CN111800445B - Message pushing method and device, storage medium and electronic equipment - Google Patents
Message pushing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111800445B CN111800445B CN201910282118.0A CN201910282118A CN111800445B CN 111800445 B CN111800445 B CN 111800445B CN 201910282118 A CN201910282118 A CN 201910282118A CN 111800445 B CN111800445 B CN 111800445B
- Authority
- CN
- China
- Prior art keywords
- message
- pushed
- target
- user
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Telephone Function (AREA)
Abstract
The embodiment of the application discloses a message pushing method, a message pushing device, a storage medium and electronic equipment, wherein panoramic data of a target user are collected, and the scene type of the target user is identified according to the panoramic data; acquiring a list of messages to be pushed of a reference user under a scene category; determining a screening rule corresponding to a scene type, acquiring a target message from a message list to be pushed according to the screening rule and pushing the target message to a user at intervals of a first preset time length under the scene type, and iteratively updating the screening rule according to the reading condition of the target message by the user until the reading condition meets a preset condition. The technical problem that the existing message pushing mode is difficult to meet the individual requirements of users on different scenes and interest preferences is solved.
Description
Technical Field
The application relates to the technical field of intelligent terminals, in particular to a message pushing method and device, a storage medium and electronic equipment.
Background
The message push service generally adopts a general push scheme, the same information is pushed to all users at the same time point, and the message content pushed by adopting the message push mode has no pertinence, so that the personalized requirements of the users on different scenes and interest preferences are difficult to meet.
Disclosure of Invention
The embodiment of the application provides a message pushing method, a message pushing device, a storage medium and electronic equipment, and can solve the technical problem that the existing message pushing mode is difficult to meet the personalized requirements of users for different scenes and interest preferences.
In a first aspect, an embodiment of the present application provides a message pushing method, including:
collecting panoramic data of a target user, and identifying the scene type of the target user according to the panoramic data;
acquiring a message list to be pushed of the target user;
based on a time difference algorithm, acquiring a target message from the message list to be pushed at intervals of preset duration and pushing the target message to a user, and iteratively updating a screening rule in the time difference algorithm according to the reading condition of the target message by the user until the reading condition meets a preset condition.
In a second aspect, an embodiment of the present application provides a message pushing apparatus, including:
the scene identification module is used for collecting panoramic data of a target user and identifying the scene type of the target user according to the panoramic data;
the data acquisition module is used for acquiring a message list to be pushed of the target user;
and the message pushing module is used for acquiring a target message from the message list to be pushed at intervals of preset duration based on a time difference algorithm, pushing the target message to a user, and iteratively updating a screening rule in the time difference algorithm according to the reading condition of the target message by the user until the reading condition meets a preset condition.
In a third aspect, a storage medium is provided in this application, and a computer program is stored on the storage medium, and when the computer program runs on a computer, the computer is caused to execute a message pushing method as provided in any embodiment of this application.
In a fourth aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, where the memory has a computer program, and the processor is configured to execute the message pushing method provided in any embodiment of the present application by calling the computer program.
According to the technical scheme provided by the embodiment of the application, the panoramic data of the target user is collected, the scene category of the target user is identified according to the panoramic data, the message list to be pushed of the reference user in the scene category is obtained, the target message is obtained from the message list to be pushed at intervals of a first preset duration and pushed to the user, the filtering rule is updated iteratively according to the reading condition of the user, the target information selected during pushing is pointed, the interest preference of the user can be met, in addition, the scheme can also push the message according to the scene category of the user actually located, and the technical problem that the personalized requirements of the user on different scenes and the interest preference cannot be met in the existing message pushing mode is solved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of a panoramic sensing architecture of a message push method according to an embodiment of the present application.
Fig. 2 is a first flowchart of a message pushing method according to an embodiment of the present application.
Fig. 3 is a schematic flowchart of a second message pushing method according to an embodiment of the present application.
Fig. 4 is a schematic flowchart of a third method for pushing a message according to an embodiment of the present application.
Fig. 5 is a schematic view of scene categories in a message pushing method according to an embodiment of the present application.
Fig. 6 is a schematic structural diagram of a message pushing apparatus according to an embodiment of the present application.
Fig. 7 is a schematic structural diagram of a first electronic device according to an embodiment of the present application.
Fig. 8 is a schematic structural diagram of a second electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without inventive step, are within the scope of the present application.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Referring to fig. 1, fig. 1 is a schematic view of a panoramic sensing architecture of a message push method according to an embodiment of the present disclosure. The message pushing method is applied to the electronic equipment. A panoramic perception framework is arranged in the electronic equipment. The panoramic perception architecture is an integration of hardware and software for implementing the message pushing method in an electronic device.
The panoramic perception architecture comprises an information perception layer, a data processing layer, a feature extraction layer, a scene modeling layer and an intelligent service layer.
The information perception layer is used for acquiring information of the electronic equipment or information in an external environment. The information-perceiving layer may include a plurality of sensors. For example, the information sensing layer includes a plurality of sensors such as a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a hall sensor, a position sensor, a gyroscope, an inertial sensor, an attitude sensor, a barometer, and a heart rate sensor.
Among other things, a distance sensor may be used to detect a distance between the electronic device and an external object. The magnetic field sensor may be used to detect magnetic field information of the environment in which the electronic device is located. The light sensor can be used for detecting light information of the environment where the electronic equipment is located. The acceleration sensor may be used to detect acceleration data of the electronic device. The fingerprint sensor may be used to collect fingerprint information of a user. The Hall sensor is a magnetic field sensor manufactured according to the Hall effect, and can be used for realizing automatic control of electronic equipment. The location sensor may be used to detect the geographic location where the electronic device is currently located. Gyroscopes may be used to detect angular velocity of an electronic device in various directions. Inertial sensors may be used to detect motion data of an electronic device. The gesture sensor may be used to sense gesture information of the electronic device. A barometer may be used to detect the barometric pressure of the environment in which the electronic device is located. The heart rate sensor may be used to detect heart rate information of the user.
And the data processing layer is used for processing the data acquired by the information perception layer. For example, the data processing layer may perform data cleaning, data integration, data transformation, data reduction, and the like on the data acquired by the information sensing layer.
The data cleaning refers to cleaning a large amount of data acquired by the information sensing layer to remove invalid data and repeated data. The data integration refers to integrating a plurality of single-dimensional data acquired by an information perception layer into a higher or more abstract dimension so as to comprehensively process the data of the plurality of single dimensions. Data transformation refers to performing data type conversion or format conversion on data acquired by an information sensing layer so that the transformed data can meet the processing requirement. The data reduction means that the data volume is reduced to the maximum extent on the premise of keeping the original appearance of the data as much as possible.
The characteristic extraction layer is used for extracting characteristics of the data processed by the data processing layer so as to extract the characteristics included in the data. The extracted features may reflect the state of the electronic device itself or the state of the user or the state of the environment in which the electronic device is located, etc.
The feature extraction layer may extract features or process the extracted features by a method such as a filtering method, a packing method, or an integration method.
The filtering method is to filter the extracted features to remove redundant feature data. Packaging methods are used to screen the extracted features. The integration method is to integrate a plurality of feature extraction methods together to construct a more efficient and more accurate feature extraction method for extracting features.
The scene modeling layer is used for building a model according to the features extracted by the feature extraction layer, and the obtained model can be used for representing the state of the electronic equipment, the state of a user, the environment state and the like. For example, the scenario modeling layer may construct a key value model, a pattern identification model, a graph model, an entity relation model, an object-oriented model, and the like according to the features extracted by the feature extraction layer.
And the intelligent service layer is used for providing intelligent services for the user according to the model constructed by the scene modeling layer. For example, the intelligent service layer can provide basic application services for users, perform system intelligent optimization for electronic equipment, and provide personalized intelligent services for users.
In addition, the panoramic perception architecture can further comprise a plurality of algorithms, each algorithm can be used for analyzing and processing data, and the plurality of algorithms can form an algorithm library. For example, the algorithm library may include algorithms such as markov algorithm, hidden dirichlet distribution algorithm, bayesian classification algorithm, support vector machine, K-means clustering algorithm, K-nearest neighbor algorithm, conditional random field, residual network, long-short term memory network, convolutional neural network, cyclic neural network, and the like.
Based on the panoramic perception framework, the electronic device collects panoramic data of a target user through the information perception layer and/or other modes, and the data processing layer processes the panoramic data, for example, data cleaning, data integration and the like are carried out on the obtained panoramic data. And then, the intelligent service layer acquires a target message and pushes the target message to the user according to the message pushing method provided by the application. For example, panoramic data of a target user is collected, a scene category where the target user is located is identified according to the panoramic data, a message list to be pushed of a reference user in the scene category is obtained, the target message is pushed to the user from the message list to be pushed every first preset time interval, and the filtering rule is iteratively updated according to the reading condition of the user, so that the target information selected in the pushing process is more pertinent and can meet the interest preference of the user.
An execution main body of the message pushing method may be the message pushing device provided in the embodiment of the present application, or an electronic device integrated with the message pushing device, where the message pushing device may be implemented in a hardware or software manner. The electronic device may be a smart phone, a tablet computer, a palm computer, a notebook computer, or a desktop computer.
Referring to fig. 2, fig. 2 is a first flowchart illustrating a message pushing method according to an embodiment of the present application. The specific process of the message pushing method provided by the embodiment of the application may be as follows:
In the embodiment of the application, before message pushing is carried out, panoramic data of a target user are collected firstly, the current scene category of the target user is identified according to the panoramic data, and targeted message pushing is carried out aiming at the scene category. For example, the electronic device performs the determination of the scene type every second preset time interval. The scene categories comprise shopping, listening to music, traveling, meetings, fitness and the like, and the specific classification of the scene categories can be set according to actual conditions.
The panoramic data of the user generally includes, but is not limited to, the following data: terminal status data, sensor data, and terminal usage data. The terminal state data includes the running state of the terminal, such as the on-off state of the mobile data network, the connection state of the wireless hotspot, the identity information of the connected wireless hotspot, the currently running application program, the previous foreground application program, the time for which the current application program stays in the background, the time for which the current application program is switched to the background last time, the plugging and unplugging state of the earphone jack, the charging state, the battery power information, the screen display time and the like. The sensor data includes signals collected by various sensors on the electronic device, for example, the following sensors are included on the electronic device: a plurality of sensors such as distance sensor, magnetometer, light sensor, acceleration sensor, fingerprint sensor, hall sensor, position sensor, gyroscope, inertial sensor, attitude sensor, barometer, heart rate sensor. The user behavior data may include: the time, place, and frequency of opening the application, etc.
And collecting the panoramic data according to a preset collection frequency, extracting features, and identifying corresponding scene categories by taking the extracted features as the input of a preset classification model. The models which can process high-dimensional data, such as a neural network classification model, a Bayesian classification model, a support vector machine classification model and the like, can be used as preset classification models. Furthermore, with respect to extracting features from panoramic data, there may be various embodiments, for example, extracting time domain features; extracting frequency domain features; or acquiring panoramic data within a certain time length to form a panoramic data sequence, extracting a model with time sequence characteristics according to a recurrent neural network model or a long-time and short-time memory network model and the like, and extracting the characteristics from the panoramic data sequence.
The scene category can be set into a secondary classification according to needs, for example, into a form of a secondary scene tree, the scene tree mainly comprises two layers, and the first layer is a father catalog scene category layer, such as tourism, business trip, fitness, meeting and the like; the second layer is a sub-directory scene classification layer, that is, a corresponding sub-directory scene is provided under each parent directory layer, for example, there are tourist attractions of various types, such as a human type, a history type, a natural scene type and the like, under a tour, and when identifying scenes, twice classification is performed, the same input data is adopted, but the output data is different, and the classification of the second layer scene classification is finer than the classification output granularity of the first scene classification.
And 102, acquiring a message list to be pushed of the target user.
After the scene type where the user is located at present is identified, according to the scene type, messages are pushed to the target user in a targeted mode.
Fig. 3 is a schematic flowchart of a second message pushing method according to an embodiment of the present application.
In some embodiments, the step of obtaining the list of messages to be pushed of the target user comprises:
The method includes the steps of presetting a push cycle, updating a message list to be pushed once in each push cycle, for example, taking one day as a push cycle, and collecting message reading records of a reference user of a target user in one or more push cycles before the current push cycle, wherein the message reading records include browser browsing messages read by the user, application internal push messages and the like. A second message list is generated from these message reading records, which collects the messages that have been read by the reference user, because: although these messages were read yesterday by other users, the target user may not have read the messages, and the messages may still be useful messages for the target user in the current push period; meanwhile, the message reading records of the target user in the last pushing period are collected, and a first message list is generated according to the message reading records, so that the messages which have been read by the target user are collected, and the reason is that: for some important information, the user may be reading repeatedly, for example, yesterday the target user viewed some coupon information but not used, while these coupons are still valid today and the user may be used today.
Generating a first message list of the target user under each preset scene category according to the collected message reading records of the target user by taking the scene category as a unit, and recording the first message list as<s n ,m n >. Wherein s is n Denotes the nth scene, m n A first list of messages representing the target user in the nth scenario. And generating a second message list of the reference user under each preset scene type according to the collected message reading of the reference user. Is marked as<s n ,m 1n >. Wherein s is n Denotes the nth scene, m 1n Represents a reference userA second message list in the nth scenario.
And acquiring a first message list of the target user under the currently identified scene category from the stored plurality of first message lists, and acquiring a second message list of the reference user under the currently identified scene category from the stored plurality of second message lists. And generating a message list to be pushed according to the acquired first message list and the acquired second message list.
Or, in some other embodiments, based on the above scheme, in addition to the first message list and the second message list, a push message received by the application in real time may be added to the message list to be pushed, that is, when the application receives an instant message sent by the application server, or when a preset application receives an instant message sent by the application server, the instant message is added to the message list to be pushed in real time.
In some embodiments, users other than the target user in the user set may be used as the reference user. Alternatively, in another embodiment, the reference user may be selected for the target user by classifying users in the set of users. Specifically, before the step of obtaining the message list to be pushed of the target user, the method further includes: classifying users in a preset user set according to a preset classification algorithm; and determining the user category to which the target user belongs, and taking other users except the target user in the user category as the reference users of the target user.
In the embodiment, similar users of the target user are determined by classifying the users, and the similar users are used as reference users, so that the pushed message is more targeted. Specifically, features are extracted from information read by a user, such as word vectors, the user is clustered by adopting a clustering method such as K-means and the like based on the extracted features, and then other users in the category where the target user is located are used as similar users.
Further, since the user has a low possibility of reading the push message in certain scene categories, the push message has a small meaning in such scenes, for example, in a meeting, a fitness and other scenes. On the contrary, in other scenes, messages are pushed to the user according to the scene type of the user, and the possibility that the user reads the messages instantly is high. For example, when the user is in the scene category of shopping, new commodity information, coupon information and the like are pushed to the user; when the user is in the scene category of listening to music, pushing new single music, albums or music listened to by other people to the user, and the like; and when the user is in the scene category of tourism, pushing articles related to the current scenic spot to the user, and the like. When the user is in these scenes, the related messages are highly likely to be needed, the messages are pushed to the user, the possibility that the user views the messages is high, the duration of the scenes is likely to be long, and the number of times of viewing the messages is likely to be large. Therefore, the user can preset specific scenes for message pushing according to needs, and store the scenes as preset scene categories. When the electronic equipment identifies that the current scene type belongs to the preset scene type, the message is pushed by adopting the message pushing mechanism of the scheme; and if the current application does not belong to the preset scene category, continuing executing the subsequent pushing step according to the current default message pushing mechanism of each application.
Specifically, before the to-be-pushed message list of the target user is obtained, the method further includes the following steps: judging whether the scene category belongs to a preset scene category or not; if yes, go to step 102.
103, determining a screening rule corresponding to the scene category, acquiring a target message from the message list to be pushed to a user according to the screening rule at intervals of a first preset time length in the scene category, and iteratively updating the screening rule according to the reading condition of the target message by the user until the reading condition meets a preset condition.
After the scene type is determined and the message list to be pushed is obtained, the message is pushed based on a time difference algorithm. The specific logic is as follows: in an initial state, when a user reading condition without feedback can be used, one or more target messages are selected from a message list to be pushed to the user according to a default screening rule, wherein the number of the target messages selected each time can be preset by the user, for example, is set to 3-10. The default screening rule may be randomly selected, or a greedy algorithm may be used as the default rule in the initial state. The selected target information is pushed to the user, the screening rule is updated iteratively according to the reading condition of the user on the pushed target information in the scene category, and due to the fact that the information pushed to the user in the first few times in the scene category is not strong in pertinence and the pushing times are increased, the screening rule can be optimized according to the fed-back reading condition of the user, and the reading condition meets the preset condition.
Fig. 4 is a schematic flowchart of a third method for pushing a message according to an embodiment of the present application.
In some embodiments, step 103 includes the steps of:
1033, after the target message is pushed to a first preset time of the user, acquiring the reading condition of the user on the target message in the scene type;
if the reading condition meets the preset condition, the process returns to step 1032.
It should be noted that, since the user activity may change, referring to fig. 5, a scene category diagram in the message pushing method provided in the embodiment of the present application is shown. Assume that the user is identified as being in scene category a at time T1, the user is identified as being in scene category B at time T2, and the user is again in scene category a at time T3, that is, the scene category of the user is changed. The scheme of the application is to perform message pushing according to the scene category, and can be applied to message pushing in such a discontinuous scene. When the scene type is changed, the related data of the scene type before the change is only needed to be stored, and when the scene type is changed again, the message pushing is continued to be performed on the scene type according to the stored related data.
Therefore, referring to fig. 5, at time T2, when it is detected that the scene type changes, the current screening rule of the scene type a and the reading condition returned by the user are stored, and when it is detected that the user enters the scene type a again, step 1031 is executed, that is, the stored current screening rule corresponding to the scene type a is obtained, and the target message is selected from the message list to be pushed according to the screening rule for pushing.
And after the target message is pushed to a first preset time of a user, acquiring the reading condition of the user on the target message under the scene type. Detecting the situation of reading the messages by the user within a first preset time period from the completion of the current push to the next push, wherein the reading situation mainly comprises which messages in the pushed target messages are read by the user and which messages are not read by the user, and judging whether the reading situation meets a preset condition or not, wherein if the ratio of the number of the read messages to the total number of the pushed target messages is greater than a first preset threshold value, the reading situation is judged to meet the preset condition; and if the ratio of the number of the read messages to the total number of the pushed target messages is not greater than the first preset threshold, judging that the reading condition does not meet the preset condition. For example, the first preset threshold is any value of 80% to 90%. The first preset threshold is set to be a value smaller than 100%, so that the algorithm of the scheme can have certain exploration capacity, and on the premise that the information which accords with the interest is recommended to the user, some information which is unknown but possibly interested by the user is still pushed to the user, namely, a part of information is needed to bring diversity and freshness to the user.
The read message is the target message read by the user in the scene category. Since the scene type when the user reads the message may not be the same as the scene type when the read message is pushed, for example, as shown in fig. 5, a message corresponding to the scene type a is pushed during the period of T1-T2, but the user does not read until the period of T2-T3, such a situation cannot actually help to improve the filtering rule, and therefore, when recording the reading situation, such data is recorded as noise data and not as valid data of the read message.
When the reading condition meets the preset condition, the target information selected according to the current screening rule can be judged to be in accordance with the requirements of the user to a great extent, and then the current screening rule is kept. And if the reading condition does not meet the preset condition, optimizing the screening rule according to the fed-back reading condition.
For example, in some embodiments, the step of updating the filtering rule according to the reading condition comprises: calculating the ratio of the number of the read messages to the total number of the pushed target messages according to the reading condition, wherein the read messages are the target messages read by the user under the scene category; and comparing the proportion pushed this time with the proportion pushed last time, and updating the screening rule according to the comparison result.
The step of comparing the proportion pushed this time with the proportion pushed last time and updating the screening rule according to the comparison result comprises the following steps: comparing the proportion pushed this time with the proportion pushed last time; if the proportion pushed this time is greater than the proportion pushed last time, the push strategy is strengthened, more messages similar to the content of the message opened by the user are pushed, namely a first screening rule is taken as the current screening rule, wherein the first screening rule is as follows: and acquiring a message similar to the read message pushed last time from the message list to be pushed as a target message pushed at this time. If the proportion of the current push is not larger than the proportion of the last push, trying more different messages, and pushing some messages which are dissimilar to the content of the current push, namely taking a second screening rule as the current screening rule, wherein the second screening rule is as follows: and acquiring a message which is dissimilar to the target message pushed last time from the message list to be pushed as the target message pushed this time. And repeating the iteration according to the steps, when the ratio of the number of the read messages in the total number of the pushed target messages is larger than a first preset threshold value, such as 90%, keeping the current screening rule unchanged, and selecting the target messages according to the same rule when pushing next time.
Furthermore, it is understood that the same message is not repeatedly pushed in the same pushing period, for example, one pushing period is one day, and the same message is not repeatedly pushed in the same day.
Further, in some embodiments, the step of obtaining a target message from the message list to be pushed and pushing the target message to a user according to the filtering rule includes:
if the current screening rule is a first screening rule, calculating the similarity between the message in the message list to be pushed and the read message pushed last time; according to the first screening rule, obtaining a message with similarity between the message to be pushed and the read message pushed last time and larger than a second preset threshold value from the message list to be pushed, taking the message as a target message pushed this time, and pushing the message to a user;
if the current screening rule is a second screening rule, calculating the similarity between the message in the message list to be pushed and the target message pushed last time; and according to the second screening rule, obtaining a message of which the similarity with the target information pushed last time is smaller than a third preset threshold value from the message list to be pushed, using the message as the target message pushed this time, and pushing the message to the user, wherein the third preset threshold value is smaller than the second preset threshold value.
Or, in some embodiments, the step of obtaining, according to the filtering rule, a target message from the message list to be pushed and pushing the target message to the user includes:
if the current screening rule is a first screening rule, calculating the similarity between the message in the message list to be pushed and the read message pushed last time; according to the first screening rule, obtaining a first preset number of messages with the maximum similarity with the read messages pushed last time from the message list to be pushed, taking the messages as target messages pushed this time, and pushing the messages to a user;
if the current screening rule is a second screening rule, calculating the similarity between the message in the message list to be pushed and the target message pushed last time; and acquiring a second preset number of messages with the minimum similarity to the target information pushed last time from the message list to be pushed according to the second screening rule, taking the messages as the target messages pushed this time, and pushing the messages to the user.
The method for calculating the similarity between the messages comprises the following steps: and acquiring word vectors of the message content, calculating cosine similarity between the word vectors, and taking the cosine similarity obtained by calculation as the similarity between the messages.
In particular implementation, the present application is not limited by the execution sequence of the described steps, and some steps may be performed in other sequences or simultaneously without conflict.
As can be seen from the above, the message pushing method provided in the embodiment of the present application collects panoramic data of a target user, identifies a scene category where the target user is located according to the panoramic data, obtains a message list to be pushed of a reference user in the scene category, obtains a target message from the message list to be pushed at intervals of a first preset duration, and pushes the target message to the user, and iteratively updates a screening rule according to a reading condition of the user, so that the target message selected during the pushing is targeted and can meet interest preferences of the user.
In one embodiment, a message pushing device is also provided. Referring to fig. 6, fig. 6 is a schematic structural diagram of a message pushing device 400 according to an embodiment of the present application. The message pushing apparatus 400 is applied to an electronic device, and the message pushing apparatus 400 includes a scene recognition module 401, a data obtaining module 402, and a message pushing module 403, as follows:
a scene identification module 401, configured to collect panoramic data of a target user, and identify a scene category of the target user according to the panoramic data;
a data obtaining module 402, configured to obtain a to-be-pushed message list of the target user;
the message pushing module 403 is configured to determine a filtering rule corresponding to the scene category, acquire, at a first preset time interval in the scene category, a target message from the message list to be pushed according to the filtering rule, and push the target message to a user, and update the filtering rule iteratively according to a reading condition of the target message by the user until the reading condition meets a preset condition.
In some embodiments, the data acquisition module 402 is further configured to: acquiring a first message list of the target user and a second message list of a reference user of the target user; and generating the message list to be pushed according to the first message list and the second message list.
In some embodiments, the message pushing device 400 further comprises a user selection module configured to: classifying users in a preset user set according to a preset classification algorithm; and determining the user category to which the target user belongs, and taking other users except the target user in the user category as the reference users of the target user.
In some embodiments, the scene recognition module 401 is further configured to: judging whether the scene category belongs to a preset scene category or not; the data obtaining module 402 is further configured to obtain a to-be-pushed message list of the target user if the scene category belongs to a preset scene category.
In some embodiments, the message pushing module 403 is further configured to: determining a screening rule corresponding to the scene category;
acquiring a target message from the message list to be pushed according to the screening rule and pushing the target message to a user;
after the target message is pushed to a first preset time of a user, acquiring the reading condition of the user on the target message under the scene category;
if the reading condition does not meet the preset condition, updating the screening rule according to the reading condition, and acquiring a target message from the message list to be pushed according to the screening rule and pushing the target message to a user based on the updated screening rule;
and if the reading condition meets a preset condition, acquiring a target message from the message list to be pushed according to the screening rule and pushing the target message to a user.
In some embodiments, the message pushing module 403 is further configured to: calculating the ratio of the number of the read messages to the total number of the pushed target messages according to the reading condition, wherein the read messages are the target messages read by the user under the scene category;
and comparing the proportion pushed this time with the proportion pushed last time, and updating the screening rule according to the comparison result.
In some embodiments, the message pushing module 403 is further configured to: comparing the proportion pushed this time with the proportion pushed last time;
if the proportion pushed this time is larger than the proportion pushed last time, taking a first screening rule as the current screening rule, wherein the first screening rule is as follows: acquiring a message similar to the read message pushed last time from the message list to be pushed as a target message pushed this time;
if the proportion of the current push is not larger than the proportion of the last push, taking a second screening rule as the current screening rule, wherein the second screening rule is as follows: and acquiring a message which is dissimilar to the target message pushed last time from the message list to be pushed as the target message pushed this time.
In some embodiments, the message pushing module 403 is further configured to: judging whether the reading condition meets the preset condition or not, wherein if the ratio of the number of the read messages to the total number of the pushed target messages is larger than a first preset threshold value, the reading condition is judged to meet the preset condition; and if the ratio of the number of the read messages to the total number of the pushed target messages is not greater than the first preset threshold, judging that the reading condition does not meet the preset condition.
In specific implementation, the above modules may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and specific implementation of the above modules may refer to the foregoing method embodiments, which are not described herein again.
As can be seen from the above, the message pushing device provided in the embodiment of the present application collects panoramic data of a target user, identifies a scene category where the target user is located according to the panoramic data, acquires a to-be-pushed message list of a reference user in the scene category, acquires a target message from the to-be-pushed message list at intervals of a first preset duration, and pushes the target message to the user, and iteratively updates a screening rule according to a reading condition of the user, so that the target message selected during the pushing is more targeted and can meet interest preferences of the user.
The embodiment of the application further provides the electronic equipment. The electronic device can be a smart phone, a tablet computer and the like. As shown in fig. 7, fig. 7 is a schematic view of a first structure of an electronic device according to an embodiment of the present application. The electronic device 300 comprises a processor 301 and a memory 302. The processor 301 is electrically connected to the memory 302.
The processor 301 is a control center of the electronic device 300, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or calling a computer program stored in the memory 302 and calling data stored in the memory 302, thereby performing overall monitoring of the electronic device.
In this embodiment, the processor 301 in the electronic device 300 loads instructions corresponding to one or more processes of the computer program into the memory 302 according to the following steps, and the processor 301 runs the computer program stored in the memory 302, so as to implement various functions:
collecting panoramic data of a target user, and identifying the scene type of the target user according to the panoramic data;
acquiring a message list to be pushed of the target user;
and determining a screening rule corresponding to the scene category, acquiring a target message from the message list to be pushed to a user according to the screening rule at intervals of a first preset time under the scene category, and iteratively updating the screening rule according to the reading condition of the target message by the user until the reading condition meets a preset condition.
In some embodiments, when obtaining the list of messages to be pushed of the target user, the processor 301 performs the following steps:
acquiring a first message list of the target user and a second message list of a reference user of the target user;
and generating the message list to be pushed according to the first message list and the second message list.
In some embodiments, before obtaining the list of messages to be pushed of the target user, the processor 301 performs the following steps:
classifying users in a preset user set according to a preset classification algorithm;
and determining the user category to which the target user belongs, and taking other users except the target user in the user category as the reference users of the target user.
In some embodiments, before obtaining the list of messages to be pushed of the target user, the processor 301 performs the following steps:
judging whether the scene category belongs to a preset scene category or not;
and if so, executing the step of acquiring the message list to be pushed of the target user.
In some embodiments, a screening rule corresponding to the scene category is determined, in the scene category, every first preset time interval, a target message is obtained from the message list to be pushed according to the screening rule and pushed to a user, and the screening rule is iteratively updated according to a reading condition of the target message by the user, until the reading condition meets a preset condition, the processor 301 performs the following steps:
determining a screening rule corresponding to the scene category;
acquiring a target message from the message list to be pushed according to the screening rule and pushing the target message to a user;
after the target message is pushed to a first preset time of a user, acquiring the reading condition of the user on the target message under the scene category;
if the reading condition does not meet the preset condition, updating the screening rule according to the reading condition, and returning to execute the step of acquiring the target message from the message list to be pushed according to the screening rule and pushing the target message to the user based on the updated screening rule;
and if the reading condition meets the preset condition, returning to execute the step of acquiring the target message from the message list to be pushed according to the screening rule and pushing the target message to the user.
In some embodiments, when updating the filtering rule according to the reading condition, the processor 301 performs the following steps:
calculating the ratio of the number of the read messages to the total number of the pushed target messages according to the reading condition, wherein the read messages are the target messages read by the user under the scene category;
and comparing the proportion pushed this time with the proportion pushed last time, and updating the screening rule according to the comparison result.
In some embodiments, comparing the ratio of the current push with the ratio of the last push, and when updating the filtering rule according to the comparison result, the processor 301 performs the following steps:
comparing the proportion pushed this time with the proportion pushed last time;
if the proportion pushed this time is larger than the proportion pushed last time, taking a first screening rule as the current screening rule, wherein the first screening rule is as follows: acquiring a message similar to the read message pushed last time from the message list to be pushed as a target message pushed this time;
if the proportion of the current push is not larger than the proportion of the last push, taking a second screening rule as the current screening rule, wherein the second screening rule is as follows: and acquiring a message which is dissimilar to the target message pushed last time from the message list to be pushed as the target message pushed this time.
In some embodiments, after the target message is pushed to the user for the first preset time period, when the reading condition of the user on the target message in the scene category is obtained, the processor 301 performs the following steps:
judging whether the reading condition meets the preset condition or not, wherein if the ratio of the number of the read messages to the total number of the pushed target messages is larger than a first preset threshold value, the reading condition is judged to meet the preset condition; and if the ratio of the number of the read messages to the total number of the pushed target messages is not greater than the first preset threshold, judging that the reading condition does not meet the preset condition.
In some embodiments, as shown in fig. 8, fig. 8 is a second schematic structural diagram of an electronic device provided in the embodiments of the present application. The electronic device 300 further includes: radio frequency circuit 303, display screen 304, control circuit 305, input unit 306, audio circuit 307, sensor 308, and power supply 309. The processor 301 is electrically connected to the rf circuit 303, the display 304, the control circuit 305, the input unit 306, the audio circuit 307, the sensor 308, and the power source 309, respectively.
The radio frequency circuit 303 is used for transceiving radio frequency signals to communicate with a network device or other electronic devices through wireless communication.
The display screen 304 may be used to display information entered by or provided to the user as well as various graphical user interfaces of the electronic device, which may be comprised of images, text, icons, video, and any combination thereof.
The control circuit 305 is electrically connected to the display screen 304, and is used for controlling the display screen 304 to display information.
The input unit 306 may be used to receive input numbers, character information, or user characteristic information (e.g., fingerprint), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. The input unit 306 may include a fingerprint recognition module.
The sensor 308 is used to collect external environmental information. The sensor 308 may include one or more of an ambient light sensor, an acceleration sensor, a gyroscope, and the like.
The power supply 309 is used to power the various components of the electronic device 300. In some embodiments, the power source 309 may be logically coupled to the processor 301 through a power management system, such that functions of managing charging, discharging, and power consumption are performed through the power management system.
Although not shown in fig. 8, the electronic device 300 may further include a camera, a bluetooth module, and the like, which are not described in detail herein.
Therefore, the electronic device collects the panoramic data of the target user, identifies the scene type of the target user according to the panoramic data, acquires the message list to be pushed of the reference user under the scene type, acquires the target message from the message list to be pushed at intervals of a first preset time and pushes the target message to the user, and iteratively updates the screening rule according to the reading condition of the user, so that the target message selected in the pushing process is more pertinent and can meet the interest preference of the user.
An embodiment of the present application further provides a storage medium, where a computer program is stored in the storage medium, and when the computer program runs on a computer, the computer executes the message pushing method according to any of the above embodiments.
It should be noted that, a person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by the relevant hardware instructed by a computer program, and the computer program can be stored in a computer readable storage medium, which can include but is not limited to: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, and the like.
In addition, the terms "first", "second", and "third", etc. in this application are used to distinguish different objects, and are not used to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to only those steps or modules recited, but rather, some embodiments include additional steps or modules not recited, or inherent to such process, method, article, or apparatus.
The message pushing method, the message pushing device, the storage medium and the electronic device provided in the embodiments of the present application are described in detail above. The principle and the implementation of the present application are explained herein by applying specific examples, and the above description of the embodiments is only used to help understand the method and the core idea of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. A message pushing method, comprising:
acquiring panoramic data of a target user, and identifying the scene type of the target user according to the panoramic data, wherein the panoramic data comprises terminal state data, sensor data and terminal use data;
acquiring a to-be-pushed message list of the target user, wherein the acquiring comprises the following steps: acquiring a first message list of the target user and a second message list of a reference user of the target user; generating the message list to be pushed according to the first message list and the second message list, and adding a push message received by an application in real time into the message list to be pushed;
determining a screening rule corresponding to the scene category, acquiring a target message from the message list to be pushed according to the screening rule at intervals of a first preset time length under the scene category, pushing the target message to the target user, and updating the screening rule in an iterative manner according to the reading condition of the target message by the target user until the reading condition meets a preset condition.
2. The message pushing method of claim 1, wherein the step of obtaining the list of messages to be pushed of the target user is preceded by the method further comprising:
classifying users in a preset user set according to a preset classification algorithm;
and determining the user category to which the target user belongs, and taking other users except the target user in the user category as the reference users of the target user.
3. The message pushing method of claim 1, wherein the step of obtaining the list of messages to be pushed of the target user is preceded by the method further comprising:
judging whether the scene category belongs to a preset scene category or not;
and if so, executing the step of acquiring the message list to be pushed of the target user.
4. The message pushing method according to any one of claims 1 to 3, wherein the step of determining the filtering rule corresponding to the scene category, acquiring a target message from the message list to be pushed to the target user according to the filtering rule at intervals of a first preset duration in the scene category, and iteratively updating the filtering rule according to a reading condition of the target message by the target user until the reading condition meets a preset condition includes:
determining a screening rule corresponding to the scene category;
acquiring a target message from the message list to be pushed according to the screening rule and pushing the target message to the target user;
after the target message is pushed to a first preset time of the target user, acquiring the reading condition of the target user on the target message under the scene category;
if the reading condition does not meet the preset condition, updating the screening rule according to the reading condition, and returning to execute the step of acquiring the target message from the message list to be pushed according to the screening rule and pushing the target message to the target user based on the updated screening rule;
and if the reading condition meets a preset condition, returning to execute the step of acquiring the target message from the message list to be pushed according to the screening rule and pushing the target message to the target user.
5. The message pushing method as claimed in claim 4, wherein the step of updating the filtering rule according to the reading condition comprises:
calculating the ratio of the number of read messages to the total number of pushed target messages according to the reading condition, wherein the read messages are the target messages read by the target user under the scene category;
and comparing the proportion pushed this time with the proportion pushed last time, and updating the screening rule according to the comparison result.
6. The message pushing method according to claim 5, wherein the step of comparing the proportion of the current pushing with the proportion of the last pushing and updating the screening rule according to the comparison result comprises:
comparing the proportion pushed this time with the proportion pushed last time;
if the proportion pushed this time is larger than the proportion pushed last time, taking a first screening rule as the current screening rule, wherein the first screening rule is as follows: acquiring a message similar to the read message pushed last time from the message list to be pushed as a target message pushed this time;
if the proportion of the current push is not larger than the proportion of the last push, taking a second screening rule as the current screening rule, wherein the second screening rule is as follows: and acquiring a message which is dissimilar to the target message pushed last time from the message list to be pushed as the target message pushed this time.
7. The message pushing method according to claim 4, wherein after the step of obtaining the reading condition of the target user for the target message in the scene category after the step of pushing the target message to the target user for the first preset time period, the method further comprises the steps of:
and judging whether the reading condition meets the preset condition or not, wherein if the ratio of the number of the read messages to the total number of the pushed target messages is greater than a first preset threshold value, the reading condition is judged to meet the preset condition, and if the ratio of the number of the read messages to the total number of the pushed target messages is not greater than the first preset threshold value, the reading condition is judged not to meet the preset condition.
8. A message push apparatus, comprising:
the system comprises a scene identification module, a scene identification module and a scene identification module, wherein the scene identification module is used for collecting panoramic data of a target user and identifying the scene type of the target user according to the panoramic data, and the panoramic data comprises terminal state data, sensor data and terminal use data;
the data acquisition module is used for acquiring a message list to be pushed of the target user;
the message pushing module is used for determining a screening rule corresponding to the scene category, acquiring a target message from the message list to be pushed at intervals of a first preset time length under the scene category according to the screening rule, pushing the target message to the target user, and updating the screening rule in an iterative manner according to the reading condition of the target message by the target user until the reading condition meets a preset condition;
the data acquisition module is further configured to: acquiring a first message list of the target user and a second message list of a reference user of the target user; and generating the message list to be pushed according to the first message list and the second message list, and adding the push message received by the application in real time into the message list to be pushed.
9. A storage medium having stored thereon a computer program, characterized in that, when the computer program runs on a computer, it causes the computer to execute a message pushing method according to any one of claims 1 to 7.
10. An electronic device comprising a processor and a memory, the memory storing a computer program, wherein the processor is configured to execute the message push method according to any one of claims 1 to 7 by calling the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910282118.0A CN111800445B (en) | 2019-04-09 | 2019-04-09 | Message pushing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910282118.0A CN111800445B (en) | 2019-04-09 | 2019-04-09 | Message pushing method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111800445A CN111800445A (en) | 2020-10-20 |
| CN111800445B true CN111800445B (en) | 2023-02-28 |
Family
ID=72805315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910282118.0A Active CN111800445B (en) | 2019-04-09 | 2019-04-09 | Message pushing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111800445B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112804309B (en) * | 2020-12-31 | 2022-09-20 | 中国人寿保险股份有限公司上海数据中心 | Multicast pushing method |
| CN114979256A (en) * | 2022-05-19 | 2022-08-30 | 北京京东乾石科技有限公司 | Message pushing method and device, electronic equipment and computer readable medium |
| CN115379005A (en) * | 2022-08-11 | 2022-11-22 | 支付宝(杭州)信息技术有限公司 | Message processing method and device, storage medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033419A (en) * | 2015-03-10 | 2016-10-19 | 深圳市腾讯计算机系统有限公司 | An information real-time push method, device and system |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN108765033A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Transmitting advertisement information method and apparatus, storage medium, electronic equipment |
| CN108763519A (en) * | 2018-05-30 | 2018-11-06 | 深圳市零度智控科技有限公司 | The recommendation method, apparatus and readable storage medium storing program for executing of reading |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104426934A (en) * | 2013-08-24 | 2015-03-18 | 上海莞东拿信息科技有限公司 | New information pushing method for tourism mobile terminal |
| CN104780193B (en) * | 2014-01-15 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Information-pushing method, device and system |
-
2019
- 2019-04-09 CN CN201910282118.0A patent/CN111800445B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106033419A (en) * | 2015-03-10 | 2016-10-19 | 深圳市腾讯计算机系统有限公司 | An information real-time push method, device and system |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN108763519A (en) * | 2018-05-30 | 2018-11-06 | 深圳市零度智控科技有限公司 | The recommendation method, apparatus and readable storage medium storing program for executing of reading |
| CN108765033A (en) * | 2018-06-08 | 2018-11-06 | Oppo广东移动通信有限公司 | Transmitting advertisement information method and apparatus, storage medium, electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111800445A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108197327B (en) | Song recommendation method, device and storage medium | |
| CN111800445B (en) | Message pushing method and device, storage medium and electronic equipment | |
| CN110147467A (en) | A kind of generation method, device, mobile terminal and the storage medium of text description | |
| CN111800331A (en) | Notification message pushing method and device, storage medium and electronic equipment | |
| CN111797288A (en) | Data screening method and device, storage medium and electronic equipment | |
| CN111611490A (en) | Resource searching method, device, equipment and storage medium | |
| CN111491123A (en) | Video background processing method and device and electronic equipment | |
| CN111797861A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN111797076A (en) | Data cleaning method and device, storage medium and electronic equipment | |
| CN111797851A (en) | Feature extraction method and device, storage medium and electronic equipment | |
| CN111797148A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN111796926A (en) | Instruction execution method and device, storage medium and electronic equipment | |
| CN111797874B (en) | Behavior prediction method and device, storage medium and electronic equipment | |
| CN108052506A (en) | Natural language processing method, apparatus, storage medium and electronic equipment | |
| CN111797849A (en) | User activity identification method and device, storage medium and electronic equipment | |
| CN111797261A (en) | Feature extraction method and device, storage medium and electronic equipment | |
| CN112948763B (en) | Piece quantity prediction method and device, electronic equipment and storage medium | |
| CN111797860B (en) | Feature extraction method and device, storage medium and electronic equipment | |
| CN109635153B (en) | Migration path generation method, device and storage medium | |
| CN108536343B (en) | Control display method and device, terminal and storage medium | |
| CN111797655A (en) | User activity identification method and device, storage medium and electronic equipment | |
| CN112232890A (en) | Data processing method, device, equipment and storage medium | |
| CN111797127A (en) | Time series data segmentation method and device, storage medium and electronic equipment | |
| CN111797227A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| CN111797877B (en) | Data processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |