CN111176750A - Resource packet sending method, device, electronic equipment and computer readable medium - Google Patents
Resource packet sending method, device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN111176750A CN111176750A CN201911305139.6A CN201911305139A CN111176750A CN 111176750 A CN111176750 A CN 111176750A CN 201911305139 A CN201911305139 A CN 201911305139A CN 111176750 A CN111176750 A CN 111176750A
- Authority
- CN
- China
- Prior art keywords
- target
- user
- service
- sequence
- access
- 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.)
- Withdrawn
Links
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
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
-
- 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
- G06F9/547—Remote procedure calls [RPC]; Web services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/541—Client-server
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the application discloses a resource package sending method, a resource package sending device, electronic equipment and a computer readable medium. An embodiment of the method comprises: determining service modules in target applications sequentially accessed by a target user within a target time length; acquiring service characteristics of service modules accessed in sequence and summarizing the service characteristics into a characteristic sequence; inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of a target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information is used for indicating a target service module which the target user intends to access; and sending the resource packet corresponding to the target service module to the target user. The embodiment reduces the downloading amount of invalid resource packages by the user.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a resource package sending method, a resource package sending device, electronic equipment and a computer readable medium.
Background
With the development of computer technology, functions of Applications (APPs) suitable for terminal devices are more and more abundant, and more data need to be loaded when the applications are used. Generally, to reduce the time consumption for loading data, a resource package (Bundle) may be sent to the user equipment in advance.
In the existing manner, after a user starts an application, resource packages of service modules of the application are downloaded in full, and the resource packages are cached, so that the user can call the resource packages in the application using process. However, each time the user uses the application, only the resource package of a certain service is needed to be used, and the resource package not used by the user can be regarded as an invalid resource package. When the application functions are more and the number of the resource packages is more, the downloading amount of the resource packages which are invalid in the method is larger, and the network flow of the user is consumed.
Disclosure of Invention
The embodiment of the application provides a resource package sending method, a resource package sending device, electronic equipment and a computer readable medium, so that the downloading amount of invalid resource packages is reduced, and the network flow of a user is saved.
In a first aspect, an embodiment of the present application provides a method for sending a resource packet, where the method includes: determining service modules sequentially accessed by a target user within a target time length; acquiring service characteristics of service modules in sequentially accessed target applications, and summarizing the service characteristics into a characteristic sequence; inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of a target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information is used for indicating a target service module which the target user intends to access; sending resource packet corresponding to target service module to target user
In a second aspect, an embodiment of the present application provides a resource packet sending apparatus, including: the determining unit is configured to determine service modules in the target application sequentially accessed by the target user within the target time length; the acquiring unit is configured to acquire service characteristics of the service modules accessed in sequence and summarize the service characteristics into a characteristic sequence; the prediction unit is configured to input the characteristic sequence into a pre-trained sequence processing model, and obtain access intention information of the target user from information output by the sequence processing model and user characteristics of the target user input into the pre-trained access intention prediction model, wherein the access intention information is used for indicating a target business module which the target user intends to access; and the sending unit is configured to send the resource packet corresponding to the target service module to the target user.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement the method as described in the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable medium on which a computer program is stored, which when executed by a processor, implements the method as described in the first aspect.
The resource package sending method, the resource package sending device, the electronic device and the computer readable medium provided by the embodiment of the application can obtain the service characteristics of the service modules sequentially accessed by the target user by determining the service modules in the target application sequentially accessed by the target user within the target time length, and summarize the service characteristics into the characteristic sequence. And then inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of the target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information can be used for indicating a target service module which the target user intends to access. And finally, sending the resource packet corresponding to the target service module to the target user. Therefore, the target service module which the user intends to access can be determined based on the service modules which are sequentially accessed by the user within the target time length, and the resource package corresponding to the target service module is sent. Therefore, the resource package can be sent according to the needs of the user, the user is prevented from downloading the whole resource package, the downloading amount of the invalid resource package by the user is reduced, and the network flow of the user is saved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is a flow diagram of one embodiment of a method for resource package transmission according to the present application;
fig. 2 is a flow chart of yet another embodiment of a resource package sending method according to the present application;
fig. 3 is a schematic structural diagram of an embodiment of a resource packet transmitting apparatus according to the present application;
FIG. 4 is a block diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a flow 100 of an embodiment of a method for sending a resource package according to the present application is shown. The resource packet sending method comprises the following steps:
In this embodiment, an execution subject (e.g., an electronic device such as a server) of the resource package sending method may determine service modules in the target application that are sequentially accessed by the target user within the target duration. The target user may be a user currently to send a resource packet to the terminal device used by the target user. The target time duration may be a preset time period (e.g., within 1 day, within 6 hours, or within 3 days) with the current time as the ending time. The target application may be any client application supported by the execution subject. For example, a comment application, a meal order application, a group purchase application, and the like are possible.
