WO2021139701A1

WO2021139701A1 - Application recommendation method and apparatus, storage medium and electronic device

Info

Publication number: WO2021139701A1
Application number: PCT/CN2021/070532
Authority: WO
Inventors: 邱彩玲
Original assignee: 宇龙计算机通信科技(深圳)有限公司
Priority date: 2020-01-06
Filing date: 2021-01-06
Publication date: 2021-07-15
Also published as: CN111277706A; CN111277706B

Abstract

Disclosed are an application recommendation method and apparatus, a storage medium and an electronic device. The method comprises: acquiring an interface start instruction input for a search interface, wherein the search interface includes an application recommendation bar; acquiring current state information of a terminal, and recommending at least one application program on the basis of the state information; and presenting each application program in the application recommendation bar. By means of the embodiments of the present application, application recommendation accuracy is improved, and the user experience is enhanced.

Description

Application recommendation method, device, storage medium and electronic equipment

Technical field

This application relates to the field of computer technology, and in particular to an application recommendation method, device, storage medium, and electronic equipment.

Background technique

The description of the background technology in this application belongs to the related technology related to this application. It is only used to illustrate and facilitate the understanding of the application content of this application. It should not be construed as the applicant's explicit belief or presumption that the applicant believes that this application is the first application Existing technology on the filing date.

With the rapid popularity of terminals (such as mobile phones, computers, tablets, etc.), users usually download various types of applications, such as social applications, game applications, shopping applications, etc., on the terminal, which greatly enriches the application after installing the terminal. The function of the terminal improves the user experience.

As the number of applications installed by users grows, a large number of applications will occupy several pages of the desktop, resulting in too many desktop pages. When the user needs to find a target application in several pages of the desktop, a search interface for searching the application is opened, and the application name of the target application is searched in the search box of the search interface to find the target application.

At present, in order to reduce the frequency of users searching for applications in the search box, the terminal provides an application recommendation bar on the search interface and recommends recently opened applications. The user can quickly find the recently opened applications through the application recommendation bar. However, using the method of displaying recently opened applications in the application recommendation bar, when the target application that the user finds is outside the application range covered by the recently opened application, the user needs to manually search for the application name of the target application in the search box. The accuracy of application recommendation is low, which reduces the user experience.

Summary of the invention

The embodiments of the present application provide an application recommendation method, device, storage medium, and electronic equipment, which can improve the accuracy of application recommendation and increase the user experience. The technical solution is as follows:

In the first aspect, an embodiment of the present application provides an application recommendation method, and the method includes:

Acquiring an interface opening instruction input for a search interface, the search interface including an application recommendation bar;

Acquiring current state information of the terminal, and recommending at least one application program based on the state information;

Display each of the application programs in the application recommendation column.

In a second aspect, an embodiment of the present application provides an application recommendation device, the device including:

An opening instruction acquisition module, configured to acquire an interface opening instruction input for a search interface, the search interface including an application recommendation bar;

An application recommendation module, configured to obtain current state information of the terminal, and recommend at least one application based on the state information;

The application program display module is used to display each of the application programs in the application recommendation column.

In a third aspect, an embodiment of the present application provides a computer storage medium that stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

In a fourth aspect, an embodiment of the present application provides an electronic device, which may include a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute the above method steps .

The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

In one or more embodiments of the present application, the terminal obtains an interface opening instruction entered for a search interface, the search interface includes an application recommendation bar, obtains current state information of the terminal, and recommends at least one application based on the state information, Display each of the application programs in the application recommendation column. By determining the recommended at least one application based on the current status information of the terminal (such as time information, location information, etc.), and displaying the application in the application recommendation bar, the accuracy of application recommendation can be improved, and the user’s search The frequency of searching applications in the box increases the user experience.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of an application recommendation method provided by an embodiment of the present application;

FIG. 2 is a schematic diagram of a scenario for opening a search interface involved in an application recommendation method provided by an embodiment of the present application;

3 is a schematic diagram of an interface of a search interface involved in an application recommendation method provided by an embodiment of the present application;

FIG. 4 is a schematic flowchart of another application recommendation method provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an application recommendation device provided by an embodiment of the present application;

Fig. 6 is a schematic structural diagram of an application recommendation module provided by an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an application recommendation unit provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. In the description of this application, it should be noted that, unless expressly stipulated and defined otherwise, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood under specific circumstances. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more. "And/or" describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects before and after are in an "or" relationship.

The application will be described in detail below in conjunction with specific embodiments.

In one embodiment, as shown in FIG. 1, an application recommendation method is specially proposed, which can be implemented by relying on a computer program and can be run on an application recommendation device based on the von Neumann system. The computer program can be integrated in the application or run as an independent tool application. Wherein, the application recommendation device may be a terminal, and the terminal may be a terminal device with an application recommendation function, including but not limited to: wearable devices, handheld devices, personal computers, tablets, in-vehicle devices, computing devices, or connected to wireless modems Other processing equipment, etc.

