括:将获取到的历史在线信息中被标记为无效的用户账号,从目标用户账号集合中删除被标记为无效的用户账号,得到有效用户账号集合;根据获取到的历史在线信息,统计有效用户账号集合中各用户账号对应的预设时间段内在线次数;从有效用户账号集合中,选取预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
在一个实施例中,根据获取到的用户兴趣标签和历史点击信息,从预测到达用户账号集合中提取预测点击用户账号集合,包括:获取信息推送任务对应的待推送消息;从获取到的待推送消息中提取消息关键词;根据获取到的用户兴趣标签和提取到的消息关键词,分别计算预测到达用户账号集合中各用户账号对应的感兴趣度;根据获取到的历史点击信息,统计预测到达用户账号集合中各用户账号对应的历史点击率;根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合。
在一个实施例中,根据计算得到的感兴趣度和统计到的历史点击率,从预测到达用户账号集合中提取预测点击用户账号集合,包括:根据计算得到的感兴趣度和统计到的历史点击率,计算预测到达用户账号集合中各用户账号对应的点击预测值;从预测到达用户账号集合中,选取点击预测值超过预 设阈值的用户账号,得到预测点击用户账号集合。
在一个实施例中,根据预测到达用户账号集合和预测点击用户账号集合,生成推送预测结果之后,处理器还执行以下步骤:提取推送预测结果中的预测到达用户账号集合;根据提取到的预测到达用户账号集合,生成与信息推送任务对应的目标用户账号调整建议。
本实施例中,提取信息推送任务中的目标用户账号,得到目标用户账号集合。通过对目标用户账号集合中各用户账号对应的历史在线信息、用户兴趣标签和历史点击信息进行分析,保证了预测到达用户账号集合和预测点击用户账号集合的准确性,从而保证生成的推送预测结果的准确性。并可以根据推送预测结果对信息推送任务中的目标用户账号进行调整,从而确保可以提高信息推送任务对应的到达量和点击量,从而提高信息推送任务的推送成功率。
根据本实施例的一个示例,上述实施例方法中的全部或部分流程,可以通过计算机可执行指令来指令相关的硬件来完成,所述计算机可执行指令可存储于一计算机可读取存储介质中,如本申请实施例中,该程序可存储于计算机***的存储介质中,并被该计算机***中的至少一个处理器执行,以实现包括如上述各方法的实施例的流程。该存储介质包括但不限于磁碟、优盘、光盘、只读存储记忆体(Read-Only Memory,ROM)等。
以上所述实施例的各技术特征可以进行任意的组合,为使描述简洁,未对上述实施例中的各个技术特征所有可能的组合都进行描述,然而,只要这些技术特征的组合不存在矛盾,都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本申请构思的前提下,还可以做出若干变形和改进,这些都属于本申请的保护范围。因此,本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种推送结果预测方法,包括:
    获取信息推送任务;
    提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
    获取所述目标用户账号集合中各用户账号对应的历史在线信息;
    根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
    获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
    根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
    根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
  2. 根据权利要求1所述的方法,其特征在于,所述根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合,包括:
    将获取到的历史在线信息中被标记为无效的用户账号,从所述目标用户账号集合中删除,得到有效用户账号集合;
    根据所述获取到的历史在线信息,统计所述有效用户账号集合中各用户账号对应的预设时间段内在线次数;及
    从所述有效用户账号集合中,选取所述预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
  3. 根据权利要求1所述的方法,其特征在于,所述根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    获取所述信息推送任务对应的待推送消息;
    从获取到的待推送消息中提取消息关键词;
    根据获取到的用户兴趣标签和提取到的消息关键词,分别计算所述预测到达用户账号集合中各用户账号对应的感兴趣度;
    根据获取到的历史点击信息,统计所述预测到达用户账号集合中各用户账号对应的历史点击率;及
    根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合。
  4. 根据权利要求3所述的方法,其特征在于,所述根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    根据计算得到的感兴趣度和统计到的历史点击率,计算所述预测到达用户账号集合中各用户账号对应的点击预测值;及
    从所述预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
  5. 根据权利要求1所述的方法,其特征在于,所述根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果之后,所述方法还包括:
    提取所述推送预测结果中的预测到达用户账号集合;及
    根据提取到的预测到达用户账号集合,生成与所述信息推送任务对应的目标用户账号调整建议。
  6. 一种推送结果预测装置,包括:
    推送任务获取模块,用于获取信息推送任务;
    用户账号提取模块,用于提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
    历史信息获取模块,用于获取所述目标用户账号集合中各用户账号对应的历史在线信息;
    在线账号选取模块,用于根据获取到的历史在线信息,从所述目标用户 账号集合中选取在线用户账号,得到预测到达用户账号集合;
    标签信息获取模块,用于获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
    点击账号选取模块,用于根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
    预测结果生成模块,用于根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
  7. 根据权利要求6所述的装置,其特征在于,所述在线账号选取模块包括:
    有效账号获得模块,用于将获取到的历史在线信息中被标记为无效的用户账号,从所述目标用户账号集合中删除,得到有效用户账号集合;
    在线次数统计模块,用于根据所述获取到的历史在线信息,统计所述有效用户账号集合中各用户账号对应的预设时间段内在线次数;及
    在线次数比较模块,用于从所述有效用户账号集合中,选取所述预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
  8. 根据权利要求6所述的方法,其特征在于,所述点击账号选取模块包括:
    推送消息获取模块,用于获取所述信息推送任务对应的待推送消息;
    关键词提取模块,用于从获取到的待推送消息中提取消息关键词;
    感兴趣度计算模块,用于根据获取到的用户兴趣标签和提取到的消息关键词,分别计算所述预测到达用户账号集合中各用户账号对应的感兴趣度;
    点击率统计模块,用于根据获取到的历史点击信息,统计所述预测到达用户账号集合中各用户账号对应的历史点击率;及
    点击集合提取模块,用于根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合。
  9. 根据权利要求8所述的装置,其特征在于,所述点击集合提取模块还用于根据计算得到的感兴趣度和统计到的历史点击率,计算所述预测到达用 户账号集合中各用户账号对应的点击预测值;从所述预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
  10. 根据权利要求6所述的装置,其特征在于,所述装置还包括:
    调整建议生成模块,用于提取所述推送预测结果中的预测到达用户账号集合;根据提取到的预测到达用户账号集合,生成与所述信息推送任务对应的目标用户账号调整建议。
  11. 一种计算机设备,包括存储器和处理器,所述存储器中存储有计算机可执行指令,所述计算机可执行指令被所述处理器执行时,使得所述处理器执行以下步骤:
    获取信息推送任务;
    提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
    获取所述目标用户账号集合中各用户账号对应的历史在线信息;
    根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
    获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
    根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
    根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
  12. 根据权利要求11所述的计算机设备,其特征在于,所述根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合,包括:
    将获取到的历史在线信息中被标记为无效的用户账号,从所述目标用户账号集合中删除,得到有效用户账号集合;
    根据所述获取到的历史在线信息,统计所述有效用户账号集合中各用户 账号对应的预设时间段内在线次数;及