In practice, the target application may involve multiple lines of service. For example, the group purchase type application may relate to a line of a food service, a line of a movie or show service, a line of a hotel or accommodation service, a line of a leisure entertainment service, a line of a take-out service, and the like. Each service line may be supported by a functional module in the target application.
In addition, the function module of the target application for providing support for each service line may include a plurality of resource packages (bundles). The resource package may store executable code and other content for providing code support when a user accesses the functional module.
It should be noted that the service module in the embodiment of the present application may be a functional module of the target application, and may also be a data module corresponding to a resource package in the functional module of the target application. Here, the range of the service module may be preset as needed, and the embodiment of the present application does not limit this.
Taking the target application as the group purchase application as an example, when the service module is the functional module of the target application, each service line corresponds to one service module. If the user browses the relevant information of the food service and the relevant information of the leisure and entertainment service in turn in one day, the service modules sequentially visited by the user sequentially provide service modules for supporting the food service and service modules for supporting the leisure and entertainment service. When the service module is a data module corresponding to the resource package, the service modules in the target application sequentially accessed by the user can be regarded as the resource packages sequentially used by the user in the process of using the target application.
In this embodiment, the execution subject may communicate with a terminal device used by a target user in real time. The execution main body can acquire various data uploaded by the terminal device through the target application in real time, such as behavior data generated when a user accesses (such as browsing, clicking and the like) a service module. Based on the data acquired in real time, the execution main body can determine the service modules sequentially accessed by the user.
In some optional implementation manners of this embodiment, the execution subject may determine the service modules that the target user sequentially accesses within the target duration by:
the method comprises the steps of responding to a received target application starting message sent by terminal equipment used by a target user, and acquiring user behavior data generated when the target user uses the target application.
In practice, starting from the start of the target application, the target application can send a data stream to the execution main body through the terminal device to perform real-time interaction. The data stream may include a target application start message to indicate that the target application has started.
And secondly, extracting access records of the target user to each service module in the target application within a target time length from the user behavior data, wherein the access records comprise access time.
And thirdly, determining the service modules which are sequentially accessed by the target user in the target time length according to the sequence of the access time from first to last.
And 102, acquiring the service characteristics of the service modules accessed in sequence, and summarizing the service characteristics into a characteristic sequence.
In this embodiment, the execution main body may obtain service features of service modules accessed sequentially, and summarize the service features into a feature sequence. The service features may be features for describing and distinguishing service modules, among others. For example, the service characteristics of a certain service module may include ID class characteristics of the service module, the number of times of access to the service module by the full number of users, and the like. It should be noted that the service features of each service module can be represented in the form of a vector.
In this embodiment, the feature sequence may be formed by service features of service modules sequentially accessed by the user.
And 103, inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and the user characteristics of the target user into a pre-trained access intention prediction model to obtain the access intention information of the target user.
In this embodiment, the execution subject may store a sequence processing model and an access intention prediction model trained in advance. The sequence processing model described above can be used to process features in the form of sequences. The access intention prediction model can be used for predicting the access intention of the user to the business module. The sequence processing model may be connected to an input layer of the access intention prediction model to input the processed feature sequence to the access intention prediction model. In practice, the sequence processing model and the access intention prediction model can be obtained by pre-training using a machine learning method (e.g., a supervised learning method).
In this embodiment, the execution agent may input the feature sequence obtained in step 102 to a pre-trained sequence processing model, and obtain the access intention information of the target user from information output by the sequence processing model and the user feature of the target user input to the pre-trained access intention prediction model.
Here, the above-mentioned access intention information may be used to indicate a target service module that a target user intends to access. As an example, the access intention information may include access probabilities of the user to the respective service modules. If the access probability of a certain service module is greater than a preset threshold, the service module is meant to be accessed, and at this time, the service module can be used as a target service module. As yet another example, the access intention information may include scores of the respective business modules. If the score of a certain service module is greater than a preset threshold, the service module is meant to be accessed, and at this time, the service module can be used as a target service module.
Here, the user characteristic of the user may be information for indicating and distinguishing the user. For example, the attribute (such as age, sex, etc.) of the user, the current location area, etc. may be included. In practice, the user features may also be represented in the form of vectors.
In some optional implementations of the embodiment, the sequence processing model and the visit intention prediction model are trained by the following steps:
in a first step, a sample set is obtained.
Wherein the sample set may comprise a large number of samples. Each sample may include feature information and annotation information. The feature information includes a sample feature sequence and a sample user feature. The sample characteristic sequence is formed by the service characteristics of historical service modules which are sequentially accessed by the user. The marking information is used for indicating a target historical service module accessed by a user after sequentially accessing the historical service modules.
It should be noted that the historical service module may be a service module in a target application for historical period access. Here, the generation manner of the sample feature sequence is basically the same as the manner of generating the feature sequence in step 102, and is not described here again.
And a second step of inputting the sample feature sequence of the sample set into a pre-established Attention model (Attention model), inputting information output by the Attention model and the sample user features into a pre-established deep neural Network, using labels of the business features in the input sample feature sequence as outputs of the Deep Neural Network (DNN), and training the Attention model and the deep neural Network by using a machine learning method.
In practice, the Attention model may be used to determine the weights of the components in the sequence, and thus, the Attention model may be used herein to determine the weights of the traffic characteristics of the traffic modules in the characteristic sequence. The information output by the attention model may be a new feature sequence obtained by weighting each service feature in the feature sequence.
And thirdly, determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
In some optional implementation manners of this embodiment, when the service module of the target application is a data module corresponding to the resource packet in the target application, the service feature of the service module is a feature of the resource packet. At this time, the target service module that the target user intends to access, which is indicated by the access intention information, is a data module corresponding to the target resource package that the user intends to use.
When a data module corresponding to a target resource package which is intended to be used by a user is used, the sequence processing model and the access intention prediction model are obtained by training through the following steps:
in a first step, a sample set is obtained.
Wherein the sample set may comprise a large number of samples. Each sample may include feature information and annotation information. The feature information includes a sample feature sequence and a sample user feature. The sample feature sequence is formed by the features of the historical resource packages which are sequentially accessed by the user. The marking information is used for indicating a target historical service module accessed by a user after sequentially accessing the historical service modules.
Inputting the sample feature sequence of the sample set into a pre-established attention model, inputting information output by the attention model and the sample user features into a pre-established deep neural network, taking the label of each feature in the input sample feature sequence as the output of the deep neural network, and training the attention model and the deep neural network by using a machine learning method;
and thirdly, determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
And 104, sending the resource packet corresponding to the target service module to the target user.
In this embodiment, after determining the target service module that the target user intends to access, the execution main body may send the resource package corresponding to the target service module to the target user.
In one scenario, the execution body may store a resource package corresponding to each service module of the target application. At this time, the execution main body may locally search for the resource package corresponding to the target service module, and send the searched resource package to the terminal device used by the target user.
In another scenario, the resource package corresponding to each service module of the target application may be stored by other devices. At this time, the execution main body may access other devices, acquire the resource packet corresponding to the target service module from the device, and send the acquired resource packet to the terminal device used by the target user.
In some optional implementation manners of this embodiment, after determining the target service module that the target user intends to access, the execution main body may send a resource package download message to the terminal device used by the target user. The resource package downloading message may be used to instruct the terminal device to download the resource package. Then, in response to receiving a resource package download request returned by the terminal device, the execution main body may send a resource package corresponding to the target service module to the terminal device.
In some optional implementation manners of this embodiment, when the service module is a function module of the target application, the target service module is a function module that a user intends to access in the target application. Each functional module in the target application is used for providing support for one service line. At this time, the execution main body may first obtain the full resource package corresponding to the target service module. The total resource packets are all resource packets corresponding to the target service module. Then, the full resource packet may be transmitted to the terminal device used by the target user.
Therefore, the target business module corresponding to the business line which the user intends to access currently can be determined based on the business modules corresponding to the business lines which the target user accesses sequentially before the current moment.
In some optional implementation manners of this embodiment, when a service module is a data module corresponding to a resource package in a target application, the target service module is a data module corresponding to a target resource package that a user intends to use in the target application. At this time, the execution subject may first obtain the target resource packet; and then, the target resource packet is sent to the terminal equipment used by the target user. Therefore, the target resource package which the user intends to access currently can be determined based on the resource packages which are sequentially accessed by the target user before the current time.
In the method provided by the above embodiment of the present application, by determining the service modules in the target application that the target user sequentially accesses within the target duration, the service characteristics of the sequentially accessed service modules can be obtained and summarized as the characteristic sequence. And then inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of the target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information can be used for indicating a target service module which the target user intends to access. And finally, sending the resource packet corresponding to the target service module to the target user. Therefore, the target service module which the user intends to access can be determined based on the service modules which are sequentially accessed by the user within the target time length, and the resource package corresponding to the target service module is sent. Therefore, the resource package can be sent according to the needs of the user, the user is prevented from downloading the whole resource package, the downloading amount of the invalid resource package by the user is reduced, and the network flow of the user is saved.
With further reference to fig. 2, a flow 200 of yet another embodiment of a resource package sending method is shown. The process 200 of the resource packet sending method includes the following steps:
In this embodiment, an execution subject (e.g., an electronic device such as a server) of the resource package sending method obtains user behavior data generated when a target user uses a target application in response to receiving a target application start message sent by a terminal device used by the target user. In practice, starting from the start of the target application, the target application can send a data stream to the execution main body through the terminal device to perform real-time interaction. The data stream may include a target application start message to indicate that the target application has started.
In this embodiment, the execution subject may extract, from the user behavior data, an access record of the target user to each service module in the target application within the target duration. Wherein the access record includes an access time.
And step 204, acquiring the service characteristics of the service modules accessed in sequence, and summarizing the service characteristics into a characteristic sequence.
In this embodiment, the execution main body may obtain service features of service modules accessed sequentially, and summarize the service features into a feature sequence. The service features may be features for describing and distinguishing service modules, among others. For example, the service characteristics of a certain service module may include ID class characteristics of the service module, the number of times of access to the service module by the full number of users, and the like. It should be noted that the service features of each service module can be represented in the form of a vector.
In this embodiment, the feature sequence may be formed by service features of service modules sequentially accessed by the user.
In this embodiment, the execution agent may input the feature sequence obtained in step 204 into a pre-trained sequence processing model, and obtain the access intention information of the target user from information output by the sequence processing model and the user feature of the target user input into a pre-trained access intention prediction model.
Here, the above-mentioned access intention information may be used to indicate a target service module that a target user intends to access. As an example, the access intention information may include access probabilities of the user to the respective service modules. If the access probability of a certain service module is greater than a preset threshold, the service module is meant to be accessed, and at this time, the service module can be used as a target service module. As yet another example, the access intention information may include scores of the respective business modules. If the score of a certain service module is greater than a preset threshold, the service module is meant to be accessed, and at this time, the service module can be used as a target service module.
Here, the user characteristic of the user may be information for indicating and distinguishing the user. For example, the attribute (such as age, sex, etc.) of the user, the current location area, etc. may be included. In practice, the user features may also be represented in the form of vectors.
In this embodiment, the sequence processing model and the access intention prediction model are obtained by training as follows:
in a first step, a sample set is obtained.
Wherein the sample set may comprise a large number of samples. Each sample may include feature information and annotation information. The feature information includes a sample feature sequence and a sample user feature. The sample characteristic sequence is formed by the service characteristics of historical service modules which are sequentially accessed by the user. The marking information is used for indicating a target historical service module accessed by a user after sequentially accessing the historical service modules.
It should be noted that the historical service module may be a service module in a target application for historical period access. Here, the generation manner of the sample feature sequence is basically the same as the manner of generating the feature sequence in step 102, and is not described here again.
And a second step of inputting the sample feature sequence of the sample set into a pre-established Attention model (Attention model), inputting information output by the Attention model and the sample user features into a pre-established Deep Neural Network, using labels of the business features in the input sample feature sequence as outputs of the Deep Neural Network (DNN), and training the Attention model and the Deep Neural Network by using a machine learning method.
In practice, the Attention model may be used to determine the weights of the components in the sequence, and thus, the Attention model may be used herein to determine the weights of the traffic characteristics of the traffic modules in the characteristic sequence. The information output by the attention model may be a new feature sequence obtained by weighting each service feature in the feature sequence.
And thirdly, determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
In this embodiment, the execution body may send a resource package download message to a terminal device used by the target user. The resource package downloading message may be used to instruct the terminal device to download the resource package.
In this embodiment, in response to receiving a resource package downloading request returned by the terminal device, the execution main body may send a resource package corresponding to the target service module to the terminal device.
The method provided by the above embodiment of the present application may determine the target service module that the user intends to access based on the service modules that the user sequentially accesses within the target time length, and enable the user to download the resource package corresponding to the target service module. Therefore, the user can download the resource package according to the current requirement, the user is prevented from downloading the whole resource package, the downloading amount of the invalid resource package by the user is reduced, and the network flow of the user is saved.
With further reference to fig. 3, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of a resource packet sending apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 1, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 3, the resource packet transmitting apparatus 300 according to this embodiment includes: a determining unit 301, configured to determine service modules in the target application that the target user sequentially accesses within the target duration; an obtaining unit 302, configured to obtain service features of the sequentially accessed service modules, and summarize the service features into a feature sequence; a prediction unit 303 configured to input the feature sequence into a pre-trained sequence processing model, and obtain access intention information of the target user from information output by the sequence processing model and user features of the target user input into a pre-trained access intention prediction model, the access intention information indicating a target service module that the target user intends to access; a sending unit 304, configured to send the resource packet corresponding to the target service module to the target user.
In some optional implementations of this embodiment, the determining unit 301 is further configured to: responding to a received target application starting message sent by terminal equipment used by a target user, and acquiring user behavior data generated when the target user uses the target application; extracting access records of the target user to each service module in the target application within a target time length from the user behavior data, wherein the access records comprise access time; and determining the service modules which are sequentially accessed by the target user in the target time length according to the sequence of the access time from first to last.
In some optional implementations of this embodiment, the sending unit 304 is further configured to: sending a resource package downloading message to the terminal equipment used by the target user; and responding to a received resource package downloading request returned by the terminal equipment, and sending the resource package corresponding to the target service module to the terminal equipment.
In some optional implementations of the embodiment, the sequence processing model and the visit intention prediction model are trained by the following steps: acquiring a sample set, wherein samples in the sample set comprise characteristic information and marking information, the characteristic information comprises a sample characteristic sequence and sample user characteristics, the sample characteristic sequence is formed by service characteristics of historical service modules accessed by a user in sequence, and the marking information is used for indicating a target historical service module accessed by the user after the user accesses the historical service modules in sequence; inputting the sample feature sequence of the sample set into a pre-established attention model, inputting information output by the attention model and the sample user features into a pre-established deep neural network, taking the labeling information of each business feature in the input sample feature sequence as the output of the deep neural network, and training the attention model and the deep neural network by using a machine learning method; and determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
In some optional implementation manners of this embodiment, a service module is a function module of the target application, each function module in the target application is configured to provide support for a service line, and the target service module is a function module that a user intends to access in the target application; and, the sending unit 304 is further configured to: acquiring a full resource packet corresponding to the target service module; and transmitting the full resource packet to the terminal equipment used by the target user.
In some optional implementation manners of this embodiment, the service module is a data module corresponding to a resource package in the target application, the service feature of the service module is a feature of the resource package, and the target service module is a data module corresponding to a target resource package that a user intends to use in the target application; and, the sending unit 304 is further configured to: acquiring the target resource packet; and sending the target resource packet to the terminal equipment used by the target user.
In some optional implementations of the embodiment, the sequence processing model and the visit intention prediction model are trained by the following steps: acquiring a sample set, wherein samples in the sample set comprise characteristic information and marking information, the characteristic information comprises a sample characteristic sequence and sample user characteristics, the sample characteristic sequence is formed by characteristics of historical resource packages sequentially accessed by a user, and the marking information is used for indicating a target historical service module accessed by the user after the user sequentially accesses the historical service module; inputting the sample feature sequence of the sample set into a pre-established attention model, inputting information output by the attention model and the sample user features into a pre-established deep neural network, taking the label of each feature in the input sample feature sequence as the output of the deep neural network, and training the attention model and the deep neural network by using a machine learning method; and determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
The device provided by the above embodiment of the present application, by determining the service modules in the target application that the target user sequentially accesses within the target duration, may obtain the service characteristics of the sequentially accessed service modules, and summarize them into a characteristic sequence. And then inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of the target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information can be used for indicating a target service module which the target user intends to access. And finally, sending the resource packet corresponding to the target service module to the target user. Therefore, the target service module which the user intends to access can be determined based on the service modules which are sequentially accessed by the user within the target time length, and the resource package corresponding to the target service module is sent. Therefore, the resource package can be sent according to the needs of the user, the user is prevented from downloading the whole resource package, the downloading amount of the invalid resource package by the user is reduced, and the network flow of the user is saved.
Referring now to FIG. 4, shown is a block diagram of a computer system 400 suitable for use in implementing the electronic device of an embodiment of the present application. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display such as a Liquid Crystal Display (LCD) and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 401. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The units described may also be provided in a processor, where the names of the units do not in some cases constitute a limitation of the units themselves.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: determining service modules in target applications sequentially accessed by a target user within a target time length; acquiring service characteristics of service modules accessed in sequence and summarizing the service characteristics into a characteristic sequence; inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of a target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information is used for indicating a target service module which the target user intends to access; and sending the resource packet corresponding to the target service module to the target user.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (10)
1. A method for transmitting a resource packet, the method comprising:
determining service modules in target applications sequentially accessed by a target user within a target time length;
acquiring the service characteristics of the service modules accessed in sequence and summarizing the service characteristics into a characteristic sequence;
inputting the characteristic sequence into a pre-trained sequence processing model, and inputting information output by the sequence processing model and user characteristics of the target user into a pre-trained access intention prediction model to obtain access intention information of the target user, wherein the access intention information is used for indicating a target business module which the target user intends to access;
and sending the resource packet corresponding to the target service module to the target user.
2. The method of claim 1, wherein the determining the service modules in the target application that the target user sequentially accesses within the target duration comprises:
responding to a received target application starting message sent by terminal equipment used by a target user, and acquiring user behavior data generated when the target user uses the target application;
extracting access records of the target user to each service module in the target application within a target time length from the user behavior data, wherein the access records comprise access time;
and determining the service modules which are sequentially accessed by the target user in the target time length according to the sequence of the access time from first to last.
3. The method of claim 1, wherein the sending the resource packet corresponding to the target service module to the target user comprises:
sending a resource package downloading message to the terminal equipment used by the target user;
and responding to a received resource package downloading request returned by the terminal equipment, and sending a resource package corresponding to the target service module to the terminal equipment.
4. The method of claim 1, wherein the sequence processing model and the access intention prediction model are trained by:
acquiring a sample set, wherein samples in the sample set comprise characteristic information and marking information, the characteristic information comprises a sample characteristic sequence and sample user characteristics, the sample characteristic sequence is formed by service characteristics of historical service modules accessed by a user in sequence, and the marking information is used for indicating a target historical service module accessed by the user after the user accesses the historical service modules in sequence;
inputting the sample feature sequence of the sample set into a pre-established attention model, inputting information output by the attention model and the sample user features into a pre-established deep neural network, taking the labeling information of each service feature in the input sample feature sequence as the output of the deep neural network, and training the attention model and the deep neural network by using a machine learning method;
and determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
5. The method of claim 1, wherein a business module is a functional module of the target application, each functional module in the target application is used for providing support for a business line, and the target business module is a functional module that a user intends to access in the target application; and
the sending the resource packet corresponding to the target service module to the target user includes:
acquiring a full resource packet corresponding to the target service module;
and sending the full resource packet to the terminal equipment used by the target user.
6. The method of claim 1, wherein the service module is a data module corresponding to a resource package in the target application, the service feature of the service module is a feature of the resource package, and the target service module is a data module corresponding to a target resource package intended by a user in the target application; and
the sending the corresponding resource packet of the target service module to the target user includes:
acquiring the target resource packet;
and sending the target resource packet to the terminal equipment used by the target user.
7. The method of claim 6, wherein the sequence processing model and the access intention prediction model are trained by:
acquiring a sample set, wherein samples in the sample set comprise characteristic information and marking information, the characteristic information comprises a sample characteristic sequence and sample user characteristics, the sample characteristic sequence is formed by characteristics of historical resource packages sequentially accessed by a user, and the marking information is used for indicating a target historical service module accessed by the user after the user sequentially accesses the historical service module;
inputting the sample feature sequence of the sample set into a pre-established attention model, inputting information output by the attention model and the sample user features into a pre-established deep neural network, taking the label of each feature in the input sample feature sequence as the output of the deep neural network, and training the attention model and the deep neural network by using a machine learning method;
and determining the trained attention model as a sequence processing model, and determining the trained deep neural network as an access intention prediction model.
8. An apparatus for transmitting a resource packet, the apparatus comprising:
the determining unit is configured to determine service modules in the target application sequentially accessed by the target user within the target time length;
the acquiring unit is configured to acquire the service characteristics of the sequentially accessed service modules and summarize the service characteristics into a characteristic sequence;
a prediction unit configured to input the feature sequence into a pre-trained sequence processing model, and obtain access intention information of the target user from information output by the sequence processing model and user features of the target user input into a pre-trained access intention prediction model, wherein the access intention information is used for indicating a target business module which the target user intends to access;
and the sending unit is configured to send the resource packet corresponding to the target service module to the target user.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911305139.6A CN111176750A (en) | 2019-12-17 | 2019-12-17 | Resource packet sending method, device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911305139.6A CN111176750A (en) | 2019-12-17 | 2019-12-17 | Resource packet sending method, device, electronic equipment and computer readable medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111176750A true CN111176750A (en) | 2020-05-19 |
Family
ID=70646407
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911305139.6A Withdrawn CN111176750A (en) | 2019-12-17 | 2019-12-17 | Resource packet sending method, device, electronic equipment and computer readable medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111176750A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109257426A (en) * | 2018-09-26 | 2019-01-22 | 平安普惠企业管理有限公司 | Service line resource loading method, device, computer equipment and storage medium |
CN109918597A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术(北京)有限公司 | Webpage preloads method and apparatus |
CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术(北京)有限公司 | method and apparatus for outputting information |
-
2019
- 2019-12-17 CN CN201911305139.6A patent/CN111176750A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110555714A (en) * | 2018-06-04 | 2019-12-10 | 百度在线网络技术(北京)有限公司 | method and apparatus for outputting information |
CN109257426A (en) * | 2018-09-26 | 2019-01-22 | 平安普惠企业管理有限公司 | Service line resource loading method, device, computer equipment and storage medium |
CN109918597A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术(北京)有限公司 | Webpage preloads method and apparatus |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109522483B (en) | Method and device for pushing information | |
CN107577807B (en) | Method and device for pushing information | |
CN107426328B (en) | Information pushing method and device | |
CN107679217B (en) | Associated content extraction method and device based on data mining | |
CN108121814B (en) | Search result ranking model generation method and device | |
CN107943877B (en) | Method and device for generating multimedia content to be played | |
CN108280200B (en) | Method and device for pushing information | |
CN109359194B (en) | Method and apparatus for predicting information categories | |
CN111340220B (en) | Method and apparatus for training predictive models | |
CN110866040B (en) | User portrait generation method, device and system | |
CN113360803B (en) | Data caching method, device, equipment and storage medium based on user behaviors | |
CN109873756B (en) | Method and apparatus for transmitting information | |
CN111262744B (en) | Multimedia information transmitting method, backup server and medium | |
CN115801980A (en) | Video generation method and device | |
CN109582854B (en) | Method and apparatus for generating information | |
US11184687B2 (en) | Wearable device, information processing method, apparatus and system | |
CN109829117B (en) | Method and device for pushing information | |
CN113822734B (en) | Method and device for generating information | |
CN111026849B (en) | Data processing method and device | |
CN112449217B (en) | Method and device for pushing video, electronic equipment and computer readable medium | |
CN111125502B (en) | Method and device for generating information | |
CN111580883A (en) | Application program starting method, device, computer system and medium | |
CN112084441A (en) | Information retrieval method and device and electronic equipment | |
CN111176750A (en) | Resource packet sending method, device, electronic equipment and computer readable medium | |
CN112307324B (en) | Information processing method, device, equipment and medium |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200519 |