Specifically, the application recommendation method includes:

Step 101: Obtain an interface opening instruction input for a search interface, where the search interface includes an application recommendation bar.

In practical applications, with the rapid development of terminals (such as mobile phones), more and more applications are installed on the terminal and more and more files are stored. The terminal usually contains a search interface that provides users with search functions. , You can quickly search for applications or related files through the search box on the search interface of the terminal. In the embodiment of the present application, the search interface includes an application recommendation bar, and the terminal can intelligently recommend applications to the user through the application recommendation bar, so as to reduce the frequency of users searching for applications in the search box and improve user experience.

The instructions are instructions and commands that direct the work of the terminal, and can be understood as codes that specify the execution of a certain operation or a certain control realized by a function. The interface opening instruction can be understood as instructing the terminal to execute the code for opening the search interface function in the embodiment of the present application. By executing the code, the terminal can open the search interface and load it on the display screen of the current terminal.

The application recommendation column may intelligently recommend at least one application to the user based on the application recommendation method of the embodiment of the present application. The application is usually an application that has been installed on the terminal or an application that has not been installed.

Specifically, the user can use a finger touch to give an interface opening instruction input to the terminal for the search interface. Among them, the terminal usually contains a touch screen, and the touch screen has the function of sensing the user's touch operation. The structure of the touch screen includes at least 4 parts: the screen glass layer, the sensor film, the display panel layer, and the controller board. The sensor film has a touch sensor layer and contains a variety of sensors, such as pressure sensors, position sensors, etc. When a user inputs an interface opening instruction through a finger touch on the application menu interface of the terminal's touch screen, the terminal's touch screen can obtain its touch position parameters through the sensors therein. Then the position parameter is processed, the specific touch mode corresponding to the position parameter (such as the finger sliding from top to bottom) is recognized, and the user inputs through the specific touch mode (such as the finger sliding from top to bottom) Start the command for the interface of the search interface. At this time, the terminal can acquire the interface opening instruction input by the user for the search interface, and the terminal executes the interface opening instruction to perform the operation of acquiring the current state information of the terminal as described in the next step.

In a specific implementation, refer to FIG. 2. FIG. 2 is a schematic diagram of a scene of opening a search interface. The terminal display interface shown in FIG. 2 contains multiple application icons. When the arrow in the terminal display interface as shown in Figure 2 indicates the direction of the finger sliding from top to bottom, the terminal specifically touches the screen glass layer of the touch screen of the terminal, and the touch screen contained in the terminal passes through the position sensor in the sensor film. Obtain the position parameters of the "finger sliding from top to bottom", and then process the position parameters to obtain the sliding track of "finger sliding from top to bottom", then the "finger sliding from top to bottom" can be obtained. The interface opening instruction indicated by the sliding track indicates the operation of obtaining the current state information of the terminal as described in the next step by executing the code corresponding to the interface opening instruction.

Optionally, the interface opening instruction input by the user for the search interface can be done through an external device. For example, the user can input a specific operation to open the search interface (such as clicking the button of the search interface) through a mouse connected to the terminal; it can be the user The interface opening instruction entered for the search interface through the keyboard or touchpad connected to the user terminal (such as entering a specific character combination for the search interface); it can be an interface opening instruction entered by the user through voice input (such as voice input to open the search interface, etc.; can be The user collects gesture control instructions through the camera to complete input specific operations (for example, collect gesture control instructions through the camera-V-shaped gesture input interface opening instructions), or input through the physical keys of the touch terminal (power on and off keys, volume keys, etc.) The interface opening instructions and so on.

Step 102: Acquire current state information of the terminal, and recommend at least one application program based on the state information.

The state information may include, but is not limited to, one or more of state information such as current time information of the terminal, exercise state information, and functional modes (such as power saving mode, do-not-disturb mode, etc.) of the terminal.

The application program may include multiple function types, such as payment application, chat application, map application, game application, shopping application, etc.

In a specific implementation, the state information may be exercise state information, and the exercise state may be a walking state, a running mode, an indoor state, an outdoor state, and other sports states. In the embodiment of the present application, different sports The status will correspond to different recommended priority applications. The terminal can collect the motion state information in the environment where the user is located through the included environmental information collection device, which can include one or more of environmental information such as geographic location information, magnetic information, acceleration information, sound information, and angle information. The fitting. There is no specific limitation here. In the embodiment of the present application, the form of the exercise state information collected by the terminal may include, but is not limited to, the following types of collection forms:

For example: the motion state information can be included in the terminal-the angular acceleration data collected by the gyroscope in the current environment, can be included in the electronic device-the acceleration value in the current environment collected by the acceleration sensor, or can be included in the terminal-magnetic force The environmental magnetic field data (magnetic north, true north, magnetic declination, etc.) collected by the sensor in the current environment, or it can be included in the terminal-the user and environmental audio data (pitch, sound intensity) in the current environment collected by the sound collection device , Tone length), it can also be a heartbeat sensor included in the terminal to collect the heartbeat of the user in the current environment, or a temperature and humidity sensor included in the terminal to collect the user in the current environment or the temperature and humidity of the environment, and so on.

