CN112417270A - Method and device for generating prompt information, electronic equipment and storage medium - Google Patents
Method and device for generating prompt information, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112417270A CN112417270A CN202011225833.XA CN202011225833A CN112417270A CN 112417270 A CN112417270 A CN 112417270A CN 202011225833 A CN202011225833 A CN 202011225833A CN 112417270 A CN112417270 A CN 112417270A
- Authority
- CN
- China
- Prior art keywords
- client
- target user
- usage
- information
- module
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明实施例提供了一种生成提示信息的方法、装置、电子设备及存储介质。所述方法包括：获取目标用户使用所述移动终端上安装的客户端的过程中产生的使用数据，所述使用数据包括以下至少一种数据：所述目标用户使用所述客户端的第一时间信息、所述目标用户使用所述客户端中的功能模块的标识和第二时间信息；对所述使用数据进行处理，确定所述目标用户对所述客户端的使用习惯；根据所述目标用户对所述客户端的使用习惯，生成使用提示信息，所述提示信息用于提示所述目标用户使用所述客户端。采用本发明技术方案可以输出因人而异的个性化的提示信息。
Embodiments of the present invention provide a method, an apparatus, an electronic device, and a storage medium for generating prompt information. The method includes: acquiring usage data generated in the process of using the client installed on the mobile terminal by the target user, the usage data including at least one of the following data: first time information of the target user using the client, The target user uses the identifier of the function module in the client and the second time information; the usage data is processed to determine the target user's usage habit of the client; The usage habit of the client is used to generate usage prompt information, and the prompt information is used to prompt the target user to use the client. By adopting the technical solution of the present invention, individualized prompt information that varies from person to person can be output.
Description
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to a method and a device for generating prompt information, electronic equipment and a storage medium.
Background
With the rapid development of the mobile internet, the mobile terminal gradually becomes a main platform of human-computer interaction, and in the daily life of a user, prompt information is pushed to the user to prompt the user to use a corresponding client, so that the user experience can be improved.
In the related art, the scheme for pushing the prompt message by the mobile terminal is as follows: the prompt information is pushed for the user regularly, the time and the content of the prompt information pushed to different users by the same client are the same, and the pushed prompt information is fixed and relatively single.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present application provide a method, an apparatus, an electronic device, and a storage medium for generating hint information, which are intended to solve the problems that hint information in the related art is fixed and relatively single, and personalization cannot be achieved.
In order to solve the technical problem, the invention adopts the following scheme:
in a first aspect, an embodiment of the present application provides a method for generating a prompt message, which is applied to a mobile terminal, and the method includes:
acquiring use data generated in the process that a target user uses a client installed on the mobile terminal, wherein the use data comprises at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the functional module in the client and the second time information;
processing the use data, and determining the use habit of the target user to the client;
and generating use prompt information according to the use habit of the target user to the client, wherein the prompt information is used for prompting the target user to use the client.
Optionally, processing the usage data to determine the usage habit of the target user to the client includes:
processing use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents a parameter value of the target user using the client;
training a first preset model according to the first training sample to obtain a use habit prediction model;
inputting the usage data into the usage habit prediction model to determine usage habits of the target user on the client.
Optionally, before training the first preset model, the method further includes:
obtaining a use habit prediction base model generated by a server, wherein the use habit prediction base model is obtained by training a second preset model by taking use data generated by a plurality of different users in the process of using corresponding clients as second training samples;
and storing the use habit prediction base model as the first preset model to the local.
Optionally, the method further comprises:
processing real-time use data of the target user using the client to generate new training samples, wherein each use data sample in the new training samples carries a label, and the label represents a parameter value of the target user using the client;
and updating the use habit prediction model according to the new training sample.
Optionally, generating a usage prompt message according to the usage habit of the target user to the client, including:
generating prompt information carrying first time information under the condition that the use data comprises the first time information of the target user using the client, wherein the prompt information is used for prompting the target user to use the client at the first time information;
and generating prompt information carrying the second time information and the identification under the condition that the use data comprises the identification of the functional module of the client used by the target user and the second time information, wherein the prompt information is used for prompting the target user to use the functional module corresponding to the identification of the client at the moment corresponding to the second time information.
Optionally, after generating the usage hint information, the method further comprises at least one of:
outputting the prompt information at a moment which is separated by a preset time length from the moment corresponding to the first time information or the second time information;
operating the client under the condition that the client is not operated at the moment that the moment corresponding to the first time information is separated by a preset duration;
and operating and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
In a second aspect, an embodiment of the present application provides an apparatus for generating a prompt message, where the apparatus is applied to a mobile terminal, and the apparatus includes:
a data obtaining module, configured to obtain usage data generated during a process in which a target user uses a client installed on the mobile terminal, where the usage data includes at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the functional module in the client and the second time information;
the using habit prediction module is used for processing the using data and determining the using habit of the target user to the client;
and the prompt information generation module is used for generating use prompt information according to the use habit of the target user to the client, and the prompt information is used for prompting the target user to use the client.
Optionally, the apparatus further comprises:
the first data processing module is used for processing use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents a parameter value of the target user using the client;
the first training module is used for training a first preset model according to the first training sample to obtain a use habit prediction model;
and the input module is used for inputting the usage data into the usage habit prediction model so as to determine the usage habit of the target user to the client.
Optionally, the apparatus further comprises:
a basic model obtaining module, configured to obtain a usage habit prediction basic model generated by a server, where the usage habit prediction basic model is obtained by training a second preset model by using, as a second training sample, usage data generated by a plurality of different users in a process of using corresponding clients;
and the storage module is used for storing the use habit prediction base model serving as the first preset model to the local.
Optionally, the apparatus further comprises:
the second data processing module is used for processing the real-time use data of the target user using the client to generate new training samples, wherein each use data sample in the new training samples carries a label, and the label represents a parameter value of the target user using the client;
and the updating module is used for updating the use habit prediction model according to the new training sample.
Optionally, the prompt information generating module includes:
a first information generation sub-module, configured to generate, when the usage data includes first time information of using the client by the target user, prompt information carrying the first time information, where the prompt information is used to prompt the target user to use the client at the first time information;
and a second information generation sub-module, configured to generate, when the usage data includes an identifier of the functional module of the client used by the target user and second time information, prompt information carrying the second time information and the identifier, where the prompt information is used to prompt the target user to use the functional module corresponding to the identifier of the client at a time corresponding to the second time information.
Optionally, the apparatus further comprises at least one of:
a prompt message output module, configured to output the prompt message at a time that is separated by a preset time from a time corresponding to the first time message or the second time message;
the client operation module is used for operating the client at the moment which is separated by the preset time length from the moment corresponding to the first time information under the condition that the client is not operated;
and the functional module running module is used for running and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing, implements the steps of the method for generating hint information according to the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for generating a prompt message according to the first aspect.
Compared with the prior art, the embodiment of the invention at least has the following advantages:
by adopting the method for generating the prompt information, the use habits of the user are predicted based on the use data of the target user, the prompt information is output according to the use habits of the user, the personal use habits of the target user are fully considered, and therefore personalized prompt information which is different from person to person can be output. For a certain client, the single fixed prompt message is output to different users, but different prompt messages are output to different users, so that the prompt messages output by the target user are richer and more accurate.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be 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 that other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a flowchart of a method for generating a prompt message according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a step S12 in a method for generating a prompt message according to an embodiment of the present application;
FIG. 3 is a flow chart of another method for generating a prompt message according to an embodiment of the invention;
FIG. 4 is a flowchart of another method for generating a prompt message according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an apparatus for generating a prompt message 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, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a flowchart of a method for generating a prompt message according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S11: acquiring use data generated in the process that a target user uses a client installed on the mobile terminal, wherein the use data comprises at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the function module in the client and the second time information.
In this embodiment, on a mobile terminal, usage data generated in a process in which a target user uses a client installed on the mobile terminal is acquired. The usage data generated by the target user in the process of using the client installed on the mobile terminal is closely related to the personal behavior habit of the target user. The user usage data includes at least one of: the first time information of the target user using the client (e.g., when the target user enables the client and how long the client is used after the client is enabled), the identification of the function module in the client used by the target user, and the second time information (e.g., which function module in the client is enabled by the target user and how long the function module is used after the function module is enabled).
The method comprises the steps that the preference degree of a user for a client or a function module in the client can be determined according to the use duration of the client or the function module in the client, so that the client used by the user in a habit is predicted from a plurality of clients, and the specific function module used by the user in a habit is predicted from a plurality of function modules included in the client, so that the client used by the user or the specific function module in the client to be prompted is determined. The time when the user is used to the client or the function module in the client can be determined by the time point when the user uses the client or the function module in the client, so that the prompting time point is determined.
In practice, the specific function modules in the client are mainly various function modules which can implement different services on the client, for example, the client in the 58 same city includes different specific function modules for full-time recruitment, part-time employment, house renting, second-hand house buying and selling, and the like, and the different function modules can implement different services (for example, the house renting modules of the client in the 58 same city can implement house renting related services, including house source release, co-renting search, house source information understanding, and the like).
Step S12: and processing the use data to determine the use habit of the target user to the client.
Specifically, processing the obtained target user usage data to obtain a usage habit of the target user to the client, which may specifically include: the client comprises a time point when the target user is used to the client, a time point when the target user is used to the specific function module in the client, and a time point when the target user is used to the specific function module in the client.
Step S13: and generating use prompt information according to the use habit of the target user to the client, wherein the prompt information is used for prompting the target user to use the client.
Specifically, after determining the usage habit of the target user to use the client, the usage prompting information for the target user is generated to prompt the target user to use the client, which may be for prompting the target user to use the client at the predicted time.
Taking the 58 co-city client as an example for explanation, assume that there is a house broker who publishes or updates the second-hand house source information on the 58 co-city client after each day of work (nine am later). Then, according to the usage data of the user, the habit of the user is predicted to use the second-hand house buying and selling module in the 58-city client terminal after nine morning hours, and prompt information is generated to prompt the user to use the 58-city second-hand house buying and selling module at nine morning hours.
Further, suppose there is a 58 user in the same city, who needs to rent a house, so that the user opens 58 a house renting module in the same city every day after work (six pm later), browses the house renting source information and finds a suitable house source. Then, according to the usage data of the user, the habit of the user to use the house renting module of the 58-city client after six pm is predicted, and prompt information is generated to prompt the user to use the house renting module of the 58-city client at six pm every day.
By adopting the method for generating the prompt information, the use habits of the user are predicted based on the use data of the target user, the prompt information is output according to the use habits of the user, the personal use habits of the target user are fully considered, and therefore personalized prompt information which is different from person to person can be output. For a certain client, the single fixed prompt message is output to different users, but different prompt messages are output to different users, so that the prompt messages output by the target user are richer and more accurate.
In one embodiment of the present application, step S13 includes the steps of:
step S131: and generating prompt information carrying first time information under the condition that the use data comprises the first time information of the target user using the client, wherein the prompt information is used for prompting the target user to use the client at the first time information.
In practice, the usage information acquired by the client only includes the time information of the target user using the client, and then according to the usage information, only the time point at which the user is used to use the client can be predicted, and the output prompt information also only includes the time information, and the user prompts the user to use the client at the corresponding time.
Still taking the 58 co-city client as an example for analysis, the target user usage information collected by the 58 co-city client indicates that the target user uses the client at nine am every day, but in the collected usage information, the specific function module usage information is missing, so that the specific function module used by the user cannot be determined, and only the fact that the user is accustomed to using the 58 co-city client at nine am can be determined, so that the 58 co-city client outputs prompt information to the user to prompt the user to use the client at nine am.
In the case that only the prompt target user is included in the prompt message to use the corresponding client at the corresponding time, after the prompt message is generated, the output method of the prompt message further includes any one of the following steps:
outputting the prompt information at the moment when the time corresponding to the first time information is separated by a preset time length;
and operating the client under the condition that the client is not operated at the moment that the moment corresponding to the first time information is separated by a preset time length.
Still taking 58 city clients as an example and the user being a premise intermediary as an example, knowing that the premise intermediary is accustomed to using 58 city clients for 9 o ' clock, a prompt is output 9 o ' clock (e.g., 8 o ' clock 55 minutes) before each day to prompt the premise intermediary to use 58 city clients.
Also exemplified above as 58-city clients and the user is a house broker, in practice, at 8 o' clock 55, if it is detected that the house broker is not using 58-city clients, then 58-city clients are automatically started and run on the mobile terminal for use by the house broker.
Step S132: and generating prompt information carrying the second time information and the identification under the condition that the use data comprises the identification of the functional module of the client used by the target user and the second time information, wherein the prompt information is used for prompting the target user to use the functional module corresponding to the identification of the client at the moment corresponding to the second time information.
In practical application, if the obtained user usage data includes not only the time information but also the function module information, the time point at which the user is accustomed to using the function module of the client can be predicted according to the usage information, so that prompt information prompting the target user to use the corresponding function module of the client at the corresponding time point can be generated according to the predicted usage habit of the user.
Still taking the 58 co-city client as an example for analysis, the target user usage information collected by the 58 co-city client includes not only the time information (including time point information and duration information) when the user uses the 58 co-city client, but also the specific function module information of the 58 co-city used by the user, and according to the usage information and the usage habit prediction model, it is predicted that the target user will use the second-hand-room transaction module of the client when the habit of the user is nine am, so that the 58 co-city client outputs prompt information to the user to prompt the user to use the second-hand-room transaction module of the 58 co-city nine am.
When the prompt message includes a prompt target user to use a corresponding function module of a corresponding client at a corresponding time, after the prompt message is generated, the output method of the prompt message further includes any one of the following steps:
outputting the prompt information at a moment which is separated by a preset time length from the moment corresponding to the second time information;
and operating and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
In practice, if not only the time that the user uses the client but also the function module that the user is used to can be predicted according to the usage data when the usage habit of the user is predicted, the specific function module of the client can be operated at the corresponding time.
Also taking the 58 city client and the user as the house broker as an example, the house broker usage data and the usage habit prediction model predict that the house broker habit uses the 58 city client's second-hand house buying and selling module nine times earlier, so that the 58 city client can be started and the corresponding second-hand house buying and selling module can be run nine times earlier.
It will be appreciated that in practice, the target user may be prompted by a time before the predicted time point (e.g., five minutes before), or may be prompted by a time corresponding to the predicted time point. The prompting mode can be pushing the prompting information, automatically operating the corresponding client, and operating and outputting the corresponding functional module under the condition that the prompting information contains the specific functional module.
Fig. 2 is a flowchart of step S12 in another method for generating prompt information according to an embodiment of the present application, and as shown in fig. 2, step S12 may specifically include the following steps:
s21: and processing the use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents the parameter value of the target user using the client.
Specifically, the method includes processing usage data, which is obtained from a mobile terminal and generated in a process that a target user uses a client, to obtain first training samples, where each usage data sample in the first training samples carries a label, and the label represents a parameter value of the client used by the target user, specifically, a usage time point, a usage duration and a specific function module of the client used by the target user may be used by the target user, and the parameter values may predict usage habits of the target user from different angles.
S22: and training a first preset model according to the first training sample to obtain a use habit prediction model.
Specifically, the first preset model is trained at the mobile terminal to obtain a usage habit prediction model, and the usage habit prediction model can predict the usage habit of the target user according to usage data generated by the target user in the process of using the client, so that personalized prompt information is output to the user according to the usage habit of the user.
In the embodiment, the client of the mobile terminal collects the use data generated in the process that the target user uses the client installed on the mobile terminal; and then processing the collected use data, and training a first preset model on the mobile terminal by using the processed data to obtain a use habit prediction model.
S23: and inputting the usage data into a usage habit prediction model to determine the usage habit of the target user to the client.
Specifically, after the usage habit prediction model for the target user is obtained through training, the obtained usage data of the target user can be input into the usage habit prediction model, and the habit prediction model predicts the usage habit of the user on the client according to the input usage data of the target user.
In the embodiment of the application, the use data acquisition and the model update of the target user are processed and completed on the client side of the mobile terminal, so that the data storage capacity and the data processing capacity of the mobile terminal are fully exerted, the pressure of the server side is reduced, the complexity of the prompt system is reduced, and the operating efficiency of the prompt system is improved.
Fig. 3 is a flowchart of another method for generating a prompt message according to an embodiment of the present application, and as shown in fig. 3, the method specifically includes the following steps:
s31: and obtaining a use habit prediction base model generated by the server, wherein the use habit prediction base model is obtained by training a second preset model by taking use data generated by a plurality of different users in the process of using corresponding clients as second training samples.
Specifically, the habit base model is generated by training at the server side. The usage habit prediction base model is trained by usage data of a large number of users, and the usage data comprises time information and/or specific function module information of a certain client used by the users. Therefore, the usage habit prediction base model can predict the usage habit of the user on the client according to the usage data of the user, but the usage habit prediction base model cannot accurately predict the usage habit of the target user on the target client, and the usage habit prediction base model needs to be updated by the usage data of the target user subsequently, so as to obtain the usage habit prediction model corresponding to the target user.
In practice, the use data generated in the process that a large number of users use the corresponding clients are collected as training samples, and the second preset model is trained by using the training samples, wherein the collection and training processes of the training data are completed at the server side.
S32: storing the use habit prediction base model serving as the first preset model to the local; in practice, the first preset model is integrated with the client and stored locally in the mobile terminal, so that the subsequent training process is completed in the mobile terminal.
In practice, in order to reduce the data storage pressure and the data processing pressure of the server side and fully exert the storage capacity and the data processing capacity of the mobile terminal, after the server side trains and generates the usage habit prediction base model, the mobile terminal can obtain the usage habit prediction base model from the server and store the usage habit prediction base model to the local of the mobile terminal. And then, the use habit prediction basic model can be further trained on the mobile terminal by utilizing the real-time use data of the target user, so that a use habit prediction model corresponding to the target user is obtained. By completing the training of the use habit prediction model at the mobile terminal, the server does not need to collect individual personalized use data of a large number of users, and does not need to generate different personalized use habit prediction models for different users. The pressure of the server end is reduced, and meanwhile, the operation efficiency of the user prompt system is improved.
S33: and processing the use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents the parameter value of the target user using the client.
Specifically, after the usage habit prediction base model acquired from the server is stored locally in the mobile terminal, the mobile terminal collects usage data generated by the target user in the process of using the corresponding client, and processes the usage data to obtain a training sample carrying the parameter value label. That is, in the present embodiment, the first preset model (i.e., the habit prediction base model) is obtained from the server side, and the habit prediction base model is a base model, and therefore, the habit of the target user cannot be predicted accurately. Therefore, further training of the obtained usage habit prediction base model is required.
S34: and training a first preset model according to the first training sample to obtain the use habit prediction model.
Specifically, the use data of the user acquired and processed by the mobile terminal is used as a first training sample, and the use habit prediction base model is further trained, so that the use habit prediction model is obtained. The use habit basic model is an individualized prediction model aiming at a target user, and can accurately predict the use habits of the user.
S35: and inputting the usage data into a usage habit prediction model to determine the usage habit of the target user to the client.
Specifically, after the usage habit prediction model for the target user is obtained through training, the obtained usage data of the target user can be input into the usage habit prediction model, and the habit prediction model predicts the usage habit of the user on the client according to the input usage data of the target user.
S36: and generating use prompt information according to the use habit of the target user to the client, wherein the prompt information is used for prompting the target user to use the client.
Specifically, after determining the usage habit of the target user to use the client according to the data output by the usage habit prediction model, usage prompt information for the target user is generated to prompt the target user to use the client, so that the target user can be prompted to use the client at the predicted time.
In the embodiment of the application, the use data acquisition and the model update of the target user are processed and completed on the client side of the mobile terminal, so that the data storage capacity and the data processing capacity of the mobile terminal are fully exerted, the pressure of the server side is reduced, the complexity of the prompt system is reduced, and the operating efficiency of the prompt system is improved. In addition, in this embodiment, the server has already completed training of the usage habit prediction base model, and the mobile terminal can directly perform training by using the usage data of the target user based on the usage habit base model, and the usage habit prediction model for the target user can be obtained only by updating the usage habit prediction base model by using the collected usage data of the target user, so that a large amount of model training work on the mobile terminal is not required, and the problem of excessive data processing pressure of the mobile terminal is avoided.
Fig. 4 is a flowchart of another method for generating a prompt message according to an embodiment of the present application, and as shown in fig. 4, the method specifically includes the following steps:
s41: and processing the real-time use data of the target user using the client to generate a new training sample. Each use data sample in the new training sample carries a label, and the label represents a parameter value of the target user using the client. The real-time use data comprises use data generated by a target user in the process of using the client and use data operated by the user according to the prompt information. And processing the data, and obtaining the use data containing the parameter value of the client used by the user through data cleaning.
In practice, the usage data of the user is collected at intervals (e.g., one week), and the collected real-time usage data (e.g., the usage data in the current week) is processed to generate a new training sample, i.e., the generated new training sample is the real-time usage data in the current period.
S42: and updating the use habit prediction model according to the new training sample.
Specifically, real-time use data of a target user to a target client is continuously collected and processed to obtain a data sample carrying a label as a new training sample, and the use habit prediction model is continuously and dynamically updated by using the obtained new training sample.
Still taking the 58 city client as an example for explanation, assuming that a user uses the 58 city renting module after six pm in the current period (one week), the usage habit prediction model can be updated according to the usage data in the week to obtain the usage habit prediction model for the real-time situation of the user, and finally, the personalized prompt information for the user is predicted according to the usage data of the user and the usage habit prediction model: the user is prompted to use 58 the rental housing module in the same city at six pm.
However, after one week, the user rents a suitable house, the house renting module in the same city 58 is not used any more, the part-time module in the same city 58 is used instead, then, in the second week, the collected use information of the user is that the user uses the part-time module in the same city 58 after six pm, at this time, a new training sample is generated by using the real-time use data collected in the current period to update the use habit prediction model, so that the use habit prediction model for the real-time situation of the user can be generated, and finally, personalized prompt information for the user is generated according to the use data of the user and the updated use habit prediction model: the user is prompted to use 58 the part-time module in the same city at six pm.
S43: and inputting the usage data into a usage habit prediction model to determine the usage habit of the target user to the client.
The process of step S43 is similar to the process of step S23, and reference may be made to the process of step S23, which is not described herein again.
S44: and generating use prompt information according to the use habit of the target user to the client, wherein the prompt information is used for prompting the target user to use the client.
The process of step S44 is similar to the process of step S13, and reference may be made to the process of step S13, which is not described herein again.
In the embodiment of the application, the usage habit prediction model is continuously updated periodically, so that the usage habit prediction model is continuously updated, the usage habit prediction model which is more fit with the current usage habit of the user is obtained, the user habit in continuous change can be predicted, the personalized prediction model for the user is generated, and more personalized prompt information is provided for the user.
Based on the same inventive concept, an embodiment of the present application provides an apparatus for generating a prompt message. Referring to fig. 5, fig. 5 is a schematic diagram of an apparatus for generating a prompt message according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:
a data obtaining module 501, configured to obtain usage data generated during a process that a target user uses a client installed on the mobile terminal, where the usage data includes at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the functional module in the client and the second time information;
a usage habit prediction module 502, configured to process the usage data and determine a usage habit of the target user on the client;
a prompt message generating module 503, configured to generate a use prompt message according to the use habit of the target user on the client, where the prompt message is used to prompt the target user to use the client.
Optionally, the apparatus further comprises:
the first data processing module is used for processing use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents a parameter value of the target user using the client;
the first training module is used for training a first preset model according to the first training sample to obtain a use habit prediction model;
and the input module is used for inputting the usage data into the usage habit prediction model so as to determine the usage habit of the target user to the client.
Optionally, the apparatus further comprises:
a basic model obtaining module, configured to obtain a usage habit prediction basic model generated by a server, where the usage habit prediction basic model is obtained by training a second preset model by using, as a second training sample, usage data generated by a plurality of different users in a process of using corresponding clients;
and the storage module is used for storing the use habit prediction base model serving as the first preset model to the local.
Optionally, the apparatus further comprises:
the second data processing module is used for processing the real-time use data of the target user using the client to generate new training samples, wherein each use data sample in the new training samples carries a label, and the label represents a parameter value of the target user using the client;
and the updating module is used for updating the use habit prediction model according to the new training sample.
Optionally, the prompt information generating module includes:
a first information generation sub-module, configured to generate, when the usage data includes first time information of using the client by the target user, prompt information carrying the first time information, where the prompt information is used to prompt the target user to use the client at the first time information;
and a second information generation sub-module, configured to generate, when the usage data includes an identifier of the functional module of the client used by the target user and second time information, prompt information carrying the second time information and the identifier, where the prompt information is used to prompt the target user to use the functional module corresponding to the identifier of the client at a time corresponding to the second time information.
Optionally, the apparatus further comprises at least one of:
a prompt message output module, configured to output the prompt message at a time that is separated by a preset time from a time corresponding to the first time message or the second time message;
the client operation module is used for operating the client at the moment which is separated by the preset time length from the moment corresponding to the first time information under the condition that the client is not operated;
and the functional module running module is used for running and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
Based on the same inventive concept, another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the computer program, when executed by the processor, implements each process of the above method for generating a prompt message, and can achieve the same technical effect, and is not described herein again to avoid repetition.
Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the above method for generating a prompt message, and can achieve the same technical effect, and is not described herein again to avoid repetition. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (14)
1. A method for generating prompt information is applied to a mobile terminal, and the method comprises the following steps:
acquiring use data generated in the process that a target user uses a client installed on the mobile terminal, wherein the use data comprises at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the functional module in the client and the second time information;
processing the use data, and determining the use habit of the target user to the client;
and generating use prompt information according to the use habit of the target user to the client, wherein the prompt information is used for prompting the target user to use the client.
2. The method of claim 1, wherein processing the usage data to determine usage habits of the target user for the client comprises:
processing use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents a parameter value of the target user using the client;
training a first preset model according to the first training sample to obtain a use habit prediction model;
inputting the usage data into the usage habit prediction model to determine usage habits of the target user on the client.
3. The method of claim 2, wherein prior to training the first pre-set model, the method further comprises:
obtaining a use habit prediction base model generated by a server, wherein the use habit prediction base model is obtained by training a second preset model by taking use data generated by a plurality of different users in the process of using corresponding clients as second training samples;
and storing the use habit prediction base model as the first preset model to the local.
4. The method of claim 2, further comprising:
processing real-time use data of the target user using the client to generate new training samples, wherein each use data sample in the new training samples carries a label, and the label represents a parameter value of the target user using the client;
and updating the use habit prediction model according to the new training sample.
5. The method according to any one of claims 1 to 4, wherein generating a usage prompt message according to the usage habit of the target user to the client comprises:
generating prompt information carrying first time information under the condition that the use data comprises the first time information of the target user using the client, wherein the prompt information is used for prompting the target user to use the client at the first time information;
and generating prompt information carrying the second time information and the identification under the condition that the use data comprises the identification of the functional module of the client used by the target user and the second time information, wherein the prompt information is used for prompting the target user to use the functional module corresponding to the identification of the client at the moment corresponding to the second time information.
6. The method of claim 5, wherein after generating the usage hint information, the method further comprises at least one of:
outputting the prompt information at a moment which is separated by a preset time length from the moment corresponding to the first time information or the second time information;
operating the client under the condition that the client is not operated at the moment that the moment corresponding to the first time information is separated by a preset duration;
and operating and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
7. An apparatus for generating a prompt message, which is applied to a mobile terminal, the apparatus comprising:
a data obtaining module, configured to obtain usage data generated during a process in which a target user uses a client installed on the mobile terminal, where the usage data includes at least one of the following data: the target user uses the first time information of the client, the identification of the target user using the functional module in the client and the second time information;
the using habit prediction module is used for processing the using data and determining the using habit of the target user to the client;
and the prompt information generation module is used for generating use prompt information according to the use habit of the target user to the client, and the prompt information is used for prompting the target user to use the client.
8. The apparatus of claim 7, further comprising:
the first data processing module is used for processing use data generated in the process that the target user uses the client installed on the mobile terminal to obtain first training samples, wherein each use data sample in the first training samples carries a label, and the label represents a parameter value of the target user using the client;
the first training module is used for training a first preset model according to the first training sample to obtain a use habit prediction model;
and the input module is used for inputting the usage data into the usage habit prediction model so as to determine the usage habit of the target user to the client.
9. The apparatus of claim 8, further comprising:
a basic model obtaining module, configured to obtain a usage habit prediction basic model generated by a server, where the usage habit prediction basic model is obtained by training a second preset model by using, as a second training sample, usage data generated by a plurality of different users in a process of using corresponding clients;
and the storage module is used for storing the use habit prediction base model serving as the first preset model to the local.
10. The apparatus of claim 8, further comprising:
the second data processing module is used for processing the real-time use data of the target user using the client to generate new training samples, wherein each use data sample in the new training samples carries a label, and the label represents a parameter value of the target user using the client;
and the updating module is used for updating the use habit prediction model according to the new training sample.
11. The apparatus according to any one of claims 7-10, wherein the prompt information generating module comprises:
a first information generation sub-module, configured to generate first prompt information carrying time information when the usage data includes first time information of the client used by the target user, where the prompt information is used to prompt the target user to use the client at the first time information;
and a second information generation sub-module, configured to generate, when the usage data includes an identifier of the functional module of the client used by the target user and second time information, prompt information carrying the second time information and the identifier, where the prompt information is used to prompt the target user to use the functional module corresponding to the identifier of the client at a time corresponding to the second time information.
12. The apparatus of claim 11, further comprising at least one of:
a prompt message output module, configured to output the prompt message at a time that is separated by a preset time from a time corresponding to the first time message or the second time message;
the client operation module is used for operating the client at the moment which is separated by the preset time length from the moment corresponding to the first time information under the condition that the client is not operated;
and the functional module running module is used for running and outputting the functional module corresponding to the identifier of the client at the moment corresponding to the second time information.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing implementing the steps of the method of generating a reminder information according to any one of claims 1 to 6.
14. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method of generating a hint information according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011225833.XA CN112417270A (en) | 2020-11-05 | 2020-11-05 | Method and device for generating prompt information, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011225833.XA CN112417270A (en) | 2020-11-05 | 2020-11-05 | Method and device for generating prompt information, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417270A true CN112417270A (en) | 2021-02-26 |
Family
ID=74827569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011225833.XA Pending CN112417270A (en) | 2020-11-05 | 2020-11-05 | Method and device for generating prompt information, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417270A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114416110A (en) * | 2021-12-23 | 2022-04-29 | 北京五八信息技术有限公司 | Application gray level release method and device, electronic equipment and readable medium |
| CN116007138A (en) * | 2022-12-06 | 2023-04-25 | 珠海格力电器股份有限公司 | Intelligent reminding method, system, device and medium for device use |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920156A (en) * | 2018-05-29 | 2018-11-30 | Oppo广东移动通信有限公司 | Application program prediction model method for building up, device, storage medium and terminal |
| US20190224568A1 (en) * | 2016-12-06 | 2019-07-25 | Tencent Technology (Shenzhen) Company Limited | Prompt method and related apparatus in virtual scene, and computer storage medium |
| CN110308661A (en) * | 2019-06-06 | 2019-10-08 | 美的集团股份有限公司 | Smart machine control method and device based on machine learning |
| CN111026959A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Prompt message pushing method, device and storage medium |
-
2020
- 2020-11-05 CN CN202011225833.XA patent/CN112417270A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190224568A1 (en) * | 2016-12-06 | 2019-07-25 | Tencent Technology (Shenzhen) Company Limited | Prompt method and related apparatus in virtual scene, and computer storage medium |
| CN108920156A (en) * | 2018-05-29 | 2018-11-30 | Oppo广东移动通信有限公司 | Application program prediction model method for building up, device, storage medium and terminal |
| CN110308661A (en) * | 2019-06-06 | 2019-10-08 | 美的集团股份有限公司 | Smart machine control method and device based on machine learning |
| CN111026959A (en) * | 2019-11-29 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Prompt message pushing method, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114416110A (en) * | 2021-12-23 | 2022-04-29 | 北京五八信息技术有限公司 | Application gray level release method and device, electronic equipment and readable medium |
| CN116007138A (en) * | 2022-12-06 | 2023-04-25 | 珠海格力电器股份有限公司 | Intelligent reminding method, system, device and medium for device use |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019080662A1 (en) | Information recommendation method, device and apparatus | |
| US10332013B2 (en) | System and method for recommending applications based on historical usage | |
| TWI430173B (en) | System and method for precaching information on a mobile device | |
| US20110125700A1 (en) | User model processing device | |
| CN105706042A (en) | Aggregating and presenting event information | |
| CN112417270A (en) | Method and device for generating prompt information, electronic equipment and storage medium | |
| CN113382087B (en) | Push time prediction method, push time prediction device, push time prediction equipment, storage medium and program product | |
| US20110165544A1 (en) | Activity data presenting apparatus, activity data presenting method and recording medium | |
| CN104956680A (en) | Intelligent prefetching of recommended media content | |
| CN111259231A (en) | Recommendation method and device for application program | |
| CN103197847A (en) | Information processing apparatus, information processing method, and computer program | |
| JP2018101201A (en) | Policy introduction effect prediction device, policy introduction effect prediction program and policy introduction effect prediction method | |
| JP5080298B2 (en) | Condition estimation device and condition estimation program | |
| US20110016161A1 (en) | System and method for the selection of context sensitive user profile fragments | |
| CN114153685A (en) | Method, system, device and storage medium for estimating in-band system information of server | |
| CN116913469A (en) | Drinking water recommending method and device, drinking water machine and storage medium | |
| JP5519210B2 (en) | Model generation apparatus, model generation method, information processing system, and program | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN104462270B (en) | A kind of method and device of information recommendation | |
| CN113055531B (en) | Time reminding method and system of intelligent terminal, electronic equipment and medium | |
| CN103198120A (en) | Webpage presenting method and device and webpage content providing method and system | |
| JP7400965B2 (en) | Mood prediction method, mood prediction device and program | |
| CN117827063A (en) | Desktop layout method, device, equipment and storage medium | |
| JP5854043B2 (en) | Action presentation device, action presentation method, and program | |
| JP2009181476A (en) | Situation estimation device and situation estimation program |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |