CN113110942A - Message distribution method and device, computer equipment and storage medium - Google Patents
Message distribution method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113110942A CN113110942A CN202110327011.0A CN202110327011A CN113110942A CN 113110942 A CN113110942 A CN 113110942A CN 202110327011 A CN202110327011 A CN 202110327011A CN 113110942 A CN113110942 A CN 113110942A
- Authority
- CN
- China
- Prior art keywords
- user
- documents
- users
- message distribution
- message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000004590 computer program Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims 1
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/542—Event management; Broadcasting; Multicasting; Notifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the specification provides a message distribution method, which comprises the steps of obtaining a plurality of documents; the plurality of files are generated based on the characteristics of preset dimensions and the same message reminding scene; inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents; and predicting the documentations matched with each user in the plurality of users through the message distribution model, and respectively distributing reminding messages of the documentations matched with the users to each user. The embodiment of the specification also provides a message distribution device, a computer device and a computer readable storage medium.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a message distribution method, a message distribution apparatus, a computer device, and a computer-readable storage medium.
Background
Software application updates are dynamic frequently, but users typically do not frequently open software applications and therefore cannot pay attention to dynamic information updated on the software applications in time. Currently, software applications often send a reminding message to a user when dynamic update exists, for example, some modules installed on software send a reminding message to a user when a specific dynamic state is updated.
The messages like this are usually sent to the user by matching with a fixed file, and if the popularity of the file is not high, the content prompted by the reminding message cannot be checked in time or the reminding message is forgotten to be checked later, so that the efficiency of reaching the reminding message is low.
Disclosure of Invention
In a first aspect, an embodiment of the present specification provides a message distribution method, where the method includes:
acquiring a plurality of documentations; the plurality of files are generated based on the characteristics of preset dimensions and the same message reminding scene;
inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and predicting the documentations matched with each user in the plurality of users through the message distribution model, and respectively distributing reminding messages of the documentations matched with the users to each user.
In a second aspect, an embodiment of the present specification provides a message distribution apparatus, including:
the file acquisition unit is used for acquiring a plurality of files; wherein the plurality of scenarios are generated based on features of a preset dimension;
the information input unit is used for inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and the reminding message distribution unit is used for predicting the file matched with each user in the plurality of users through the message distribution model and respectively distributing reminding messages of the file matched with the user to each user.
In a third aspect, an embodiment of the present specification provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the following steps when executing the program:
acquiring a plurality of documentations; wherein the plurality of scenarios are generated based on features of a preset dimension;
inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and predicting the documentations matched with each user in the plurality of users through the message distribution model, and respectively distributing reminding messages of the documentations matched with the users to each user.
In a fourth aspect, the embodiments of the present specification provide a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method according to any of the embodiments described above.
According to the message distribution method provided by the embodiment of the specification, under the same message reminding scene, the reminding messages matched with the users are respectively sent to the users through the pre-trained message distribution model, wherein the reminding messages matched with the users can be matched with the most preferable documents of the users. Therefore, the reminding message is prompted to be processed by the user at the first time when the reminding message is received, and the touch efficiency of the sent reminding message is effectively improved. In addition, for the same message reminding scene, for example, the same software application updates the same dynamic message reminding scene, based on the characteristics of the preset dimensionality, multiple patterns of documents can be quickly generated to meet the preference requirements of a large number of users.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of embodiments of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the embodiments of the specification and, together with the description, serve to explain the principles of the embodiments of the specification.
Fig. 1 is a flowchart illustrating a message distribution method according to an exemplary embodiment of the present specification.
FIG. 2 is a flow chart illustrating one method of obtaining training data in accordance with an exemplary embodiment of the present disclosure.
FIG. 3 is another flow chart illustrating the acquisition of training data in an exemplary embodiment of the present description.
FIG. 4 is a flow chart illustrating training of a message distribution model in an exemplary embodiment of the present description.
Fig. 5 is a link diagram of a distribution document shown in an exemplary embodiment of the present description.
Fig. 6 is a diagram of a trained and predicted link shown in an exemplary embodiment of the present description.
Fig. 7 is a schematic diagram of a message distribution apparatus according to an exemplary embodiment of the present specification.
Fig. 8 is a schematic diagram of a hardware structure of an AI cloud service platform according to an exemplary embodiment of the present specification.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the examples of this specification. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the embodiments of the specification, as detailed in the appended claims.
The terminology used in the embodiments of the present specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the present specification. As used in the specification examples and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality.
It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present specification to describe various information, the information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the embodiments herein. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In order to make the technical solutions in the embodiments of the present disclosure better understood and make the above objects, features and advantages of the embodiments of the present disclosure more obvious and understandable to those skilled in the art, the technical solutions in the embodiments of the present disclosure are described in further detail below with reference to the accompanying drawings.
In the embodiment of the present specification, a software application refers to an application program that can be installed on a device and can run in a system on which the device is mounted. The reminding message may be a message sent by the software application to the user when the software application is updated dynamically, and is used for reminding the user to open the software application to view the dynamic state, for example, the reminding message may be a short message, a push message of the software application, or the like. The text of the reminder message refers to the content used to compose the reminder message, and may include, for example, the header content, the body content, and the like of the message.
The dynamic attention of the user to the software application update is related to the dynamic content information, and is also related to the file of the reminder message received by the user, for example, in the case that the dynamic state of the software update does not include the content information concerned by the user, when the user receives the reminder message corresponding to the dynamic state, the user may still open the related software application to view the updated dynamic state immediately due to the interest in the file of the reminder message. Therefore, under the same message reminding scene, if the reminding message corresponds to different users and the interesting patterns of the users can be matched in the reminding message respectively, the touch efficiency of the reminding message can be improved to a certain extent, and the users can be prompted to pay attention to the dynamic information updated by the software application in time.
Based on the above idea, an exemplary embodiment of the present specification provides a message distribution method, and referring to fig. 1, fig. 1 is a flowchart of a message distribution method shown in an exemplary embodiment of the present specification, the method including the following steps:
s101, acquiring a plurality of documentaries; the plurality of files are generated based on the characteristics of preset dimensions and the same message reminding scene;
s102, inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
s103, predicting the documentations matched with the users in the plurality of users through the message distribution model, and distributing reminding messages of the documentations matched with the users to the users respectively.
According to the message distribution method provided by the embodiment of the specification, the reminding messages matched with the users can be respectively sent to the users under the same message reminding scene, for example, when the same software application updates the same dynamic state, wherein the reminding messages sent to different users are respectively matched with the most preferable documents of the users. Therefore, the reminding message is prompted to be processed by the user at the first time when the reminding message is received, and the touch efficiency of the sent reminding message is effectively improved. In addition, for the same message reminding scene, for example, the same software application updates the same dynamic message reminding scene, based on the characteristics of the preset dimensionality, multiple patterns of documents can be quickly generated to meet the preference requirements of a large number of users.
The above-described message distribution method is further described below. The preset dimension in S101 may include one or more dimensions, and a dimension may be understood as a core element referred to in generating a document, in colloquial, that is, the content of the generated document is considered from a certain aspect. The features of the preset dimension can be understood as features that the core element referred to specifically can include, and for clarity, some examples of the features of the preset dimension are given below:
in an embodiment, the preset dimension may be a dimension of a language sender of the document, that is, the content expressed by the document may be considered from the level of which language sender the document should adopt when generating the document, for example, the adopted language sender may be a content subject, a user himself, a third party, and the like, which is not limited herein. The corresponding feature of the preset dimension at this time may be a feature of a speaker used for characterizing the copy, that is, the feature of the preset dimension may be a content subject, a user himself, a third party, or the like. A practical example is presented to illustrate how multiple documents can be generated based on the characteristics of the speaker used to characterize the document and the same message alert scenario. At present, some applications can promote the development of services by setting up some modules for breeding virtual plants, raising virtual pets and the like, taking an example that a user opens a module for virtual pet raising on some application, if the user raises a pet chick in the opened virtual pet raising module and a certain time has elapsed since the user last fed the pet chick, the application can send a reminding message to the user to remind the user to enter the application for feeding, at this time, a plurality of documents can be generated based on different characteristics of a speaker for characterizing the documents and a current message reminding scene, for example, when the characteristics of the speaker for characterizing the documents are a main content body, that is, when the pet chick is used as the speaker to remind the pet chick from the perspective of the pet chick, the generated documents can include that the owner quickly feeds me; or when the characteristic of the speaker used for representing the file is a third party, namely the third party is used as the speaker to remind through the angle of the third party, the generated file can comprise that the chicken hungry goes to the feeding bar, and the like. Multiple styles of documents may be generated to meet the preferences of different types of users by basing the characteristics of the speakers used to characterize the documents.
In one embodiment, the preset dimension may also be a keyword dimension of the document, that is, the content expressed by the document may be considered from the aspect of what kind of keywords should be used in generating the document, where the used keywords may be keywords capable of driving the emotion of the user, for example, the used keywords may be errands, achievements, authorizations, possessions, socializations, scarcity, losses, and the like, which is not limited thereto. The corresponding feature of the preset dimension at this time may be a feature of a keyword for characterizing the document, that is, the feature of the preset dimension may be the aforementioned errands, achievements, authorizations, possessions, socialization, scarcity, loss, unknown, and the like. The keyword may not necessarily be described in the document by a letter, and may be expressed by the entire content of the document. Multiple styles of documents may be generated to meet the preferences of different types of users by basing features on different keywords used to characterize the documents.
In some other embodiments, the preset dimension may also be a title information dimension of the document, that is, the construction of the document may be considered from the title content level of the document when the document is generated, and the feature of the corresponding preset dimension may be a feature for characterizing the title information of the document; or the preset dimension may also be a sentence pattern dimension of the document, that is, the construction of the document may be considered from the level of the sentence pattern that the document should adopt when generating the document, and the feature of the corresponding preset dimension may be a feature of the sentence pattern used for characterizing the document. The further possible predetermined dimensions and the characteristics of the corresponding predetermined dimensions are not further exhaustive here.
In the embodiment of the present specification, when a plurality of documents are generated based on the features of the preset dimensions, the plurality of documents may be based on different features of one preset dimension, for example, different features of one preset dimension among the above-mentioned preset dimensions; or may be based on different features of more than one preset dimension, for example, may be based on different features of more than one preset dimension mentioned above, or may be based on other possible preset dimensions than the above mentioned preset dimensions. By combining different features based on different preset dimensions, multiple styles of documents can be generated to meet the preferences of different types of users.
For the generated multiple styles of documents, documents matched with the user need to be determined. In the embodiment of the present specification, a document matching a user can be predicted by a pre-constructed model. Specifically, in S102, for the obtained multiple documents, the multiple documents and the feature information of multiple users of the reminder message to be sent may be input into a pre-trained message distribution model, and the message distribution model is used to predict the documents matched with the users. The message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents. The message distribution model can acquire the labels of the users according to the input characteristic information of the users, and predict the file matched with the input users according to the analysis result of click data in the training process.
The feature information of the user may be personal information of the user, and may include, for example, feature information representing an identity type of the user, feature information representing an interest and hobby type of the user, feature information representing a region type of the user, feature information representing an educational level of the user, and the like, and specifically, the feature information of the user may include one or more of an age, a region, an occupation, a gender, a scholarship, an access activity to a specific application, and the like of the user, which is not limited thereto. The feature information of the user may be acquired when the user registers the software application, or acquired by analyzing data generated by the software application used by the user daily, which is not limited.
The message distribution model of the embodiments of the present specification is further described below. The message distribution model in the embodiments of the present specification may be any one or a combination of multiple kinds of an xgboost (extreme Gradient Boosting) model, a DNN (Deep Neural Networks) model, a gbdt (Gradient Boosting Decision tree) + lr (logical regression) model, and the like. The message distribution model can be built based on various user characteristic information and various user tags, so that the built message distribution model can acquire the user tags corresponding to the characteristic information according to the input user characteristic information, and the user tags corresponding to the user are given to the user. In order to enable the constructed message distribution model to predict the file matched with the input user, the message distribution model can be further trained.
In one embodiment, the process of acquiring training data may be referred to fig. 2, and fig. 2 is a flowchart illustrating an exemplary embodiment of the present disclosure for acquiring training data, including the following steps:
s201, respectively sending the reminding message of each file in the plurality of files to a preset user group;
s202, acquiring characteristic information of users included in the preset user group and click data of the users on the plurality of files as training data.
It is understood that the plurality of documents stated in S201 correspond to the plurality of documents acquired in S101, which may be a plurality of documents generated in the same scene of the message alert according to the method provided in the previous embodiment, for being subsequently used as an input of the message distribution model in S102. The preset user group may be any user group, and the preset user group may be one or more. The method comprises the steps of sending a reminding message of each of a plurality of documents to a preset user group, and obtaining characteristic information of users included in the preset user group and click data of the plurality of documents by the users as training data. Wherein, the reminding messages of different documents can be simultaneously sent to the user; or in order to avoid that the user receives the reminding information of a plurality of different documents at the same time to cause trouble to the user, the reminding information of different documents can be sent to the user at different times respectively, for example, the reminding information of one document can be sent to the user every day, and the click data of a plurality of days is collected as the training data. The method provided by the embodiment can acquire one or more sets of training data for subsequent training of the message distribution model.
In another embodiment, the training data obtaining process can refer to fig. 3, and fig. 3 is a flowchart illustrating another method for obtaining training data according to an exemplary embodiment of the present disclosure, which includes the following steps:
s301, selecting a reminding message of each of the plurality of documents respectively and sending the reminding message to different preset user groups; the number of users of each preset user group is the same;
s302, obtaining the characteristic information of the users included in each preset user group and the click data of the users on the plurality of files as training data.
Similar to the previous embodiment, the plurality of documents stated in S301 correspond to the plurality of documents acquired in S101, which may be a plurality of documents generated under the same message reminding scene according to the method provided in the previous embodiment, for being subsequently used as an input of the message distribution model in S102. The method comprises the steps of selecting a reminding message of each pattern in a plurality of patterns and sending the reminding message to different preset user groups, and acquiring characteristic information of users included in each preset user group and click data of the users on the patterns as training data. In order to make the audience number of the reminding messages of each document consistent, the number of users of each preset user group in this embodiment may be the same, and it can be understood that, because the number of users included in the user group is large, the same may not require the number of users of each preset user group to be completely the same, and may be within a certain range, and may also ensure the reasonability of the training data. The method provided by the embodiment can acquire one or more sets of training data for subsequent training of the message distribution model.
Two embodiments for acquiring training data are provided above, and it is understood that the above is only an example and is not intended to be limiting, and how to acquire specific training data, a skilled person may select an acquisition mode according to actual needs.
The following describes a training process of the message distribution model, and takes the training data obtained in the foregoing embodiment as an example. Referring to fig. 4, fig. 4 is a flowchart illustrating a training process of a message distribution model according to an exemplary embodiment of the present disclosure, including the following steps:
s401, acquiring a user label of a user based on the characteristic information of the user included in a preset user group;
s402, determining the preference degree of the users under the user labels to the plurality of documents based on the click data of the users under the user labels to the plurality of documents.
In the training process of the message distribution model, the message distribution model can firstly acquire the input user tags of the users according to the input characteristic information of the users included in the preset user group, and further analyzes the click data of the users under the user tags on the plurality of documents to calculate the scores of the users under the user tags on the documents, so that the preference degree of the users under the user tags on the documents is acquired. And training and iterating the message distribution model based on one or more groups of training data, so that the message distribution model can more accurately predict the file matched with the user according to the characteristic information of the user.
In one embodiment, since there may be some documents with insufficient originality among the generated plurality of documents, such documents are difficult to obtain the favor of the user, in S101, for the obtained plurality of documents, documents with a click rate lower than a preset threshold value among the plurality of documents, that is, documents that the user will not click basically, may be screened out. The click rate of the documents may be obtained when the training data is obtained, and specifically, may be obtained when the generated documents are sent to a preset user group and the click data of the documents by the user is obtained.
The method described in the above embodiments of the present specification may be performed by a server, and in particular, may be performed by one or more platforms and/or one or more background servers that provide services for software application execution. Referring to fig. 5, fig. 5 is a link diagram of a distribution document shown in an exemplary embodiment of the present description. For the sake of simple expression, the following description directly refers to "put a document" as "a reminder message for distributing a document", in which a plurality of documents included in the document set 500 are put on the test platform 502 through the putting platform 501, the test platform 502 puts a plurality of documents on the preset user group 503 to test the sensitivity of users to each document, and sends click data of the documents fed back by the users and user characteristic information to the distribution server 504 to analyze the preferences of users with different user tags for the documents, and then puts documents matching the users to the global user group 505 facing the software application based on the analysis result.
The message distribution model of the present specification will be described further below from an algorithmic perspective, referring to fig. 6, where fig. 6 is a diagram of a trained and predicted link shown in an exemplary embodiment of the present specification. The message distribution model 601 obtains sample feature information 602 of a sample user, click data 604 of the sample user on a plurality of documents in the document set 603 is used as training data to complete a training process, user feature information 605 and the document set 603 of a user to send a reminding message are used as inputs of the message distribution model 601, the message distribution model 601 outputs a document 606 matched with the user based on the input user feature information 605 and the document set 603, and a device (such as a server) deploying the message distribution model 601 completes sending the reminding message of the matched document to the user.
It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.
An embodiment of the present specification further provides a message distribution apparatus, and referring to fig. 7, fig. 7 is a schematic diagram of a message distribution apparatus shown in an exemplary embodiment of the present specification, where the apparatus includes:
a document acquiring unit 701 configured to acquire a plurality of documents; wherein the plurality of scenarios are generated based on features of a preset dimension;
an information input unit 702, configured to input feature information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
a reminding message distributing unit 703, configured to predict, through the message distribution model, a document that matches each of the multiple users, and distribute a reminding message of the document that matches each of the users to each of the users.
In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present specification may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.
Embodiments of the present specification also provide a computer device, which at least includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method according to any of the foregoing embodiments when executing the program.
Fig. 8 is a schematic diagram illustrating a more specific hardware structure of an AI cloud service platform according to an embodiment of the present specification, where the device may include: a processor 801, a memory 802, an input/output interface 803, a communication interface 804, and a bus 805. Wherein the processor 801, the memory 802, the input/output interface 803 and the communication interface 804 are communicatively connected to each other within the device via a bus 805.
The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.
The Memory 802 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 802 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 802 and called to be executed by the processor 801.
The input/output interface 803 is used for connecting an input/output module to realize information input and output. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 804 is used for connecting a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 801, the memory 802, the input/output interface 803, the communication interface 804 and the bus 805, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The embodiments of the present specification also provide a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the method of any one of the foregoing embodiments.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
From the above description of the embodiments, it is clear to those skilled in the art that the embodiments of the present disclosure can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the embodiments of the present specification may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments of the present specification.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described apparatus embodiments are merely illustrative, and the modules described as separate components may or may not be physically separate, and the functions of the modules may be implemented in one or more software and/or hardware when implementing the embodiments of the present disclosure. And part or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing is only a specific embodiment of the embodiments of the present disclosure, and it should be noted that, for those skilled in the art, a plurality of modifications and decorations can be made without departing from the principle of the embodiments of the present disclosure, and these modifications and decorations should also be regarded as the protection scope of the embodiments of the present disclosure.
Claims (10)
1. A method of message distribution, the method comprising:
acquiring a plurality of documentations; the plurality of files are generated based on the characteristics of preset dimensions and the same message reminding scene;
inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and predicting the documentations matched with each user in the plurality of users through the message distribution model, and respectively distributing reminding messages of the documentations matched with the users to each user.
2. The method of claim 1, the feature of the preset dimension comprising at least one of:
the characteristics of the speaker for characterizing the file, the characteristics of the keywords for characterizing the file, the characteristics of the header information for characterizing the file, and the characteristics of the sentence pattern for characterizing the file.
3. The method of claim 1, the characteristic information of the user comprising at least one of:
age, location, occupation, gender, academic calendar, access liveness to a given application of the user.
4. The method of claim 1, the obtaining of the training data of the message distribution model comprising:
respectively sending the reminding message of each of the plurality of documents to a preset user group;
and acquiring characteristic information of the users included in the preset user group and click data of the users on the plurality of files as training data.
5. The method of claim 1, the obtaining of the training data of the message distribution model comprising:
selecting one reminding message of each of the plurality of documents respectively and sending the selected reminding message to different preset user groups; the number of users of each preset user group is the same;
and acquiring characteristic information of users included in each preset user group and click data of the users on the plurality of files as training data.
6. The method of claim 4 or 5, the training process of the message distribution model comprising:
acquiring a user label of the user based on the characteristic information of the user included in the preset user group;
and determining the preference degree of the user under each user tag to the plurality of documents based on the click data of the user under each user tag to the plurality of documents.
7. The method of claim 4 or 5, the obtaining a plurality of documents, comprising:
and screening out the documents of which the click rate is lower than a preset threshold value from the obtained plurality of documents.
8. A message distribution apparatus comprising:
the file acquisition unit is used for acquiring a plurality of files; wherein the plurality of scenarios are generated based on features of a preset dimension;
the information input unit is used for inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and the reminding message distribution unit is used for predicting the file matched with each user in the plurality of users through the message distribution model and respectively distributing reminding messages of the file matched with the user to each user.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps when executing the program of:
acquiring a plurality of documentations; wherein the plurality of scenarios are generated based on features of a preset dimension;
inputting the characteristic information of the plurality of documents and the plurality of users into a pre-trained message distribution model; the message distribution model is obtained by training based on the characteristic information of the sample user and the click data of the sample user on the plurality of documents;
and predicting the documentations matched with each user in the plurality of users through the message distribution model, and respectively distributing reminding messages of the documentations matched with the users to each user.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110327011.0A CN113110942A (en) | 2021-03-26 | 2021-03-26 | Message distribution method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110327011.0A CN113110942A (en) | 2021-03-26 | 2021-03-26 | Message distribution method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113110942A true CN113110942A (en) | 2021-07-13 |
Family
ID=76712426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110327011.0A Pending CN113110942A (en) | 2021-03-26 | 2021-03-26 | Message distribution method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113110942A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766580A (en) * | 2017-11-20 | 2018-03-06 | 北京奇虎科技有限公司 | The method for pushing and device of message |
| CN108563753A (en) * | 2018-04-16 | 2018-09-21 | 深圳壹账通智能科技有限公司 | Message pushes generation method, device and the computer readable storage medium of official documents and correspondence |
| CN110400166A (en) * | 2019-06-24 | 2019-11-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for selecting the official documents and correspondence pushed to target user |
| CN111125536A (en) * | 2019-12-30 | 2020-05-08 | 北京每日优鲜电子商务有限公司 | Information pushing method and device, computer equipment and storage medium |
-
2021
- 2021-03-26 CN CN202110327011.0A patent/CN113110942A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766580A (en) * | 2017-11-20 | 2018-03-06 | 北京奇虎科技有限公司 | The method for pushing and device of message |
| CN108563753A (en) * | 2018-04-16 | 2018-09-21 | 深圳壹账通智能科技有限公司 | Message pushes generation method, device and the computer readable storage medium of official documents and correspondence |
| CN110400166A (en) * | 2019-06-24 | 2019-11-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for selecting the official documents and correspondence pushed to target user |
| CN111125536A (en) * | 2019-12-30 | 2020-05-08 | 北京每日优鲜电子商务有限公司 | Information pushing method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhao et al. | User profiling from their use of smartphone applications: A survey | |
| CN105427129B (en) | Information delivery method and system | |
| JP5454357B2 (en) | Information processing apparatus and method, and program | |
| CN111801674A (en) | Improving natural language interfaces by processing usage data | |
| WO2019080662A1 (en) | Information recommendation method, device and apparatus | |
| US20170315996A1 (en) | Focused sentiment classification | |
| US20150032753A1 (en) | System and method for pushing and distributing promotion content | |
| CN110555469A (en) | Method and device for processing interactive sequence data | |
| US20220253647A1 (en) | Automatic machine learning model evaluation | |
| US11907860B2 (en) | Targeted data acquisition for model training | |
| CN114902212A (en) | Image generation method, image generation device, server and storage medium | |
| CN105308591A (en) | Dynamics of tie strength from social interaction | |
| CN112241327A (en) | Shared information processing method and device, storage medium and electronic equipment | |
| CN111783873A (en) | Incremental naive Bayes model-based user portrait method and device | |
| CN110909768B (en) | Method and device for acquiring marked data | |
| US9536207B2 (en) | Using data obtained from an online social network to optimize subscription offers | |
| US20230126821A1 (en) | Systems, devices and methods for the dynamic generation of dialog-based interactive content | |
| US20220215287A1 (en) | Self-supervised pretraining through text alignment | |
| US11455555B1 (en) | Methods, mediums, and systems for training a model | |
| CN114202402A (en) | Behavior characteristic prediction method and device | |
| CN117708428A (en) | Recommendation information prediction method and device and electronic equipment | |
| JP6680663B2 (en) | Information processing apparatus, information processing method, prediction model generation apparatus, prediction model generation method, and program | |
| CN113110942A (en) | Message distribution method and device, computer equipment and storage medium | |
| CN113901328A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| KR102018906B1 (en) | Method for selecting target user group and computer system performing the same |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40056749 Country of ref document: HK |