The terminal parses the exercise state information based on the exercise state information it is in to determine the current target exercise state of the terminal. The terminal pre-stores a set of applications corresponding to each exercise state, and the set of applications includes at least one application. The terminal may obtain the application set corresponding to the target motion state, and then may determine at least one application to be recommended based on the historical access record of each application in the application set. It is also possible to obtain the application recommendation index of each application in the application set. The application recommendation index can be understood as the corresponding application recommendation score when the application is downloaded, for example, the application recommendation index of a certain application is 4.7 points. At least one application program is determined based on the high and low order of the application recommendation index.

In a specific implementation, the status information may be time information, and the terminal may determine the recommended at least one application from the multiple applications according to the usage time records of the multiple applications. Specifically, the terminal may perform statistical analysis on the recorded usage time records of multiple applications to obtain usage time information of each application, and then determine at least one application indicated by the shortest time from the current time node according to the usage time information for application recommendation.

In a specific implementation, the status information may be application usage information, and the usage information may include multiple types, such as the usage sequence of a certain application program used in history among multiple applications, and the usage frequency of the application program. , Application usage correlation degree, etc. Usage information can indicate the usage of a certain application, can indicate the usage of a certain application relative to multiple other applications, and can reflect the user's usage habits of the application. Generally, specifically, the terminal can perform statistical analysis on the recorded usage records of multiple applications to obtain usage information of each application, and then make application recommendation based on the usage information.

The recommendation method may be that among a plurality of applications arranged in the order of use time from near to far, the application with the highest order of use is recommended first, and at least one application with a higher ranking priority is selected based on the ranking of the applications;

The recommendation method may be that among a plurality of applications arranged in the order of the frequency of use from near to far, the application with the highest order of use is recommended first, and at least one application with a higher ranking priority is selected based on the ranking of the applications, that is, Applications with a higher frequency of use are highly recommended;

The recommendation method may be that among a plurality of applications arranged in the order of higher relevance of use, from near to far, the application with the higher order of use is recommended first, and at least one application with higher ranking priority is selected based on the ranking of the application. Programs, that is, applications with a higher degree of relevance are highly recommended.

Optionally, the terminal may refer based on multiple types of the above-mentioned status information, respectively set weighting factors based on each status information, calculate the recommendation scores of applications installed on the terminal based on the weighting factors, and recommend at least one application based on the recommendation scores, such as Recommend a specified number of applications. Wherein, the weight factor can be modified based on the actual environment to improve the accuracy of application recommendation. In the process of making corrections, the results of each recommendation can be scored based on the error backpropagation algorithm of the accuracy of the application recommendation. The scoring method may be to provide the user with a scoring page for the user to score, or It is the terminal that scores based on the user's operation information (such as the selected time of selecting the target application to be used), and so on.

Step 103: Display each of the application programs in the application recommendation column.

Specifically, as shown in Fig. 3, Fig. 3 is a schematic diagram of an interface of a search interface. The search interface includes multiple control bars, such as a search bar, an application recommendation bar, a discovery bar, etc., in the embodiment of the present application, The terminal may be in the search interface as shown in FIG. 3, and the terminal may intelligently recommend applications to the user through the application recommendation bar, so as to reduce the frequency of users searching for applications in the search box and improve user experience.

Specifically, after the terminal determines at least one recommended application based on the status information, it may display and load the search interface on the current display interface of the terminal, and display the icon of the at least one application on the application recommendation bar for the user to view and use. After the terminal displays the search interface, the user can select the icon of the desired application from the application recommendation bar included in the search interface, among the icons of multiple applications displayed in the When the application start instruction is inputted by the "application program icon", the code corresponding to the application start instruction is executed to start the required application.

Wherein, after the terminal determines at least one recommended application program based on the state information, when displaying each application program in the application recommendation column, the application program with a higher priority may be displayed on the current display interface based on the ranking priority of each application program. Priority display.

In the embodiment of the present application, the terminal obtains an interface opening instruction input for a search interface, the search interface includes an application recommendation bar, obtains current state information of the terminal, recommends at least one application based on the state information, and compares each of the The application program is displayed in the application recommendation column. By determining the recommended at least one application based on the current status information of the terminal (such as time information, location information, etc.), and displaying the application in the application recommendation bar, the accuracy of application recommendation can be improved, and the user’s search The frequency of searching applications in the box increases the user experience.