    从所述有效用户账号集合中,选取所述预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
  13. 根据权利要求11所述的计算机设备,其特征在于,所述根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    获取所述信息推送任务对应的待推送消息;
    从获取到的待推送消息中提取消息关键词;
    根据获取到的用户兴趣标签和提取到的消息关键词,分别计算所述预测到达用户账号集合中各用户账号对应的感兴趣度;
    根据获取到的历史点击信息,统计所述预测到达用户账号集合中各用户账号对应的历史点击率;及
    根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合。
  14. 根据权利要求13所述的计算机设备,其特征在于,所述根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    根据计算得到的感兴趣度和统计到的历史点击率,计算所述预测到达用户账号集合中各用户账号对应的点击预测值;及
    从所述预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
  15. 根据权利要求11所述的计算机设备,其特征在于,所述根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果之后,所述处理器还执行以下步骤:
    提取所述推送预测结果中的预测到达用户账号集合;及
    根据提取到的预测到达用户账号集合,生成与所述信息推送任务对应的目标用户账号调整建议。
  16. 一个或多个存储有计算机可执行指令的存储介质,所述计算机可执行指令被一个或多个处理器执行时,使得所述一个或多个处理器执行以下步骤:
    获取信息推送任务;
    提取所述信息推送任务中的目标用户账号,得到目标用户账号集合;
    获取所述目标用户账号集合中各用户账号对应的历史在线信息;
    根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合;
    获取所述预测到达用户账号集合中各用户账号对应的用户兴趣标签和历史点击信息;
    根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合;及
    根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果。
  17. 根据权利要求16所述的存储介质,其特征在于,所述根据获取到的历史在线信息,从所述目标用户账号集合中选取在线用户账号,得到预测到达用户账号集合,包括:
    将获取到的历史在线信息中被标记为无效的用户账号,从所述目标用户账号集合中删除,得到有效用户账号集合;
    根据所述获取到的历史在线信息,统计所述有效用户账号集合中各用户账号对应的预设时间段内在线次数;及
    从所述有效用户账号集合中,选取所述预设时间段内在线次数高于预设次数的用户账号,得到预测到达用户账号集合。
  18. 根据权利要求16所述的存储介质,其特征在于,所述根据获取到的用户兴趣标签和历史点击信息,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    获取所述信息推送任务对应的待推送消息;
    从获取到的待推送消息中提取消息关键词;
    根据获取到的用户兴趣标签和提取到的消息关键词,分别计算所述预测到达用户账号集合中各用户账号对应的感兴趣度;
    根据获取到的历史点击信息,统计所述预测到达用户账号集合中各用户账号对应的历史点击率;及
    根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合。
  19. 根据权利要求18所述的存储介质,其特征在于,所述根据计算得到的感兴趣度和统计到的历史点击率,从所述预测到达用户账号集合中提取预测点击用户账号集合,包括:
    根据计算得到的感兴趣度和统计到的历史点击率,计算所述预测到达用户账号集合中各用户账号对应的点击预测值;及
    从所述预测到达用户账号集合中,选取点击预测值超过预设阈值的用户账号,得到预测点击用户账号集合。
  20. 根据权利要求16所述的存储介质,其特征在于,所述根据所述预测到达用户账号集合和所述预测点击用户账号集合,生成推送预测结果之后,所述处理器还执行以下步骤:
    提取所述推送预测结果中的预测到达用户账号集合;及
    根据提取到的预测到达用户账号集合,生成与所述信息推送任务对应的目标用户账号调整建议。
PCT/CN2017/104871 2017-07-24 2017-09-30 推送结果预测方法、装置、计算机设备和存储介质 WO2019019396A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710608094.4 2017-07-24
CN201710608094.4A CN107666506B (zh) 2017-07-24 2017-07-24 推送结果预测方法、装置、计算机设备和存储介质

Publications (1)

Publication Number Publication Date
WO2019019396A1 true WO2019019396A1 (zh) 2019-01-31

Family

ID=61122492

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/104871 WO2019019396A1 (zh) 2017-07-24 2017-09-30 推送结果预测方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN107666506B (zh)
WO (1) WO2019019396A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111311015A (zh) * 2020-02-28 2020-06-19 深圳前海微众银行股份有限公司 个性化点击率预测方法、设备及可读存储介质
CN111460319A (zh) * 2020-03-31 2020-07-28 深圳前海微众银行股份有限公司 消息播放优化方法、装置、设备及可读存储介质
CN112733012A (zh) * 2020-12-30 2021-04-30 杭州网易再顾科技有限公司 一种执行用户触达的方法、装置、设备和介质
CN113254759A (zh) * 2020-02-12 2021-08-13 北京沃东天骏信息技术有限公司 点击率预测方法、装置、介质及电子设备
CN113726839A (zh) * 2021-06-17 2021-11-30 武汉理工数字传播工程有限公司 一种虚拟资源发送方法、装置、设备及存储介质
CN114742479A (zh) * 2022-06-10 2022-07-12 深圳竹云科技股份有限公司 账号识别方法、装置、服务器及存储介质

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109218411B (zh) * 2018-08-22 2022-10-18 中国平安人寿保险股份有限公司 数据处理方法及装置、计算机可读存储介质、电子设备
CN110213216B (zh) * 2018-08-22 2024-02-09 腾讯科技(北京)有限公司 确定不同账号集合中相同账号的方法、装置及存储介质
CN109271420B (zh) * 2018-09-03 2023-07-11 深圳平安医疗健康科技服务有限公司 信息推送方法、装置、计算机设备和存储介质
CN109558542B (zh) * 2018-12-04 2020-11-27 北京达佳互联信息技术有限公司 一种信息质量评估方法、信息推送方法及装置
CN110399550B (zh) * 2019-03-14 2023-08-15 腾讯科技(深圳)有限公司 一种信息推荐方法及装置
CN110674395B (zh) * 2019-08-23 2022-07-05 深圳市新系区块链技术有限公司 信息推送方法、装置及设备
CN111079006B (zh) * 2019-12-09 2024-05-10 腾讯科技(深圳)有限公司 一种消息推送方法、装置、电子设备及介质
CN111368552B (zh) * 2020-02-26 2023-09-26 北京市公安局 一种面向特定领域的网络用户群组划分方法及装置
CN111753201A (zh) * 2020-06-23 2020-10-09 厦门美柚股份有限公司 信息推送方法、装置、终端及介质
CN113704616B (zh) * 2021-08-30 2023-10-27 康键信息技术(深圳)有限公司 信息推送方法、装置、电子设备及可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102592235A (zh) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 一种互联网广告投放***
CN103150663A (zh) * 2013-02-18 2013-06-12 亿赞普(北京)科技有限公司 一种网络投放数据投放的方法和装置
CN105227429A (zh) * 2014-06-25 2016-01-06 腾讯科技(深圳)有限公司 一种信息推送方法和装置
WO2016180138A1 (zh) * 2015-05-11 2016-11-17 腾讯科技(深圳)有限公司 推广信息投放有效性确定方法、监测服务器及终端
CN106649774A (zh) * 2016-12-27 2017-05-10 北京百度网讯科技有限公司 基于人工智能的对象推送方法及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101123520B (zh) * 2006-08-07 2012-07-04 腾讯科技(深圳)有限公司 一种定向投放广告的方法和广告***
US20090006188A1 (en) * 2007-06-26 2009-01-01 Microsoft Corporation Associating an activity with an online advertisement
US8738443B2 (en) * 2009-05-18 2014-05-27 George M. Davison System and method for advertising using pushed video
CN105897847A (zh) * 2015-12-15 2016-08-24 乐视网信息技术(北京)股份有限公司 一种信息推送方法及信息推送装置
CN106790570A (zh) * 2016-12-27 2017-05-31 山东开创云软件有限公司 一种消费者行为分析管理***及其分析方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102592235A (zh) * 2011-12-28 2012-07-18 北京品友互动信息技术有限公司 一种互联网广告投放***
CN103150663A (zh) * 2013-02-18 2013-06-12 亿赞普(北京)科技有限公司 一种网络投放数据投放的方法和装置
CN105227429A (zh) * 2014-06-25 2016-01-06 腾讯科技(深圳)有限公司 一种信息推送方法和装置
WO2016180138A1 (zh) * 2015-05-11 2016-11-17 腾讯科技(深圳)有限公司 推广信息投放有效性确定方法、监测服务器及终端
CN106649774A (zh) * 2016-12-27 2017-05-10 北京百度网讯科技有限公司 基于人工智能的对象推送方法及装置

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113254759A (zh) * 2020-02-12 2021-08-13 北京沃东天骏信息技术有限公司 点击率预测方法、装置、介质及电子设备
CN111311015A (zh) * 2020-02-28 2020-06-19 深圳前海微众银行股份有限公司 个性化点击率预测方法、设备及可读存储介质
CN111460319A (zh) * 2020-03-31 2020-07-28 深圳前海微众银行股份有限公司 消息播放优化方法、装置、设备及可读存储介质
CN112733012A (zh) * 2020-12-30 2021-04-30 杭州网易再顾科技有限公司 一种执行用户触达的方法、装置、设备和介质
CN112733012B (zh) * 2020-12-30 2023-06-02 杭州网易再顾科技有限公司 一种执行用户触达的方法、装置、设备和介质
CN113726839A (zh) * 2021-06-17 2021-11-30 武汉理工数字传播工程有限公司 一种虚拟资源发送方法、装置、设备及存储介质
CN113726839B (zh) * 2021-06-17 2023-05-26 武汉理工数字传播工程有限公司 一种虚拟资源发送方法、装置、设备及存储介质
CN114742479A (zh) * 2022-06-10 2022-07-12 深圳竹云科技股份有限公司 账号识别方法、装置、服务器及存储介质
CN114742479B (zh) * 2022-06-10 2022-09-06 深圳竹云科技股份有限公司 账号识别方法、装置、服务器及存储介质

Also Published As

Publication number Publication date
CN107666506A (zh) 2018-02-06
CN107666506B (zh) 2019-11-12

Similar Documents

Publication Publication Date Title
WO2019019396A1 (zh) 推送结果预测方法、装置、计算机设备和存储介质
CN111339327B (zh) 作品推荐方法及装置、服务器和存储介质
EP3399434A1 (en) Short link processing method, device and server
WO2015188733A1 (en) Group user level association method and system
JP6986187B2 (ja) 人物識別方法、装置、電子デバイス、記憶媒体、及びプログラム
CN107305611B (zh) 恶意账号对应的模型建立方法和装置、恶意账号识别的方法和装置
WO2019055506A1 (en) PREDICTING NON-OBSERVABLE PARAMETERS FOR DIGITAL COMPONENTS
US10313746B2 (en) Server, client and video processing method
JP6309539B2 (ja) 音声入力を実現する方法および装置
CN110413867B (zh) 用于内容推荐的方法及***
WO2019019652A1 (zh) 推送信息的处理方法、装置、计算机设备和存储介质
WO2019019642A1 (zh) 应用信息推送方法、装置、计算机设备和存储介质
CN111586126A (zh) 小程序预下载方法、装置、设备及存储介质
US10085046B2 (en) Video transmission method, gateway device, and video transmission system
US9866454B2 (en) Generating anonymous data from web data
WO2021190470A1 (zh) 电子设备定位的方法、装置、服务器、***以及存储介质
WO2019011295A1 (zh) 负一屏内容推送及请求方法、装置、服务器及终端
CN108401005B (zh) 一种表情推荐方法和装置
CN109885729B (zh) 一种显示数据的方法、装置及***
WO2019210585A1 (zh) 消息推送方法、计算机可读存储介质、终端设备及装置
CN106570003B (zh) 数据推送方法及装置
CN103365892A (zh) 一种用于对多个联系对象进行处理的方法与设备
US10924365B2 (en) Method and system for generating directed graphs
CN110457089B (zh) 数据采集方法、装置、计算机可读存储介质和计算机设备
CN106294457B (zh) 网络信息推送方法及装置

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: 17919137

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17919137

Country of ref document: EP

Kind code of ref document: A1

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 1205N DATED 17/03/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 17919137

Country of ref document: EP

Kind code of ref document: A1