Information processing method, device, and storage medium

Abstract

An embodiment of the present invention discloses an information processing method, device, and storage medium, including: upon obtaining information to be pushed, determining a target object corresponding to the information to be pushed; determining an active time period of the target object based on the target object's historical active time period; and sending the information to be pushed to the target object within the active time period.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to an information processing method and device, and a storage medium. Background Art

[0002] With the development of big data and artificial intelligence, more and more users tend to obtain information from the Internet, and the Internet will also push some information to users to facilitate their acquisition of information.

[0003] In the prior art, when push information is obtained, the push information is directly sent to the user, but some users will not read the push information, thus reducing the push efficiency of the push information. Summary of the Invention

[0004] To solve the above technical problems, embodiments of the present invention are intended to provide an information processing method and apparatus, and a storage medium, which can improve the efficiency of information push.

[0005] The technical solution of the present invention is achieved as follows:

[0006] The present invention provides an information processing method, which includes:

[0007] When the information to be pushed is obtained, determining the target object corresponding to the information to be pushed;

[0008] The active time period of the target object is determined based on the historical active time period of the target object; and the information to be pushed is sent to the target object within the active time period, where the active time period is a time period during which the target object views the pushed information.

[0009] An embodiment of the present application provides an information processing device, the device comprising:

[0010] A determination unit is configured to, upon obtaining information to be pushed, determine a target object corresponding to the information to be pushed; and determine an active time period of the target object based on a historical active time period of the target object, the active time period being a time period during which the target object views the pushed information;

[0011] A sending unit is used to send the information to be pushed to the target object within the active time period.

[0012] An embodiment of the present application provides an information processing device, the device comprising:

[0013] A memory, a processor and a communication bus, wherein the memory communicates with the processor via the communication bus, and the memory stores an information processing program executable by the processor. When the information processing program is executed, the information processing method described above is executed by the processor.

[0014] An embodiment of the present application provides a storage medium on which a computer program is stored, which is applied to an information processing device. When the computer program is executed by a processor, the above-mentioned information processing method is implemented.

[0015] The embodiment of the present invention provides an information processing method, device, and storage medium. The information processing method includes: determining the target object corresponding to the information to be pushed when the information to be pushed is acquired; determining the active time period of the target object based on the historical active time period of the target object; and sending the information to be pushed to the target object during the active time period. When the above method is implemented, when the information processing device determines the target object corresponding to the information to be pushed, the information processing device will determine the active time period of the target object based on the historical active time period of the target object, so that the information processing device can send the information to be pushed to the target object during the active time period of the target object. Since the acquisition time period is the active time period for the target object to view the pushed information, by sending the recommended information to the target object during the active time period for the target object to view the pushed information, the probability of the target object viewing the recommended information is increased, and the efficiency of pushing the information is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of an information processing method provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of the structure of an exemplary information processing device provided in an embodiment of the present application;

[0018] Figure 3 A flowchart of an exemplary information processing method provided in an embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 ;

[0020] Figure 5 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0021] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0022] Example 1

[0023] The present application provides an information processing method. Figure 1 A flow chart of an information processing method provided in an embodiment of the present application is as follows: Figure 1 As shown, the information processing method may include:

[0024] S101: When information to be pushed is obtained, determine a target object corresponding to the information to be pushed.

[0025] An information processing method provided in an embodiment of the present application is applicable to a scenario in which information to be recommended is sent to a target object.

[0026] In the embodiments of the present application, the information processing device may be implemented in various forms. For example, the information processing device described in the present application may include devices such as mobile phones, cameras, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, and devices such as digital TVs, desktop computers, and servers.

[0027] For example, if the information processing device is a server, the information processing device may specifically be a server at a certain e-commerce shopping platform center.

[0028] In the embodiment of the present application, the information to be pushed can be current news that the user is interested in, dynamic information about the products that the user is interested in, or other information. The specific information can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0029] For example, if the information to be pushed can be dynamic information of the product that the user is interested in, then the information to be pushed can be price reduction information of the product that the user is interested in, payment information of the product that the user is interested in, or shopping voucher information of the product that the user is interested in, etc. The specific information can be determined according to actual conditions, and the embodiments of this application are not limited to this.

[0030] In an embodiment of the present application, the information to be pushed can be information generated in the information processing device, or it can be information obtained by the information processing device from other devices. The specific way in which the information processing device obtains the information to be pushed can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0031] In an embodiment of the present application, if the information to be pushed is information generated in an information processing device, when the information processing device generates the information to be pushed, the information processing device also obtains the information to be pushed.

[0032] In an embodiment of the present application, the target object can be the user who receives the information to be pushed. The number of target objects can be one, two, or multiple. The specific number of target objects can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0033] In an embodiment of the present application, user information is stored in the information processing device, and the information processing device can filter the user information to obtain a target object corresponding to the information to be pushed.

[0034] In an embodiment of the present application, if the information processing device is a server of an e-commerce shopping platform center, the information processing device stores the user's registration information on the e-commerce platform, that is, user information, and the information processing device can determine the target object from the user information.

[0035] It should be noted that the information processing device can store user information through a hive table, and the information processing device can also store user information in other ways. The specific method can be determined according to actual conditions, and the embodiments of the present application do not limit this.

[0036] In an embodiment of the present application, the process of the information processing device determining the target object corresponding to the information to be pushed includes: the information processing device filters out the objects to be recommended that are related to the information to be recommended from a preset object group; the information processing device removes non-target objects from the objects to be recommended to obtain the target object.

[0037] It should be noted that non-target objects include objects whose frequency of viewing push information is lower than the lower frequency threshold, duplicate objects, and false objects.

[0038] It should be noted that the preset target group is a specific target group when the push information receiving switch is turned on. The preset target group may be a target group when the push information receiving switch is turned on that is filtered from user information.

[0039] In an embodiment of the present application, if the information to be recommended is information related to a product, the information processing device may first determine the users who follow the product, and then the information processing device may select the users who follow the product as objects to be recommended.

[0040] In an embodiment of the present application, after the information processing device determines the objects to be recommended, the information processing device can remove duplicate objects, false objects, and objects whose frequency of viewing push information is lower than the lower frequency threshold from the objects to be recommended.

[0041] It should be noted that the information processing device will send the information to be pushed to the target device of the target object so that the target object can use the target device to obtain the information to be pushed. The user information stored in the information processing device includes the device number of the device corresponding to the user.

[0042] It should be noted that a duplicate object is a device that has a different device number than other devices in the recommended objects, but has the same object as the other devices. A false object is an object with an empty device number.

[0043] In an embodiment of the present application, the frequency lower limit threshold is a frequency threshold configured in the information processing device, or it may be a frequency threshold obtained before the information processing device executes the step of removing non-target objects from the objects to be recommended and obtaining the target object. It may also be a frequency threshold obtained by the information processing device in other ways. The specific frequency threshold can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0044] In an embodiment of the present application, the frequency offline threshold can be the frequency of the user opening the push information seven times in the past three months, or the frequency of the user opening the push information twice in the past month, or other frequencies. The specific frequency can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0045] S102: Determine an active time period of the target object based on the target object's historical active time period; and send the information to be pushed to the target object within the active time period, where the active time period is a time period during which the target object views the pushed information.

[0046] In an embodiment of the present application, after the information processing device determines the target object corresponding to the information to be pushed, the information processing device can determine the active time period of the target object based on the historical active time period of the target object; and send the information to be pushed to the target object within the active time period.

[0047] It should be noted that the active time period is the time period during which the target object views the pushed information.

[0048] In an embodiment of the present application, the information processing device can determine the active time period of the user based on the user's historical active time period. The information processing device can also use an active time prediction model to determine the active time period of the user. The information processing device can also use other methods to determine the active time period of the user. The specific method can be determined based on actual conditions, and the embodiment of the present application does not limit this.

[0049] In an embodiment of the present application, before the information processing device determines the active time period of the target object based on the historical active time period of the target object, the information processing device will also obtain the historical active time period of the target object. Accordingly, the process of the information processing device determining the active time period of the target object based on the historical active time period of the target object includes: the information processing device determines the historical active time period of the target object; the information processing device inputs the historical active time period information into the active time prediction model to obtain the active time period.

[0050] In an embodiment of the present application, an active time prediction model is configured in the information processing device. The active time prediction model is specifically a model obtained by the information processing device training an initial active time prediction model using the user's historical active time periods.

[0051] It should be noted that the active time prediction model can be a model obtained using a long short-term memory network (LSTM), or a model obtained by an information processing device using other neural networks. The specific model can be determined according to actual conditions, and the embodiments of the present application do not limit this.

[0052] In an embodiment of the present application, after the information processing device obtains the active time prediction model, the information processing device may store the active time prediction model and update the active time prediction model within a preset time period.

[0053] It should be noted that the information processing device can store the active time prediction model in a cache cloud, or the information processing device can store the active time prediction model in a memory. The specific area where the information processing device stores the active time prediction model can be determined based on actual conditions, and the embodiments of the present application do not limit this.

[0054] It should be noted that the historical active time period may be the user's active time period within the past 7 days, that is, the information processing device uses the user's active time period within the past 7 days to predict the user's active time period within the 8th day.

[0055] In an embodiment of the present application, the historical active time period may also be the user's active time period within the past 15 days, or the historical active time period may be the user's active time period within the past 20 days. The specific historical time period corresponding to the historical active time period may be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0056] In an embodiment of the present application, the process of the information processing device obtaining the historical active time period of the target object includes the information processing device obtaining the length of time the target object views the target application within a first time period; when the time length is greater than or equal to a preset time length threshold, the first time period is used as the historical active time period.

[0057] It should be noted that the target application is the application that receives the push information.

[0058] In an embodiment of the present application, there may be multiple target objects, and the information processing device may obtain the length of time each target object views the target application within the first time period, thereby determining the historical active time corresponding to each target object.

[0059] It should be noted that the first time period is the time period of the historical viewing target application corresponding to the target object.

[0060] In an embodiment of the present application, the preset duration threshold may be a duration threshold configured in the information processing device, or may be a duration threshold received by the information processing device before the information processing device uses the first time period as a historical active time period when the time length is greater than or equal to the preset duration threshold. It may also be a duration threshold obtained by the information processing device using other methods. The specific method may be determined based on actual conditions, and the embodiment of the present application does not limit this.

[0061] In an embodiment of the present application, the information processing device may also determine the number of times the user requests the target application within a first time period. If the number of requests is greater than or equal to a preset threshold, the information processing device will use the first time period as a historical active time period.

[0062] In an embodiment of the present application, the information processing device can also determine the number of clicks of the user in the target application within a first time period. When the information processing device determines that the number of clicks is greater than or equal to the preset number of clicks, the information processing device uses the first time period as a historical active time period. The specific way in which the information processing device determines the historical active time period of the target object can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0063] In an embodiment of the present application, the information processing device inputs the historical active time period information into the active time prediction model. After obtaining the active time period, the information processing device will also update the active time prediction model within a preset time period to obtain an updated active time prediction model, and determine the active time period of the next round of target objects based on the updated active time prediction model and the historical active time period.

[0064] In an embodiment of the present application, the preset time period can be a time period configured in the information processing device, or a time period received by the information processing device before the information processing device updates the active time prediction model, or a time period obtained by the information processing device in other ways. The specific time period can be determined according to actual conditions, and the embodiment of the present application does not limit this.

[0065] Exemplarily, the preset time period can be five months, the preset time period can also be one year, and the preset time period can also be two years. The specific length of the preset time period can be determined according to actual conditions, and the embodiments of the present application do not limit this.

[0066] In an embodiment of the present application, after obtaining the updated active time prediction model, the information processing device deletes the active time prediction model from the area storing the active time prediction model and stores the updated active time prediction model in the area.

[0067] For example, Figure 2As shown: If the recommended object corresponding to the information to be recommended is a product, the information processing device can obtain the product information from the message portrait, and the information processing device will store the product information in the message material pool. The information processing device can use the user selection module to determine the target object corresponding to the product information from the user portrait. After that, the information processing device will determine the time period for sending the product information to the target object according to the message candidate set construction module, and push the information to be pushed to the target object within the time period. Specifically, the user selection module includes model fusion selection, rule selection and business direct selection. The information processing device can use any of the model selection models of model fusion selection, rule selection or business direct selection to determine the target object. If the information processing device uses model fusion selection to determine the target object, the information processing device can use any of the models such as churn warning model, activity model, message sensitivity model, etc. to determine the target object. In the process of the information processing device using the message candidate set construction module to determine the acquisition time period of the target object, the information processing device can use the user set division to determine whether to send the product information to the target object based on the message preference time period (active time period) or to send the product information to the target object by real-time triggering. If the information processing device determines that the product information is sent to the target object based on the message preference time period, the information processing device will use the user timing scheduling module to obtain the product information from the multi-channel material calling module at a regular interval, and generate the copy corresponding to the product information through the file management and generation module in the copy splicing module, and assemble the copy using the message body assembly module to obtain the information to be recommended. After that, the information processing device can send the information to be recommended to the target object during the message preference time period.

[0068] It should be noted that the multi-channel material calling module can specifically be a recommendation service module, a middle-end service module, or a rule calculation script module.

[0069] For example, Figure 3As shown, the information processing device can also obtain and save an active time prediction model based on business scenarios, push timing plans, data analysis, time series model training, and online reasoning. The active time prediction model can then be used to predict the active time period of a target object. An AB test can then be conducted by comparing the effectiveness of sending recommended information to the target object during this active time period with directly sending the recommended information to the target object after the information processing device has acquired the information to be pushed. The business scenario includes push context, user selection, message candidates, and message sending. When the information processing device determines based on the push context that recommended information should be sent, it uses user selection to determine the target object. It then uses message candidates to determine whether to send the recommended information to the target object during the active time period, in real time, or periodically. Once it is determined that the recommended information should be sent to the target object during the active time period, the information processing device then determines through message sending whether to send the recommended information to the target object based on rule priority or based on a ranking model. The information processing device uses the push time plan to determine whether the push message delivery scheme is a classification or timing problem. If it is a classification problem, the classification problem module calculates the coarse-grained message delivery time points, such as morning or afternoon. By building user features and labels, the probability of users belonging to different categories, namely, whether they will open the push message in the morning or afternoon, is predicted. If it is a timing problem, the push message delivery time points are predicted end-to-end using a timing model, extracting the user's historical active time periods. Then, using an LSTM model, a sliding window is designed to predict the user's active time periods. Based on data requirements, the exposure table is used to count the time users request the target application daily and divide it into time periods. The time period with the highest number of target application requests is preliminarily defined as the user's active time period. The Hive table of the message push center is then linked to calculate the users who need to send messages each day and package them into PIN packages. Data preprocessing is used to filter the data in the PIN packages to remove dirty and duplicate data and identify the target objects. The information processing device investigates the log table of the push information through a database table investigation, including the timestamp of the push information generation and the status of the push information (10 indicates that the push information is processed, 20 indicates that the push information is sent successfully, 30 indicates that the push information arrives at the user device, 40 indicates that the push information is opened, 98 indicates that there is no valid device or binding relationship, and 99 indicates that the switch judgment is not passed). The information processing device filters out a preset object group based on the time when the push information is opened every day, and then filters out the recommended objects related to the recommended information from the preset object group, removes objects whose viewing frequency of push information is lower than the lower frequency threshold, duplicate objects and false objects from the recommended objects, and then obtains the sequence data for customer identification of the active time prediction model through time conversion, i.e. normalization processing.The length of time the target object views the target application within the first time period is obtained through the activity definition. When the time length is greater than or equal to the preset time threshold, the first time period is used as the historical active time period to define the activity. The sequence length design is used to use the historical active time period of the past 7 days as the sequence length, and the sequence length is used to train the initial active time prediction model. The information processing device sets the sequence of the sequence sliding window to 7 to use the historical active time period of the past 7 days to predict the active time period of the target object on the 8th day. The information processing device uses the historical active time period of the past 7 days to train the initial active time prediction model (LSTM model), thereby obtaining the trained initial active time prediction model. The information processing device then debugs the parameters in the trained initial active time prediction model through parameter debugging, and then debugs the trained initial active time prediction model through optimizer debugging, thereby obtaining the active time prediction model. The inference data construction uses an active time prediction model to predict the target object corresponding to the information to be pushed. This model is then stored in a cache cloud through model preservation. The active time prediction model is regularly updated, and the prediction results are stored on disk. The target object is processed according to downstream needs and saved to the Hadoop Distributed File System (HDFS). The target object saved in HDFS is then imported into the designated area of the resource management platform using a technology import tool, creating an automatically updated scheduled task. The information processing device set up control experiments A and B with a control group. Experiment A sent push notifications to all users at 7:00 PM every day. Experiment B first determined that the active time period for the first group of users was 10:00 AM, the active time period for the second group of users was 1:00 PM, and the active time period for the third group of users was 7:00 PM. The device then sent push notifications to the first group of users at 10:00 AM, the second group of users at 1:00 PM, and the third group of users at 7:00 PM. The device then used the push open rate to determine the push open rate of the push notifications, the push recall rate to calculate the push recall rate of the push notifications, and the push close rate to calculate the push close rate of the push notifications. The push open rate is calculated as the number of users who opened the push notifications divided by the number of users who successfully received the push notifications. It should be noted that the number of users who opened the push notifications is represented in the push log table by a push status of 40, and the number of users who successfully received the push notifications is represented in the push log table by a push status of 30. It should be noted that the push recall rate is calculated as the number of users who were exposed to the push notifications divided by the number of users who processed the messages in the push log table.The number of users exposed to the pending push information is counted in the exposure table using the recommended conditions, and the number of users who processed the pending push information is counted in the push log table. The push status in the push log table is 10, 20, 30, 40, 98, and 99 (10 indicates that the pending push information has been processed, 20 indicates that the pending push information has been successfully sent, 30 indicates that the pending push information has arrived at the phone, 40 indicates that the pending push information has been opened, 98 indicates that there is no valid device or binding relationship, and 99 indicates that the user has not made a switch to determine whether to push the information). It should be noted that the push shutdown rate is the number of users who received the pending push information but actively closed it / the number of users who successfully received the pending push information. The number of users who received the pending push information but actively closed it is marked in another message zipper log table by whether the push enable field is 0. The number of users who successfully received the pending push information is represented in the push log table using a push status of 30.

[0070] It should be noted that the rule priority-based method can be that if the target object has not logged into the target application in the past period of time (that is, the target object's historical message opening rate, historical message active user number (Dailyactive user, DAU) contribution rate, user portrait, message portrait message material positive and negative feedback, material product coupon heterogeneous characteristics and other information determine that the target object has not logged into the target application in the past period of time), then the information processing device will not send the rules for the recommended information to the target object; if the target object has logged into the target application in the past period of time, then the information processing device will send the rules for the recommended information to the target object. The sorting model is used to detect the sensitivity of the target object to the pushed information. If the target object is sensitive to the pushed information, all recommended information related to the target object is sent to the target object. If the target object is not sensitive to the pushed information, then part of the recommended information related to the target object is sent to the target object. The information processing device can also optimize the sending method of the recommended information through product frequency control, copy frequency control, category frequency control, etc.

[0071] It should also be noted that the ranking model can be a multi-model fusion scoring model, a multi-objective MMOE prediction model, a re-ranking model, etc.

[0072] It's important to note that the LSTM model consists of an input gate, a forget gate, a memory gate, and an output gate. The forget gate is used to ignore unimportant information in the sequence, retaining only the important information, thus providing fault tolerance to the recurrent neural network. The input gate and memory gate jointly control the input derived from the feature embedding and serve as the source of information. Two sets of weights are used to calculate the input gate and memory gate, respectively. The neural network obtains the memory gate and input gate, and then updates the data in the memory gate.

[0073] It should be noted that the learning rate of the parameter debugging part automatically decays with the number of iterations, limiting the normalized gradient to within 5. L2 regularization is also set to prevent overfitting.

[0074] It should be noted that the optimizer can be an adagrad optimizer.

[0075] It can be understood that when the information processing device determines the target object corresponding to the information to be pushed, the information processing device will determine the active time period of the target object based on the historical active time period of the target object, so that the information processing device can send the information to be pushed to the target object during the active time period of the target object. Since the acquisition time period is the active time period for the target object to view the pushed information, by sending the recommended information to the target object during the active time period for the target object to view the pushed information, the probability of the target object viewing the recommended information is increased, and the efficiency of pushing the information is improved.

[0076] Example 2

[0077] Based on the same inventive concept of the first embodiment, the embodiment of the present application provides an information processing device 1 corresponding to an information processing method; Figure 4 A schematic diagram of the structure of an information processing device provided in an embodiment of the present application Figure 1 , the information processing device 1 may include:

[0078] The determining unit 11 is configured to, upon obtaining information to be pushed, determine a target object corresponding to the information to be pushed; determine an active time period of the target object based on a historical active time period of the target object, the active time period being a time period during which the target object views the pushed information;

[0079] The sending unit 12 is configured to send the information to be pushed to the target object within the active time period.

[0080] In some embodiments of the present application, the apparatus further includes an input unit and an acquisition unit;

[0081] The acquiring unit is configured to acquire the historical active time period;

[0082] Correspondingly, the input unit is used to input the historical active time period information into the active time prediction model to obtain the active time period.

[0083] In some embodiments of the present application, the apparatus further includes an acquisition unit;

[0084] The acquisition unit is used to obtain the length of time the target object views the target application within a first time period; when the time length is greater than or equal to a preset time threshold, the first time period is used as the historical active time period, and the target application is the application that receives push information.

[0085] In some embodiments of the present application, the apparatus further includes an updating unit;

[0086] The updating unit is configured to update the active time prediction model within a preset time period to obtain an updated active time prediction model, and determine the active time period of the target object in the next round based on the updated active time prediction model.

[0087] In some embodiments of the present application, the device further comprises a screening unit and a removal unit;

[0088] The screening unit is configured to screen out the recommended objects related to the information to be recommended from a preset object group, wherein the preset object group is the object group when the push information receiving switch is turned on;

[0089] The removing unit is used to remove non-target objects from the objects to be recommended to obtain the target object, wherein the non-target objects include objects whose frequency of viewing pushed information is lower than a frequency lower limit threshold, duplicate objects, and false objects.

[0090] It should be noted that, in actual applications, the above-mentioned determination unit 11 and sending unit 12 can be implemented by a processor 13 on the information processing device 1, specifically a CPU (Central Processing Unit), an MPU (Microprocessor Unit), a DSP (Digital Signal Processing) or a field programmable gate array (FPGA); the above-mentioned data storage can be implemented by a memory 14 on the information processing device 1.

[0091] The embodiment of the present invention further provides an information processing device 1, such as Figure 5 As shown, the information processing device 1 includes: a processor 13, a memory 14 and a communication bus 15. The memory 14 communicates with the processor 13 through the communication bus 15. The memory 14 stores a program executable by the processor 13. When the program is executed, the information processing method described above is executed by the processor 13.

[0092] In practical applications, the memory 14 may be a volatile memory, such as a random-access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 13.

[0093] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by the processor 13 , the information processing method described above is implemented.

[0094] It can be understood that when the information processing device determines the target object corresponding to the information to be pushed, the information processing device will determine the active time period of the target object based on the historical active time period of the target object, so that the information processing device can send the information to be pushed to the target object during the active time period of the target object. Since the acquisition time period is the active time period for the target object to view the pushed information, by sending the recommended information to the target object during the active time period for the target object to view the pushed information, the probability of the target object viewing the recommended information is increased, and the efficiency of pushing the information is improved.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0099] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. An information processing method, characterized in that: The method comprises: When information to be pushed is obtained, determining a target object corresponding to the information to be pushed; the information to be pushed is dynamic information of a product; Determining an active time period of the target object based on the historical active time period of the target object; and sending the information to be pushed to the target object within the active time period, where the active time period is a time period during which the target object views the pushed information; The step of determining the target object corresponding to the information to be pushed includes: Filtering objects to be recommended that are related to the information to be recommended from a preset object group, the preset object group being the object group when the push information receiving switch is turned on; Removing non-target objects from the objects to be recommended to obtain the target objects, wherein the non-target objects include objects whose frequency of viewing push information is lower than a lower frequency threshold, duplicate objects, and false objects; the duplicate objects are devices that exist in the objects to be recommended and have different device numbers from other devices but have the same objects corresponding to the other devices; The determining of the active time period of the target object based on the historical active time period of the target object includes: Determining the active time period based on the historical active time period using an active time prediction model; After determining the active time period based on the historical active time period using the active time prediction model, the method further includes: Within a preset time period, the active time prediction model is updated to obtain an updated active time prediction model, and the active time period of the next round of target objects is determined based on the updated active time prediction model and the historical active time period; the historical active time period is a time period when the number of requests made by the target object to the target application is greater than or equal to a preset number threshold.

2. The method according to claim 1, characterized in that Before determining the active time period of the target object based on the historical active time period of the target object, the method further includes: Obtain the historical active time period; Accordingly, determining the active time period of the target object based on the historical active time period of the target object includes: The historical active time period information is input into an active time prediction model to obtain the active time period.

3. The method according to claim 2, characterized in that The obtaining of the historical active time period includes: Obtaining a time length for the target object to view a target application within a first time period, where the target application is an application that receives push information; When the time length is greater than or equal to a preset time length threshold, the first time period is used as the historical active time period.

4. An information processing device, characterized in that The device comprises: a determination unit configured to, upon obtaining information to be pushed, determine a target object corresponding to the information to be pushed; determine an active time period of the target object based on a historical active time period of the target object, the active time period being a time period during which the target object views the pushed information; the information to be pushed is dynamic information about a product; A sending unit, configured to send the information to be pushed to the target object within the active time period; Wherein, the device further comprises a screening unit and a removal unit; The screening unit is configured to screen out the recommended objects related to the information to be recommended from a preset object group, wherein the preset object group is the object group when the push information receiving switch is turned on; The removal unit is configured to remove non-target objects from the objects to be recommended to obtain the target objects, wherein the non-target objects include objects whose frequency of viewing push information is lower than a lower frequency threshold, duplicate objects, and false objects; the duplicate objects are devices that exist in the objects to be recommended but have different device numbers from other devices but have the same objects corresponding to the other devices; The determining unit is configured to determine the active time period based on the historical active time period using an active time prediction model; The apparatus further comprises an updating unit; The updating unit is configured to update the active time prediction model within a preset time period to obtain an updated active time prediction model, and determine the active time period of the next round of target objects based on the updated active time prediction model and the historical active time period; the historical active time period is a time period when the number of requests made by the target object to the target application is greater than or equal to a preset number threshold.

5. The device according to claim 4, characterized in that The device further includes an input unit and an acquisition unit; The acquiring unit is configured to acquire the historical active time period; Correspondingly, the input unit is used to input the historical active time period information into the active time prediction model to obtain the active time period.

6. The device according to claim 5, characterized in that The acquisition unit is used to obtain the length of time the target object views the target application within a first time period; when the time length is greater than or equal to a preset time threshold, the first time period is used as the historical active time period, and the target application is the application that receives push information.

7. An information processing device, characterized in that The device comprises: A memory, a processor, and a communication bus, wherein the memory communicates with the processor via the communication bus, the memory stores an information processing program executable by the processor, and when the information processing program is executed, the method according to any one of claims 1 to 3 is performed by the processor.

8. A storage medium having a computer program stored thereon, applied to an information processing device, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images