Please refer to FIG. 4, which is a schematic flowchart of another embodiment of an application recommendation method proposed by the present application. specific:

Step 201: Obtain an interface opening instruction input for a search interface, the search interface including an application recommendation bar.

For details, please refer to step 101, which will not be repeated here.

Step 202: Acquire current time information of the terminal, and determine the target time period to which the time information belongs.

The time information may be time information such as a specific date, a specific time point, and whether it is a working day. In the embodiment of the present application, the time information may be the current time point.

The target time period refers to the time period indicated by the current time information of the terminal. In the embodiment of this application, the terminal presets multiple time periods, such as the first time period (7:00-9:00) and the second time period (7:00-9:00). Time period (11: 00-13:00), third time period (12:00-14:00), etc., by setting multiple time periods, it is possible to recommend applications to users more intelligently based on the current time period.

Specifically, the terminal may obtain current time information through the network, and the time information may be accurate to the date, hour, minute, or second, etc., and then the terminal determines the target time period to which it belongs based on the time information.

Step 203: Obtain historical access records of each application program in the target time period, and recommend a preset number of applications according to the historical access record of each application program.

The historical access record refers to the user's use record of the application on the terminal during the historical target time period, such as the use of the application on the terminal by the user in the target time period in the past specific period (for example, within one month) Records. The historical access records usually include, but are not limited to, access records such as the opening time, opening duration, and opening frequency of the application.

The preset number may be understood as a preset recommended number. For example, if the preset number is 5, the terminal recommends 5 applications according to the historical access records of each application.

Wherein, the preset number may be preset by the terminal at the factory, or may be set by the user in the corresponding preset number setting situation during the later use process, such as in the corresponding preset number Set the situation to set the default number of presets-6 to 5 and so on.

Specifically, when the terminal obtains the historical access record of each application, it can filter the historical access record, extract the usage information in the historical access record of the application in a specific period, and then analyze and analyze the extracted usage information. Based on statistics, a preset number of applications are selected based on the historical access records of each application.

In a feasible implementation manner, the historical access record includes the length of use and the total number of openings, and the weighted calculation is performed on the length of use of each application and the total number of openings to obtain the total number of openings of each application. Recommended value.

One way of calculation is to set a first weighting factor a for the use time and a second weighting factor b for the total number of openings based on the value of the use time and the value of the total number of opening times. For a certain application, the obtained use time is The value of is X, and the value of the total number of openings is Y, then the recommended value for this application is X*a+Y*b.

One calculation method is to set multiple time value ranges based on the value of the use time, each time value range corresponds to a different first weighting factor a; based on the total number of times of opening, set multiple open value ranges, and each open value range corresponds to a different value. The second weighting factor b; for a certain application, the obtained value of the use time is X, and the value of the total number of times of opening is Y. At this time, determine the target time value range corresponding to the value of the use time X to determine the target time value The first weighting factor a corresponding to the range, and then the target opening value range corresponding to the value Y of the total number of times of opening, to determine the second weighting factor b corresponding to the target opening value range. The recommended value for this application is X*a+Y*b.

Wherein, the weight factor can be modified based on the actual environment to improve the accuracy of application recommendation. In the process of making corrections, the results of each recommendation can be scored based on the error backpropagation algorithm of the accuracy of the application recommendation. The scoring method may be to provide the user with a scoring page for the user to score, or It is the terminal that scores based on the user's operation information (such as the selected time of selecting the target application to be used), and so on.

Specifically, after calculating the recommended value of each of the application programs as described above, the application programs are sorted according to the order of the recommended value, and a preset number (such as 5) with a high ranking priority is selected based on the ranking of the application programs. )s application.

Step 204: Obtain current location information of the terminal, and determine a scene tag corresponding to the location information, and the scene tag is associated with at least one application.

The location information can be understood as the location, the place occupied, or the orientation of the terminal located at the current moment. In practical applications, the location information can usually be in the form of latitude and longitude, coordinates, direction, and orientation. It characterizes the location, the occupied place, or the location of the terminal, that is, the current location information of the terminal.

Specifically, after the terminal acquires the interface opening instruction input for the search interface, the positioning function of the terminal associated with the interface opening instruction is triggered, and the terminal acquires the location information at the current moment, for example, the terminal's location information After the positioning function is triggered, the satellite positioning technology is used to obtain the geographic position at the current moment, and the pre-stored reference intensity value is obtained from the local storage space.

Optionally, the terminal can obtain the location information at the current moment by using a corresponding location acquisition technology. The location acquisition technology includes but is not limited to: wireless positioning technology, short-distance connection technology, sensor technology, location image processing technology, etc., among them:

Wireless positioning technology includes but is not limited to: satellite positioning technology, infrared indoor positioning technology, ultrasonic positioning technology, Bluetooth technology, radio frequency identification technology, ultra-wideband technology, Wi-Fi technology, ZigBee technology, etc.

Sensor technology uses position-sensing sensors such as proximity sensors to determine the location of the terminal.

Image processing technology uses the location image collected by the terminal camera to perform image processing to obtain location information and so on.

It should be noted that there are many ways for the terminal to obtain the current location information, which may be one or more of the above-mentioned fitting methods, which are not specifically limited here.

In practical applications, each scene tag corresponds to a piece of reference location information. After acquiring the location information, the terminal then searches the reference location information corresponding to each scene tag for the target reference location information corresponding to the location information, and then The target reference location information serves as a scene tag corresponding to the location information.

Optionally, the terminal obtains the current location information. When the real-time location information is not obtained, the terminal may include the historical location information in the location reference range, that is, the historical location information closest to the current time point is used as the current location information .

The scene tag is used to characterize the location of the scene where the terminal is located. The scene tag includes, but is not limited to, shopping mall scene tag, subway station scene tag, high-speed rail station scene tag, tourist attraction scene tag, restaurant scene tag, school scene tag, hospital At least one of scene tags such as scene tags, movie theater scene tags, bank scene tags, etc.

In practical applications, the terminal may associate at least one application program for each scene tag based on at least one preset scene tag, and the at least one application program associated with each scene tag may be calculated and matched by the server based on big data, and It is understood that the scene tag is associated with at least one application program. Generally, when the user's terminal is under the scene tag, the frequency of opening and the number of times of use are high, and it is highly recommended.

For example, shopping mall scene tags are associated with users with a high frequency or frequency of use: a shopping application, a review application, a payment application, and so on.

For example, the tags associated with subway station scenes are used frequently or frequently by users: a certain navigation application, a certain subway application, a certain payment application, and so on.

For example, the hospital scene label is associated with a high frequency or frequency of use by users: a registered application, a payment application, a medical health application, and so on.

Step 205: Obtain historical access records of each application program, and determine a preset number of application programs according to the historical access record of each application program.

Specifically, after determining the scene tag corresponding to the location information, the terminal obtains the historical access records of all applications associated with the scene tag. The historical access records usually include, but are not limited to, the opening time and the opening duration of the application. , Opening frequency and other access records.

Specifically, when the terminal obtains the historical access records of all applications associated with the scene tag, it can filter the historical access records, extract the usage information in the historical access records of the applications in a specific period, and then extract Analyze and count the usage information of each application, and select a preset number of applications based on the historical access records of each application.

In a feasible implementation manner, the historical access record includes the length of use and the total number of openings, and the weighted calculation is performed on the length of use of each application and the total number of openings to obtain the total number of openings of each application. The recommended value determines the preset number of the application programs according to the order of the recommended value.

In a feasible implementation manner, the historical access record includes usage duration, total number of opening times, and usage correlation degree, and the usage duration, the total number of opening times and the usage correlation degree of each of the applications are performed. A weighted calculation is performed to obtain the recommended value of each of the application programs, and a preset number of the application programs is determined according to the order of the recommended value.

The specific calculation method for obtaining the recommended value based on the weighted calculation can refer to step 203, which will not be repeated here.

Step 206: Acquire current state information and notification information of the terminal, and extract semantic features of the notification information. The notification information includes short message notification information, application notification information, and session notification information.

The notification information is usually a sentence or a combination of multiple sentences with complete and systematic meaning. The text content takes the Chinese language as an example, and can be a word, a sentence, or a paragraph, and the notification information can be an actual use form of the daily notification content.

Specifically, the terminal can obtain current status information and obtain notification information. The notification information includes short message notification information, application notification information, and session notification information. According to the semantic characteristics of various notification information, it can be used to predict what the user needs to open. application.

Among them, the step of obtaining the current status information by the terminal may refer to step 102, which will not be repeated here.

The semantic feature refers to the unique semantic attributes of unstructured data expressed in words. Taking a paper as an example, the semantic feature includes semantic elements such as author's creative intention, data topic description, and underlying feature meaning. The semantic feature information is a variety of features that can express the semantics of the object itself and the semantics in the environment. Taking text content as an example, the semantic feature information can be composed of letters, the order of words, emotional information of words, mutual information, etc. .

Among them, the constituent letters refer to which letters a word is composed of, and the order of these letters.

The word order is the sequence of each word that expresses a sentence (a meaning).

The emotional information of a word is the emotional meaning expressed by the word in the sentence, and the emotional meaning can be understood as whether the word is commendatory or derogatory, high or low, happy or sad, etc. in the sentence.

Mutual information refers to the statistically independent relationship between a certain word or character and category. Mutual information is often used to measure the mutuality between two objects.

In the embodiments of the present application, the semantic feature can be understood as the semantic feature information of the text content. For the notification information, the first semantic feature information may include, but is not limited to, the keyword information of the information, Word frequency distribution information, grammatical-level entity information, semantic-level topics, etc., based on the semantic features extracted from the notification information can be used to predict the applications that the user needs to open.

Specifically, the terminal may obtain all notification information within a specific period of time (for example, within 2 hours), and use a semantic extraction algorithm to extract the semantic features of the notification information.

Optionally, the semantic extraction algorithm may be a text feature information extraction method based on a contextual framework, that is, first determine the extraction elements of the text content (sentences, words, characters, symbols, etc.), and then integrate semantic analysis into the statistical algorithm The text content is extracted to obtain the semantic features of the notification information; it may be a text feature extraction method based on ontology, that is, using an on-tology model to input the notification information and output the notification information Semantic feature information; it can be a conceptual feature extraction method based on HowNet, that is, a feature extraction method based on conceptual features. On the basis of the Vector Space Model (VSM), the notification information is semantically analyzed and used HowNet’s database acquires semantic information of words, maps words with the same semantics to the same concept, then clusters the clustered words and uses them as feature items of the text vector of the VSM model, and then performs model operations, etc. It should be noted that there are many ways to extract the semantic features of the notification information, which may be one or more of the above-mentioned fitting methods, which are not limited here.

Step 207: Input the state information and the semantic feature into the trained application recommendation model, and output the state information and the recommended at least one application program corresponding to the semantic feature.

Specifically, in practical applications, the application recommendation model may be a recommendation analysis algorithm based on deep learning, such as a convolutional neural network (Convolutional Neural Network, CNN) model, a deep neural network (Deep Neural Network, DNN) model, and a loop One or more of neural networks (Recurrent Neural Networks, RNN), models, embedding models, Gradient Boosting Decision Tree (GBDT) models, Logistic Regression (LR) models, etc. At the same time, the error back propagation algorithm is introduced on the basis of the existing neural network model for optimization, which can improve the recommendation accuracy of the initial application recommendation model based on the neural network model.

In practical applications, an initial application recommendation model can be created based on the neural network model CNN. The application recommendation model is a densely interconnected configuration of simple nonlinear simulation processing elements of each node in many nodes, which is a kind of imitation of biology. System model of neuron. The neural network model is formed by connecting the input of at least one node with the output of each node, similar to the synaptic connection of real neurons. Each neuron expresses a specific output function, that is, an excitation function, and every connection between two neurons includes a connection strength, that is, a weighted value that acts on the signal passing through the connection.

In the embodiments of the present application, a large amount of sample data containing state information and the semantic features can be obtained in advance, the state information in the sample data can be preprocessed, and the key features in the state information can be extracted, and based on the The recommended application program for which the sample data has been marked, the key features and semantic feature information are input to the initial application recommendation model for training, and the application recommendation model after training is obtained. The application recommendation model has state information feature extraction, semantic feature knowledge summarization, and The ability of learning and memory, usually the information or knowledge learned by the application recommendation model is stored in the connection matrix between each unit node.

Specifically, after acquiring the status information and notification information, the terminal extracts the semantic features of the notification information, inputs the status information and the semantic features into the trained application recommendation model, and outputs the status information and all the information. The semantic feature corresponds to at least one recommended application.

It should be noted that the above training process for the application recommendation model can be performed on the terminal or on the server that establishes a communication connection with the terminal. For example, the server can pre-train the application recommendation model to generate After the trained application recommendation model, the installation package corresponding to the application recommendation model is pushed to the terminal, and the terminal only needs to install the installation package to obtain the trained application recommendation model. There is no specific limitation here.

Step 208: Obtain current state information of the terminal, send the state information to a server, and receive at least one application that the server feeds back based on the state information.

The server may be a single server device, such as a rack, blade, tower, or cabinet-type server device, or a workstation, a large computer, and other hardware devices with strong computing capabilities; or multiple servers Each server in the service cluster may be formed in a symmetrical manner, where each server is equivalent in function and position in the business link, and each server can provide services independently to the outside world. Providing services can be understood as without the assistance of another server. The terminal communicates with the service server through a network, and the network may be a wireless network or a wired network.

Specifically, after obtaining the current status information, the terminal may send the status information to the server via the network. The server receives the state information (time information, position information, exercise state information, etc.) for analysis and processing. It is understandable that the server can perform analysis and modeling based on the sample data obtained in advance on a large number of electronic devices that contain status information and user application activation records. One way of analysis and modeling is to create an application recommendation model based on a neural network model. Acquire a large amount of sample data containing status information and user application activation records, preprocess the status information in the sample data, extract key features in the sample data, and recommend applications based on the sample data that have been marked, The key features are input to the initial application recommendation model for training, and the trained application recommendation model can be obtained. After receiving the state information (time information, location information, exercise state information, etc.) of the terminal, the server inputs the state information into the application recommendation model, and outputs the application corresponding to the state information that contains at least one application Collection, and then the server pushes the application collection containing at least one application to the terminal. The terminal can then receive at least one application program fed back by the server based on the status information.

Step 209: Display each of the application programs in the application recommendation column.

For details, refer to step 103, which will not be repeated here.

The following are device embodiments of this application, which can be used to implement the method embodiments of this application. For details that are not disclosed in the device embodiments of this application, please refer to the method embodiments of this application.

Please refer to FIG. 5, which shows a schematic structural diagram of an application recommendation apparatus provided by an exemplary embodiment of the present application. The application recommendation device can be implemented as a whole or a part of the device through software, hardware or a combination of the two. The device 1 includes an opening instruction acquisition module 11, an application recommendation module 12, and an application display module 13.

An opening instruction acquisition module 11, configured to acquire an interface opening instruction input for a search interface, the search interface including an application recommendation bar;

The application recommendation module 12 is configured to obtain current state information of the terminal, and recommend at least one application based on the state information;

The application program display module 13 is configured to display each of the application programs in the application recommendation column.

Optionally, as shown in FIG. 6, the status information is time information, and the application recommendation module 12 includes:

The time period determining unit 121 is configured to determine the target time period to which the time information belongs;

The application recommendation unit 122 is configured to obtain the historical access records of each application in the target time period, and recommend a preset number of the applications according to the historical access record of each application.

Optionally, as shown in FIG. 6, the status information is location information, and the application recommendation module 12 includes:

The scene tag determining unit 123 is configured to determine a scene tag corresponding to the location information, where the scene tag is associated with at least one application;

The application recommendation unit 122 is further configured to obtain historical access records of each application, and determine a preset number of the application according to the historical access record of each application.

Optionally, as shown in FIG. 7, the historical access record includes the duration of use and the total number of openings, and the application recommendation unit 122 includes:

The recommended value calculation subunit 1221 is configured to perform a weighted calculation on the usage duration of each application program and the total number of opening times to obtain the recommended value of each application program;

The application program determining subunit 1222 is configured to determine a preset number of the application programs according to the order of the recommended value.

Optionally, as shown in Figure 6, the application recommendation module 12 includes:

The semantic feature extraction unit 124 is configured to obtain the current state information and notification information of the terminal, and extract the semantic feature of the notification information. The notification information includes short message notification information, application notification information, and session notification information;

The application recommending unit 122 is configured to recommend at least one application based on the status information and the semantic feature.

Optionally, the application recommendation module 12 is specifically used for:

The status information is sent to a server, and at least one application program fed back by the server based on the status information is received.

It should be noted that, when the application recommendation device provided in the above embodiment executes the application recommendation method, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be allocated by different functional modules as required. , Divide the internal structure of the device into different functional modules to complete all or part of the functions described above. In addition, the application recommendation device provided in the foregoing embodiment and the application recommendation method embodiment belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the advantages and disadvantages of the embodiments.

In this embodiment, the terminal obtains an interface opening instruction input for a search interface, the search interface includes an application recommendation column, obtains current state information of the terminal, recommends at least one application based on the state information, and assigns each application to The program is displayed in the application recommendation column. By determining the recommended at least one application based on the current status information of the terminal (such as time information, location information, etc.), and displaying the application in the application recommendation bar, the accuracy of application recommendation can be improved, and the user’s search The frequency of searching applications in the box increases the user experience.

The embodiment of the present application also provides a computer storage medium. The computer storage medium may store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executed as described in the embodiments shown in FIGS. 1 to 4 above. The recommended method is applied, and the specific execution process can be referred to the specific description of the embodiment shown in FIG. 1 to FIG. 4, which will not be repeated here.

The present application also provides a computer program product, the computer program product stores at least one instruction, and the at least one instruction is loaded by the processor and executes the application recommendation according to the embodiment shown in FIG. 1 to FIG. 4. For the specific execution process of the method, please refer to the specific description of the embodiment shown in FIG. 1 to FIG.

Please refer to FIG. 8, which provides a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in FIG. 8, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

Among them, the communication bus 1002 is used to implement connection and communication between these components.

The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

Among them, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

The processor 1001 may include one or more processing cores. The processor 1001 uses various excuses and lines to connect various parts of the entire server 1000, and executes the server by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Various functions and processing data of 1000. Optionally, the processor 1001 may adopt at least one of digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), and Programmable Logic Array (Programmable Logic Array, PLA). A kind of hardware form to realize. The processor 1001 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), a modem, and the like. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is used to render and draw the content that the display needs to display; the modem is used to process wireless communication. It is understandable that the above-mentioned modem may not be integrated into the processor 1001, but may be implemented by a chip alone.

The memory 1005 may include random access memory (Random Access Memory, RAM), and may also include read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, where the program storage area may store instructions for implementing the operating system and instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), Instructions and the like used to implement the above method embodiments; the storage data area can store the data and the like involved in the above method embodiments. Optionally, the memory 1005 may also be at least one storage device located far away from the foregoing processor 1001. As shown in FIG. 8, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application recommendation application program.

In the electronic device 1000 shown in FIG. 8, the user interface 1003 is mainly used to provide an input interface for the user to obtain data input by the user; and the processor 1001 may be used to call the application recommendation application stored in the memory 1005, and specifically Do the following:

In one embodiment, the state information is time information, and the processor 1001 specifically performs the following operations when executing the recommending at least one application based on the state information:

Determine the target time period to which the time information belongs;

Obtaining the historical access records of each application program in the target time period, and recommending a preset number of the application programs according to the historical access record of each application program.

In one embodiment, the status information is location information, and the processor 1001 specifically performs the following operations when executing the recommending at least one application based on the status information:

Determine a scene tag corresponding to the location information, where the scene tag is associated with at least one application;

Obtain the historical access records of each application program, and determine a preset number of the application programs according to the historical access record of each application program.

In one embodiment, the historical access record includes the duration of use and the total number of openings, and the processor 1001 specifically executes when the predetermined number of applications is determined according to the historical access records of each application. The following operations:

Performing a weighted calculation on the usage time and the total number of openings of each of the application programs to obtain the recommended value of each of the application programs;

The preset number of the application programs is determined according to the high and low order of the recommended value.

In one embodiment, when the processor 1001 executes the acquisition of the current state information of the terminal and recommends at least one application program based on the state information, the processor 1001 specifically executes the following operations:

Acquiring current state information and notification information of the terminal, and extracting semantic features of the notification information, where the notification information includes short message notification information, application notification information, and session notification information;

Recommend at least one application based on the status information and the semantic feature.

In an embodiment, when the processor 1001 executes the recommendation of at least one application program based on the state information and the semantic feature, the processor 1001 specifically performs the following operations:

Those skilled in the art can clearly understand that the technical solution of the present application can be implemented by means of software and/or hardware. The "unit" and "module" in this specification refer to software and/or hardware that can independently complete or cooperate with other components to complete specific functions. The hardware may be a Field-Programmable Gate Array (FPGA), for example. , Integrated Circuit (IC), etc.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited by the described sequence of actions. Because according to this application, some steps can be performed in other order or at the same time. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed device may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections may be indirect couplings or communication connections through some service interfaces, devices or units, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory. A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: flash memory Disk, Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk or optical disk, etc.

The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited by this. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope of the present disclosure. Those skilled in the art will easily think of other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. This application is intended to cover any modifications, uses, or adaptive changes of the present disclosure. These modifications, uses, or adaptive changes follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field that are not recorded in the present disclosure. . The description and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

An application recommendation method, characterized in that the method includes:

Acquiring an interface opening instruction input for a search interface, the search interface including an application recommendation bar;

Acquiring current state information of the terminal, and recommending at least one application program based on the state information;

Display each of the application programs in the application recommendation column.
The method according to claim 1, wherein the state information is time information, and the recommending at least one application program based on the state information comprises:

Determine the target time period to which the time information belongs;

Obtaining the historical access records of each application program in the target time period, and recommending a preset number of the application programs according to the historical access record of each application program.
The method according to claim 1, wherein the status information is location information, and the recommending at least one application program based on the status information comprises:

Determine a scene tag corresponding to the location information, where the scene tag is associated with at least one application;

Obtain the historical access records of each application program, and determine a preset number of the application programs according to the historical access record of each application program.
The method according to claim 2 or 3, wherein the historical access record includes the length of use and the total number of openings, and the determination of a preset number of applications according to the historical access records of each application includes :

Performing a weighted calculation on the usage time and the total number of openings of each of the application programs to obtain the recommended value of each of the application programs;

The preset number of the application programs is determined according to the high and low order of the recommended value.
The method according to claim 1, wherein the acquiring current state information of the terminal and recommending at least one application program based on the state information comprises:

Acquiring current state information and notification information of the terminal, and extracting semantic features of the notification information, where the notification information includes short message notification information, application notification information, and session notification information;

Recommend at least one application based on the status information and the semantic feature.
The method of claim 5, wherein the recommending at least one application program based on the state information and the semantic feature comprises:

The state information and the semantic feature are input into a trained application recommendation model, and the state information and the at least one application program recommended corresponding to the semantic feature are output.
The method according to claim 1, wherein the at least one application program determined based on the state information comprises:

The status information is sent to a server, and at least one application program fed back by the server based on the status information is received.
An application recommendation device, characterized in that the device includes:

An opening instruction acquisition module, configured to acquire an interface opening instruction input for a search interface, the search interface including an application recommendation bar;

An application recommendation module, configured to obtain current state information of the terminal, and recommend at least one application based on the state information;

The application program display module is used to display each of the application programs in the application recommendation column.
A computer storage medium, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1-7.
An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is adapted to be loaded by the processor and executed as claimed in any one of claims 1 to 7. Method steps.