WO2023125692A1

WO2023125692A1 - Service recommendation method and related apparatus

Info

Publication number: WO2023125692A1
Application number: PCT/CN2022/142915
Authority: WO
Inventors: 王云路; 邹志国; 方荣杰; 李序旸; 唐鹏程; 刘成; 卓晓燕; 朱君浩
Original assignee: 华为技术有限公司
Priority date: 2021-12-30
Filing date: 2022-12-28
Publication date: 2023-07-06
Also published as: CN116415061A

Abstract

Provided in the present application are a service recommendation method and a related apparatus. The method comprises: a first electronic device generating a first service set on the basis of personal data of a first user, wherein the first service set comprises a plurality of service functions, and the personal data of the first user comprises historical use data of the first user (S3501); and when it is detected that a trigger condition for the first service set is satisfied, the first electronic device executing a plurality of functional operations corresponding to the first service set (S3502). A first electronic device can automatically recommend a plurality of different service functions to a user according to historical use data of the user, thereby realizing the convenience and accuracy of service recommendation.

Description

A service recommendation method and related device

This application claims the priority of a Chinese patent application with application number 202111670318.7 and application title "A Service Recommendation Method and Related Device" filed with the China Patent Office on December 30, 2021, the entire contents of which are incorporated by reference in this application middle.

technical field

The present application relates to the technical field of artificial intelligence, in particular to a service recommendation method and related devices.

Background technique

With the continuous development of electronic technology and computer technology, terminals such as mobile phones, tablet computers, and smart wearable devices have been popularized. The terminal can use various services provided by the application program or the system to realize corresponding functions. When the user needs to use a certain function of the application, for example, viewing the booking information in application A requires the user to independently search for the corresponding application and open the relevant function interface of the application through multiple operations, which are relatively cumbersome operations. How to improve the convenience and accuracy of service recommendation is an urgent problem to be solved.

Contents of the invention

The present application provides a service recommendation method and a related device, which realize the convenience and accuracy of service recommendation.

In a first aspect, the present application provides a service recommendation method, including: a first electronic device generates a first service collection based on the personal data of the first user, the first service collection includes multiple service functions, and the personal data of the first user includes The historical usage data of the first user; when it is detected that the trigger condition of the first service set is satisfied, the first electronic device executes multiple functional operations corresponding to the first service set.

The first service set includes multiple service functions, that is to say, the first electronic device can integrate multiple services with different functions into one service set (that is, the first service set) and recommend it to the user, realizing "one-click use" by the user Operation of multiple services.

The historical use data of the first user may be personal portrait data for the first user, such as user preferences, behavior habits, gender, age, and the like. That is to say, the first electronic device automatically generates the first service set for the user based on the personal portrait data of the first user, and the user does not need to manually set the scene-related service set. On the other hand, with the change of the user's personal portrait data, the service set generated by the first electronic device for the user is also different, which reflects the accuracy of the service recommendation.

The historical use data of the first user may also be the user's historical operations. That is, the user behavior of the user within a period of time, such as the setting items of the first electronic device within a period of time, or the setting items of the first electronic device controlling other electronic devices. For example, yesterday the first user used the setting items of turning on the air conditioner and closing the curtains in the movie watching scene. Today, in the movie watching scene, the first electronic device recommends the recommendation card for the user to turn on the air conditioner and close the curtains.

Through the method provided in the first aspect, on the one hand, the user does not need to perform complex operations to set the service set, which saves user operations and improves user experience. On the other hand, the service set includes multiple service functions, so that the first electronic device can automatically recommend multiple service functions to the user at the same time, that is, the first electronic device can simultaneously execute multiple functions corresponding to multiple service functions Easy to operate. On the other hand, as the user's personal data becomes more and more abundant, the service set automatically generated by the first electronic device for the user is more in line with the behavior characteristics of the user, that is, the service set recommended by the first electronic device for the user is more accurate. At different times, locations and device states, that is, for the same user, in different scenarios, the first electronic device automatically recommends different service sets for the user. The convenience and accuracy of service recommendation are realized.

Optionally, in a possible implementation manner, after the first electronic device generates the first service set based on the personal data of the first user, before the first electronic device executes multiple functional operations corresponding to the first service set, The method further includes: when the first condition is met, the first electronic device displays the first recommendation card corresponding to the first service set; when it is detected that the trigger condition of the first service set is met, the first electronic device executes the The multiple functional operations specifically include: when a trigger operation for the first recommended card is detected, the first electronic device executes multiple functional operations corresponding to the first service set.

Wherein, the first electronic device may simultaneously display recommendation cards corresponding to multiple service sets, and each service set may include multiple services, or may only include one service.

In this way, after the first electronic device displays the first recommendation card corresponding to the service set, the user can check which service functions the first electronic device automatically recommends for the user, so that the user can decide whether the first electronic device needs to execute the first electronic device Multiple service functions that are automatically recommended for users.

When the trigger condition is a trigger operation on the first recommended card, the first electronic device detects the user's trigger operation (for example, click) on the first recommended card, which enables the user to "use" multiple services with one click.

The triggering condition can also be a voice command, the identity information of the first user, a gesture, etc., so that the first electronic device can be triggered to execute multiple services in the first service set without manual operation by the user, which is convenient and fast.

Optionally, in a possible implementation manner, the method further includes: the first electronic device generates a second service set based on the personal data of the first user, the second service set includes multiple service functions, and the second service set corresponds to The multiple functional operations are different from the multiple functional operations corresponding to the first service set; when it is detected that the trigger condition of the second service set is met, the first electronic device executes the multiple functional operations corresponding to the second service set. In this way, for the same user, in different scenarios, the first electronic device can automatically generate different service sets for the user, reflecting the intelligence of service recommendation.

Optionally, in a possible implementation manner, the method further includes: the first electronic device generates a third service set based on the personal data of the second user, the third service set includes multiple service functions, and the personal data of the second user It includes the historical usage data of the second user; when it is detected that the trigger condition of the third service set is satisfied, the first electronic device executes multiple functional operations corresponding to the third service set. If the personal data of the first user is different from the personal data of the second user, the multiple functional operations corresponding to the third service set are different from the multiple functional operations corresponding to the first service set. In this way, in the same scene, for different users, the service sets generated by the electronic device are also different, which reflects the differences of users and the intelligence of service recommendation.

Optionally, in a possible implementation manner, the first electronic device executes multiple functional operations corresponding to the first service set, specifically including: the first electronic device executes the first service based on the execution relationship of multiple services in the first service set Multiple functional operations corresponding to a service set. Wherein, the execution relationship of multiple services in the first service set includes but not limited to sequential execution, simultaneous execution and so on.

Optionally, in a possible implementation manner, multiple service functions in the first service set correspond to multiple service functions of different applications, or multiple service functions in the first service set correspond to control of multiple different devices. In this way, different applications are controlled simultaneously or different devices are controlled simultaneously.

Optionally, in a possible implementation manner, the multiple service function types in the first service set include any one or more of the following: application services, system services, and services for controlling working states of other electronic devices. The first electronic device executes multiple functional operations corresponding to the first service set, specifically including: the first electronic device controls the first electronic device to work with a first working parameter, where the first working parameter includes any one or more of the following: The setting state of the system of the first electronic device, the setting state of the application installed on the first electronic device, and the opening/closing of the application installed on the first electronic device. And/or, the first electronic device controls the third electronic device to work with the second working parameter, wherein the second working parameter includes any one or more of the following: on/off of the third electronic device, setting state of the third electronic device .

Optionally, in a possible implementation manner, before the first electronic device generates the first service set based on the personal data of the first user, the method further includes: when the first condition is met, the first electronic device acquires multiple The first electronic device generates the first service set based on the personal data of the first user, specifically including: the first electronic device generates the first service set based on multiple candidate service functions based on the first user's personal data. That is, before generating the first service set, the first electronic device needs to acquire multiple candidate service functions.

Optionally, in a possible implementation manner, before the first electronic device obtains multiple candidate service functions, the method further includes: the first electronic device obtains a candidate service set, and the service functions in the candidate service set include the following Any one or more items: the service function sent by the server, the service function sent by other electronic devices, the service function preset in the first electronic device; the first electronic device obtains multiple candidate service functions, specifically including: the first electronic device The device acquires multiple candidate service functions from the candidate service set based on the personal data of the first user.

Optionally, in a possible implementation manner, the first electronic device acquires multiple candidate service functions from the candidate service set based on the first user's personal data, specifically including: the first electronic device obtains multiple candidate service functions based on the first user's personal data The probability of using each service function in the candidate service set by the first user is obtained from the data; the first electronic device screens out multiple service functions whose usage probability is greater than a preset value, and obtains candidate service functions.

Optionally, in a possible implementation manner, the first condition includes any one or more of the following: the current time meets the first time, the location of the first electronic device meets the preset location, and the location associated with the first user The device state of the electronic device satisfies the preset state, wherein the device state includes the current power of the electronic device, whether the electronic device is connected to WiFi, whether the electronic device is connected to Bluetooth, whether the electronic device is on, whether the electronic device outputs audio, and whether the electronic device is turned on/off .

Wherein, in different places, the electronic device recommends different services for the user. For example, in Shenzhen, the first electronic device may recommend the Shenzhen subway boarding code for the user. In Wuhan, the first electronic device can recommend Wuhan subway codes for users.

Optionally, in a possible implementation manner, before the first electronic device generates the first service set based on the personal data of the first user, the method further includes: the first electronic device acquires multiple service sets in the first scene The first electronic device generates the first service set based on the first user's personal data, specifically including: the first electronic device determines the first service set from multiple service sets based on the first user's personal data. That is, the first electronic device may not filter out a single service and generate a service set based on multiple individual services, but directly select a service set that may be used by the user from multiple service sets.

Optionally, in a possible implementation manner, the multiple service sets are service sets whose similarity with the service function used by the first user in the first scenario is greater than a preset value; The personal data of the service determines the first service set from multiple service sets, specifically including: the first electronic device determines the type of device that the first user cares about in the first scenario; the first electronic device determines the type of device that the first user cares about based on the A first service set similar to the device type concerned by the first user is determined from the plurality of service sets based on the personal data of the first user. That is to say, the first electronic device may recommend to the user a set of services used by similar users that are close to the type of device that the first user cares about.

Optionally, in a possible implementation manner, the first electronic device determines the type of device that the first user pays attention to in the first scenario, which specifically includes: the first electronic device based on the working status of the device associated with the first user . The state of the first user detected by the device associated with the first user determines the type of device concerned by the first user.

Optionally, in a possible implementation manner, the first electronic device determines based on the working status of the device associated with the first user and the status of the first user detected by the device associated with the first user The type of device, specifically includes: the first electronic device determines the degree of attention of the first user to multiple devices based on the working status of the device associated with the first user and the status of the first user detected by the device associated with the first user ; The first electronic device regards the top M devices of the first user's attention to multiple devices as the type of device that the first user is concerned about.

Optionally, in a possible implementation manner, the method further includes: the first electronic device acquires the first time when the user history uses the first service set and the second time when the first electronic device history displays the first recommendation card; When the first electronic device determines that the first time is earlier than the second time, or the first time is later than the second time and the difference between the first time and the second time is greater than a preset value, the first electronic device A preset trigger condition of a service set is adjusted; after the first electronic device adjusts the preset trigger condition of the first service set, the first electronic device displays the first recommendation card at a third time, wherein the third time is at Before the first time, and the difference between the third time and the first time is smaller than the preset value. That is to say, the first electronic device can dynamically adjust the time for the first electronic device to display the first service set based on the time when the user uses the first service set and the time for displaying the first service set, so as to prevent the first electronic device from displaying the first service set. There is a large deviation between the time of the service set and the time when the user uses the first service set.

Optionally, in a possible implementation manner, the first time is the average time of the user using the first service set within the first time period; the second time is the first time displayed by the first electronic device within the first time period. The average of the time to serve the collection. In this way, the time for displaying the first service set by the first electronic device is adjusted based on the statistical data within a period of time, which ensures the reliability of the statistical data.

Optionally, in a possible implementation manner, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset trigger condition, and the preset The trigger condition includes one or more subconditions, and the maximum constraint condition is the last executed subcondition among the one or more subconditions; the first electronic device delays the execution time of the maximum constraint condition of the preset trigger condition by a first duration; the first electronic device A first newly added sub-condition is determined, wherein the execution time of the first newly added sub-condition is earlier than the execution time after the maximum constraint condition of the preset trigger condition is delayed by a first duration. In this way, the first electronic device can adjust the preset trigger condition that triggers the scene too early.

Optionally, in a possible implementation manner, the displaying the first recommendation card by the first electronic device at the third time specifically includes: before the third time, the first electronic device detects that the first newly added sub-condition has not been Execution, the first electronic device displays the first recommendation card at a third time. In this way, the first electronic device can prevent the user from using the first service set in advance, but the maximum constraint condition of the preset trigger condition has not been implemented, resulting in the late recommendation of the first service set.

Optionally, in a possible implementation manner, the method further includes: before the third time, the first electronic device detects that the first newly added sub-condition is executed within the first duration of delayed execution of the maximum constraint condition, The first electronic device displays the first recommendation card at a fourth time, and the fourth time is earlier than the third time.

Optionally, in a possible implementation manner, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset trigger condition; the first The electronic device determines the second newly added sub-condition, wherein the execution time of the second newly added sub-condition is earlier than the execution time of the maximum constraint condition of the preset trigger condition; the first electronic device replaces the maximum constraint condition of the preset trigger condition Add a sub-condition for the second. In this way, the first electronic device can adjust the preset trigger condition that the scene is triggered too late.

Optionally, in a possible implementation manner, the first electronic device presenting the first recommendation card at the third time specifically includes: the first electronic device detects that the second new sub-condition is executed, and the first electronic device The first recommendation card is displayed at a third time.

Optionally, in a possible implementation manner, the method further includes: before the third time, the first electronic device detects that the second newly added sub-condition is not executed but the maximum constraint condition of the preset trigger condition is executed, The first electronic device displays the first recommendation card at a fourth time, and the fourth time is later than the third time. In this way, the first electronic device can avoid the situation that the user uses the first service set in advance, and the maximum constraint condition of the preset trigger condition triggers but the second new sub-condition has not been executed, resulting in the late recommendation of the first service set.

Optionally, in a possible implementation manner, the method further includes: the first electronic device acquires the first time when the user history used the first service set and the second time when the first electronic device stopped displaying the first recommendation card in the history; When the first electronic device determines that the first time is later than the second time, or the first time is earlier than the second time and the difference between the first time and the second time is greater than a preset value, the first electronic device The default exit condition of the first service set is adjusted; after the first electronic device adjusts the preset exit condition of the first service set, the first electronic device stops displaying the first recommendation card at a third time, wherein the third The time is after the first time, and the difference between the third time and the first time is smaller than a preset value. That is to say, the first electronic device can dynamically adjust the time when the first electronic device stops displaying the first service set based on the time when the user uses the first service set and the time when the user stops displaying the first service set, so as to prevent the first electronic device from stopping There is a large deviation between the time when the first service set is displayed and the time when the user uses the first service set.

Optionally, in a possible implementation manner, the first time is the average time of the user using the first service set within the first time period; the second time is the first electronic device stops displaying the first service set within the first time period. The average value of time for a collection of services. In this way, the time at which the first electronic device stops displaying the first set of services is adjusted based on the statistical data within a period of time, which ensures the reliability of the statistical data.

Optionally, in a possible implementation manner, the first electronic device adjusts the preset exit condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset exit condition, and the preset The exit condition includes one or more subconditions, and the maximum constraint condition is the last executed subcondition among the one or more subconditions; the first electronic device delays the execution time of the maximum constraint condition of the preset exit condition by a first duration;

Alternatively, the first electronic device determines the first newly added sub-condition, wherein the execution time of the first newly added sub-condition is earlier than the execution time after the maximum constraint condition of the preset exit condition is delayed by a first duration. In this way, the first electronic device can adjust the preset trigger condition that the scene exits too early.

Optionally, in a possible implementation manner, the displaying the first recommendation card by the first electronic device at the third time specifically includes: before the third time, the first electronic device detects that the first newly added sub-condition has not been Execution, the first electronic device displays the first recommendation card at a third time.

Optionally, in a possible implementation manner, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset exit condition; the first The electronic device determines the second newly added sub-condition, wherein the execution time of the second newly added sub-condition is earlier than the execution time of the maximum constraint condition of the preset exit condition; the first electronic device replaces the maximum constraint condition of the preset exit condition Add a sub-condition for the first. In this way, the first electronic device can adjust the preset trigger condition that the scene exits too late.

Optionally, in a possible implementation manner, the displaying of the first recommendation card by the first electronic device at the third time specifically includes: the first electronic device detects that the first new sub-condition is executed, and the first electronic device The first recommendation card is displayed at a third time.

Optionally, in a possible implementation manner, the method further includes: before the third time, the first electronic device detects that the first newly added sub-condition is not executed but the maximum constraint condition of the preset exit condition is executed, The first electronic device displays the first recommendation card at a fourth time, and the fourth time is later than the third time.

Optionally, in a possible implementation manner, the method further includes: after the first electronic device displays the first recommendation card, and the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements , the first electronic device generates a fourth service set based on the personal data of the first user, and the fourth service set does not include the first service function in the first service set; the first electronic device displays the second recommendation corresponding to the fourth service set card, the display elements on the second recommended card are the same as the default display elements. In this way, the first electronic device can avoid displaying incomplete services recommended for the user.

Optionally, in a possible implementation manner, after the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements, the method further includes: the first electronic device adds the The identification of the first service function is sent to the server, and the identification of the first service function is used by the server to reduce the credibility of the first service function; the first electronic device receives the credibility information sent by the server after reducing the credibility of the first service function , the reputation information is used to indicate the reputation of multiple different service functions. In this way, the first electronic device avoids recommending and displaying incomplete services for the user by reducing the credibility of displaying incomplete services.

Optionally, in a possible implementation manner, the first electronic device generates the fourth service set based on the personal data of the first user, which specifically includes: the first electronic device selects multiple different service functions based on the reputation information sent by the server. A fourth service set is generated based on the personal data of the first user, and the credibility of the second service function in the fourth service set is higher than the credibility of the first service function in the first service set.

Optionally, in a possible implementation manner, before the first electronic device displays the first recommendation card, the method further includes: the first electronic device acquires the verification result generated by the first service function in the first service set, The verification result is used to indicate whether the first service function has obtained the preset permission information and the preset data information. Displaying the first recommendation card by the first electronic device specifically includes: displaying the first recommendation card by the first electronic device when the verification result is that the first service function has acquired preset authority information and preset data information. In this way, the first electronic device determines whether to recommend the service to the user through service self-verification, which improves the efficiency of service verification.

Optionally, in a possible implementation manner, before the first electronic device displays the first recommendation card corresponding to the first service set, it further includes: establishing a communication connection between the first electronic device and the second electronic device; The device acquires the first degree of attention of the first user to the first electronic device, and the second degree of attention of the first user to the second electronic device; the first electronic device determines based on the first degree of attention and the second degree of attention to display the first The device of the service set; the first electronic device displays the first recommendation card corresponding to the first service set, specifically including: when the device displaying the first service set is the first electronic device, the first electronic device displays the first recommendation card corresponding to the first service set First recommendation card. In this way, the first electronic device may recommend services on devices that the user cares about based on the user's current degree of attention to each device.

Optionally, in a possible implementation manner, the method further includes: when the device displaying the first service set is the second electronic device, the first electronic device sends the identifier of the service function in the first service set to the second electronic device. On the electronic device, the identifier of the service function in the first service set is used by the second electronic device to display the first recommendation card.

Optionally, in a possible implementation manner, before the first electronic device determines the device displaying the first service set based on the first degree of attention and the second degree of attention, the method further includes: the first electronic device acquires the first The degree of matching between the service functions in a service set and the first electronic device, the matching degree between the service functions in the first service set and the second electronic device, the priority of the service functions in the first service set, and the displayable information on the first electronic device Service function capacity, service function capacity that can be displayed on the second electronic device; the first electronic device determines the device displaying the first service set based on the first degree of attention and the second degree of attention, specifically including: the first electronic device based on the first Degree of attention, second degree of attention, matching degree of service functions in the first service set and the first electronic device, matching degree of service functions in the first service set and the second electronic device, priority of service functions in the first service set , the service function capacity that can be displayed on the first electronic device, and the service function capacity that can be displayed on the second electronic device determine the device displaying the first service set.

In a second aspect, the present application provides an electronic device, which is a first electronic device, characterized in that the first electronic device includes: one or more processors, one or more memories; one or more memories and one or more A plurality of processors are coupled, and one or more memories are used to store computer program codes, and the computer program codes include computer instructions, and one or more processors invoke computer instructions to make the first electronic device perform any of the above-mentioned aspects. A service recommendation method provided in the implementation.

In the third aspect, a computer-readable storage medium provided by an embodiment of the present application is used to store computer instructions. When the computer instructions are run on the first electronic device, it is possible for the first electronic device to perform any one of the above-mentioned aspects. A service recommendation method provided in the implementation of .

In a fourth aspect, the embodiment of the present application provides a computer program product, which is characterized in that, when the computer program product is run on the first electronic device, the first electronic device is made to execute any possible implementation of any of the above aspects A service recommendation method provided in .

Description of drawings

FIG. 1A-FIG. 1B exemplarily show schematic diagrams of two service recommendation areas;

FIG. 2 exemplarily shows a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application;

Figure 3-Figure 4 exemplarily shows a schematic diagram of a group of users manually setting recommendation services provided by the embodiment of the present application;

FIG. 5 exemplarily shows a functional module schematic diagram of how the electronic device 100 recommends services for users in the first manner provided by the embodiment of the present application;

FIG. 6 exemplarily shows a flowchart of a method for how the electronic device 100 recommends a service set for a user according to an embodiment of the present application;

FIG. 7 exemplarily shows a schematic diagram of how an electronic device 100 trains a model 702 according to an embodiment of the present application;

FIG. 8 exemplarily shows a schematic diagram of how an electronic device 100 uses a model to recommend multiple services provided by an embodiment of the present application;

FIG. 9A-FIG. 9L exemplarily show a set of UI diagrams provided by the embodiment of the present application;

FIG. 10 exemplarily shows a schematic diagram of how the server 200 calculates the similarity of different users according to the embodiment of the present application;

FIG. 11 exemplarily shows a schematic diagram of how the server 200 calculates the similarity of service sets used by different users based on the similarity according to the embodiment of the present application;

FIG. 12 exemplarily shows a UI diagram of an electronic device 100 recommending a set of services used by similar users for user A in a movie viewing scene provided by an embodiment of the present application;

FIG. 13 exemplarily shows a UI diagram of an electronic device 100 recommending a set of services used by similar users for user A in a driving scene provided by an embodiment of the present application;

FIG. 14 exemplarily shows a schematic diagram of how an electronic device 100 trains an attention calculation model according to an embodiment of the present application;

FIG. 15 exemplarily shows a schematic diagram of how an electronic device 100 according to an embodiment of the present application obtains user attention scores for different devices based on the attention calculation model;

Figure 16-Figure 17 exemplarily shows a UI diagram of a set of recommended service sets for similar users provided by the embodiment of the present application;

18A-18E exemplarily show a schematic diagram of a deviation between the time when the electronic device 100 enters the scene or exits the scene and the time when the user actually uses the service set in the scene;

FIG. 19 exemplarily shows a functional block diagram of an electronic device 100 for adaptively adjusting scene conditions provided by an embodiment of the present application;

FIG. 20 exemplarily shows a schematic diagram of a normal distribution of data of a scene service set used by a user provided by an embodiment of the present application;

FIG. 21 exemplarily shows a schematic diagram of an electronic device 100 adjusting a trigger condition for entering a scene too early according to an embodiment of the present application;

FIG. 22 exemplarily shows a schematic diagram of an electronic device 100 adjusting a trigger condition for entering a scene too late according to an embodiment of the present application;

FIG. 23 exemplarily shows a schematic diagram of an electronic device 100 adjusting the exit condition of a scene exiting too late according to an embodiment of the present application;

FIG. 24 exemplarily shows a schematic diagram of an electronic device 100 adjusting preset exit conditions for prematurely exiting a scene provided by an embodiment of the present application;

25A-25D exemplarily show a schematic diagram of a group of recommended cards provided by the embodiment of the present application in which the function is abnormal;

FIG. 26 exemplarily shows a schematic diagram of how an electronic device 100 verifies a service to be recommended according to an embodiment of the present application;

FIG. 27 exemplarily shows a software structural block diagram of an electronic device 100 provided by an embodiment of the present application;

Fig. 28 exemplarily shows an interactive schematic diagram of a service review method provided by an embodiment of the present application;

Fig. 29 exemplarily shows a schematic diagram of how a recommendation system provided by an embodiment of the present application checks the service to be recommended through the service management module;

Fig. 30 exemplarily shows a schematic diagram of how to update the credibility score of the service to be recommended provided by the embodiment of the present application;

FIG. 31 exemplarily shows a schematic diagram of service recommendation on a single device provided by the embodiment of the present application;

Fig. 32 exemplarily shows a schematic diagram of service loading on multiple devices provided by the embodiment of the present application;

FIG. 33A exemplarily shows a schematic framework diagram of a multi-device simultaneous triggering service recommendation process provided by an embodiment of the present application;

FIG. 33B exemplarily shows a schematic framework diagram of a single-device-triggered service recommendation process provided by an embodiment of the present application;

FIG. 34 exemplarily shows a schematic diagram of service recommendation areas of several different specifications provided by the embodiment of the present application;

FIG. 35 exemplarily shows a schematic flowchart of a service recommendation method provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the accompanying drawings. Among them, in the description of the embodiments of this application, unless otherwise specified, "/" means or means, for example, A/B can mean A or B; "and/or" in the text is only a description of associated objects The association relationship indicates that there may be three kinds of relationships, for example, A and/or B, which may indicate: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiment of the present application , "plurality" means two or more than two.

Hereinafter, the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as implying or implying relative importance or implicitly specifying the quantity of indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the embodiments of the present application, unless otherwise specified, the "multiple" The meaning is two or more.

The term "user interface (UI)" in the following embodiments of this application is a medium interface for interaction and information exchange between an application program or an operating system and a user, and it realizes the difference between the internal form of information and the form acceptable to the user. conversion between. The commonly used form of user interface is the graphical user interface (graphic user interface, GUI), which refers to the user interface related to computer operation displayed in a graphical way. It may be text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, Widgets, and other visible interface elements displayed on the display screen of the electronic device.

First, technical terms involved in the embodiments of the present application are explained.

1. Scenes and services: Scenes are user-defined, such as morning scenes, commuting scenes, leaving home scenes, returning home scenes, watching movies, sleeping scenes, navigation scenes, taxi scenes, driving scenes, etc. Scenarios include trigger conditions. Scenes can also correspond to corresponding services. The trigger condition is used to identify the category of the scene, and can trigger the electronic device to recommend the preset service of the scene. The trigger conditions may include one or more items, and the trigger conditions may include but not limited to time, location, device status, etc. When one or more items such as time, place, and device state meet the trigger conditions, the electronic device can execute the service in the corresponding scene.

Services can be used to implement preset functions in a scene or provide convenient functions for this type of scene. Services may include system services, application services, and services for controlling the working status of other electronic devices. Different applications can provide the same service, and the same application can also provide multiple services with different functions.

Wherein, the system service is a service provided based on native capabilities of the electronic device, such as an alarm clock service, a schedule service, a weather service, a time service, an audio playback service, a Bluetooth service, and the like.

The service for controlling the working state of other electronic devices may control the working modes of other electronic devices establishing a communication connection with the electronic device. For example, the electronic device can control the smart speaker with which it establishes a communication connection to start or stop playing music. The electronic device can control the large screen with which the communication connection is established to start playing or stop playing the video.

Application services are services provided by providers of applications installed on electronic devices. Different applications can provide the same service, for example, a taxi application can provide a taxi service, and a map application can also provide a navigation service. The same application can also provide multiple services with different functions, for example, the WeChat application can provide payment services, and the WeChat application can also provide call services, etc.

Optionally, the setting state of the device may also be called a service. For example, setting the brightness of the device, setting the volume of the device, controlling the device to turn on, controlling the device to turn off, etc., can all be understood as services.

Optionally, the service may also include an application recommended by the electronic device 100 for the user. For example, when the electronic device 100 detects that there are unread messages in a social application, the electronic device 100 recommends the social application for the user. The embodiment of the present application does not limit the type of service recommended by the electronic device 100 for the user.

Exemplarily, when the electronic device recognizes that the current scene is a sleep scene, the electronic device is automatically set to a do-not-disturb mode, and controls the smart speaker and the large screen that have established a communication connection with it to enter a rest mode, and at the same time close the curtains.

When the electronic device recognizes that the current scene is a sports scene, the electronic device will adjust the local ringtone to the maximum, and set the social software to the do-not-disturb mode. Telephone".

When the electronic device recognizes that the current scene is a scene of leaving home, if the user does not have a car, the electronic device recommends a taxi service for the user. If the user has a car, the electronic device recommends a navigation service for the user.

2. Scene recognition: Based on the data collected by different sensors, electronic devices can use one or more of models, rules and expert knowledge to analyze the data collected by sensors under certain criteria to complete the scene recognition process. The process of analyzing the data collected by the sensor includes a pre-fusion algorithm and a post-fusion algorithm. The pre-fusion algorithm fuses the original sensor data together through the data collected by multiple sensors. The post-fusion algorithm processes and analyzes the original sensor data to obtain the analysis results, that is, to determine the specific scene category. Common sensors include, but are not limited to, pressure sensors, gyroscope sensors, acceleration sensors, distance sensors, proximity light sensors, fingerprint sensors, temperature sensors, touch sensors, and ambient light sensors. Electronic devices can perceive the current scene of the user based on the sensor data acquired by the sensor, combined with time, location, device status and other information, such as working scene, driving scene, sleeping scene, movie watching scene, etc.

Exemplarily, when the electronic device detects that the electronic device turns on the screen for the first time after a long time off screen through the proximity light sensor, and the time displayed on the electronic device is between 5:00 and 8:00 in the morning, the electronic device can determine that A user of an electronic device is in a morning scene.

When the electronic device detects that the large screen in the home is playing video, the smart speaker is outputting audio, the curtains in the living room are closed, and the lights in the living room are also turned off, and the large screen detects that the user is staring at the large screen for a long time through the camera on the screen. screen, the electronic device can determine that the user using the electronic device is in a movie viewing scene.

3. Service recommendation: It can also be called personalized service recommendation or service recommendation. It usually refers to actively recommending one or more services to the user on the desktop after the electronic device recognizes a specific scene, so as to promote the user to be more effective. An information service method that utilizes each service efficiently. The service in the embodiment of the present invention is an object that can provide users with information or interactive functions. In an initial state, the electronic device may display a service recommendation area on the desktop for recommending various services to the user; or may display the service recommendation area or close the service recommendation area based on the user's instruction. The service recommendation area may be located in any area on the desktop, which is not limited in this embodiment of the present application. For example, the service recommendation area may be located on the page displayed on the status bar or the drop-down status bar, one screen behind, the area adjacent to the area where the global search function is located, and so on.

Exemplarily, FIG. 1A and FIG. 1B show possible locations of two service recommendation areas on the UI. As shown in Figure 1A, the service recommendation area can be directly displayed on the desktop, and the service recommendation area can also be displayed on the display interface that slides out from the side as shown in Figure 1B, and the user can invoke the display interface through preset instructions , to get the service recommendation area.

4. Group portraits: Group portraits are labels for user groups generated using group data.

The tags of the user group may include but not limited to: in each scenario, the service category that the user group frequently uses, the service category that the user group ignores the most services, the service category that the user group closes the most services, and the service category that the user group reports the most Service category and so on. According to eh, how to make a group portrait of the user group to obtain the service usage of the user group will be introduced in detail in the subsequent embodiments, and the embodiments of the present application will not be repeated here.

In some embodiments, the user group is a collection of all users regardless of gender, age or region. In some embodiments, user groups can be classified according to gender, for example, user groups can be divided into female user groups and male user groups. Alternatively, the user groups may also be divided into user groups of various age groups. Exemplarily, when the user group is divided into a female user group and a male user group, group portraits may be divided into female user group portraits and male user group portraits. Specifically, group data may be divided into data of male user groups and data of female user groups. According to the data of the male user group, the male user group is profiled, that is, the male user group is labeled, for example, the male user group is most interested in sports services, and not interested in movie viewing services, etc. According to the data of female user groups, make portraits of female user groups, that is, label female user groups, for example, female user groups are interested in health monitoring services, not interested in sports services, etc. Exemplarily, when the user group is divided into user groups of various age groups, the group portrait can also be used to profile the user group according to the user groups of various age groups. Specifically, group data may be classified according to age groups. For example, the user group data whose user age is between 0-20 years old is divided into one category, the user group data whose user age is between 21-35 years old is divided into one category, and the user group data whose user age is between 36-50 years old is divided into one category. The user group data is divided into one category, and the user group data whose users are between 51 and 70 years old are divided into one category. According to the user group data of each age group, the user groups of each age group are profiled, that is, the user groups of each age group are labeled. For example, the user group aged 0-20 is most interested in sports services, the user group aged 21-35 is most interested in food delivery services, and the user group aged 36-50 is most interested in Health testing services are the most interested, and user groups aged 51-70 are most interested in social services.

The embodiment itself provides a service recommendation method, the method includes: the electronic device 100 generates a first service set based on the personal data of the first user, the first service set includes a plurality of service functions, and the personal data of the first user includes the first service set A user's historical usage data; when it is detected that the trigger condition of the first service set is met, the electronic device 100 executes multiple functional operations corresponding to the first service set. In this way, the convenience and accuracy of service recommendation are realized.

The first service set includes multiple service functions, that is to say, the electronic device 100 can integrate multiple services with different functions into one service set (that is, the first service set) operation of a service.

The historical use data of the first user may be personal portrait data for the first user, such as user preferences, behavior habits, gender, age, and the like. That is to say, the electronic device 100 automatically generates the first service set for the user based on the personal portrait data of the first user, and does not require the user to manually set the scene-related service set. On the other hand, as the user's personal portrait data changes, the service sets generated by the electronic device 100 for the user are also different, reflecting the accuracy of service recommendation.

Optionally, the historical usage data of the first user may also be the user's historical operations. That is, the user behavior of the user within a period of time, such as the setting items of the electronic device 100 within a period of time, or the setting items of controlling other electronic devices by the electronic device 100 . For example, yesterday the first user used the setting items of turning on the air conditioner and closing the curtains in the movie watching scene, and today in the movie watching scene, the electronic device 100 recommends recommendation cards for the user to turn on the air conditioner and close the curtains.

Optionally, the historical usage data of the first user may also be personal portrait data of the first user and historical operations of the user.

Optionally, the electronic device 100 may also combine the user's degree of attention to different devices, and recommend to the user a set of services used by similar users with similar devices concerned. Specifically, reference may be made to the embodiments described in subsequent FIG. 10-FIG. 17 , and details are not described here in this embodiment of the present application.

Optionally, the embodiment of the present application may also adjust the preset trigger condition and the preset exit condition of the scene, so that the electronic device 100 improves the accuracy of the recommended service. Exemplarily, when the trigger condition is satisfied, the electronic device 100 will recommend one or more services to the user, and display the one or more services in the form of a recommendation card in a recommendation area on the desktop. The electronic device 100 may record the time when the user triggers the electronic device 100 to execute the one or more services, and based on the actual execution time of the one or more services and the time when the electronic device 100 displays the one or more services, determine that the electronic device 100 100 whether the time for displaying one or more services is appropriate, if not, electronic device 100 will adjust the time for electronic device 100 to display one or more services based on preset rules, so that electronic device 100 displays one or more services The difference between the time of the electronic device 100 and the time when the electronic device 100 actually executes the one or more services is less than the preset time, which improves the accuracy of the electronic device 100 in displaying the service card. The principle of how to adjust the launch condition of the service is similar to the principle of how to adjust the trigger condition of the service. Specifically, how the electronic device 100 adjusts the triggering condition of the service may refer to the embodiments introduced in FIG. 21-FIG. 22 , and details will not be described here in this embodiment.

Optionally, this embodiment of the present application may also verify the displayed services. The electronic device 100 obtains the verification result sent by the service, and when the verification result is that the preset authority information and the preset data information are obtained, the electronic device 100 recommends the service. After the electronic device 100 recommends a service, the electronic device 100 may also score the credibility of the service whose display content does not comply with the rules, so as to reduce the recommendation of the service by the electronic device 100 . Specifically, when the trigger condition is satisfied, the electronic device 100 will recommend one or more services to the user, and display the one or more services in the form of a card in a designated area on the desktop. The electronic device 100 will detect whether the displayed content of the one or more services is complete. If the electronic device 100 detects that the displayed content of the one or more services is incomplete, the electronic device 100 will reduce the reputation of the one or more services, so that the probability of recommending the service with reduced reputation to the user is reduced. Specifically, how the electronic device 100 reduces service credibility can refer to the embodiments introduced in FIG. 25A-FIG. 30 , which will not be repeated in this embodiment of the present application.

Optionally, this embodiment of the present application may also implement service distribution to multiple devices on a single device. Specifically, after the electronic device 100 recalls multiple services, the electronic device 100 can realize the priority based on multiple services, the user's current attention to each device, the service capacity of each device, and the matching of each service on each device. Sort the recalled multiple services based on factors such as speed, get the optimal distribution of each service on each device, and then distribute and transfer the services, and finally display each service on the most suitable device to achieve cross-device recommendation services . Reference can be made to the embodiments introduced in FIG. 32-FIG. 34 , and the embodiments of the present application will not be described in detail here.

FIG. 2 shows a schematic structural diagram of the electronic device 100 .

The electronic device 100 may be a large screen, a mobile phone, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, as well as a cellular phone, a personal digital Assistant (personal digital assistant, PDA), augmented reality (augmented reality, AR) equipment, virtual reality (virtual reality, VR) equipment, artificial intelligence (artificial intelligence, AI) equipment, vehicle-mounted equipment, etc. The specific type of equipment is not particularly limited.

The electronic device 100 may include a processor 110, an internal memory 121, a universal serial bus (universal serial bus, USB) interface 130, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, Receiver 170B, microphone 170C, earphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, and the like.

It can be understood that, the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine certain components, or separate certain components, or arrange different components. The illustrated components can be realized in hardware, software or a combination of software and hardware.

The processor 110 may include one or more processing units, for example: the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The controller can generate an operation control signal according to the instruction opcode and timing signal, and complete the control of fetching and executing the instruction.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in processor 110 is a cache memory. The memory may hold instructions or data that the processor 110 has just used or recycled. If the processor 110 needs to use the instruction or data again, it can be directly called from the memory. Repeated access is avoided, and the waiting time of the processor 110 is reduced, thereby improving the efficiency of the system.

In some embodiments, processor 110 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous transmitter (universal asynchronous receiver/transmitter, UART) interface, mobile industry processor interface (mobile industry processor interface, MIPI), general-purpose input and output (general-purpose input/output, GPIO) interface, subscriber identity module (subscriber identity module, SIM) interface, and /or universal serial bus (universal serial bus, USB) interface, etc.

The USB interface 130 is an interface conforming to the USB standard specification, specifically, it can be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. The USB interface 130 can be used to connect a charger to charge the electronic device 100 , and can also be used to transmit data between the electronic device 100 and peripheral devices. It can also be used to connect headphones and play audio through them. This interface can also be used to connect other electronic devices, such as AR devices.

The wireless communication function of the electronic device 100 can be realized by the antenna 1 , the antenna 2 , the mobile communication module 150 , the wireless communication module 160 , a modem processor, a baseband processor, and the like.

Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 may be used to cover single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization of the antennas.

The mobile communication module 150 can provide wireless communication solutions including 2G/3G/4G/5G applied on the electronic device 100 . The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. The mobile communication module 150 can receive electromagnetic waves through the antenna 1, and filter and amplify the received electromagnetic waves, and send them to the modem processor for demodulation. The mobile communication module 150 can also amplify the signals modulated by the modem processor, and convert them into electromagnetic waves and radiate them through the antenna 1 . A modem processor may include a modulator and a demodulator.

The wireless communication module 160 can provide wireless local area networks (wireless local area networks, WLAN) (such as wireless fidelity (Wireless Fidelity, Wi-Fi) network), bluetooth (bluetooth, BT), global navigation satellite, etc. applied on the electronic device 100. System (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , demodulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 . The wireless communication module 160 can also receive the signal to be sent from the processor 110 , frequency-modulate it, amplify it, and convert it into electromagnetic waves through the antenna 2 for radiation.

The electronic device 100 realizes the display function through the GPU, the display screen 194 , and the application processor. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos and the like. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light emitting diode or an active matrix organic light emitting diode (active-matrix organic light emitting diode, AMOLED), flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light emitting diodes (quantum dot light emitting diodes, QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194 , where N is a positive integer greater than 1.

The electronic device 100 can realize the shooting function through the ISP, the camera 193 , the video codec, the GPU, the display screen 194 and the application processor.

Camera 193 is used to capture still images or video. The object generates an optical image through the lens and projects it to the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other image signals. In some embodiments, the electronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.

The internal memory 121 may include one or more random access memories (random access memory, RAM) and one or more non-volatile memories (non-volatile memory, NVM).

The electronic device 100 can implement audio functions through the audio module 170 , the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor. Such as music playback, recording, etc.

The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signal. The audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be set in the processor 110 , or some functional modules of the audio module 170 may be set in the processor 110 .

Speaker 170A, also referred to as a "horn", is used to convert audio electrical signals into sound signals. Electronic device 100 can listen to music through speaker 170A, or listen to hands-free calls.

Receiver 170B, also called "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or a voice message, the receiver 170B can be placed close to the human ear to receive the voice.

The microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a phone call or sending a voice message, the user can put his mouth close to the microphone 170C to make a sound, and input the sound signal to the microphone 170C. The electronic device 100 may be provided with at least one microphone 170C. In some other embodiments, the electronic device 100 may be provided with two microphones 170C, which may also implement a noise reduction function in addition to collecting sound signals. In some other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and realize directional recording functions, etc.

The earphone interface 170D is used for connecting wired earphones. The earphone interface 170D can be a USB interface 130, or a 3.5mm open mobile terminal platform (OMTP) standard interface, or a cellular telecommunications industry association of the USA (CTIA) standard interface.

The pressure sensor 180A is used to sense the pressure signal and convert the pressure signal into an electrical signal. In some embodiments, pressure sensor 180A may be disposed on display screen 194 . The electronic device 100 determines the intensity of pressure according to the change in capacitance. When a touch operation acts on the display screen 194, the electronic device 100 detects the intensity of the touch operation according to the pressure sensor 180A. The electronic device 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A.

The gyro sensor 180B can be used to determine the motion posture of the electronic device 100 . In some embodiments, the angular velocity of the electronic device 100 around three axes (ie, x, y and z axes) may be determined by the gyro sensor 180B. The acceleration sensor 180E can detect the acceleration of the electronic device 100 in various directions (generally three axes). The distance sensor 180F is used to measure the distance. Proximity light sensor 180G may include, for example, light emitting diodes (LEDs) and light detectors, such as photodiodes. The light emitting diodes may be infrared light emitting diodes. The electronic device 100 emits infrared light through the light emitting diode. Electronic device 100 uses photodiodes to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it may be determined that there is an object near the electronic device 100 . When insufficient reflected light is detected, the electronic device 100 may determine that there is no object near the electronic device 100 . The ambient light sensor 180L is used for sensing ambient light brightness. The electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. The fingerprint sensor 180H is used to collect fingerprints. The temperature sensor 180J is used to detect temperature. In some embodiments, the electronic device 100 uses the temperature detected by the temperature sensor 180J to implement a temperature treatment strategy. The touch sensor 180K is also called "touch device". The touch sensor 180K can be disposed on the display screen 194, and the touch sensor 180K and the display screen 194 form a touch screen, also called a “touch screen”.

The keys 190 include a power key, a volume key and the like. The key 190 may be a mechanical key. It can also be a touch button. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100 .

The motor 191 can generate a vibrating reminder. The motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations applied to different applications (such as taking pictures, playing audio, etc.) may correspond to different vibration feedback effects. The motor 191 may also correspond to different vibration feedback effects for touch operations acting on different areas of the display screen 194 .

The indicator 192 can be an indicator light, and can be used to indicate charging status, power change, and can also be used to indicate messages, missed calls, notifications, and the like.

Firstly, how the electronic device 100 recommends services for the user is introduced.

Currently, the electronic device 100 supports the user to manually add in an application program (for example, a smart life application program), and in a certain scene, when a trigger condition is met, the electronic device 100 will be triggered to execute a task.

As shown in Figure 3, the user has added a new scene as the "go home" scene in the setting interface of the smart life application, and the trigger condition of the "go home" scene is "when this scene card is clicked" or "say Voice command Xiaoyi Xiaoyi, I’m home”, the electronic device 100 will perform the following tasks, “turn on the air conditioner in the living room and adjust it to 26°C”, “turn on the air purifier in the living room” and “turn on the light in the living room, And adjusted to warm white". After the user sets the scene name, trigger conditions and execution tasks, the electronic device 100 receives the user's input operation (for example, click) on the completion control in the setting interface, and in response to the user's input operation, the electronic device 100 will display the "My Scenes" interface. In this way, the triggering conditions and execution tasks of the "going home" scene have been created.

From the operation steps in Figure 3-4, it can be seen that the user needs to manually add the trigger conditions of the scene and execute the task, the user operation is cumbersome, and the user experience is not good.

Therefore, how to reduce user operations and recommend personalized services for users is an urgent problem to be solved.

In the service generation method provided in the embodiment of the present application, the electronic device 100 may generate a service set based on the user's personal data, and the service set includes multiple service functions. The user's personal data includes the first user's historical usage data. When it is detected that the trigger condition of the first service set is satisfied, the electronic device 100 executes multiple functional operations corresponding to the service set.

In this way, the electronic device 100 can automatically generate a service set for the user based on the user's personal data, without requiring the user to manually set and generate the service set. On the one hand, it does not require users to perform complex operations to set up service collections, which saves user operations and improves user experience. On the other hand, the service set includes multiple service functions, so that the electronic device 100 can automatically recommend multiple service functions for the user at the same time, that is, the electronic device 100 can simultaneously perform multiple functional operations corresponding to multiple service functions, Convenient. On the other hand, as the user's personal data becomes more and more abundant, the service set automatically generated by the electronic device 100 for the user is more in line with the behavior characteristics of the user, that is, the service set recommended by the electronic device 100 for the user is more accurate. At different times, locations and device states, that is, for the same user, in different scenarios, the electronic device 100 automatically recommends different service sets for the user. The convenience and accuracy of service recommendation are realized.

Optionally, based on the personal data of different users, if the personal data of different users is different at the same time, place and device status, the electronic device 100 recommends different service sets to different users, reflecting the The difference of users reflects the intelligence of service recommendation.

Optionally, after the electronic device 100 generates the service set, the electronic device 100 may display a recommendation card corresponding to the service set. The recommendation card can display information functions of multiple service functions in the service collection. In this way, after displaying the recommendation card corresponding to the service set, the user can check which service functions are automatically recommended by the electronic device 100 for the user, so that the user can decide whether to need the electronic device 100 to execute multiple service functions automatically recommended by the electronic device 100 for the user. .

Optionally, the electronic device 100 may also combine the user's degree of attention to different devices, and recommend to the user a set of services used by similar users with similar devices concerned.

Among them, generating a service set based on the user's personal data can be understood as the electronic device 100 obtains the user's historical usage data by learning the user's usage habits on the device associated with the user, and actively generates the user's high probability of using in each scenario. service combination, generate a recommendation card based on the service combination, and display the recommendation card on the electronic device 100.

Based on the user's degree of attention to different devices, recommend to the user a set of services used by similar users with similar devices. A service combination is recommended for similar users of devices with close attention, and a recommendation card is generated based on the service combination, and the recommendation card is displayed on the electronic device 100 .

The above service generating methods are described in detail below respectively.

Firstly, the specific implementation of the electronic device 100 generating a service set based on the user's personal data is introduced.

The user's personal data includes the user's historical usage data. The user's historical usage data may be personal portrait data for the user, such as user preferences, behavior habits, gender, age, and so on. That is to say, the electronic device 100 automatically generates a service set for the user based on the user's personal portrait data, and does not require the user to manually set a scene-related service set. As the user's personal portrait data changes, the service sets generated by the electronic device 100 for the user are also different, reflecting the accuracy of service recommendation.

Optionally, the user's personal data can also be operated on the user's history. That is, the user behavior of the user within a period of time, such as the setting items of the electronic device 100 within a period of time, or the setting items of controlling other electronic devices by the electronic device 100 . For example, yesterday the first user used the setting items of turning on the air conditioner and closing the curtains in the movie watching scene, and today in the movie watching scene, the electronic device 100 recommends recommendation cards for the user to turn on the air conditioner and close the curtains.

Optionally, the electronic device 100 may also generate a service set based on the user's personal portrait data and the user's historical operations.

The electronic device 100 needs to obtain services, and the services obtained by the electronic device 100 may be sent to the electronic device 100 by a server, may be sent to the electronic device 100 by other electronic devices, or may be preset by the electronic device 100 .

The service sources acquired by the server 200 may be the following three types:

(1) Scenarios preset in the server 200 and service sets in each scenario.

That is to say, based on experience and analysis, developers have preset a collection of services that users may use in a scenario. For example, in the scene of getting up in the morning, the user may use the service at home to play services for speakers, sports and health services, etc. In the movie watching scene, the services that users may use are large-screen playback service, speaker playback service, curtain closing service, and light turning off service, etc.

(2) The usage record of the user is synchronized to the server 200, and the server 200 acquires service sets used by different users in different scenarios.

Optionally, the user can choose whether to synchronize the use records on the electronic device to the server 200 . That is, the electronic device 100 may display prompt information, and the prompt information is used to prompt the user whether to synchronize the use record on the electronic device to the server 200 . If the user refuses, the electronic device will not synchronize the usage record on the electronic device to the server 200 . If the user agrees, the electronic device can periodically synchronize the use records on the electronic device to the server 200 . In this way, the electronic device respects the user's privacy by asking for the user's permission and then synchronizing the use record on the electronic device to the server 200 .

That is to say, after the user uses the service locally, the user's usage record is uploaded to the server 200 locally. It is understandable that in the same scenario, different users may use different sets of services. For example, in the morning scene, user A likes to exercise, then user A has the habit of going out to exercise every morning, then the services used by user A in the morning scene can be sports health service and box play service. If user B does not like sports, then the service that user B may use in the scene of getting up in the morning is the speaker playback service. User C doesn't like sports and has no speakers at home, so the service that user B may use in the morning scene is the mobile phone playback service.

After obtaining the use records of different users, the server 200 summarizes the use records of different users to obtain a service set that may be used by the user in each scenario. For example, after obtaining the usage records uploaded by users A, B and C, the server 200 summarizes the usage records of users A, B and C, and obtains the service set that users may use in the morning scene as follows: Sports health service, box broadcast service and mobile phone broadcast service.

(3) A collection of services shared by users in preset scenarios.

Users can manually edit the set of services used in the scene they want in the application (such as smart life). Afterwards, when the user thinks that the effect of the setting is better, the user can share the scene set by himself and the service collection under the scene in the sharing interface of the application. After other users log in to the same application (such as smart life), Other users can see the scene shared by other users and the collection of services in the scene in the sharing interface. And refer to the scene in the common interface and the service set in the scene to set the service set in the scene for yourself.

After the user shares the scene and the service set under the scene set by the user in the sharing interface of the application, the electronic device will synchronize the scene set by the user and the service set under the scene to the server 200, and the server 200 can obtain the user's The set scene and the set of services under the scene.

The methods for obtaining user data are not limited to those listed above. In some embodiments, the server 200 may also collect user data in other ways, for example, the user data may also be obtained by analyzing test data. The test data can be that the developer can analyze and summarize the use records of different users (also called testers) within a certain period of time to obtain the collection of services used by different users in the preset scenario, and obtain user data. The server 200 may also collect user data in other ways, which is not limited in this embodiment of the present application.

After the server 200 acquires the user data, the server 200 will perform statistics on the user data, and calculate service sets used by different users at different times, different locations, and on different devices.

Table 1

Table 1 exemplarily shows statistical results of services that users aged 0-10 will use at different locations during the time of 7:00-09:00 on Saturday morning. In places where the location type is gourmet, such as snack fast food restaurants, Chinese restaurants and beverage stores, the service that users will use is gourmet service, which can be understood as the application on electronic devices that can provide functions of searching and purchasing gourmet food, electronic devices Different applications on the Internet can provide different food services. In places where the location type is leisure and entertainment, such as leisure sports venues and public leisure places, the services that users will use are entertainment services. Entertainment services can be understood as applications on electronic devices that can provide leisure and entertainment functions. Entertainment services include but are not limited to Different applications on electronic devices can provide different entertainment services such as game services, music playback services, video playback services, and shopping services. In places where the location type is sports services, such as stadiums, fitness centers, swimming pools, martial arts fighting rooms, ball games and dance studios, the services that users will use are sports services. Sports services include but are not limited to step counting services, timing Services, calorie consumption services, etc., different applications on the electronic device can provide different exercise services. In locations where the type of location is cultural education, such as schools, training and educational institutions, scientific research institutions, and driving schools, the services that users will use are educational services. Educational services include but are not limited to course explanation services, homework guidance services, etc. Different electronic devices The application can provide different educational services. In locations where the type of location is medical, such as medical examination institutions, specialized hospitals, general hospitals, and pharmaceutical health care stores, the services that users will use are medical services, including but not limited to medical consultation services, registration services, consultation services, etc. Different applications on electronic devices can provide different medical services. In locations where the location type is transportation facilities, such as airports, train/high-speed rail stations, subway stations, passenger stations, parking lots, and bus stations, the services that users will use are transportation services, which include but are not limited to taxi-hailing services, ride-hailing Different applications on electronic devices can provide different traffic services. In a location where the type of location is office or residence, such as a residence or a commercial building, the service that the user will use is an entertainment service, and different applications on the electronic device may provide different entertainment services. In places where the type of place is shopping, such as a supermarket and a convenience store, the service that the user will use is a payment service, and different applications on the electronic device may provide different payment services.

It should be noted that during weekends and non-weekends, in the same time period, users may use different services in different locations. The server 200 also needs to calculate the collection of services that users of the same age group will use in different locations at the same time point, on weekends and non-weekends. For example, Table 1 exemplarily shows a set of services that users aged 0-10 will use in different places between 7:00 am and 9:00 am on Saturday. Similarly, the server 200 also needs to count the collection of services that users aged 0-10 will use in different locations between 7:00 am and 9:00 am on Monday.

Table 1 exemplarily shows the collection of services that users aged 0-10 will use at different locations between 7:00 am and 9:00 am. The server 200 also needs to count the collection of services that users aged 0-10 will use in different time periods and places. For example, a collection of services that users aged 0-10 will use at different locations between 10:00 am and 12:00 am. A collection of services that users aged 0-10 will use at different locations between 1:00 p.m. and 3:00 p.m. A collection of services that users aged 0-10 will use at different locations between 4:00 p.m. and 6:00 p.m. A collection of services that users aged 0-10 will use at different locations between 7:00 p.m. and 9:00 p.m. A collection of services that users aged 0-10 will use at different locations between 10:00 p.m. and 12:00 p.m.

Table 1 exemplarily shows service sets that users aged 0-10 will use in different locations. The server 200 can calculate service sets that users of other age groups will use in different locations based on the user data. For example, a collection of services used by users aged 11-20 in different locations. A collection of services that users aged 21-30 use in different locations. A collection of services used by users aged 31-40 in different locations. A collection of services used by users aged 41-50 in different locations. A collection of services used by users aged 51-60 in different locations. A collection of services used by users aged 61-70 in different locations. A collection of services used by users aged 71-80 in different locations. A collection of services used by users aged 81-90 in different locations. The services used by users of different ages in different locations may be different or the same, which will not be repeated in this embodiment of the present application.

It should be noted that Table 1 is only an example showing service sets that users aged 0-10 will use in different locations. In practical applications, more statistical results of services used by users in other locations than in Table 1 may be included, and Table 1 does not list them one by one, nor should it be construed as a limitation.

Optionally, the user may use multiple services at the same location, so the server 200 can also calculate the probability of multiple services that the user will use at the same location type, and calculate the probability of multiple services that the same location type will use The probabilities are sorted from largest to smallest. Exemplarily, when a user is at a place where the place type is food, the service with the highest probability of use is food service, followed by payment service, and finally entertainment service. When a user is in a place where the location type is leisure and entertainment, the service with the highest probability of use is entertainment service, followed by sports service, and finally transportation service. When a user is in a place where the location type is sports and fitness, the service with the highest probability of use is sports service, followed by entertainment service, and finally schedule service. When a user is in a place whose location type is culture and education, the service with the highest probability of use is education service, followed by memo service, and finally entertainment service. When a user is in a location where the location type is medical, the service with the highest probability of use is medical service, followed by entertainment service, and finally telephone service. When a user is at a location where the location type is transportation facilities, the service with the highest probability of use is transportation service, followed by entertainment service, and finally telephone service. When a user's location type is office or residence, the service with the highest probability of use is entertainment service, followed by education service, and finally transportation service. When a user is in a location where the type of location is shopping, the service with the highest probability of use is entertainment service, followed by transportation service, and finally food service.

Optionally, at the same time and at the same place, the same user uses different services when using different electronic devices. Therefore, the server 200 can also calculate statistical results of services used by the same user at the same time and at the same place when using different electronic devices. For example, the services used by users aged 0-10 through mobile phones in residences between 7:00 am and 9:00 am are entertainment services. Users between the ages of 0-10 years old will use the service of Bluetooth watch in the residence between 7:00 am and 9:00 am for the health detection service.

Optionally, not limited to dividing users into different user groups based on age, statistics may also be performed based on user types. For example, users are divided into categories such as otaku, schoolmaster, beauty makeup party, outfit party, sports party, travel buddy, and fitness expert. The server 200 counts service collections that different types of user groups will use in different locations. For example, the server 200 collects statistics on service sets that otaku users will use in different locations. The server 200 counts the collection of services used by top class users in different locations. The server 200 counts the collection of services that the beauty party users will use in different locations. The server 200 counts the collection of services that the wearable party users will use in different locations. The server 200 counts the collection of services that the sports party users will use in different locations. The server 200 counts service collections that donkey-friend users will use in different locations. The server 200 collects statistics on the collection of services that the fitness expert user will use in different locations.

After the server 200 obtains the user group portrait, the server 200 sends the result of the overall user portrait to the electronic device 100 . That is to say, the server 200 sends to the electronic device 100 a collection of services that different user groups will use at different times, locations, and locations.

After the electronic device 100 receives the set of services that different user groups will use at different times, places and places sent by the server 200, the electronic device 100 will filter the above set, delete useless data, and obtain a candidate service set.

After collecting the user data, the electronic device 100 may also perform preprocessing on the user data. For example, standardize the processing of various types of data and classify them according to their importance, sensitivity, timeliness or other specifics, and establish a unified data storage mode. In this way, user data obtained through different methods and platforms can be stored in a unified standard, and complete and comprehensive data can be collected to facilitate subsequent construction of complete user attributes. Here, different types of user data can have different storage standards, for example, exercise health data and travel data can be stored by different standards.

Specifically, the electronic device 100 may, based on the personal information of the user using the electronic device 100, the services that can be provided by the installed applications on the electronic device 100, etc., send the server 200 information about the services that different user groups will use at different times, places, and locations. Filter the set, delete services irrelevant to the user using the electronic device 100, and obtain the user's candidate service set.

Exemplarily, if the age of the user using the electronic device 100 is between 20-30 years old, then the electronic device 100 can only retain the user group whose user is between the age of 20-30 at different times, places, and will use A collection of services, delete the collection of services that users whose age is not between 20 and 30 years old will use at different times, places, and services.

Exemplarily, if there is no application installed on the electronic device 100 that can provide the takeaway service, then the electronic device 100 may delete the information that the service is the takeaway service.

In some embodiments, after the electronic device 100 obtains the candidate service set, the electronic device 100 will sort the multiple services in each scenario in the candidate service set based on the user's personal data, and estimate the service in each scenario. The service probability that the user will use personally, and filter out the set of services whose usage probability is greater than the preset value. Afterwards, the electronic device 100 obtains a set of services for which the user's personal usage rate is greater than a preset value in each scenario, and obtains a set of marked services.

In other embodiments, the electronic device 100 may not receive the candidate service set sent by the server, but sort the preset services on the electronic device 100 based on the user's personal data, And estimate the service probability that the user will use in each scenario, and filter out the set of services whose usage probability is greater than the preset value. Afterwards, the electronic device 100 obtains a set of services for which the user's personal usage rate is greater than a preset value in each scenario, and obtains a set of marked services. Among them, the services preset on the electronic device 100 are the services configured by the electronic device 100 at the factory, and the like.

Alternatively, the electronic device 100 may not receive the set of candidate services sent by the server, but filter out the services preset on the electronic device 100 based on the user's historical operations, and the user's history Operate services with a high degree of matching to obtain a set of calibrated services.

The electronic device 100 acquires the user's personal data. The sources of the user's personal data include but are not limited to the following: 1. Personal data in various devices related to the user; User's personal data, personal data obtained by information input devices of various devices related to users.

Optionally, the user can choose whether to authorize the electronic device to obtain the user's personal data. That is, the electronic device 100 may display prompt information, and the prompt information is used to prompt the user whether to authorize the electronic device to acquire the user's personal data. If the user refuses, the electronic device will not obtain the user's personal data. If the user agrees, the electronic device can periodically obtain the user's personal data from the above-mentioned methods. In this way, the electronic device respects the user's privacy by asking for the user's permission and then obtaining the user's personal data.

It is not limited to the several methods of collecting data listed above, and in some embodiments, user data may also be collected in other ways, which are not limited here.

The electronic device 100 screens the candidate service sets acquired by the electronic device 100 based on the personal data to obtain a marked service set. Alternatively, the electronic device 100 filters the services stored on the electronic device 100 based on the personal data to obtain the marked service set.

Table 2

The calibration service set records the set of services that the user A will use in each scenario is greater than the preset value. For example, in the scene of waking up in the morning, the set of services that user A will use includes but is not limited to speaker broadcast service, health detection service, and so on. In the sleep scene, the set of services that user A will use includes but is not limited to air-conditioning timing service, light off service, etc. In the home scene, the set of services that user A will use includes, but is not limited to, the service of turning on the air conditioner, the service of turning on the purifier, and the service of opening the curtains. In the movie viewing scene summary, the services that user A will use include but are not limited to the speaker opening service, the large screen opening service, the light closing service, the curtain closing service, etc. In the taxi-hailing scenario, the services that user A will use include but are not limited to taxi-hailing services and the like. Summarized in the driving scene, the services that user A will use include but are not limited to navigation services, music playback services, and so on.

It should be noted that knowledge in Table 2 exemplarily shows service sets that may be used by user A in some scenarios. In practical applications, it may also include service sets that user A will use in other scenarios, which are not listed here in this embodiment of the present application. For example, in the scenario of leaving home, the service set that user A may use includes but is not limited to light off service, curtain close service, taxi service, etc.

Table 2 exemplarily shows that in some scenarios, the probability of the service that user A will use is greater than the set value of the service set. In these scenarios, user A may also use other services, but the probability of user A using other services is low at the default value. For example, in the morning scene, the probability of user A using the speaker broadcast service and health detection service is greater than the preset value, but user A may also use the curtain opening service, but the probability of user A using the curtain opening service is less than the preset value. In the sleep scene, the probability of user A using the air-conditioning timing service and the light off service is greater than the preset value, but user A may also use the sleep detection service, but the probability of the user using the sleep detection service is less than the preset value. In the scenario of returning home, the probability of user A using the air conditioner, purifier, and curtain opening services is greater than the preset value, but user A may also use the large screen to open the service, but the probability of user A using the large screen is less than the preset value. set value. In the movie-watching scene, the probability of user A using the speaker to turn on the service, the large screen to turn on the service, the light to turn off the service, and the curtain to close the service is greater than the preset value, but user A may also use the mobile phone Do Not Disturb service, but the user uses the mobile phone Do Not Disturb The probability of service is less than the preset value. In the taxi-hailing scenario, the probability of user A using the taxi-hailing service is greater than the preset value, but user A may also use the navigation service, but the probability of the user using the navigation service is less than the preset value. In the driving scene, the probability of user A using navigation service and music playing service is greater than the preset value, but user A may also use the phone answering service, but the probability of user A using the phone answering service is less than the preset value.

It should be noted that the marked service set in each of the above scenarios is obtained from the candidate service set based on the user's personal data. Since the personal data recorded on the electronic device changes in real time, the calibration service set in each scene will also change with the change of the user's personal data, that is to say, the calibration service set in each scene is not static.

As shown in FIG. 5 , FIG. 5 exemplarily shows a functional module diagram of how the electronic device 100 recommends services for users.

Wherein, the functional modules include but are not limited to a probability estimation module and a service card generation module.

Wherein, the probability estimation module is used to estimate the probability of the service that user A will use based on the personal data of user A. Afterwards, the probability estimation module retains one or more services whose probability of using the service is greater than the preset value, and obtains the service to be recommended. The probability estimation module sends the service to be recommended to the service card generation module. For how the probability estimation module obtains the service to be recommended based on the personal data of user A, please refer to the relevant descriptions of S602 and S603 in the subsequent embodiment of Figure 6. The probability estimation module can be implemented based on a model, and the specific model training process can refer to The training process of the model 702 introduced in the embodiment of FIG. 7 will not be described in detail here in the embodiment of the present application.

The service card generation module is used to receive the service to be recommended sent by the probability estimation module, and generate a recommendation card based on the service to be recommended. Finally, the service card generation module displays the recommendation card generated based on the service to be recommended on the desktop. For how the service card generation module generates a recommendation card based on the service to be recommended, please refer to the subsequent embodiments shown in FIG. 9A-FIG.

The probability estimation module can also update the probability estimation module based on whether the user has used the service to be recommended, so that the service to be recommended estimated by the probability estimation module is closer to the behavior of the user. For this part of the content, please refer to the following FIG. 7 to introduce the embodiment, and the embodiment of the present application will not be described in detail here.

The service card generation module can also update the service card generation module based on whether the user has used the service to be recommended, so that the service card generated by the service card generation module is closer to the behavior of the user. For this part of the content, please refer to the following FIG. 7 to introduce the embodiment, and the embodiment of the present application will not be described in detail here.

It should be noted that the above modules may also be the same functional module, which is not limited in this embodiment of the present application.

As shown in FIG. 6 , FIG. 6 exemplarily shows a flow chart of how the electronic device 100 recommends a service set for a user.

S601. After the electronic device 100 determines that the first condition is met, the electronic device 100 will start a recommendation process.

In a possible implementation manner, the first condition may be that the electronic device 100 detects that the electronic device 100 is in a preset scene. The electronic device 100 may recognize the scene where the user is located based on at least one of time, location, device status and user operation. Here, the device status may indicate the device status of the electronic device 100, and may also indicate the device status of other electronic devices that establish a communication connection with the electronic device 100. , Bluetooth (bluetooth), infrared, near field communication (near field communication, NFC), ZigBee, wireless fidelity direct (wireless fidelity direct, Wi-Fi direct) (also known as wireless fidelity peer-to-peer , Wi-Fi P2P)) and other technical communications to realize the wireless communication connection between the electronic device 100 and other electronic devices. The communication connection may also refer to a wired communication connection between the electronic device 100 and other electronic devices through a USB interface or the like. The communication connection may also refer to a communication connection in which the electronic device 100 communicates with other electronic devices by logging into the same account (for example, a Huawei account). Other electronic devices include, but are not limited to, wearable devices, smart home devices in the home, and other devices. The electronic device 100 may detect states of wearable devices, smart home devices at home, and the like. The user can set different ways to determine whether the electronic device 100 is in a preset scene. Exemplarily, taking the preset scene as the commuting scene as an example, the method of judging whether the electronic device 100 enters the commuting scene may include: the current time belongs to the time period corresponding to the common route, the current location belongs to the map point on the common route, and the device current The direction of movement of is towards at least one of the destinations of common routes. The preset scenes in the embodiment of the present application may include commuting scenes, leisure scenes, etc. Corresponding to each preset scene, different ways can be set to determine whether to enter the corresponding scene, and the embodiment of the present application does not carry out this limited. Exemplarily, after the user returns home, the user utters the voice command "Xiaoyi Xiaoyi, I'm going home", and the electronic device 100 recognizes that the user is in the scene of going home, then the electronic device 100 recommends the user in the scene of going home. Collection of services. Exemplarily, after the user returns home, the smart door lock in the home recognizes the user's fingerprint or face image, and the electronic device 100 recognizes that the user is in the home scene through the smart door lock, and the electronic device 100 recommends a home for the user. A collection of services in the home scene.

In a possible implementation, the first condition may also be that the electronic device obtains that the electronic device 100 enters the unlocked state from the locked screen state, that is, the electronic device 100 obtains that the user has performed an unlocking operation, and then the electronic device starts the recommended service. process. It should be noted that, before the execution of the service recommendation process this time, the electronic device 100 may have displayed the result of the service recommendation according to the result of the previous execution of the service recommendation. If the results are consistent, the service recommendation result of the electronic device 100 will not be updated. If the result of the service recommendation executed this time is inconsistent with the result of the service recommendation executed in the previous execution, the result of the service recommendation executed in the previous execution will be updated. In a possible implementation, in order to save consumption and prevent the electronic device 100 from being frequently triggered to start the service recommendation process when the user frequently performs unlocking operations, it is also possible to set an interval between two adjacent unlocking operations If the duration does not exceed the preset duration, the service recommendation process will not be started when the unlock operation is obtained for the next time. If the interval between two adjacent unlock operations exceeds the preset duration, the next time the unlock operation is obtained , to start the process of service recommendation. For example, assuming that the preset duration is 10 minutes, if the user's previous unlocking operation time is 11:10, and the current unlocking operation time is 11:13, since the interval between two unlocking operations is 3 minutes, it does not exceed If the preset duration is 10 minutes, this unlocking operation will not trigger the electronic device 100 to execute the service recommendation process; If the preset duration exceeds 10 minutes, the unlocking will trigger the electronic device 100 to perform a service recommendation process. Wherein, the preset duration may be set independently by the user, or may be preset by the electronic device 100, which is not limited in this embodiment of the present application.

In a possible implementation manner, the first condition may also be that the electronic device 100 acquires a change in the top N services to be recommended whose historical click-through rate changes from high to low, and the electronic device 100 starts a service recommendation process. Wherein, N is a positive integer. The electronic device 100 can count the historical click-through rate of each service included in the acquired multiple services, and sort the multiple services according to the historical click-through rate, for example, according to the order of the historical click-through rate from high to low, sort the multiple services Sort. When the electronic device 100 acquires that one or more services with the highest historical click-through rates have changed, the electronic device 100 starts a service recommendation process, and recommends services for the user based on the updated historical click-through rates of each service. For example, N is 5. At the first moment, after sorting the services according to the order of historical click-through rates from high to low, the top 5 services are Service 1, Service 2, Service 3, Service 4, and Service 5. At the second moment, after the services are sorted according to the order of historical click-through rates from high to low, the top 5 services are respectively service 1, service 6, service 2, service 4 and service 3, and the electronic device 100 obtains the history If the top 5 services with the click-through rate from high to low are changed, the electronic device 100 starts the service recommendation process, and recommends services to the user based on the updated historical click-through rate of the service.

It should be noted that the several examples given above are only used to explain the present application. In practical applications, the electronic device 100 may also trigger the recommendation process in other ways, which is not limited in this embodiment of the present application.

S602. After the electronic device 100 starts the recommendation process, the electronic device 100 may obtain multiple services from multiple channels.

Multiple approaches may include, but are not limited to, a scene-bound calibration service set, a historical click-through rate service list, a service interest list, a reminder service list, and the like.

Among them, the calibration service set bound to the scene has been introduced above, that is to say, one or more services whose user usage probability is greater than the preset value are preset in each scene, and will not be described here.

The historical click rate service list includes multiple services with high historical click frequency by the user. Among them, it can be considered that the top M services are services with high historical click frequency by users, and M is a positive integer. For example, it can be considered that the top 10 services in historical click rate are services with high click frequency. Or you can also set the service with the top M historical click-through rate within the preset time from the current moment to be the service with the highest historical click frequency of the user. For example, it can be considered that the service with the top M historical click-through rate within 1 week from the current moment is the user Services with high historical click frequency.

The service interest list includes multiple services that the user has recently used. For example, a list formed by arranging the services used in the last day in chronological order is called a service interest list. For example, the services used in the last hour are arranged in chronological order. The resulting list is called a service interest list.

The history reminder service list includes the service to be reminded detected by the electronic device 100, the service to be reminded is used to remind the user, and may include the service to be reminded triggered based on an event, or the service to be reminded defined by the user. For example, the electronic device obtains from a third-party application program or a text message that the user has booked an airline ticket, and the electronic device 100 can start a service to be reminded to remind the user of the flight information; A service to be reminded to remind the user of the event at the time specified by the user.

Optionally, the probability estimation module introduced in the embodiment of FIG. 5 may be implemented based on a model. For example, the model 702 introduced in the embodiment of FIG. 7 . 7 and 8 will be described below. FIG. 7 shows how the electronic device 100 trains the model 702, and FIG. 8 shows how the electronic device 100 uses the model to recommend multiple services.

As shown in FIG. 7 , in the model training phase, there may be multiple training samples in the training data 701 . The training samples can be obtained through multiple channels, which is not limited in the embodiment of the present application. For example, the input of the training samples can be the time, place and the state of the electronic device (such as Bluetooth open state, data connection state, earphone connection state, etc. etc.), the output of the training sample can be the service actually used by the user. In this way, the electronic device 100 uses the training data 701 to iteratively train the preset model based on the preset model to obtain the trained model 702 . Specifically, the electronic device 100 takes the input of the training sample as the input of the model 702, and the model 702 outputs the predicted service set, and the electronic device 100 calculates the similarity between the predicted service set and the service actually used by the user, and when the similarity is greater than the preset When setting the value, the electronic device 100 modifies the output of the training sample, and recalculates the similarity between the output of the service set predicted by the model 702 and the output of the sample data until the similarity is less than the preset value, and the training of the model 702 is completed.

Optionally, the training process of the model 702 can also be run on other devices (such as the server 200). After the model 702 is trained, the server 200 sends the trained model 702 to the electronic device 100, and the electronic device 100 will train it. The model 702 is saved locally.

As shown in FIG. 8 , in the service recommendation stage, the electronic device 100 may take the current time, location and state of the electronic device 100 as input to the model 702 , and the electronic device 100 predicts the service set that the user may currently use based on the model 702 .

Wherein, the location may be latitude and longitude information where the electronic device 100 is located. The state of the electronic device 100 includes, but is not limited to, the Bluetooth on state, the wireless fidelity (Wi-Fi) on state, the movement form of the device, the current scene type, the voice at the current location, the connection state of WiFi, and the connection state of Bluetooth. , battery power, etc. The exercise form of the device is used to indicate the exercise form of the electronic device 100 , such as a running state, a walking state, and the like. The voice of the current location and the current scene type are used to indicate the location type of the electronic device 100, such as a company, a shopping mall, a store, a bar, a gas station, a hospital, a station, and the like.

The model 702 determines a set of services that may be used by the current electronic device 100 based on the current time, location, and state of the electronic device 100 , and the service set may include one or more different services.

Exemplarily, if the current time is 8:00 p.m., the user is at home, and the electronic device 100 is connected to a large-screen device and a smart speaker, and the electronic device 100 is in the off-screen state and the screen-off time exceeds the preset time, then the electronic device 100 can If it is determined that the user is in a movie watching scene, then the electronic device 100 may recommend services frequently used in the movie watching scene to the user through the model 702 .

It should be noted that the electronic device 100 can also continue to train the model 702 based on the deviation between the service set actually used by the user in the current preset scenario and the predicted service set, so that the user's possible usage predicted by the model 702 The closer the set of services is to the user's real behavior. Among them, the service set actually used by the user in each preset scene, as well as the time, place and various states of the electronic device 100 in each preset scene can be stored through the data storage module 703, which can be stored every preset The duration trains the model 702 based on the data stored in the data storage module 703 to update the model 702 . For the process of updating the model 702, reference may be made to the process of training the model 702, which is not repeated in this embodiment of the present application.

It should be noted that the update of the model 702 may also be performed by other devices (such as the server 200). The electronic device 100 periodically sends the data stored in the data storage module 703 to the server 200 , and the server 200 updates the model 702 based on the data stored in the data storage module 703 . Afterwards, the server 200 sends the updated model 702 to the electronic device 100, and the electronic device 100 saves the updated model 702 locally after receiving the updated model 702.

S603. The electronic device 100 determines a service to be recommended.

Optionally, when the electronic device 100 obtains multiple services from the above multiple channels, there will be duplicate services. Therefore, after the electronic device 100 obtains multiple services, it needs to perform deduplication processing, so that more Each of the services is different.

In this way, after obtaining multiple services, the electronic device 100 uses the multiple services as services to be recommended. The service to be recommended may be one or multiple different services.

The service to be recommended may be one or more system services, may be one or more third-party services, or may be a combination of one or more system services and one or more third-party services.

Exemplarily, system services may include but not limited to: adjusting system settings of the electronic device 100 , services provided by system applications on the electronic device 100 , and controlling the working status of other electronic devices establishing communication connections with the electronic device 100 . Wherein, the system settings of the electronic device 100 include but are not limited to the brightness, volume, Bluetooth on state, WiFi on state, flashlight on state, and alarm clock on state of the electronic device 100 . The services provided by the system applications on the electronic device 100 include but are not limited to: services provided by applications developed by the manufacturer of the electronic device 100, such as music playback services provided by music applications developed by the manufacturer of the electronic device 100, production of the electronic device 100 The video playback service provided by the video application developed by the vendor. Controlling the working status of other electronic devices that establish a communication connection with the electronic device 100 includes, but is not limited to: controlling the Bluetooth watch that establishes a communication connection with the electronic device 100 to detect the user's motion data service, and controlling the smart home device that establishes a communication connection with the electronic device 100 (e.g. air conditioner) turn on/off service.

Third-party services may include, but are not limited to: services provided by applications not developed by the manufacturer of the electronic device 100 . For example, the navigation service provided by the map application developed by the non-electronic device 100 manufacturer, the food delivery service provided by the food delivery application developed by the non-electronic device 100 manufacturer, the taxi-hailing service provided by the taxi-hailing application developed by the non-electronic device 100 manufacturer, etc.

After the electronic device 100 obtains the service to be recommended, the electronic device 100 will generate a recommendation card based on the service to be recommended, and display the recommendation card on the desktop.

Based on the type of service to be recommended, the electronic device 100 may obtain a recommendation card that matches the type of service to be recommended from a preset recommendation card template, and fill the service to be recommended into the recommendation card to generate a recommended card. Testimonial cards for services. How the electronic device 100 generates a recommendation card based on the service to be recommended will be described in detail in the subsequent embodiment shown in FIG. 12 , and will not be repeated in this embodiment of the present application.

The electronic device 100 may generate a set of services that may be used by the user in one or more scenarios. After one or more service sets are generated, the electronic device 100 will judge whether the trigger condition of a certain scene is currently satisfied, and when the execution condition of a certain scene is met, the electronic device 100 will execute the function of the associated service set in the scene operate. A service collection can include multiple services. When an execution condition of a certain scenario is satisfied, the electronic device may trigger functional operations corresponding to multiple services of the corresponding service set.

Execution conditions may include, but are not limited to: the user's trigger operation on the recommended card, the user's voice command meeting the preset voice command, and the user's identity information meeting the preset identity information.

Optionally, the electronic device 100 may perform multiple functional operations based on the execution relationship of multiple services in the service set displayed on the recommendation card. For example, functional operations corresponding to multiple services may be executed simultaneously, or multiple services may be executed in a certain sequence, and so on.

9A-9L exemplarily show schematic diagrams of electronic device 100 displaying a recommendation card and executing a service set in the recommendation card.

Wherein, FIG. 9A-FIG. 9H exemplarily show the schematic diagrams of the electronic device 100 displaying the recommendation card of the system service.

Exemplarily, the system service may be to control the working state of other electronic devices establishing a communication connection with the electronic device 100 .

The electronic device 100 may trigger the electronic device 100 to execute the service set shown in the recommendation card based on any of the following methods.

Way 1: The electronic device 100 receives and responds to the user's input operation on the recommendation card, and executes the set of services shown in the recommendation card.

Exemplarily, after the electronic device 100 recognizes that user A goes home, the electronic device 100 recognizes that the current scene is the home scene, and the electronic device 100 will obtain the services to be recommended in the home scene, such as smart home linkage service, smart home Linkage services may include controlling the opening of the air conditioner in the living room, controlling the opening of the air purifier in the living room, and controlling the opening of the curtains in the living room, etc.

After the electronic device 100 obtains the service to be recommended in the home scene, the electronic device 100 will generate a recommendation card based on the service to be recommended in the home scene, and the recommendation card may be a card 801 as shown in FIG. 9A .

The card 801 shows the smart home linkage service recommended by the electronic device 100 for user A in the scene of returning home. The card 801 may be composed of text, pictures and other elements.

As shown in FIGS. 9A and 9B , the electronic device 100 receives user A's input operation (such as clicking) on the card 801, and in response to the user A's input operation, the electronic device 100 executes the smart home linkage service shown in the card 801, For example, the electronic device 100 sends open commands to the air purifier in the living room, the air conditioner in the living room, and the curtains in the living room. In response to the open commands sent by the electronic device 100, the air purifier in the living room, the air conditioner in the living room, and the curtains in the living room are opened.

Optionally, the execution order of different services is different. For example, after the electronic device 100 receives the user's input operation (for example, click) on the card 801, the electronic device 100 may first control the air conditioner in the living room to be turned on. Afterwards, the electronic device 100 controls to turn on the air purifier in the living room, and finally, the electronic device 100 controls to turn on the curtains in the living room. Or, after the electronic device detects that the user returns home, the electronic device 100 then controls the opening of the curtains in the living room.

It should be noted that the items contained in the smart home linkage service learned by the electronic device 100 for different users may be different.

Exemplarily, after the electronic device 100 recognizes that the user B goes home, the electronic device 100 recognizes that the current scene is the home scene, and the electronic device 100 will obtain services to be recommended in the home scene, such as smart home linkage service, smart home Linkage services may include controlling the air conditioner in the living room to turn on, controlling the air purifier in the living room to turn on, controlling the lights in the living room to turn on, and so on.

After the electronic device 100 obtains the service to be recommended in the home scene, the electronic device 100 will generate a recommendation card based on the service to be recommended in the home scene, and the recommendation card may be a card 802 as shown in FIG. 9C . The card 802 shows the smart home linkage service recommended by the electronic device 100 for the user B in the scene of returning home. The card 802 can be composed of text, pictures and other elements.

As shown in FIG. 9C and FIG. 9D , the electronic device 100 receives user B's input operation (such as clicking) on the card 802, and in response to the user B's input operation, the electronic device 100 executes the smart home linkage service shown in the card 802, For example, the electronic device 100 sends turn-on commands to the air purifier in the living room, the air conditioner in the living room, and the light in the living room.

Way 2: The electronic device 100 receives and responds to the user's voice instruction for executing the recommendation card, and executes the set of services shown in the recommendation card.

Exemplarily, as shown in FIG. 9E , after user A returns home, user A speaks the voice command "Xiaoyi, Xiaoyi, I'm home", and the electronic device 100 performs semantic analysis on the voice command and matches it according to the voice recognition result. to the "Coming Home" scene. Afterwards, the electronic device 100 will get recommended services in the home scene, such as smart home linkage services. The smart home linkage services may include controlling the opening of the air conditioner in the living room, controlling the opening of the air purifier in the living room, and controlling the opening of the curtains in the living room.

Afterwards, the electronic device 100 respectively sends opening instructions to the air purifier in the living room, the air conditioner in the living room, and the curtains in the living room. .

Optionally, after the air purifier in the living room, the air conditioner in the living room, and the curtains in the living room are turned on, the electronic device 100 can play the working status of the above-mentioned smart home devices through voice, and give feedback to user A.

Exemplarily, as shown in FIG. 9F , after user B returns home, user B speaks the voice command "Xiaoyi Xiaoyi, I'm home", and the electronic device 100 performs semantic analysis on the voice command and matches it according to the voice recognition result. to the "Coming Home" scene. Afterwards, the electronic device 100 will get recommended services in the home scene, such as smart home linkage services. The smart home linkage services may include turning on the air conditioner in the living room, turning on the air purifier in the living room, and turning on the lights in the living room.

After the electronic device 100 obtains the service to be recommended in the home scene, the electronic device 100 will generate a recommendation card based on the service to be recommended in the home scene, and the recommendation card may be a card 801 as shown in FIG. 9C .

Afterwards, the electronic device 100 respectively sends turn-on commands to the air purifier in the living room, the air conditioner in the living room, and the light in the living room. .

Optionally, after the air purifier in the living room, the air conditioner in the living room, and the light in the living room are turned on, the electronic device 100 can broadcast the working status of the above-mentioned smart home devices through voice, and give feedback to user B.

Mode 3: The electronic device 100 receives and responds to the user's biological information for executing the recommendation card, and executes the set of services shown in the recommendation card.

Biological information includes but is not limited to facial images, fingerprint images and other information.

Exemplarily, as shown in FIG. 9G , after user A returns home, the device that collects the user's biological information (such as a smart door lock) collects the user's biological information (such as the user's facial image or fingerprint image), and the smart door lock is responsible for the user's biological information. Feature extraction is performed on the biological information of the user, and the biological information characteristics of the user are obtained. The smart door lock determines the user's identity (for example, user A) based on the user's biometric information. At the same time, the smart door lock determines that user A returns home based on time and location. The smart door lock sends to the electronic device 100 the identity of the user (user A) and the context ("going home" context). After the electronic device 100 receives the identity of user A and the scene of "going home", the electronic device 100 will obtain the recommended service in the scene of going home, such as smart home linkage service. The smart home linkage service may include controlling the air conditioner in the living room to turn on, controlling Turn on the air purifier in the living room, control the opening of the curtains in the living room, etc. Afterwards, the electronic device 100 will get recommended services in the home scene, such as smart home linkage services. The smart home linkage services may include controlling the opening of the air conditioner in the living room, controlling the opening of the air purifier in the living room, and controlling the opening of the curtains in the living room.

Exemplarily, as shown in FIG. 9H, after user B returns home, the device that collects the user's biological information (such as a smart door lock) collects the user's biological information (such as the user's facial image or fingerprint image), and the smart door lock will Feature extraction is performed on the biological information of the user, and the biological information characteristics of the user are obtained. The smart door lock determines the identity of the user (for example, user B) based on the user's biometric information. At the same time, the smart door lock determines that user B returns home based on time and location. The smart door lock sends to the electronic device 100 the identity of the user (User B) and the context ("going home" context). After the electronic device 100 receives the identity of user B and the "going home" scene, the electronic device 100 will get the recommended service in the home scene, such as smart home linkage service, and the smart home linkage service may include controlling the air conditioner in the living room to turn on, controlling Turn on the air purifier in the living room, control the lights in the living room, etc. Afterwards, the electronic device 100 will get recommended services in the home scene, such as smart home linkage services. The smart home linkage services may include turning on the air conditioner in the living room, turning on the air purifier in the living room, and turning on the lights in the living room.

After the electronic device 100 obtains the service to be recommended in the home scene, the electronic device 100 will generate a recommendation card based on the service to be recommended in the home scene, and the recommendation card may be a card 802 as shown in FIG. 9C .

The foregoing exemplarily shows several ways of triggering the electronic device 100 to execute the service set displayed on the recommendation card, and other ways may also be used to trigger the electronic device 100 to execute the service set displayed on the recommendation card, which is not done in this embodiment of the present application. limited.

Optionally, the electronic device 100 can automatically generate multiple services with different functions for the user at the same time, reducing user operations. In terms of service sources, services can be divided into system services and third-party services, where third-party services are services provided by non-electronic device 100 manufacturers, and system services are services provided by electronic device 100 manufacturers. Services can also be divided according to functions, which is not limited in this embodiment of the present application.

Exemplarily, the electronic device 100 can freely combine system services and third-party services to generate service sets in different combinations.

9I-9K exemplarily show schematic views of the electronic device 100 displaying a recommendation card of a third-party service.

Exemplarily, the third-party service may be a flight information display service, a taxi service, a navigation service, a food service, and the like.

The electronic device 100 recognizes a flight information associated with user A based on the SMS application or the ticket booking application. When traveling by subway or bus, the electronic device 100 will get recommended services in the business trip scene, such as flight information display service, taxi service and food service.

After the electronic device 100 obtains the service to be recommended in the business trip scenario, the electronic device 100 will generate a recommendation card based on the service to be recommended in the business trip scenario, and the recommendation card may be the card 803 shown in FIG. 9I .

Card 803 shows a set of services recommended by electronic device 100 for user A in a business trip scenario. The card 801 may be composed of text, pictures and other elements.

Card 803 shows cards of three third-party services, which can be understood as services with the highest probability of being used by user A in a business trip scenario. The cards for the three third-party services are respectively the card 804 for the flight information display service, the card 805 for the taxi service, and the card 806 for the gourmet service. Among them, card 804 shows the information of user A's last flight, such as airline name (UA947), flight departure city (Shanghai), flight arrival city (Shenzhen), flight departure time (9:10 am on November 9) , the boarding gate of the flight (A zone 1), and the seat number (B400).

The card 805 displays the name of the application that provides taxi-hailing service (taxi-hailing application one). Card 806 shows that there are delicacies (coffee) that the user likes.

It should be noted that the three services displayed on the card 803 are automatically generated and recommended by the electronic device 100 for the user.

After the electronic device 100 displays the card 803, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the card 803 is located, and the electronic device 100 will enter the corresponding detail page of the service . For example, the electronic device 100 receives and responds to the user's input operation on the card 804 , and the electronic device 100 will enter the details page of the SMS application or ticket booking application that provides the service, and the details page may include more information than the card 804 . For another example, the electronic device 100 may receive and respond to the user's input operation (for example, click operation) on the card 805, and the electronic device 100 will enter the details page in the taxi application one, and the details page displays the information from the current position of the electronic device 100 to the The route and vehicle information between the airports where the flight takes off. For another example, the electronic device 100 may receive and respond to the user's input operation (such as a click operation) on the card 806, and the electronic device 100 will enter the details page of a nearby convenience store or supermarket where coffee can be purchased or takeaway.

Optionally, the electronic device 100 may also receive an input operation (such as a click operation) from the user on an area of the card 803 other than the card 804, the card 805, and the card 806, and the electronic device 100 may execute all the operations shown in the card 803. The third-party service, that is, the electronic device 100 simultaneously enters the details pages of the flight information display service, taxi service and food service, reducing user operations.

It should be noted that the service sets included in the business trip scenarios learned by the electronic device 100 for different users may be different.

Exemplarily, the electronic device 100 recognizes a flight information associated with user B based on the SMS application or the ticket booking application, the electronic device 100 recognizes that the current scene is a business trip scene, and the electronic device 100 and the user's personal data analyze the user A If you have a car and often travel by car, the electronic device 100 will get recommended services in the business trip scene, such as flight information display service and navigation service.

After the electronic device 100 obtains the service to be recommended in the business trip scenario, the electronic device 100 will generate a recommendation card based on the service to be recommended in the business trip scenario, and the recommendation card may be a card 807 as shown in FIG. 9J .

Card 807 shows cards of two third-party services, and the two third-party services can be understood as services with the highest probability of being used by user B in a business trip scenario. The cards of the two third-party services are respectively the card 808 of the flight information display service and the card 809 of the navigation service. Among them, card 808 shows the information of user B's latest flight, such as airline name (UA948), flight departure city (Shanghai), flight arrival city (Shenzhen), flight departure time (10:10 am on November 9th) , the boarding gate of the flight (A zone 1), and the seat number (A400).

The card 809 displays the name of the application providing the navigation service (map application one).

After the electronic device 100 displays the card 807, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the card 807 is located, and the electronic device 100 will enter the corresponding detail page of the service . For example, the electronic device 100 receives and responds to the user's input operation on the card 808 , and the electronic device 100 will enter the details page of the SMS application or ticket booking application that provides the service, and the details page may include more information than the card 808 . For another example, the electronic device 100 may receive and respond to the user's input operation (for example, click operation) on the card 809, and the electronic device 100 will enter the details page in the map application one, which displays the information from the current position of the electronic device 100 to the map application one. Information about the vehicle travel path between the airports where the flight takes off.

Optionally, the electronic device 100 may also receive an input operation (such as a click operation) from the user on an area of the card 807 other than the card 808 and the card 809, and the electronic device 100 may execute all third-party services shown in the card 807 , that is, the electronic device 100 enters the details pages of the flight information display service and the navigation service at the same time, reducing user operations.

Exemplarily, FIG. 9K shows another kind of recommendation card 810 that the electronic device 100 will generate based on the service to be recommended in the business trip scenario after the electronic device 100 obtains the service to be recommended in the business trip scenario by the user B.

Based on the personal data of user B, the electronic device 100 learns that the user often uses the barrier-free mode. After the electronic device 100 turns on the barrier-free function, the user touches an icon on the display screen of the electronic device 100, and the electronic device 100 will give a voice prompt. The handicap feature is a great help for some visually impaired people. Based on this, after the electronic device 100 recognizes that the current scene is a business trip scene, the electronic device 100 will display the card 811 of the flight information display service on the card 810 . The difference between the card 811 and the card 808 is that, besides the flight information associated with the user B, the card 811 also includes a control 812 . The function of the control 812 is that when the user clicks the control 812, the electronic device 100 will play the flight information associated with the user B in the form of voice. Departure from Shanghai Pudong Airport at 10:10, boarding gate is Zone A 1, your seat number is A400".

FIG. 9L exemplarily shows a schematic diagram of electronic device 100 simultaneously displaying recommendation cards of third-party services and system services.

Exemplarily, the third-party service may be a navigation service, the system service may be a do-not-disturb service, and so on.

When the electronic device 100 determines based on the location information that the user is walking from home to the parking lot and the user has a car, then the electronic device 100 determines that the user will travel by car. Based on this, the electronic device 100 infers that the current scene of the user is a driving scene, and the electronic device 100 will obtain services to be recommended in the driving scene, such as navigation service and do-not-disturb service. It is understandable that the navigation service and the do-not-disturb service make the user use the service with the highest probability in the driving scene.

After the electronic device 100 obtains the service to be recommended in the driving scene, the electronic device 100 will generate a recommendation card based on the service to be recommended in the driving scene, and the recommendation card may be a card 813 as shown in FIG. 9L .

The card 813 shows a set of services recommended by the electronic device 100 for the user in the driving scene. The card 813 can be composed of text, pictures and other elements.

Card 813 shows a third-party service card and a system service card. The card for the third-party service is the card 814 for the navigation service, and the card for the system service is the card 815 for the do-not-disturb service. Among them, the card 814 displays information such as an icon and text of the user's do-not-disturb mode. The card 815 displays the name of the application that provides the navigation service (map application one).

After the electronic device 100 displays the card 813, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the card 813 is located, and the electronic device 100 will enter the corresponding detail page of the service . For example, when the electronic device 100 receives and responds to the user's input operation on the card 814, the electronic device 100 will enter the details page of setting the do not disturb mode, and the user can set the value that the user wants to be do not disturb in the details page of setting the do not disturb mode. applications (such as telephony applications, social applications, etc.). For another example, the electronic device 100 may receive and respond to the user's input operation (for example, click operation) on the card 815, and the electronic device 100 will enter the details page in the first map application, and the user may input the purpose in the details page in the first map application. Therefore, the electronic device 100 can display a navigation route from the current location to the destination.

Optionally, the electronic device 100 may also receive an input operation (such as a click operation) from the user on an area of the card 813 other than the card 814 and the card 815, and the electronic device 100 may execute all third-party services shown in the card 813 , that is, the electronic device 100 simultaneously sets the details page of the do-not-disturb mode and the details page of the map application 1 to reduce user operations.

After the electronic device 100 displays the recommendation card or executes the service set displayed in the recommendation card, the electronic device 100 can update the probability estimation module or the service card generation module shown in the embodiment of FIG. 5 so that the probability estimation module and the service card generation module The generated recommendation cards are more in line with the user's behavioral characteristics.

Specifically, after the electronic device 100 displays the recommendation card, the electronic device 100 may detect whether the user has used the service set shown on the recommendation card, and update the probability estimation module or the service card generation module based on the user's usage behavior.

The electronic device 100 displays a recommendation card, and the probability of the service shown on the recommendation card is greater than a preset value, indicating that the probability estimation module estimates that it is correct. When the electronic device 100 detects that the user has used the service set shown on the recommendation card, in this case, the electronic device 100 can determine that the service set that the probability estimation module may use is correct, and the card The recommended card generated by the generation module is also correct and conforms to the behavior characteristics of the user, then the electronic device 100 will not update the card generation module and the probability estimation module.

The electronic device 100 displays a recommendation card, and the probability of the service shown on the recommendation card is greater than a preset value, indicating that the probability estimation module estimates that it is correct. When the electronic device 100 detects that the user does not use the service set shown on the recommended card, or the user manually closes the recommended card, the electronic device 100 can determine that it is a service if the probability estimation module predicts that it is correct. If the recommended card generated by the card generation module does not conform to the behavior characteristics of the user, then the electronic device 100 will update the service card generation module, so that the probability of the service card generation module generating the above-mentioned recommended card is reduced, and avoid generating recommendations for the user that the user will not use. card.

The electronic device 100 displays a recommendation card, and the probability of the service shown on the recommendation card is less than a preset value, but when the electronic device 100 detects that the user has used the service set shown on the recommendation card, in this case, the electronic device 100 100 can determine that the probability estimation module estimates that the service set that the user may use is wrong, then the electronic device 100 will update the probability estimation module so that the probability estimation module estimates that the user will use the above service set probability increases.

The electronic device 100 displays a recommendation card, the probability of the service shown on the recommendation card is less than a preset value, and when the electronic device 100 detects that the user does not use the service set shown on the recommendation card, or the user manually closes the recommendation card, in this case, the electronic device 100 can update the probability estimation module, so that the probability that the probability estimation module estimates the above-mentioned service set that the user may use is further reduced, and avoid generating services that the user will not use. Recommendation card.

Through the electronic device 100 in the above method 1 automatically recommending services for the user, the electronic device 100 can learn the usage habits of the user on the electronic device 100, actively generate a service set that the user may use at different times and places, and generate recommendations based on the service set card. In this way, on the one hand, the user is not required to manually set the services to be used, which reduces user operations. On the other hand, the electronic device 100 recommends a service set for the user based on the usage habits of the user. The more usage data of the user, the more accurate the service set recommended by the electronic device 100 is, and the service set recommended by the electronic device 100 is more in line with the behavior characteristics of the user.

Next, the specific implementation of the electronic device 100 automatically recommending to the user a set of services used by similar users will be introduced.

The electronic device 100 can acquire multiple service sets in each scenario. After the user enters a certain scene, the electronic device 100 may preferentially obtain a service set with a higher probability of use by the user from multiple service sets. The electronic device 100 recommends to the user a set of services with a high probability of being used by the user. In this way, the electronic device 100 does not need to obtain multiple services from multiple single services with different functions, and then generate a service set based on the multiple services.

Optionally, the multiple service sets in each scene may be preset service sets in the electronic device 100 . After entering a certain scene, the electronic device 100 filters out a service set that the user may use from the preset services, and recommends the service set to the user.

Optionally, the multiple service sets in each scene may be service sets sent to the electronic device 100 by other electronic devices. After entering a certain scene, the electronic device 100 screens out a service set that the user may use from service sets sent to the electronic device 100 by other electronic devices, and recommends the service set to the user.

Optionally, the multiple service sets in each scene may be service sets sent by the server to the electronic device 100 . After entering a certain scene, the electronic device 100 screens out a service set that the user may use from the service sets sent by the server to the electronic device 100, and recommends the service set to the user.

Optionally, after the electronic device 100 obtains multiple service sets in each scenario, the electronic device 100 may determine a service set that the user may use based on the user's degree of attention to the device associated with the user. In this way, the electronic device 100 may recommend devices that the user cares about for the user.

In other embodiments, after the electronic device 100 obtains multiple service sets in each scenario, the electronic device 100 calculates the similarity between the service set used by the user and the above multiple service sets based on the usage data of the user. Afterwards, the electronic device 100 determines M service sets used by similar users whose similarity to the service set used by the user is greater than a preset value. In this way, the electronic device 100 can recommend a set of services used by similar users to the user.

In other embodiments, after the electronic device 100 obtains a set of services used by similar users, the electronic device 100 may, in combination with the user's degree of attention to the electronic devices associated with the user, recommend to the user the services used by similar users whose types of devices are close to the ones they follow. Collection of services.

Next, how the electronic device 100 recommends to the user a set of services used by similar users with similar device types that the user is concerned about will be described as an example.

Specifically, the electronic device 100 acquires the current scene of user A, and based on the service set used by user A, analyzes other users whose similarity with the service set used by user A in the current scene is greater than a preset value, and Sort the set of services used by similar users from high to low. Afterwards, the electronic device 100 reorders the service sets used by similar users based on user A's attention to each device in the current scene, and finally gives N recommendation results, and generates a recommendation card based on the recommendation results. The electronic device 100 will Recommendation cards are displayed on the desktop.

Here, the similarity refers to the similarity between users. The similarity describes the similarity of service sets used by different users in the same scenario. The higher the similarity between two users, the closer the set of services used by the two users. For example, in a movie watching scene, the service set used by user A includes setting items for one or more devices. For example, user A sets the large screen as follows: the volume is set to 60, and the brightness is set to 20. The setting of user A to the mobile phone is: the ringtone volume of the mobile phone is set to the maximum. User A's setting for the curtains is: the curtains in the living room are closed. The service set used by user B also includes setting items for one or more devices. User B's settings for the large screen are: the volume is set to 60, and the brightness is set to 20. The setting of user B to the mobile phone is: the ringtone volume of the mobile phone is set to the maximum. User B sets the curtains as follows: the curtains in the living room are closed. Then in the movie watching scene, the similarity between user A and user B is 100%.

The attention degree is used to describe the state of the user, and can also be understood as the degree of attention of the user to the associated electronic device. Exemplarily, in a movie watching scene, the large screen detects through the camera that user A stares at the screen of the large screen for a long time, and user A's mobile phone is in the off-screen state for a long time, then it can be determined that user A pays attention to the large screen higher than the attention paid to mobile phones.

As shown in FIG. 10 , FIG. 10 exemplarily shows a schematic diagram of how the server 200 calculates the similarity of different users.

First, the electronic devices of different users periodically send the historical usage data of the local users to the server 200 . Among them, the historical usage data is: in different scenarios (also can be understood as different time, place and device status), the collection of services used by the user. Exemplarily, in the driving scene, the set of services used by the user includes but is not limited to: the communication software on the mobile phone automatically sets the do not disturb mode, and when there is an incoming call, the default reply is "driving, reply later". In the sports scene, the ringtone of the mobile phone is adjusted to the maximum. When there is a new message on the social software, the default reply is "please call if you have something to do during the sports". In the sleep scene, the mobile phone automatically enters the do not disturb mode, the speaker and the voice assistant on the large screen enter the rest mode, the air conditioner is set to the timer mode, and the curtains are closed. In the work scene: the tone of the mobile phone rings to the maximum, the social software will reply "please call if you have something to do at work" by default, and the work software will cancel the default reply when there is a message. In the movie watching scene, the ringtone of the mobile phone is adjusted to the maximum, and the social software responds by default "watching the movie, urgent call", the volume of the large screen is adjusted to an appropriate level, and the curtains are closed.

As shown in FIG. 10 , the user of the electronic device 100 is user A, and the electronic device 100 periodically sends the historical usage data of the user A to the server 200 . The user of the electronic device 300 is user B, and the electronic device 300 periodically sends the historical usage data of the user B to the server 200 . The user of the electronic device 400 is a user C, and the electronic device 400 periodically sends the historical usage data of the user C to the server 200 .

The server 200 receives historical usage data of different users uploaded by different electronic devices. For example, the server 200 receives the historical usage data of the user A uploaded by the electronic device 100 . The server 200 receives the historical usage data of user B uploaded by the electronic device 300 , and the server 200 receives the historical usage data of user C uploaded by the electronic device 400 .

After the server 200 receives the historical use data of different users uploaded by different electronic devices, the server 200 will classify and summarize the historical use data of different users to obtain service sets used by different users in the same scene. Afterwards, the server 200 will calculate the similarity of service sets used by different users in the same scene.

The server 200 may calculate the similarity of service sets used by different users based on the similarity calculation model.

FIG. 11 exemplarily shows a schematic diagram of how the server 200 calculates the similarity of service sets used by different users based on the similarity.

Before the server 200 calculates the similarity of the service sets used by different users based on the similarity calculation model, the server 200 needs to train the similarity calculation model so that the similarity calculation model can accurately calculate the similarity of the service sets used by different users. Specifically, in the model training phase, there are multiple training samples. The training samples can be obtained through various channels, which is not limited in this embodiment of the present application. For example, the input of the training sample can be a set of services used by different users in the same scenario, and the output of the training sample can be the value of the similarity between different users. In this way, the server 200 uses the training data to iteratively train the similarity calculation model based on the preset model to obtain a trained similarity calculation model. Specifically, the server 200 uses the input of the training sample as the input of the similarity calculation model, the similarity calculation model outputs the predicted similarity value, and the server 200 calculates the predicted similarity value and the output of the training data between different users. The difference between the values of the similarity, when the difference between the two is greater than the preset value, the server 200 modifies the parameters of the similarity calculation model, and calculates the similarity calculation model again to output the numerical value of the predicted similarity and the output of the training data The difference between the values of the similarity between different users in , until the difference between the two is less than the preset value, the calculation and training of the similarity calculation model is completed.

Optionally, the training data may include service sets used by multiple different users in multiple different scenarios.

Optionally, the training process of the similarity calculation model calculation can also be run on other devices (such as the electronic device 100). After the electronic device 100 has trained the similarity calculation model, the electronic device 100 will train the similarity calculation model. Save locally.

After the server 200 has trained the similarity calculation model, the server 200 can determine the similarity between users based on the set of services used by different users in the same scene, and recommend to the user the service used by other users whose similarity is greater than the preset value. Collection of services.

As shown in FIG. 11 , the server 200 obtains service sets used by multiple different users in the first scenario. Afterwards, the server 200 may calculate the similarity of the service sets used by multiple different users. For example, the server 200 may calculate and obtain the similarity of the service sets used by user A and other users.

Afterwards, the server 200 sends the similarity between user A and the service sets used by other users and the service sets used by other users to the electronic device 100 . After the electronic device 100 obtains the similarity between user A and the service sets used by other users and the service sets used by other users, it saves the similarity between user A and the service sets used by other users and the service sets used by other users locally. The next time the electronic device 100 triggers scene one, the electronic device 100 can filter out the service sets used by other users whose similarity is greater than a preset value from the similarity between user A and the service sets used by other users and the service sets used by other users , and recommend the filtered set of services used by other users to the user.

Optionally, after obtaining the similarity between user A and the service sets used by other users, the server 200 may first filter out the service sets used by other users whose similarity is greater than a preset value. Afterwards, the server 200 sends the set of services used by other users whose similarity is greater than the preset value to the electronic device 100, and the electronic device 100 locally saves the set of services used by other users whose similarity is greater than the preset value. When the electronic device 100 triggers scene one next time, the electronic device 100 recommends to the user a set of services used by other users whose similarity is greater than a preset value.

Next, taking a movie watching scene and a driving scene as examples, how the server 200 calculates the similarity of service sets used by different users is introduced.

Firstly, it is introduced how the server 200 calculates the similarity of service sets used by different users in a movie watching scene.

table 3

Table 3 exemplifies the collection of services used by different users in the movie viewing scene, which are collected by the server 200 . Among them, the set of services used by user A in the movie viewing scene includes: turning on the do-not-disturb mode of the mobile phone, and turning off the lights in the living room. The set of services used by user B in the movie viewing scene includes: turning on the do-not-disturb mode on the mobile phone, turning off the lights in the living room, and closing the curtains in the living room. The set of services used by user C in the movie viewing scene includes: turning off the do-not-disturb mode of the mobile phone, and turning on the lights in the living room. The set of services used by user D in the movie viewing scene includes: turning on the do-not-disturb mode on the mobile phone, turning off the lights in the living room, and turning on the air conditioner in the living room to 26 degrees.

It should be noted that it is not limited to the set of services used by users A, B, C, and D in the movie viewing scene, but the server 200 can also include more service sets used by other users in the movie watching scene. Embodiment is not enumerated one by one here.

The server 200 expresses each scene and service set used by different users with a vector. Exemplarily, each service in the service set may be represented by a 0 vector and a 1 vector. For example, in the service set used by user A in Table 3, turning on the DND mode of the mobile phone can be expressed as a vector "1", turning off the lights in the living room can be expressed as a vector "1", and closing the curtains in the living room can be expressed as a vector "1" 1. Turning off the air conditioner in the living room can be expressed as a vector "1". On the contrary, the do-not-disturb mode of the mobile phone can be expressed as a vector "0", the light in the living room can be expressed as a vector "0", the curtains in the living room can be expressed as a vector "0", and the air conditioner in the living room can be expressed as a vector "0". ". Then the set of services used by user A in the movie viewing scene can be expressed as a vector "11". The server 200 may also represent the service set used by the user in other ways, which is not limited in this embodiment of the present application.

Afterwards, the server 200 calculates the similarity between the vectors to obtain the similarity of service sets used by different users in the same scene. Here, the server 200 can calculate the similarity between vectors by any of the following methods: cosine similarity between vectors, Euclidean distance between vectors, Manhattan distance between vectors, Pearson correlation between vectors Coefficient etc. The server 200 may also calculate the similarity of service sets used by different users in the same scenario in other ways.

For example, after the server 200 obtains the service sets used by different users in the movie watching scene, the service sets used by different users are represented by vectors. For example, the service sets used by user A in Table 3 can be expressed as vector A, vector A can be embodied as a vector "11". The set of services used by user B in Table 3 can be expressed as a vector B, and the vector B can be specifically expressed as a vector "111". The set of services used by user C in Table 3 can be expressed as a vector C, and the vector C can be specifically expressed as a vector "00". The set of services used by user D in Table 3 can be expressed as a vector D, and the vector D can be specifically expressed as a vector "110".

The server 200 calculates the similarities between the above-mentioned vector A and vector B, vector C and vector D respectively. For example, the similarity between vector A and vector B is 0.8, the similarity between vector A and vector C is 0.1, and the similarity between vector A and vector D is 0.6. Then in the movie watching scene, the similarity between the service set used by user A and the service set used by user B is 0.8. In the movie watching scene, the similarity between the service set used by user A and the service set used by user C is 0.1. In the movie watching scene, the similarity between the service set used by user A and the service set used by user D is 0.6. Then, in the movie watching scene, the ranking results of the similarity with the service set used by user A from high to low are: the service set used by user B, the service set used by user D, and the service set used by user C.

FIG. 12 exemplarily shows a UI diagram of the electronic device 100 recommending a set of services used by similar users for user A in a movie watching scene.

The electronic device 100 can recommend to user A a service set used by other users whose similarity with the service set used by user A ranks in the top N (for example, N is equal to 1). The set of services used by user B and the set of services used by user D in the scenario. Afterwards, the electronic device 100 will generate a recommendation card based on the service set used by user B and the service set used by user D, and display it on the desktop of the electronic device 100 .

As shown in FIG. 12 , FIG. 12 exemplarily shows a recommendation card 1200 generated by the electronic device 100 . Wherein, the recommendation card 1200 may include the history service collection card 1201 used by user A in the movie watching scene and the service collection card (namely card 1202 ) recommended by the electronic device 100 for user A to be used by similar users. The card can be composed of text, pictures and other elements. Among them, the services displayed in the card 1201 include turning on the do-not-disturb mode of the mobile phone and turning off the lights in the living room. Card 1202 is a collection of services used by user B in the movie watching scene. The services displayed in card 1202 include turning on the do-not-disturb mode of the mobile phone, turning off the lights in the living room, and closing the curtains in the living room.

Optionally, if user A has not used the service in the movie viewing scene before, then the recommendation card 1200 generated by the electronic device 100 may not include the set of historical services used by user A, that is, the electronic device 100 does not display the card 1201 in the card 1200 .

After the electronic device 100 displays the recommendation card 1200, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the recommendation card 1200 is located, and the electronic device 100 will enter the corresponding Details page. For example, the electronic device 100 receives and responds to the user's input operation for the curtain closing service in the living room on the recommendation card 1202, the electronic device 100 will enter the details page of setting the curtains to close, and the user can control the curtains to close in the details page of setting the curtains to close .

Next, in the driving scene, how the server 200 calculates the similarity of service sets used by different users will be introduced.

Table 4

Table 4 exemplifies the collection of services used by different users in driving scenarios collected by the server 200 . Among them, the set of services used by user A in the driving scene includes: transfer to the car when a call comes in, and the cockpit automatically restores the driving position. The set of services used by user B in the driving scene includes: transfer to the car when a call comes in, the cockpit automatically restores the driving seat, and uses the map application on the mobile phone to navigate the route. The set of services used by user C in the driving scene includes: answering the phone when a call comes in, the cockpit does not automatically restore the driving position, and does not navigate the route. The set of services used by user D in the driving scene includes: transfer to the car when a call comes in, the cockpit automatically restores the driving position, uses the map application navigation route on the car, and plays music through the stereo on the car.

It should be noted that it is not limited to the service sets used by users A, B, C, and D in the driving scene, the server 200 may also include more service sets used by other users in the driving scene, the embodiment of the present application I will not list them all here.

After obtaining the service sets used by different users in the driving scene, the server 200 represents the service sets used by different users with vectors. Exemplarily, each service in the service set can be represented by a 0 vector and a 1 vector. For example, "transfer to the car when a call comes in" can be expressed as a vector "1", "the cockpit automatically restores the driving position" can be expressed as a vector "1", and "applying a navigation route through the map on the car" can be expressed as a vector "1" ", "Play music through the stereo on the car" can be expressed as a vector "1". On the contrary, "the mobile phone answers the call" can be expressed as a vector "0", "the cockpit does not automatically return to the driving position" can be expressed as a vector "0", "use the map application navigation route on the mobile phone" can be expressed as a vector "0" ", "Play music through mobile phone" can be expressed as a vector "0". Then the set of services used by user A in Table 4 can be expressed as a vector A, and the vector A can be specifically expressed as a vector "11". The set of services used by user B in Table 4 can be expressed as a vector B, and the vector B can be specifically expressed as a vector "110". The set of services used by user C in Table 4 can be expressed as a vector C, and the vector C can be specifically expressed as a vector "00". The set of services used by user D in Table 4 can be expressed as a vector D, and the vector D can be specifically expressed as a vector "1111".

The server 200 calculates the similarities between the above-mentioned vector A and vector B, vector C and vector D respectively. For example, the similarity between vector A and vector B is 0.9, the similarity between vector A and vector C is 0.1, and the similarity between vector A and vector D is 0.7. Then in the driving scene, the similarity between the service set used by user A and the service set used by user B is 0.9. In the driving scene, the similarity between the service set used by user A and the service set used by user C is 0.1. In the driving scene, the similarity between the service set used by user A and the service set used by user D is 0.7. Then, in the driving scene, the ranking results of the similarity with the service set used by user A from high to low are: the service set used by user B, the service set used by user D, and the service set used by user C.

FIG. 13 exemplarily shows a UI diagram of the electronic device 100 recommending a set of services used by similar users for user A in a driving scene.

The electronic device 100 may recommend to user A a service set used by other users whose similarity with the service set used by user A ranks in the top N (for example, N is equal to 1). For example, the electronic device 100 may recommend to user A a driving scene The set of services used by user B. Afterwards, the electronic device 100 will generate a recommendation card based on the set of services used by the user B, and display it on the desktop of the electronic device 100 .

As shown in FIG. 13 , FIG. 13 exemplarily shows a recommendation card 1300 generated by the electronic device 100 . Wherein, the recommendation card 1300 may include the historical service set card 1301 used by user A in the driving scene and the service set card (namely card 1302 ) recommended by the electronic device 100 for user A to be used by similar users. The card can be composed of text, pictures and other elements. Among them, the service displayed in the card 1301 is transferred to the car and the cockpit when there is an incoming call, and the cockpit automatically restores the driving position. Card 1302 is a collection of services used by user B in the driving scene. The services displayed in card 1302 include transfer to the car when an incoming call is received, the cockpit automatically restores the driving position, and the navigation route through the map application on the mobile phone.

After the electronic device 100 displays the recommendation card 1300, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the recommendation card 1300 is located, and the electronic device 100 will execute the corresponding service. For example, the electronic device 100 receives and responds to the user's input operation on the service of "the cockpit automatically restores the driving seat sitting posture" on the recommendation card 1302, and the electronic device 100 will control the cockpit to automatically restore the driving seat sitting posture".

Optionally, if user A has not used the service in the driving scene before, then the recommendation card 1300 generated by the electronic device 100 may not include the historical service set used by user A (that is, the card 1300 does not include the historical service set card 1301) .

It should be noted that the server 200 is not limited to counting the service sets used by different users in the movie watching scene and driving scene, and the server 200 can also count the service sets used by different users in other scenes (such as work scenes), The embodiments of the present application are not listed here.

The embodiment of the present application may also combine the user's attention to different devices in different scenarios, and recommend to the user a set of services used by similar users whose types of devices the user is concerned about are similar.

Optionally, the electronic device may score the degree of attention of the device associated with the user, and reorder the set of services used by similar users obtained above based on the user's degree of attention to the device associated with the user to obtain the final recommendation result . In this way, the electronic device 100 can recommend to the user a set of services used by similar users that is close to the type of device that the user cares about, so that the set of services recommended by the electronic device 100 is more accurate.

Wherein, the attention degree of the user to the device can be obtained based on the following information: the working state of the device associated with the user, and the state of the user detected by the device associated with the user. Exemplarily, the working state of the device associated with the user includes, but not limited to: whether the device associated with the user is turned on, and whether the device associated with the user is in a working state (for example, whether there is image or audio output). The state of the user detected by the device associated with the user includes but is not limited to: whether the user is staring at the large screen or the mobile phone for a long time. The system settings of the device associated with the user and the settings of the third-party application include, but are not limited to: whether the device associated with the user has enabled the do not disturb mode, whether the third-party application has enabled the new information notification permission, whether the third-party application has enabled the automatic reply permission, and whether the third-party application has enabled the automatic reply permission. Whether the third-party application is enabled to obtain the current location permission, whether the third-party application is enabled to obtain the microphone permission, and so on. The above examples are only used to explain how to obtain the user's attention to the device, and should not be construed as a limitation.

Next, it will be introduced how the electronic device 100 calculates the user's degree of attention to different devices.

The electronic device 100 may determine the user's degree of attention to different devices based on the following manner.

Manner 1: The electronic device 100 scores the device based on the state of the device, and obtains a user's degree of attention to the device.

The electronic device 100 may classify the user's degree of attention to the device into N levels. The lower the level, the user's attention to the device is not clear, and the user's attention to the device is lower. The higher the level, the clearer the user's attention to the device, and the higher the user's attention to the device. Exemplarily, when the user's attention score on the device is the first level, the user's attention score on the device is 1/N. When the user's degree of attention to the device is rated at the second level, the user's degree of attention to the device is rated as 2/N.

Assuming that N is equal to 3, in the movie-watching scene, the first-level scoring events include but are not limited to: the curtain is closed, the screen of the mobile phone is off, and the duration of the screen of the mobile phone exceeds a certain time threshold. Then the attention score of the first-level scoring event is 0.3. The scoring event of the second level includes but is not limited to: the electric light in the living room is turned off, so the attention score of the scoring event of the second level is 0.6. Scoring events at the third level include but are not limited to: the mobile phone is unlocked and the screen is turned on, and the duration of the mobile phone's bright screen exceeds a certain time threshold. The large screen is turned on, and the media channel of the large screen is occupied, there is audio output, or the large screen detects that the user stares at the large screen for more than a certain time threshold through a camera or other device. If the smart speaker has audio output, the attention score of the third-level scoring event is 1.

Assuming that N is equal to 3, in the driving scene, the first-level scoring events include but are not limited to: closing of the car window, off-screen of the mobile phone, and the off-screen duration of the mobile phone exceeds a certain time threshold. Then the attention score of the first-level scoring event is 0.3. The scoring event of the second level includes but is not limited to: the car light is turned on, so the attention score of the scoring event of the second level is 0.6. Scoring events at the third level include but are not limited to: the screen of the on-board computer is turned on, and the media channel of the on-board audio is occupied and there is audio output. If the Bluetooth headset is connected to a device (such as a mobile phone or a car), then the attention score of the third-level scoring event is 1.

It should be noted that the scoring events in the above-mentioned different scenarios are obtained based on user experience and should not be construed as a limitation.

Manner 2: The electronic device 100 obtains the user's attention degree score on the device based on the user's settings.

When the electronic device 100 detects that the user is in a certain scene, the electronic device 100 may allow the user to select a device that the user needs to pay attention to by means of a pop-up window. The device selected by the user has an attention score of 1. For example, in a movie watching scene, if the user selects a large screen to focus on, the electronic device 100 obtains a score of 1 for the user's attention to the large screen. In the driving scene, if the user selects the car computer to be concerned about, the electronic device 100 obtains a score of 1 for the user's attention to the car computer.

Not limited to scoring the attention degree of the device through the above two methods, the electronic device 100 may also use other methods to score the attention degree of the device, which will not be repeated in this application.

The electronic device 100 may calculate the user's attention scores for different devices based on the attention calculation model.

FIG. 14 exemplarily shows a schematic diagram of how the electronic device 100 trains an attention calculation model.

Before the electronic device 100 calculates the user's attention scores for different devices based on the attention calculation model, the electronic device 100 needs to train the attention calculation model, so that the attention calculation model can accurately calculate the user's attention for different devices score.

Specifically, in the model training phase, the electronic device 100 needs to acquire multiple training samples. The training samples can be obtained through various channels, which is not limited in this embodiment of the present application. The training sample includes the input of the training sample and the output of the training sample, wherein the input of the training sample is the status of different devices in a certain scene, and the output of the training sample is the user's attention score for different devices. In this way, the electronic device 100 uses the training data to iteratively train the attention degree calculation model based on the preset model to obtain a trained attention degree calculation model.

Afterwards, the electronic device 100 takes the input of the training samples as the input of the attention degree calculation model, and the attention degree calculation model outputs the predicted user's attention degree scores for different devices. The electronic device 100 calculates the difference between the predicted user's attention score for different devices and the user's attention score for different devices in the output of the training data. When the difference between the two is greater than a preset value, the electronic device 100 Modify the parameters of the attention calculation model, and repeat the previous steps until the electronic device 100 confirms that the difference between the user's attention scores for different devices in the predicted user's attention scores for different devices and the user's attention scores for different devices in the output of the training data is less than The default value, the attention calculation model has been calculated and trained.

Optionally, the training data may include states of different devices in multiple different scenarios and user attention scores for different devices.

Optionally, the training process of the degree of attention calculation model can also be run on other devices (such as server 200). After the server 200 has trained the degree of attention calculation model, the server 200 will send the degree of attention calculation model trained to the electronic device 100. The electronic device 100 locally saves the trained attention calculation model.

FIG. 15 exemplarily shows a schematic diagram of how the electronic device 100 obtains user attention scores for different devices based on the attention calculation model.

After the electronic device 100 has trained the attention degree calculation model, the electronic device 100 may determine the user's attention degree score for different devices based on the states of different devices in a certain scene.

As shown in FIG. 15 , the electronic device 100 acquires the state of the device associated with user A in scenario 1. For example, the devices associated with user A in scenario 1 include device 1, device 2, device 3, and device n. Electronic device 100 The state of device 1, the state of device 2, the state of device 3 and the state of device n need to be obtained. Afterwards, the electronic device 100 may determine user A's attention score for each device in the next scene based on the state of the device associated with user A through a similarity calculation model. For example, the electronic device 100 calculates user A's attention score for device 1 , user A's attention score for device 2 , user A's attention score for device 3 , and user A's attention score for device n.

Next, the movie watching scene and the driving scene are taken as examples to introduce how the electronic device 100 scores the attention degree of the device.

table 5

Table 5 exemplifies the statistical events of user A's degree of attention to different devices determined by the electronic device 100 in the movie watching scene. Exemplarily, user A's attention scoring event on the mobile phone includes "the time when the mobile phone screen is off exceeds a certain time threshold", user A's attention scoring event on the large screen includes "user A has been watching the screen of the large screen", and user A A's attention rating event on curtains includes "no curtains in the living room", and user A's attention rating event on electric lights includes "lights off". Based on the above attention scoring event, the electronic device 100 can obtain user A's attention score for mobile phones as 0.3, user A's attention score for large screens as 1, user A's attention score for living room curtains as 0, and user A's attention score for living room curtains. The attention score for the electric light in the living room is 0.3.

Table 6

Table 6 exemplifies the statistical events of user A's degree of attention to different devices determined by the electronic device 100 in the driving scene. Wherein, for example, user A's attention scoring event on the mobile phone includes "the time when the screen of the mobile phone is off exceeds a certain time threshold", and the user A's attention scoring event on the car machine includes "vehicle machine". Based on the above-mentioned attention rating event, the electronic device 100 can obtain the user A's attention score for the mobile phone as 0.3, and the user A's attention score for the car machine as 1.

It should be noted that the server 200 is not limited to counting user A's attention to different devices in the movie watching scene and driving scene, and the server 200 can also count user A's attention to different devices in other scenes (such as work scenes). attention, the embodiments of this application are not listed here.

After the electronic device 100 obtains user A's attention scores for different devices, the electronic device 100 will reorder the previously obtained service sets used by similar users based on user A's attention scores for different devices to obtain the final recommendation result. In this way, the electronic device 100 can recommend to the user a set of services used by similar users who are close to the device followed by user A in the same scene, which improves the accuracy of the electronic device 100 in recommending service sets for the user.

When the aforementioned server 200 obtains the overall similarity of the service sets used by other users whose similarity with the service set used by user A is greater than the preset value, the server 200 can also obtain each service used by user A and each service set used by other users. Similarity of a service. For example, the service set used by user A includes service 1, service 2, and service 3, and the service set used by other users also includes service 1, service 2, and service 3. The similarity between user A and service 1 used by other users is 0.9. The similarity between A and service 2 used by other users is 0.8, and the similarity between user A and service 3 used by other users is 0.6.

When the server 200 sends the service set used by similar users to the electronic device 100, in addition to sending the overall similarity between user A and the service set used by similar users, it also needs to send the similarity between each service used by similar users and user A to the electronic device 100.

After the electronic device 100 obtains the similarity between each service used by similar users and user A, and the attention scores of user A for different devices, the electronic device 100 can compare the service based on the similarity of each service and the attention scores of different devices. The previously obtained service sets used by similar users are reordered, so as to recommend to the user a service set used by similar users that is close to the device that user A cares about.

Optionally, the electronic device 100 may multiply the similarity between each service used by similar users and user A in the set of services used by similar users by the attention score of user A's device corresponding to each service, to obtain each For the score of the service, the electronic device 100 adds up the scores of each service in the service set to be the overall score of the service set. And based on the overall score of the service set, the cards are grouped from high to low, and the final recommendation result is obtained.

It should be noted that the electronic device 100 may also obtain the overall score of the service set in other ways, which is not limited in this embodiment of the present application.

Next, taking a movie watching scene and a driving scene as examples, how the electronic device 100 obtains the overall score of the service set used by similar users is introduced.

First, in the movie watching scene, how the electronic device 100 obtains the overall score of the service set used by similar users is introduced.

First, the electronic device 100 obtains the similarity between each service used by similar users and user A.

Table 7

Table 7 shows the similarity between each service used by similar users and the corresponding service used by user A in the movie watching scene. Exemplarily, in the movie watching scene, the similarity between the service of the mobile phone used by user B and the service of the mobile phone used by user A with the service in the do not disturb mode turned on is 0.9. The similarity between the light-off service in the living room used by user B and the light-off service in the living room used by user A is 0.7. The similarity between the service for turning on the air conditioner in the living room used by user B and the service for turning on the air conditioner in the living room used by user A is 0.1. The similarity between the curtain closing service in the living room used by user B and the curtain closing service in the living room used by user A is 0.6.

Similarly, in the movie watching scene, the similarity between user C and user A using the mobile phone to turn on the do-not-disturb mode service and the mobile phone used by user A to turn on the do-not-disturb mode service is 0.1. The similarity between the light-off service in the living room used by user C and the light-off service in the living room used by user A is 0.1. The similarity between the service for turning on the air conditioner in the living room used by user C and the service for turning on the air conditioner in the living room used by user A is 0. The similarity between the curtain closing service in the living room used by user C and the curtain closing service in the living room used by user A is 0.1.

Similarly, in the movie watching scene, the similarity between user D and user A using the mobile phone to turn on the do not disturb mode service and the mobile phone used by user A to turn on the do not disturb mode service is 1. The similarity between the light-off service in the living room used by user D and the light-off service in the living room used by user A is 0.8. The similarity between the service for turning on the air conditioner in the living room used by user D and the service for turning on the air conditioner in the living room used by user A is 0.3. The similarity between the curtain closing service in the living room used by user D and the curtain closing service in the living room used by user A is 0.1.

After the electronic device 100 obtains the similarity between each service used by similar users and the corresponding service used by user A, the electronic device 100 calculates the similarity of each service in the service set used by similar users and the degree of attention to the device corresponding to each service The scores are multiplied to get an overall score for the collection of services used by similar users.

Table 8

Table 8 exemplarily shows the overall scores of service sets used by similar users. Among them, the overall score of the service set used by user B is 0.49, the overall score of the service set used by user C is 0.11, and the overall score of the service set used by user C is 0.57.

An overall score based on a collection of services used by similar users. The electronic device 100 reorders the service sets used by similar users, that is, makes a group based on the overall score of the service sets used by similar users from high to low, and obtains the final recommendation result.

Finally, in the movie watching scene, the electronic device 100 recommends for user A the service sets used by similar users: the service set used by user D, the service set used by user B, and the service set used by user C.

FIG. 16 exemplarily shows a UI diagram of another set of services recommended by the electronic device 100 for user A to be used by similar users in a movie watching scene.

The electronic device 100 can recommend to user A a service set used by other users whose similarity with the service set used by user A ranks in the top N (for example, N is equal to 1). Service collection used by user D in the scenario. Afterwards, the electronic device 100 will generate a recommendation card based on the set of services used by the user D, and display it on the desktop of the electronic device 100 .

As shown in FIG. 16 , FIG. 16 exemplarily shows a recommendation card 1600 generated by the electronic device 100 . Wherein, the recommendation card 1600 may include the history service collection card 1601 used by user A in the movie watching scene and the service collection card (namely card 1602 ) recommended by the electronic device 100 for user A to be used by similar users. The card can be composed of text, pictures and other elements. Among them, the services displayed in the card 1601 include turning on the do-not-disturb mode of the mobile phone and turning off the lights in the living room. Card 1602 is a collection of services used by user D in the movie watching scene. The services displayed in card 1602 include turning on the Do Not Disturb mode on the mobile phone, turning off the lights in the living room, and turning on the air conditioner in the living room.

Optionally, if user A has not used the service in the movie viewing scene before, then the recommendation card 1600 generated by the electronic device 100 may not include the set of historical services used by user A, that is, the electronic device 100 does not display the card 1601 in the card 1600 .

After the electronic device 100 displays the recommendation card 1600, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the recommendation card 1600 is located, and the electronic device 100 will enter the corresponding Details page. For example, when the electronic device 100 receives and responds to the user's input operation for the service of turning on the air conditioner in the living room on the recommendation card 1602, the electronic device 100 will enter the details page for setting the air conditioner in the living room to be turned on. to control the air conditioner in the living room.

The difference between the recommendation card 1600 shown in FIG. 16 and the recommendation card 1200 shown in FIG. A collection of services corresponding to devices that are more concerned about in movie viewing scenarios. From the foregoing analysis, it can be known that there is no curtain installed in the living room of user A, so user A's attention to the curtains in the living room is 0, and then the electronic device 100 shown in FIG. The recommendation service "closing the curtains in the living room" is a useless recommendation item for user A.

Therefore, based on the foregoing analysis, the electronic device 100 can reorder the set of services used by similar users obtained by the electronic device 100 based on user A's attention scores on different devices in the movie viewing scene, so that the electronic device 100 can be User A recommends a set of services used by similar users that are close to the device that user A cares about, so as to prevent the electronic device 100 from recommending to the user the corresponding service of the device that the user does not care about or the corresponding service of the device that does not currently exist. The accuracy of recommending a collection of services for a user.

Next, in the driving scene, how the electronic device 100 obtains the overall score of the service set used by similar users will be introduced.

Table 9

Table 9 shows the similarity between each service used by similar users and the corresponding service used by user A in the driving scene. Exemplarily, in a movie watching scene, the similarity between the call answering service used by user B and the call answering service used by user A is 0.5. The similarity between the cockpit automatic recovery of the driving position service used by user B and that of user A is 0.6. The similarity between the navigation service used by user B and the navigation service used by user A is 0.4. The similarity between the music playback service used by user B and the music playback service used by user A is 0.1.

Similarly, in the movie watching scene, the similarity between the call answering service used by user C and the call answering service used by user A is 0. The similarity between the cockpit automatic recovery of the driving position service used by user C and the service of user A's automatic recovery of the cockpit position is 0. The similarity between the navigation service used by user C and the navigation service used by user A is 0.3. The similarity between the music playback service used by user C and the music playback service used by user A is 0.1.

Similarly, in the movie watching scene, the similarity between the call answering service used by user D and the call answering service used by user A is 0.4. The similarity between the cockpit automatic recovery of the driving position service used by user D and the cockpit automatic recovery of the driving position service used by user A is 0.6. The similarity between the navigation service used by user D and the navigation service used by user A is 0.3. The similarity between the music playback service used by user D and the music playback service used by user A is 0.3.

Table 10

Table 10 exemplarily shows the overall scores of service sets used by similar users. Among them, the overall score of the service set used by user B is 1.32, the overall score of the service set used by user C is 0.48, and the overall score of the service set used by user C is 1.60.

Finally, in the driving scene, the electronic device 100 recommends for user A the service sets used by similar users: the service set used by user D, the service set used by user B, and the service set used by user C.

FIG. 17 exemplarily shows a UI diagram of another set of services used by similar users recommended by the electronic device 100 for user A in a driving scene.

The electronic device 100 may recommend to user A a service set used by other users whose similarity with the service set used by user A ranks in the top N (for example, N is equal to 1). For example, the electronic device 100 may recommend to user A a driving scene The collection of services used by user D. Afterwards, the electronic device 100 will generate a recommendation card based on the set of services used by the user D, and display it on the desktop of the electronic device 100 .

As shown in FIG. 17 , FIG. 17 exemplarily shows a recommendation card 1700 generated by the electronic device 100 . Wherein, the recommendation card 1700 may include the history service collection card 1701 used by user A in the driving scene and the service collection card (namely card 1702) recommended by the electronic device 100 for user A to be used by similar users. The card can be composed of text, pictures and other elements. Among them, the service displayed in the card 1701 is transferred to the car machine and the cockpit automatically restores the driving seat when there is an incoming call. Card 1702 is a service collection card used by user D in the driving scene. The services displayed in card 1702 include transfer to the car when an incoming call is received, the cockpit automatically restores the driving position, the car audio plays music on the car, and the map application on the car Navigation route.

Optionally, if user A has not used the service in the driving scene before, then the recommendation card 1700 generated by the electronic device 100 may not include the set of historical services used by user A, that is, the electronic device 100 does not display the card 1701 in the card 1700 .

After the electronic device 100 displays the recommendation card 1700, the electronic device 100 receives and responds to the user's input operation (such as a click operation) on the area where the card of any service on the recommendation card 1700 is located, and the electronic device 100 will enter the corresponding Details page. For example, when the electronic device 100 receives and responds to the user's input operation on the car audio playing music service on the recommendation card 1702, the electronic device 100 will enter the details page for setting the car audio playing music on the car, and the user can set the car audio on the car. On the details page of playing music on the car audio, control the car audio on the car to play music.

The difference between the recommendation card 1700 shown in FIG. 17 and the recommendation card 1300 shown in FIG. A collection of services corresponding to devices that are more concerned in driving scenarios. From the above analysis, it can be seen that user A pays more attention to the car while driving, and user A does not pay attention to the mobile phone. Then user A has a higher probability of navigating the route and playing music through the car, and user A uses the mobile phone to navigate the route. and playing music may affect user A's driving concentration. Then the recommended service "navigation route through the map application on the mobile phone" displayed in the service collection card (namely card 1702) shown in the electronic device 100 shown in FIG. 17 may be a useless recommendation item for user A.

Therefore, in combination with the foregoing analysis, it can be seen that the electronic device 100 can reorder the set of services used by similar users obtained by the electronic device 100 based on user A's attention scores on different devices in the driving scene, so that the electronic device 100 can be used by the user A. A recommends a set of services used by similar users that are close to the device that user A cares about, and avoids the electronic device 100 recommending to the user the corresponding service of the device that the user does not care about or the corresponding service of the device that does not currently exist. The electronic device 100 can be mentioned as Accuracy of a collection of user recommendation services.

Based on the service generation methods introduced in the first and second ways above, the electronic device 100 can set the application setting status and system setting status of the electronic device 100 with one click based on the generated service set, or control the working status of other electronic devices.

Specifically, if the service set displayed on the recommendation card is a service set of application setting items on multiple electronic devices 100, for example, the service set can be "set the instant messaging application to the do not disturb mode, and set the phone application to the reminder mode" When the electronic device 100 receives a user's trigger operation (such as clicking) on the service card corresponding to the service set, the electronic device 100 can automatically set the instant messaging application to the do-not-disturb mode, and set the phone application to the reminder mode. In this way, the user can set multiple different applications with one click, which is convenient and quick.

Optionally, the recommendation service is executed by the system of the electronic device 100 . After the electronic device 100 obtains the permission of the application in the startup wizard, when the electronic device 100 subsequently sets the state of the application, the electronic device 100 will not pop up a box to prompt whether to obtain the user's authorization.

If the service collection displayed on the recommendation card is a service collection of system setting items on multiple electronic devices 100, for example, the service collection can be "adjust the brightness of the mobile phone to 20%, and set the electronic device 100 to silent mode", the electronic device 100 After receiving a user's trigger operation (for example, clicking) on the service card corresponding to the service set, the electronic device 100 can automatically adjust the brightness of the mobile phone to 20%, and set the electronic device 100 to a silent mode. In this way, users can set multiple system settings with one key, which is convenient and quick.

If the service set displayed on the recommendation card is a service set that controls the working status of other electronic devices, for example, the service set can be "turn on the air conditioner in the living room, turn on the light in the living room", and the electronic device 100 receives the service corresponding to the service set from the user. The electronic device 100 can automatically control to turn on the air conditioner in the living room and automatically control to turn on the light in the living room by the trigger operation (for example, click) of the card. In this way, the user can set the working states of multiple other electronic devices with one key, which is convenient and quick.

The service set displayed on the recommendation card may also be any one or a combination of a service set of system setting items, a service set of application setting items, and a service set of controlling the working status of other electronic devices. In this way, the electronic device 100 can set multiple application setting states and system setting states with one key, or control the working states of other electronic devices.

Not limited to the methods of service generation described in the above method 1 and method 2, the embodiment of the present application also provides another service generation method, that is, the electronic device 100 can recommend services for the user based on the user's historical operations.

Optionally, the electronic device 100 may also recommend services for the user based on the user's behavior and the user's personal data.

The user's historical operations can be understood as the user's behavior within a period of time. The user's behavior may be the user's system settings for the electronic device 100, system settings for applications, working status of other electronic devices controlled by the electronic device 100, and so on.

Exemplarily, the user's operation may be "set the instant messaging application to the do not disturb mode, set the phone application to the reminder mode", and the user's operation may also be "adjust the brightness of the mobile phone to 20%, set the electronic device 100 to Silent mode", the user's operation can also be "turn on the air conditioner in the living room, turn on the light in the living room".

In this way, the electronic device 100 records the behavior of the user within a certain period of time, and recommends to the user setting items whose usage frequency of the user's historical operations is greater than a preset value. In this way, the electronic device 100 can recommend services to the user based on the behavior of the user, which is more in line with the behavior characteristics of the user.

Exemplarily, if the user operates the electronic device "set the instant messaging application to the do not disturb mode and set the phone application to the reminder mode" most frequently in the movie watching scene, then in the next movie watching scene, the electronic device The 100 may recommend the most frequently operated setting items for the user, and the service recommended by the electronic device 100 for the user may be "set the instant messaging application to a do-not-disturb mode, and set the phone application to a reminder mode".

The foregoing embodiments describe how the electronic device 100 generates a service set for the user. After the electronic device 100 generates a service set for the user, when the electronic device 100 detects that the current time, location or state of the device satisfies certain conditions, the electronic device 100 will recognize the corresponding scene. The associated service set in the scene is recommended for the user, and the electronic device 100 generates a recommendation card for the user based on the associated service set in the scene, and displays the recommendation card on the desktop.

That is to say, a scenario is composed of scenario trigger conditions and service collections, and some scenarios may also include exit conditions. Wherein, the trigger condition is used to trigger the electronic device 100 to generate a recommendation card based on the service set corresponding to the current scene, and display the recommendation card on the desktop. The exit condition is used to trigger the electronic device 100 to stop displaying the aforementioned recommendation card on the desktop.

The trigger condition includes any one or multiple items of time, location, or device status, and the exit condition may also include any one or multiple items of time, location, or device status.

Next, the trigger conditions will be described in detail.

Table 11

触发条件的组成类型Component types of trigger conditions	触发条件的内容The content of the trigger condition
时间类time class	早上5点之后after 5 am

时间类time class	每次平均起床时间之后after each average wake up time
时间类time class	每日平均睡眠时间后average sleep time per day
时间类time class	工作日上午平均离家时间后After the average time away from home on weekday mornings
地点类location class	进入距离家位置一定范围内后After entering a certain range from home location
地点类location class	进入小区位置一定范围内后After entering the community within a certain range
地点类location class	到达地铁站后After arriving at the subway station
地点类location class	到达公交站后After arriving at the bus station
设备状态类Device Status Class	手机早上首次亮屏后After turning on the screen for the first time in the morning
设备状态类Device Status Class	手机检测到用户进入运动状态后After the mobile phone detects that the user enters the exercise state
设备状态类Device Status Class	手机检测到用户进入驾驶状态后After the mobile phone detects that the user enters the driving state
设备状态类Device Status Class	手机检测到连接至其他的设备后After the phone detects that it is connected to other devices

Table 11 exemplarily shows the composition types of the trigger conditions and the content of the conditions. When the composition type of the trigger condition is time, the content of the trigger condition can include any one or more of the following: after 5:00 in the morning, after each average wake-up time, after the daily average sleep time, and the average departure time on weekday mornings after time. When the composition type of the trigger condition is location, the content of the trigger condition can include any one or more of the following: after entering a certain range from home, after entering a community within a certain range, after arriving at a subway station, after arriving at a bus station back. Wherein, the location of the user can be determined based on the device (such as a mobile phone) bound to the user connected to the WiFi of the corresponding location, or based on the positioning information of the device (such as a mobile phone) bound to the user. For example, when a device bound to the user (such as a mobile phone) is connected to the home WiFi, it can be determined that the user is within a certain range from the home location. When the location information of the device bound to the user (such as a mobile phone) shows that the user has entered a certain community, and the user lives in the community, it can be determined that the user enters the community within a certain range. When the composition type of the trigger condition is device state, the content of the trigger condition can include any one or more of the following: after the mobile phone turns on the screen for the first time in the morning, after the mobile phone detects that the user enters the exercise state, after the mobile phone detects that the user enters the driving state , After the mobile phone detects that it is connected to other devices. Wherein, the state of the device can be determined based on data collected by sensors on the device bound to the user (such as a mobile phone), or information such as status on the device. For example, the mobile phone can detect that the user is running based on the motion data collected by the motion sensor on the mobile phone, or the mobile phone can detect that the user is running through the motion data collected on a wearable device (such as a Bluetooth watch) that establishes a communication connection. For another example, if the Bluetooth of the user's mobile phone is changed from the no-connected state to the Bluetooth connected to the vehicle, the mobile phone determines that the user is about to enter the driving state.

It should be noted that Table 11 is only an example of the composition type and content of trigger conditions. In practical applications, it may include more composition types and content of trigger conditions than Table 11. The implementation of the present application Examples are not limited to this.

It should be noted that the exit condition of the scene is similar to the trigger condition of the scene. For the specific explanation of the exit condition, refer to the specific explanation of the trigger condition, which will not be repeated in this embodiment of the present application.

Taking the morning scene as an example, the trigger conditions of the morning scene can be composed of time and device status conditions;

1. After 5 o'clock in the morning.

2. Within plus or minus one hour of the user's morning wake-up time.

3. After turning off the screen for a long time, the phone turns on for the first time.

Exemplarily, the triggering conditions of the morning scene may consist of the above three conditions: the first condition is after 5:00 in the morning. The second condition is, within plus or minus one hour of the user's wake-up time. Here, the user's wake-up time is calculated by the electronic device based on the user's historical usage data, such as a wake-up alarm clock on the electronic device. The third condition is that the phone is turned on for the first time after the screen has been off for a long time. Only when the above three conditions are met at the same time, the electronic device 100 will recommend the service set in the morning scene for the user.

Taking the morning scene as an example, the exit conditions of the morning scene can be composed of time and location conditions;

1. One hour after the screen is turned on for the first time after the phone has been off for a long time.

2. The user leaves the house, and the location is getting farther and farther away from home.

Exemplarily, the exit condition of the morning scene may be composed of the above three conditions: the first condition is that one hour after the screen of the mobile phone is turned on for the first time after the screen of the mobile phone has been off for a long time. The second condition is that the user is out of the house, and the location is getting farther and farther away from home. Only when the above two conditions are satisfied at the same time, the electronic device 100 will stop recommending the service set in the morning scene for the user.

From the above analysis, it can be known that when the electronic device 100 detects that the time, place and device state meet the trigger conditions of a certain scene, the electronic device 100 will recommend the corresponding service set in the scene for the user; when the electronic device 100 detects that the time, place When the device status meets the exit condition of a certain scene, the electronic device 100 will stop recommending the corresponding service set in the scene for the user. Since the trigger conditions and exit conditions of the scene are predetermined, the user's usage habits are not uniform, which will cause the electronic device 100 to recommend a service set in a certain scene for the user according to the predetermined trigger conditions, or the electronic device 100 According to the predetermined exit conditions, stop recommending the service set in a certain scene for the user, and there is a deviation from the time when the user actually uses the service set in the scene. For example, the electronic device 100 recommends a service set in a certain scene for the user according to a predetermined trigger condition, which may cause the electronic device 100 to recommend a service set in a certain scene to the user too early, or the electronic device 100 recommends a certain service set for the user. It happens that the collection of services in a scene is too late. For another example, the electronic device 100 stops recommending a service set in a certain scenario for the user according to a predetermined exit condition, which may cause the electronic device 100 to stop recommending a service set in a certain scenario for the user too early, or the electronic device 100 stops It is too late to recommend a set of services in a certain scenario to users.

Next, the above scenario will be described in detail with reference to the accompanying drawings.

FIGS. 18A-18E exemplarily show a schematic diagram of a time when the electronic device 100 enters a scene or exits a scene and the time when the user actually uses the service set in the scene deviates.

Wherein, FIG. 18A exemplarily shows a schematic diagram of a preset entry time and a preset exit time in a single scene.

In FIG. 18A , when the electronic device 100 judges that the time, location and device state meet the trigger conditions for entering a scene, the electronic device 100 recommends a service set for the user at time t1. Since the trigger conditions of the scene are preset, t1 The moment can be understood as the preset entry moment of the scene. After a certain period of time after the electronic device 100 recommends the service set to the user, for example, at time t2, which is greater than time t1, when the electronic device 100 judges that the scene time, location and device state meet the exit conditions for exiting the scene, the electronic device 100 stops recommending service sets for the user. Since the exit condition of the scene is preset, time t2 can be understood as the preset exit time of the scene.

FIG. 18B exemplarily shows a schematic diagram of a single scene entering too late.

In FIG. 18B , the preset entry time of the scene is time t1. Due to the change of the user's behavior habit, the electronic device 100 detects that the user uses the service set in the scene at time t3, and the time t3 is smaller than the time t1. In this way, the user has already used the service in the scene, and at time t1, the electronic device 100 will again recommend the service set in the scene to the user when the preset entry time of the scene arrives. Alternatively, the electronic device 100 detects that the user has used the service set in the scene at time t1, then at time t1, the electronic device 100 no longer recommends the service set in the scene for the user. Wherein, (t1-t3) is the time period for the electronic device 100 to enter the scene. In this way, the electronic device 100 may not be able to recommend the service set in the scene for the user in time, which affects the user experience.

Exemplarily, the user will use the taxi service in the commuting scene on weekdays, and the triggering condition of the commuting scene is: after the user leaves home. However, in the actual application of the user, the user will use the taxi service to call a car before leaving home, and the user will leave home after the car is called. Due to the deviation between the preset trigger condition and the actual behavior of the user, the electronic device 100 cannot timely adjust the trigger condition of the scene and recommend corresponding services for the user.

FIG. 18C exemplarily shows a schematic diagram of a single scene entering prematurely.

In FIG. 18C, the preset entry time of the scene is time t1. Due to the change of the user's behavior habits, the electronic device 100 detects that the user recommends the service set in the scene at the time t1, but the user does not use the service set immediately. Instead, the user uses the service set recommended by the electronic device 100 at the time t1 at a certain time after the time t1, for example, the time t3, and the time t3 is greater than the time t1. (t3-t1) is the time period for the electronic device 100 to enter the scene in advance. In this way, the electronic device 100 may enter the scene in advance.

Exemplarily, in the scene of getting up in the morning, the user will use the speaker to play the weather service, and the triggering conditions of the scene of getting up in the morning are: 1. After 5:00 in the morning. 1. One hour after the screen is turned on for the first time after the phone has been off for a long time. 2. Within plus or minus one hour of the user's morning wake-up time. 3. After turning off the screen for a long time, the phone turns on for the first time. After the electronic device 100 detects that the time, location and device status meet the above trigger conditions in the morning, the electronic device 100 will recommend the speaker to play the weather service for the user. However, in the actual scene of waking up in the morning, the user has the habit of waking up in the morning, usually after going out for a run and returning home to use the speaker to play the weather service. In this way, the user will use the speaker to play the weather service for a long time after the electronic device 100 recommends the speaker to play the weather service for the user.

FIG. 18D exemplarily shows a schematic diagram of a single scene exiting too late.

In FIG. 18D, the preset entry time of the scene is time t1, and the preset exit time of the scene is time t2. At time t1, the electronic device 100 recommends a service set in a certain scene to the user. Suppose the user uses the service set near time t1, but the user stops using the service set in the scene at time t3, and time t3 is greater than t1 The time is less than the time t2. However, after the user finishes using the service set in the scene, the electronic device 100 will continue to recommend the service set in the scene for the user before the time reaches the preset exit time t2 of the scene. When the electronic device 100 detects that the time reaches the preset exit time t2 of the scene, the electronic device 10 will stop recommending the service set in the scene. In this way, the electronic device 100 cannot pause in advance to display the service set in the recommended scene based on the usage of the user, and the recommendation resources of the electronic device 100 will be wasted.

Exemplarily, in the morning scene, the user will use the speaker to play the weather service, and when the electronic device 100 detects that the trigger condition of the morning scene is met, the electronic device 100 recommends the speaker to play the weather service to the user at time t1. If the user has finished using the speaker to play the weather service before reaching the preset exit time of the speaker to play the weather service. After the user has finished using the speaker to play the weather service, before reaching the preset exit time of the speaker to play the weather service, the electronic device 100 will continue to recommend the speaker to play the weather service until the time reaches the preset exit time of the box to play the weather service.

FIG. 18E exemplarily shows a schematic diagram of premature exit of a single scene.

In FIG. 18E , the preset entry time of the scene is time t1 , and the preset exit time of the scene is time t2 . At time t1, the electronic device 100 recommends a service set in a certain scene to the user. Assuming that the user has not used the service set between time t1 and time t2, the electronic device 100 detects that the time reaches the preset exit time t2 of the scene. At time , the electronic device 100 will stop recommending the service set in the scene for the user. However, the user has not used the service set in the scene, and at a certain time after the electronic device 100 stops recommending the service set in the scene for the user, the user may want to use the service set in the scene again. In this way, the scene will be exited too early and the time when the user actually uses the service will be missed.

Exemplarily, in the morning scene, the user will use the speaker to play the weather service, and when the electronic device 100 detects that the trigger condition of the morning scene is met, the electronic device 100 recommends the speaker to play the weather service to the user at time t1. If the electronic device 100 detects that the user has not used the speaker to play the weather service before the preset exit time for the speaker to play the weather service. When the time reaches the preset exit time of the weather service played by the speaker, the electronic device 100 will stop recommending the weather service played by the speaker to the user. However, it may be because the user has not woken up in the morning, but the user missed the time to use the speaker to play the weather service, but after the user wakes up, the user may use the speaker to play the weather service again, but the electronic device 100 has stopped recommending weather services for the user. The speaker plays the weather service, causing users to be unable to use the speaker to play the weather service.

Based on the above analysis, in order to avoid a large discrepancy between the time when the electronic device 100 recommends a service set for the user, or the time when the electronic device 100 stops recommending a service set for the user, and the time when the user actually uses the service set in this scenario, the electronic device 100 may Based on the user's habit of using scene-associated services, the scene entry and exit rules are adaptively adjusted to achieve the purpose of personalized matching between scene entry and exit and the user's actual needs.

First, a functional block diagram for adaptively adjusting scene conditions provided by the embodiment of the present application is introduced.

FIG. 19 exemplarily shows a functional block diagram of the electronic device 100 for adaptively adjusting scene conditions.

The functional modules for adaptively adjusting scene conditions include but are not limited to a scene condition collection module, a scene decision module and a rule adjustment module.

Among them, the scene condition collection module is used to collect current time, current location and equipment status. Among them, the device refers to all the devices associated with the user. In addition to portable terminal devices (such as mobile phones), they can also be wearable devices (such as Bluetooth watches, Bluetooth bracelets, etc.), and smart home devices (such as large-screen , smart speakers, smart curtains, etc.). The device associated with the user may also be other devices, such as a smart toothbrush, etc. The embodiment of the present application does not limit the type of device associated with the user.

Before the scene condition collection module collects the current time, current location and device status, the electronic device 100 has preset service sets in each scene, scene trigger conditions, and scene exit conditions in some scenes. As mentioned above, the triggering conditions of the scene and the exiting conditions of the scene are preset. As for how to obtain the user's service set in different scenarios, the two types of electronic devices 100 described in the foregoing embodiments may be used to refer to the specific implementation of recommending services for the user, and the embodiments of the present application will not repeat them here.

After the scene condition collection module obtains the current time, current location and equipment state, the scene condition collection module sends the obtained current time, current location and equipment state to the scene decision module.

After the scene decision module receives the current time, current location and device status sent by the scene condition acquisition module, the scene decision module will judge whether the entry conditions of a certain scene are met based on the time, place and device status, and if so, recommend it to the user. A collection of services in a certain scenario. Alternatively, the scenario decision module will judge whether the exit condition of a certain scenario is satisfied based on the time, location and device status, and if so, stop recommending the service set in the certain scenario for the user.

After the service set of a certain scene is recommended for the user, the scene decision module will detect whether the user has used the service set of the certain scene. If the user uses the service set of the certain scene, the scene decision module records the time when the scene decision module recommends the service set for the user and the time when the user uses the service set of the certain scene. If the user does not use the service set of a certain scene, and when the time, location and device status meet the exit conditions of the certain scene, the scene decision module will stop recommending the service set in the certain scene for the user. After that, the scene The decision-making module records the time when it stops recommending the service set in the certain scene for the user. If the user has used the service set in a certain scene after the scene decision-making module stops recommending the service set in the certain scene for the user, the scene decision-making module will record the time when the user uses the service set in the certain scene .

After the scene decision-making module recommends the service set for the user, the scene decision-making module sends the time of recommending the service set, the time of stopping the recommended service set and the time when the user actually uses the service set to the rule adjustment module. Optionally, if the user does not use the recommended service set, it only needs to send the time when the scenario decision module recommends the service set and the time when the recommended service set stops to the rule adjustment module.

After the rule adjustment module receives the time of the recommended service set sent by the scenario decision module, the time of stopping the recommended service set and the time when the user actually uses the service set, the rule adjustment module will determine whether to adjust the trigger conditions and exit conditions of the above scenarios .

Specifically, when the rule adjustment module determines that the time when the user actually uses the service set is earlier than the time when the scenario decision module recommends the service set, refer to the relevant description in FIG. 18B for details. Then the rule adjustment module will adjust the trigger conditions of the scenario, so that the time when the user actually uses the service set is later than the time when the scenario decision module recommends the service set, and the time between the time when the scenario decision module recommends the service set and the time when the user actually uses the service set The time difference between them is less than the preset value. As for how the rule adjustment module adjusts the triggering conditions of the scene, reference may be made to the related description of how the electronic device 100 adjusts the triggering conditions of the scene, which will not be repeated in this embodiment of the present application.

When the rule adjustment module judges that the time when the user actually uses the service set is later than the time when the scene decision module recommends the service set, but the time difference between the time when the user actually uses the service set and the time when the scene decision module recommends the service set is greater than the preset value, For details, refer to the relevant description in FIG. 18C. Then the rule adjustment module will adjust the trigger conditions of the scenario, so that the time when the scenario decision module recommends the service set is earlier than the time when the user actually uses the service set, and the time between the time when the scenario decision module recommends the service set and the time when the user actually uses the service set The time difference between them is less than the preset value. As for how the rule adjustment module adjusts the triggering conditions of the scene, reference may be made to the related description of how the electronic device 100 adjusts the triggering conditions of the scene, which will not be repeated in this embodiment of the present application.

When the rule adjustment module determines that the time when the user actually uses the service set is earlier than the time when the scenario decision module stops recommending the service set, but the time difference between the time when the user actually uses the service set and the time when the scenario decision module stops recommending the service set is greater than the preset time For details, please refer to the relevant description in Figure 18D. Then the rule adjustment module will adjust the exit conditions of the scene, so that the time when the user actually uses the service set is later than the time when the scene decision module recommends the service set, and the time when the user actually uses the service set is earlier than the time when the scene decision module stops recommending the service set At the same time, the time difference between the time when the user actually uses the service set and the time when the scene decision module stops recommending the service set is less than the preset value. As for how the rule adjustment module adjusts the exit conditions of the scene, reference may be made to the related description of how the subsequent electronic device 100 adjusts the exit conditions of the scene, which will not be repeated in this embodiment of the present application.

When the rule adjustment module determines that the time when the user actually uses the service set is later than the time when the scenario decision module stops recommending the service set, please refer to the related description in FIG. 18E for details. Then the rule adjustment module will adjust the exit conditions of the scene, so that the time when the user actually uses the service set is later than the time when the scene decision module recommends the service set, and the time when the user actually uses the service set is earlier than the time when the scene decision module stops recommending the service set At the same time, the time difference between the time when the user actually uses the service set and the time when the scene decision module stops recommending the service set is less than the preset value. As for how the rule adjustment module adjusts the exit conditions of the scene, reference may be made to the related description of how the subsequent electronic device 100 adjusts the exit conditions of the scene, which will not be repeated in this embodiment of the present application.

Next, it will be introduced how the electronic device 100 adjusts the trigger condition and the exit condition of the scene.

Firstly, it is introduced how the electronic device 100 adjusts the triggering conditions of the scene when the scene is entered too early.

The electronic device 100 counts the data of the set of scene services used by the user within a certain period of time (for example, one month). In order to reduce the error of data statistics, the data of the scene service collection used by the user within a certain period of time can be represented by a normal distribution.

Not limited to the normal distribution, the electronic device 100 may also represent the data of the scene service set used by the user within a certain period of time in other ways, which is not limited in this embodiment of the present application.

Assume that the time when the scene enters is T _P , and the time when the electronic device 100 detects that the user uses the service set in the scene is Tq. The electronic device 100 respectively obtains the mean value of the time T _P when the scene enters in each scene and the time Tq when the user uses the service set in the scene, and the mean value can be expressed as E(Tq-T _P ). The electronic device 100 can also obtain the standard deviation of the time Tq when the user enters the scene in each scene and the time Tq when the user uses the service set in the scene, and the standard deviation can be expressed as δ(Tq-T _P ).

FIG. 20 exemplarily shows a schematic diagram of a normal distribution of data of a scene service set used by a user.

In Figure 20, it can be obtained from the characteristics of the data in the normal distribution, [E(Tq-T _P )-3δ(Tq-T _P ),E(Tq-T _P )+δ(Tq-T _P )] Contains 99.7% of user data.

When E(Tq-T _P )-3δ(Tq-T _P ) is greater than 0 and smaller than the threshold, and the threshold is a positive integer, such as 5 minutes, it means that the time to enter the scene is just right.

When E(Tq-T _P )-3δ(Tq-T _P ) is greater than the threshold, it means that the time to enter the scene is too early, that is, the user uses the service collection in the scene after a long time after entering the scene.

When E(Tq-T _P )-3δ(Tq-T _P ) is less than 0, it means that the time to enter the scene is too late, that is, the electronic device 100 recommends the scene to the user only after the user uses the service set in the scene. collection of services.

When |E(Tq-T _P )|-3δ(Tq-T _P ) is greater than 0 and less than the threshold, it means that the time to exit the scene is too late, that is, after the user has used the service set in the scene for a long time, the electronic device 100 Only then stop recommending the set of services in the scenario.

When |E(Tq-T _P )|-3δ(Tq-T _P ) is less than 0, it means that the scene exit time is too early, that is, the user has not had time to use the service set in the scene, and the electronic device 100 has stopped recommending the scene collection of services.

A scenario's trigger condition can consist of one or more conditions. In the trigger conditions of the scene, find a condition that finally restricts the entry of the scene, and this condition is the maximum constraint condition of the trigger condition.

When the scene enters too early, the electronic device 100 only needs to adjust the maximum constraint condition, so that the adjusted maximum constraint condition can make the scene entry time earlier than the user's actual use time, and the scene entry time is different from the user's actual use time. The difference between the times is within the preset value.

The electronic device 100 may adjust the maximum constraint condition in any of the following manners:

Way 1: The electronic device 100 delays the execution time of the maximum constraint condition by a time λ.

Way 2: The electronic device 100 adds a new trigger condition, and the electronic device 100 executes the new trigger condition within λ time after the maximum constraint condition is triggered.

The electronic device 100 may also adjust the maximum constraint condition for scene entry in other ways, which is not limited in this embodiment of the present application.

Next, it will be introduced how the electronic device 100 finds the delay time λ and the new trigger condition.

The following takes the scene of getting up in the morning as an example to illustrate how the electronic device 100 finds the delay time λ of the maximum constraint condition and a new trigger condition.

FIG. 21 exemplarily shows a schematic diagram of the electronic device 100 adjusting the trigger condition for entering a scene too early.

S2101. The electronic device 100 determines the delay time λ of the maximum constraint condition among the preset trigger conditions.

The maximum constraint condition in the preset trigger conditions can be understood as the last executed condition in the original trigger conditions.

Assume that the preset triggering conditions of the morning scene are: 1. After 5:00 in the morning. 2. After the phone is turned off for the first time after the screen has been turned off for a long time. Since the preset trigger condition of the morning scene consists of multiple conditions, the electronic device 100 needs to determine the maximum limit condition from the multiple conditions, and the maximum limit condition can be understood as a condition that the electronic device 100 executes last. For example, if the user often gets up at six o'clock in the morning and the current time is half past six, then the electronic device 100 determines that both

conditions

1 and 2 of the morning wake-up scene are satisfied, and the current condition 3 is not satisfied, then condition 3 is the entry into the scene. Maximum constraints.

Before adjusting the preset trigger conditions, the electronic device 100 has obtained the value of E(Tq-TP)-3δ(Tq-TP). Since the scene enters too early, from the perspective of normal distribution, it will lead to E(Tq-TP) The value of -3δ(Tq-TP) is greater than the threshold, and the electronic device 100 uses the value of {E(Tq-TP)-3δ(Tq-TP)-threshold} as the delay time λ of the maximum constraint. That is to say, after the electronic device 100 delays the maximum constraint condition among the preset trigger conditions by a time λ, the electronic device 100 can make the time between the time when the electronic device 100 recommends the service collection service of the morning scene and the time when the user actually uses the service of the morning scene The time difference is less than the threshold. From the perspective of normal distribution, it can also be said that the value of E(Tq-TP)-3δ(Tq-TP) is greater than 0 and less than the threshold.

S2102. Based on the delay time λ and the candidate addition conditions, the electronic device 100 determines the addition condition (the first addition sub-condition) and the maximum constraint condition among the preset trigger conditions.

Wherein, the electronic device 100 records the behavior of the user within a period of time before and after using the service set in the scenario. For example, the electronic device 100 records the user's behavior for a period of time (for example, within 5 minutes) before the electronic device 100 recommends a set of services in the scene. The electronic device 100 records the behavior of the user within a period of time (for example, within 5 minutes) after the electronic device 100 stops the service set in the recommendation scenario. The user's behavior can be understood as what the electronic device 100 detects the user does, or the electronic device 100 detects what the user does through other devices. For example, the user's behavior can be outdoor exercise, brushing teeth, leaving home, returning home, wearing a watch, listening to music, turning off the lights, turning off the air conditioner, and so on. Users may behave differently for a period of time before and after using a collection of services in different scenarios.

Table 12

Table 12 exemplarily shows some behaviors of the user before and after the electronic device 100 recommends the service set of the scenario in some scenarios. For example, in the scene of getting up in the morning, within a period of time (for example, 5 minutes) before the service set of the scene recommended by the electronic device 100, the user may finish running and return home, and the user may also use an electric toothbrush to brush his teeth. Within a period of time (for example, 5 minutes) after the electronic device 100 stops the service collection of recommended scenes, the user may open the curtains of the living room. In the commuting scene on weekdays, the user may turn off the light in the bedroom, and the user may also put on a bluetooth watch for a period of time (for example, 5 minutes) before the electronic device 100 recommends the service collection of the scene. Within a period of time (for example, 5 minutes) after the electronic device 100 stops the service collection of recommended scenarios, the user may take the elevator and leave home.

Optionally, the behavior of the user may also be referred to as a candidate addition condition.

It is not limited to the user behaviors described above, and may also include other user behaviors in the morning scene and weekday commuting scene, which is not limited in this embodiment of the present application.

It is not limited to the user behaviors mentioned in the morning scene and the commuting scene on weekdays described above, but also includes user behaviors in other scenes or situations, which will not be described here in this embodiment of the present application.

After the electronic device 100 finds the delay time λ of the maximum constraint condition, the electronic device 100 can also add a new condition. The preset trigger condition of the morning scene after adding the new condition can make the scene entry time different from the user's actual use. The difference between the times is within the preset value. In this way, it can be prevented that in some cases, the electronic device 100 delays the maximum constraint condition by a time λ, and the scene enters too late. For example, in some cases, in the morning scene, the preset trigger condition of the morning scene is: 1. 7:00 am. The set of services for the morning scene serves the alarm clock. If the electronic device 100 delays the preset trigger condition by a time λ, for example, λ is 15 minutes, then the trigger condition of the morning scene is: 1. 7:15 in the morning. The user may get up before 7:15 in the morning, but the electronic device 100 has not recommended the alarm clock service, and the electronic device 100 may recommend the alarm clock service too late. Therefore, the electronic device 100 can add another constraint condition, the trigger condition of the morning scene is: 1. 7:15 in the morning, or the user's mobile phone turns on the screen for the first time within 7:15 in the morning. In this way, even if the time in the modified trigger condition is 7:00, but it is not yet 7:15, the user's mobile phone turns on and the user wakes up, and the electronic device 100 can recommend an alarm clock service for the user.

Table 12 shows user behaviors (or candidate new conditions) before the electronic device 100 recommends the service set of the scene in the morning scene. If there is one user behavior (or candidate addition condition) before the service set of the scene recommended by the electronic device 100, then this user behavior is used as an addition condition of the preset trigger condition. If there are multiple user behaviors prior to the service set of scenarios recommended by the electronic device 100, the electronic device 100 needs to determine an optimal user behavior from the multiple user behaviors as a new condition for the preset trigger condition.

Optionally, in some embodiments, the electronic device 100 may only determine the maximum constraint condition among the preset trigger conditions, without determining the new condition based on the user's behavior, which is not limited in this embodiment of the present application. .

Next, it will be introduced how the electronic device 100 determines the maximum constraint condition and the newly added condition in the preset trigger conditions.

Optionally, the electronic device 100 may use an enumeration method to determine the maximum constraint condition and the newly added condition in the preset trigger conditions. Specifically, the electronic device 100 respectively modifies each of the preset trigger conditions into the following form: each of the preset trigger conditions is delayed by a time λ, or each of the preset trigger conditions is triggered by λ Within the time, the candidate new conditions are executed. It should be noted that only one of the preset trigger conditions needs to be modified to the above form each time, and other conditions in the preset trigger conditions remain unchanged. In this way, after modifying each of the preset trigger conditions, a candidate trigger condition is obtained, and based on the candidate trigger condition, the time TP at which the electronic device 100 recommends the service set in the scenario is determined here. Based on the time Tp when the electronic device 100 recommends the service set in the scene and the time Tq when the user uses the service set in the scene, the electronic device 100 determines whether the time difference between the two is within a preset value. Or from the perspective of normal distribution, the electronic device 100 can obtain E(Tq-Tp) and δ(Tq-Tp), and detect whether the value of E(Tq-T _P )-3δ(Tq-T _P ) is greater than 0 and less than threshold.

If according to the above method, there are multiple candidate trigger conditions, which can make the time difference between the time when the electronic device 100 recommends the service set in the scene and the time when the user uses the service set in the scene is less than the preset value, then the electronic device 100 The best candidate trigger condition can be determined based on the following formulas, formula (1) and formula (2).

M=αE(Tq-Tp)+βδ(Tq-Tp) Formula (1)

E(Tq-Tp)>3δ(Tq-Tp) Formula (2)

As shown in formula (1) and formula (2), both α and β are preset values, for example, both α and β can be 1. In the case that α and β are the same, the electronic device 100 may make the candidate trigger condition with the smallest M value in the above formula (1) and formula (2) the best candidate trigger condition.

It should be noted that it is not limited to formula (1), and other formulas can also be used to determine the best candidate trigger condition that can minimize the mean and standard deviation, which is not limited in this embodiment of the present application.

After the electronic device 100 determines the best candidate trigger condition, the candidate added condition I corresponding to the best candidate trigger condition adds a new condition, and the condition item modified relative to the original trigger condition in the best candidate trigger condition is the maximum constraint condition.

Exemplarily, for the scene of waking up in the morning, assuming that the delay time λ of the maximum constraint condition is 15 minutes, the candidate addition condition may be finishing running and returning home, and brushing teeth. Then the electronic device 100 needs to modify each of the trigger conditions of the morning scene to obtain multiple different candidate trigger conditions, and obtain multiple M values based on the multiple different candidate trigger conditions.

Table 13

Table 13 exemplarily shows the processes of multiple different candidate trigger conditions obtained after modifying the preset trigger conditions in the morning scene. Among them, the preset trigger conditions in the morning scene include "1. After 5:00 in the morning. 2. After the mobile phone turns off the screen for a long time and turns on for the first time". According to the above rules, based on the delay time λ (15 minutes) of the maximum constraint condition and candidate new conditions (running and returning home and brushing teeth), 4 different sets of candidate trigger conditions can be obtained. The first set of candidate trigger conditions is "1 1. After 5:15 in the morning, or within 5:15 in the morning, the user finishes running and returns home. 2. The screen of the mobile phone turns on for the first time after being off for a long time. The electronic device 100 obtains the value of M in the formula (1) as A1 based on the first group of candidate trigger conditions. The second group of candidate trigger conditions are "1. After 5:00 in the morning. 2. 15 minutes after the mobile phone turns off for the first time, or within 15 minutes after the phone turns off for the first time, the user finishes running and returns home. ". The electronic device 100 obtains the value of M in the formula (1) as A2 based on the second group of candidate trigger conditions. The third group of candidate trigger conditions is "1. After 5:15 in the morning, or within 5:15 in the morning, the user finishes running and returns home. 2. After the screen of the mobile phone is turned off for the first time after a long time". Based on the third group of candidate trigger conditions, the electronic device 100 obtains the value of M in formula (1) as A3. The fourth group of candidate trigger conditions is "1. After 5:00 in the morning. 2. The user brushes his teeth within 15 minutes after the phone is turned on for the first time after the screen has been off for a long time, or within 15 minutes after the phone is turned on for the first time after the screen has been turned off for a long time". Based on the fourth group of candidate trigger conditions, the electronic device 100 obtains the value of M in formula (1) as A4.

Afterwards, the electronic device 100 compares the sizes of A1, A2, A3, and A4, and the candidate trigger condition corresponding to the smallest M value is the best candidate trigger condition.

Assuming that the value of A2 is the smallest, then the best candidate trigger condition is "1. After 5:00 in the morning. 2. 15 minutes after the phone is turned on for the first time after the screen has been off for a long time, or within 15 minutes after the phone is turned on for the first time after the screen has been off for a long time, The user finishes running and returns home", then the candidate added condition corresponding to the best candidate trigger condition is the added condition, that is, "completes running and returns home". The condition item modified relative to the preset trigger condition in the best candidate trigger condition is the maximum constraint condition, that is, "after the screen of the mobile phone is turned on for the first time after being off for a long time".

S2103. The electronic device 100 modifies the preset trigger condition based on the maximum constraint condition, the newly added condition, and the delay time λ of the maximum constraint condition, to obtain a modified trigger condition.

It should be noted that modifying the trigger condition can be understood as the best candidate trigger condition obtained in S2102. Specifically, for how the electronic device 100 obtains the modified trigger condition, reference may be made to How to Obtain the Best Candidate Trigger Condition in S2102, which will not be repeated in this embodiment of the present application.

Exemplarily, for the scene of getting up in the morning, modify the trigger condition to "1. After 5:00 in the morning. 2. 15 minutes after the screen of the mobile phone is turned on for the first time after being off for a long time, or 15 minutes after the screen of the mobile phone is turned on for the first time after being off for a long time Within, the user completes the run and returns home". In a specific implementation, only when the electronic device 100 judges that the current time, place, and device status satisfy two conditions in the modification trigger condition at the same time, the electronic device 100 will recommend the service set in the morning scene for the user.

Next, it will be introduced how the electronic device 100 adjusts the triggering condition of the scene when the scene enters too late.

From the embodiment shown in Figure 20, it can be known that when E(Tq-T _P )-3δ(Tq-T _P ) is less than 0, it means that the scene entry time is too late, that is, after the user uses the service set in the scene, The electronic device 100 recommends the service set in the scene for the user. Then, the electronic device 100 needs to advance the entry condition of the scene, so that the time when the user actually uses the service set is later than the time when the electronic device 100 recommends the service set for the user.

A scenario's trigger condition can consist of one or more conditions. In the trigger conditions of the scene, find a condition that finally restricts the progress of the scene, and this condition is the maximum constraint condition of the trigger condition.

When the scene enters too late, the electronic device 100 only needs to adjust the preset trigger condition of the scene, so that the adjusted preset trigger condition can make the scene enter time earlier than the user's actual use time, and the scene enter time is the same as the user's The difference between the times actually used is within the preset value.

Manner 1: The electronic device 100 modifies the maximum constraint condition to a newly added condition.

Mode 2: After the electronic device 100 triggers the maximum constraint condition among the preset trigger conditions, the newly added condition in Mode 1 is not triggered.

The electronic device 100 may also adjust the preset trigger condition of the scene in other ways, which is not limited in this embodiment of the present application.

Next, it will be introduced how the electronic device 100 finds the newly added condition and the maximum constraint condition.

The following takes the scene of getting up in the morning as an example to illustrate how the electronic device 100 finds the newly added condition and the maximum constraint condition.

FIG. 22 exemplarily shows a schematic diagram of the electronic device 100 adjusting the trigger condition of the scene entering too late.

S2201. The electronic device 100 determines the maximum constraint condition among the newly added condition (the second newly added sub-condition) and the preset trigger condition based on the candidate added condition.

The candidate addition conditions have been described in detail in S2102. For details, reference may be made to relevant descriptions in S2102, which will not be repeated in this embodiment of the present application.

The electronic device 100 may use an enumeration method to determine the maximum constraint condition among the newly added condition and the preset trigger condition. For specific implementation, reference may be made to related descriptions in S2102, which will not be repeated in this embodiment of the present application.

Exemplarily, for the commuting scene on weekdays, it is assumed that the candidate addition condition may be turning off the light in the bedroom and wearing a Bluetooth watch. Then the electronic device 100 needs to modify each condition in the commuting scene on weekdays to obtain multiple different candidate trigger conditions, and obtain multiple M values based on the multiple different candidate trigger conditions.

Table 14

Table 14 exemplarily shows the process of multiple different candidate trigger conditions obtained after modifying the preset trigger conditions in the commuting scene on weekdays. Among them, the preset trigger conditions in the morning scene include "1. After 7:00 am on weekdays. 2. The user leaves the bedroom within the above time period". According to the above rules, based on the candidate new conditions and preset trigger conditions, four different candidate trigger conditions can be obtained. The first group of candidate trigger conditions is "1. Turn off the light in the bedroom, or the user does not turn off the light in the bedroom after 7:00 am on weekdays. 2. The user leaves the bedroom within the above time period". The electronic device 100 obtains the value of M in formula (1) as B1 based on the first group of candidate trigger conditions. The second group of candidate trigger conditions is "1. After 7:00 a.m. on weekdays. 2. Turn off the light in the bedroom, or leave the light in the bedroom on after the user leaves home within the above time period". The electronic device 100 obtains the value of M in formula (1) as B2 based on the second group of candidate trigger conditions. The third group of candidate trigger conditions is "1. The user wears the Bluetooth watch, or the user does not wear the Bluetooth watch after 7:00 am on weekdays. 2. The user leaves home within the above time period". Based on the third group of candidate trigger conditions, the electronic device 100 obtains the value of M in formula (1) as B3. The fourth group of candidate trigger conditions is "1. After 7:00 a.m. on weekdays. 2. The user wears the Bluetooth watch, or the user does not wear the Bluetooth watch after the user leaves the bedroom within the above time period". Based on the fourth group of candidate trigger conditions, the electronic device 100 obtains the value of M in formula (1) as B4.

Afterwards, the electronic device 100 compares the sizes of B1, B2, B3 and B4, and the candidate trigger condition corresponding to the smallest M value is the best candidate trigger condition.

Assuming that the value of B2 is the smallest, then the best candidate trigger condition is "1. After 7:00 a.m. on weekdays. 2. Turn off the lights in the bedroom, or leave the lights in the bedroom on after the user leaves home within the above time period", then The candidate added condition corresponding to the best candidate trigger condition is the added condition, that is, "turn off the light in the bedroom". The condition item modified relative to the preset trigger condition in the best candidate trigger condition is the maximum constraint condition, that is, "the user leaves the bedroom within the above time period".

S2202. The electronic device 100 modifies the preset trigger condition based on the newly added condition and the maximum constraint condition among the preset trigger conditions, to obtain a modified trigger condition.

It should be noted that modifying the trigger condition can be understood as the best candidate trigger condition obtained in S2201. Specifically, for how the electronic device 100 obtains the modified trigger condition, reference may be made to How to Obtain the Best Candidate Trigger Condition in S2201, which will not be repeated in this embodiment of the present application.

Exemplarily, for the commuting scene on weekdays, modify the trigger condition to "1. After 7:00 am on weekdays. 2. Turn off the lights in the bedroom, or turn off the lights in the bedroom after the user leaves home within the above time period." Not closed". In a specific implementation, only when the electronic device 100 judges that the current time, location, and device status meet the two conditions in the modification trigger conditions at the same time, the electronic device 100 will recommend the service set for the user in the commuting scene on weekdays .

Next, it will be introduced how the electronic device 100 adjusts the exit condition of the scene when the scene is exited too late.

From the embodiment shown in Figure 20, it can be seen that when |E(Tq-T _P )|-3δ(Tq-T _P ) is greater than 0 and smaller than the threshold, it means that the time to exit the scene is too late, that is, the user has used up all the The electronic device 100 stops recommending the service set in the scene after a long time of service set.

Then, the electronic device 100 needs to advance the exit condition of the scene, so that the electronic device 100 stops recommending the service set for the user within a certain period of time after the user actually uses the service set.

A scenario's exit condition can consist of one or more conditions. In the exit conditions of the scenario, find a condition that finally constrains the exit of the scenario, and this condition is the maximum constraint condition of the exit condition.

When the scene exits too late, the electronic device 100 only needs to adjust the maximum constraint condition in the preset exit conditions, so that the adjusted maximum constraint condition can make the scene exit time later than the actual use time of the user, and the scene exit The difference between the time and the time actually used by the user is within the preset value.

Method 2: The electronic device 100 adds a new exit condition, and the electronic device 100 executes the new exit condition within λ time after the maximum constraint condition is triggered.

The electronic device 100 may also adjust the maximum constraint condition among the preset exit conditions in other ways, which is not limited in this embodiment of the present application.

Next, it will be introduced how the electronic device 100 finds the delay time λ and the new exit condition.

FIG. 23 exemplarily shows a schematic diagram of the electronic device 100 adjusting the exit condition of the scene exiting too late.

S2301. The electronic device 100 determines the delay time λ of the maximum constraint condition among the preset exit conditions.

The principle that the electronic device 100 determines the delay time λ of the maximum constraint condition among the preset exit conditions is similar to the principle that the electronic device 100 determines the delay time λ of the maximum constraint condition among the preset entry conditions. For details, refer to the relevant description in S2101. The embodiment of the present application will not be repeated here.

S2302. Based on the delay time λ and the candidate addition condition, the electronic device 100 determines the maximum constraint condition among the addition condition (the first addition sub-condition) and the preset exit condition.

The electronic device 100 determines the newly added condition in the scene exiting too late and the maximum constraint condition in the preset exit condition, and the electronic device 100 determines the principle of the scene entering too early in the newly added condition and the maximum constraint condition in the preset entry condition Similarly, for details, reference may be made to relevant descriptions in S2102, which will not be repeated in this embodiment of the present application.

After the electronic device 100 determines the maximum constraint condition in the newly added condition and the preset exit condition, it modifies the maximum constraint condition in the preset exit condition based on the delay time λ and the newly added condition, so that the modified maximum constraint condition can make the scenario The exit time is later than the time actually used by the user, and the difference between the scene exit time and the time actually used by the user is within the preset value.

Exemplarily, for the scene of waking up in the morning, assuming that the delay time λ of the maximum constraint condition is 15 minutes, the candidate addition condition may be finishing running and returning home, and brushing teeth. Then the electronic device 100 needs to modify each of the exit conditions of the morning scene to obtain multiple different candidate exit conditions, and obtain multiple M values based on the multiple different candidate exit conditions.

Table 15

Table 15 exemplarily shows the process of multiple different candidate exit conditions obtained after modifying the preset exit conditions in the morning scene. Among them, the preset exit conditions in the morning scene include "1. One hour after the screen is turned on for the first time after the mobile phone has been off for a long time. 2. The user leaves home". According to the above rules, based on the delay time λ (15 minutes) of the maximum constraint condition and candidate new conditions (opening the curtains in the living room and opening the sweeping robot in the living room), 4 different sets of candidate exit conditions can be obtained. The first set of candidate exit conditions "1. One hour and 15 minutes after the mobile phone turns off the screen for a long time, or within one hour after the mobile phone turns off the screen for the first time, open the curtains of the living room. 2. The user leaves home", Electronics The device 100 obtains the value of M in formula (1) as C1 based on the first group of candidate exit conditions. The second group of candidate exit conditions is "1. One hour after the screen of the mobile phone is turned off for a long time. 2. The user opens the curtains of the living room 15 minutes after leaving home, or before the user leaves home", the electronic device 100 Based on the second set of candidate exit conditions, the value of M in formula (1) is C2. The third group of candidate exit conditions is "1. Turn on the sweeping robot in the living room within one hour and 15 minutes after the phone is turned off for the first time after the screen has been off for a long time, or within one hour after the phone is turned on for the first time after the phone has been off the screen for a long time. 2 . The user leaves home", the electronic device 100 obtains the value of M in the formula (1) as C3 based on the third group of candidate exit conditions. The fourth group of candidate exit conditions is "1. One hour after the phone is turned on for the first time after the screen has been off for a long time. 2. After the user leaves home for 15 minutes, or before the user leaves home, turn on the sweeping robot in the living room", electronic equipment 100 Based on the fourth set of candidate exit conditions, the value of M in formula (1) is C4.

Afterwards, the electronic device 100 compares the sizes of C1, C2, C3, and C4, and the candidate exit condition corresponding to the smallest M value is the best candidate exit condition.

Assuming that the value of C2 is the smallest, then the best candidate exit condition is "1. One hour after the phone is turned off for the first time after the screen has been off for a long time. 2. After the user leaves home for 15 minutes, or before the user leaves home, the user turns on the Curtains", then the candidate new condition corresponding to the best candidate exit condition is the new condition, that is, "open the curtains of the living room". The condition item modified relative to the preset exit condition in the best candidate exit condition is the maximum constraint condition, that is, "the user leaves home".

S2303. The electronic device 100 modifies the preset exit condition based on the maximum constraint condition, the newly added condition, and the delay time λ of the maximum constraint condition to obtain the modified exit condition.

It should be noted that modifying the exit condition can be understood as the best candidate exit condition obtained in S2302. Specifically, for how the electronic device 100 obtains the modified exit condition, reference may be made to How to Obtain the Best Candidate Exit Condition in S2302, which will not be repeated in this embodiment of the present application.

Exemplarily, for the scene of getting up in the morning, the exit condition is changed to "1. One hour after the phone is turned on for the first time after the screen has been off for a long time. 2. 15 minutes after the user leaves home, or before the user leaves home, the Curtains in the living room". In a specific implementation, only when the electronic device 100 judges that the current time, location, and device status meet the two conditions in the modification trigger condition at the same time, the electronic device 100 will exit the morning scene, that is, stop recommending the morning scene for the user. collection of services in .

The following describes how the electronic device 100 adjusts the triggering conditions of the scene when the scene exits too early.

From the embodiment shown in Figure 20, it can be seen that when |E(Tq-T _P )|-3δ(Tq-T _P ) is less than 0, it means that the time to exit the scene is too early, that is, the user has not started using the service in the scene set, the electronic device 100 has stopped recommending a set of services in the scene.

Then the electronic device 100 needs to delay the exit condition of the scene, so that the scene exit time is later than the time when the user actually uses the service set in the scene, and the electronic device 100 stops within a certain period of time after the user actually uses the service set. A collection of recommended services for users.

In the case that the scene exits too early, the electronic device 100 only needs to adjust the maximum constraint condition, so that the adjusted maximum constraint condition can make the scene exit time later than the time when the user actually uses the service set in the scene, and the scene exit The difference between the time and the time actually used by the user is within the preset value.

Mode 2: After the electronic device 100 triggers the maximum constraint condition in the preset exit conditions, the newly added condition in Mode 1 is not triggered.

The electronic device 100 may also adjust the preset exit condition of the scene in other ways, which is not limited in this embodiment of the present application.

FIG. 24 exemplarily shows a schematic diagram of the electronic device 100 adjusting the preset exit condition that the scene exits too early.

S2401. The electronic device 100 determines the maximum constraint condition among the newly added condition (the second newly added sub-condition) and the preset exit condition based on the candidate added condition.

The electronic device 100 may use an enumeration method to determine the maximum constraint condition among the newly added condition and the preset exit condition. For specific implementation, reference may be made to related descriptions in S2102, which will not be repeated in this embodiment of the present application.

Exemplarily, for the commuting scene on weekdays, it is assumed that the candidate addition condition may be after leaving home or after leaving a community. Then the electronic device 100 needs to modify each condition in the commuting scene on weekdays to obtain multiple different candidate trigger conditions, and obtain multiple M values based on multiple different candidate exit conditions.

Table 16

Table 16 exemplarily shows the process of multiple different candidate exit conditions obtained after modifying the preset exit conditions in the commuting scene on weekdays. Among them, the preset exit conditions in the commuting scene on weekdays include "1. After 7:30 in the morning on weekdays. 2. Turn off the light in the living room". According to the above rules, based on candidate addition conditions and preset exit conditions, four different candidate exit conditions can be obtained. The first group of candidate exit conditions is "1. After leaving home, or after 7:30 am on weekdays, the user does not leave home. 2. Turn off the light in the living room". Based on the first group of candidate exit conditions, the electronic device 100 obtains The value of M in formula (1) is D1. The second group of candidate exit conditions is "1. After 7:30 am on weekdays. 2. After leaving home, or after the user has turned off the light in the living room, the electronic device 100 has not left home", the electronic device 100 is based on the second group of candidate exit conditions , and the value of M in formula (1) is D2. The third group of candidate exit conditions is "1. After leaving the community, or after 7:30 in the morning on weekdays, the user did not leave the community. 2. Turn off the light in the living room". Based on the third group of candidate exit conditions, the electronic device 100 obtains The value of M in formula (1) is D3. The fourth group of candidate exit conditions is "1. After 7:30 am on weekdays. 2. After leaving the community, or after the user turns off the light in the living room, the user does not leave the community", the electronic device 100 based on the fourth group of candidate exit conditions , and the value of M in formula (1) is D4.

Afterwards, the electronic device 100 compares the sizes of D1, D2, D3, and D4, and the candidate exit condition corresponding to the smallest M value is the best candidate exit condition.

Assuming that the value of D2 is the smallest, then the best candidate exit condition is "1. After 7:30 am on weekdays. 2. After leaving home, or after the user turns off the light in the living room and has not left home", then the best candidate The candidate added condition corresponding to the exit condition is the added condition, that is, "after leaving home". The condition item modified relative to the preset exit condition in the best candidate exit condition is the maximum constraint condition, that is, "the light in the living room is turned off".

S2402. The electronic device 100 modifies the preset exit condition based on the newly added condition and the maximum constraint condition among the preset exit conditions, to obtain a modified exit condition.

It should be noted that modifying the exit condition can be understood as the best candidate exit condition obtained in S2401. Specifically, for how the electronic device 100 obtains the modified exit condition, reference may be made to How to Obtain the Best Candidate Exit Condition in S2401, which will not be repeated in this embodiment of the present application.

Exemplarily, for the commuting scenario on weekdays, modify the exit condition to "1. After 7:30 am on weekdays. 2. After leaving home, or after the user turns off the light in the living room, the user has not left home" . In a specific implementation, only when the electronic device 100 judges that the current time, location, and device status meet the two conditions in the modified exit condition at the same time, the electronic device 100 will stop recommending services for the user in the commuting scene on weekdays. gather.

After the electronic device 100 modifies the entry condition or exit condition of the scene, the electronic device 100 can evaluate the modified entry condition or exit condition, including but not limited to whether the user's click rate, scene entry time and exit time meet the requirements etc., if the requirement is not met, the electronic device 100 may further modify the entry condition or exit condition of the scene according to the aforementioned method until the requirement is met. The user's behavior habits are also constantly changing. Based on the user's behavior habits, e-Hebei 100 can periodically adjust the entry conditions or exit conditions of the scene to improve the intelligence of the recommended scene service.

The aforementioned embodiments describe how the electronic device 100 generates scene services and how the electronic device 100 adjusts the entry conditions of the scene and the exit conditions of the scene. The embodiment of the present application also provides another service verification method, that is, Say that after the electronic device 100 triggers a certain scene, the electronic device 100 will recommend a service set for the user, and generate a recommendation card based on the service set. Anomalies, such as incomplete display of service collection information in the recommendation card, that is, the display elements on the recommendation card are different from the default display elements. Or the recommendation card is displayed normally, but the user cannot directly use the service collection in the recommendation card after clicking the recommendation card.

25A-25D exemplarily show schematic diagrams of a group of recommended card malfunctions.

Wherein, FIG. 25A exemplarily shows a schematic diagram of incomplete display of service information in the recommendation card.

Exemplarily, the service set may be a weather service.

Before the electronic device 100 recommends the weather service for the user, the electronic device 100 needs to authorize the weather service to acquire location information and other permissions.

After the electronic device 100 authorizes the weather service and obtains the permission to acquire location information, the electronic device 100 can normally display the weather service for the user to view. For example, the recommendation card 2501 shown in Figure 25A, the recommendation card 2501 is a service card when the weather service can be displayed normally, and the recommendation card 2501 includes location information (such as Nanshan, Shenzhen), current temperature (22°C), and the highest temperature in a day (26°C) and the lowest temperature of the day (14°C), today's air index (eg good).

If the electronic device 100 does not authorize the weather service to acquire location information and other permissions, then when the electronic device 100 displays the weather service in the recommendation card, the information of the weather service displayed in the recommendation card is abnormal, resulting in the user being unable to view the current weather information. That is, the display elements on the recommendation card are different from the default display elements. For example, the recommendation card 2502 shown in Fig. 25A, the recommendation card 2502 is the service card when the weather service is abnormally displayed, the location is not displayed in the recommendation card 2502, and the temperature information and air information cannot be displayed in the recommendation card 2502 because there is no location information wait. For example, the location information (such as Shenzhen Nanshan) cannot be displayed in the display area 2503 of the recommendation card 2502, the current temperature (22°C) cannot be displayed in the display area 2504 of the recommendation card 2502, and cannot be displayed in the display area 2505 of the recommendation card 2502 The highest temperature (26° C.) and the lowest temperature (14° C.) of the day, the display area 2506 in the recommendation card 2502 cannot display today’s air index (for example, good). However, the display form of the recommendation card 2502 should be the same as that of the recommendation card 2501 . In this way, the electronic device 100 recommends a recommendation card displaying an abnormal service set for the user, which wastes recommendation resources of the electronic device 100 .

FIG. 25B-FIG. 25D exemplarily show a schematic diagram of a recommendation card being displayed normally, but the user cannot directly use the service set in the recommendation card.

Exemplarily, the service set may be a home service.

Before the electronic device 100 recommends the home service for the user, the user needs to authorize the weather service for information such as the location of the user's home. , although the recommendation card displayed on the electronic device 100 is normal, but when the user clicks on the recommendation card, the electronic device cannot navigate the route to home for the user. Only after the user inputs the location of home on the user interface, the electronic device 100 will The location of the home may be navigated for the user.

When the electronic device 100 determines that the home scene is entered, the electronic device 100 may recommend the home service in the home scene to the user, and generate a recommendation card based on the home service, and the electronic device 100 displays the recommendation card on the desktop. For example, the recommendation card 2507 shown in FIG. 25B is a service card corresponding to the home service, and the recommendation card 2507 includes information such as the text of the home icon. If the user authorizes information such as the location of the user's home to the home service, as shown in FIG. 25B, the electronic device 100 receives the user's input operation (for example, click) on the recommendation card 2507, and in response to the user's input operation, the electronic device 100 will To enter a user interface for a route from the current location to the location of the user's home, for example, the electronic device 100 may display a user interface 2508 as shown in FIG. 25C . The user interface 2508 includes a route from the current location to the user's home location, and the route may include multiple different routes, such as the recommended route 1, the total duration of the recommended route 1 is 14 minutes, and the distance of the recommended route 1 is 2.2 kilometers. The route may also be a recommended route 2, the total duration of the recommended route 2 is 15 minutes, and the distance of the recommended route 2 is 2.5 kilometers. The route may also be a recommended route 3, the total duration of the recommended route 3 is 18 minutes, and the distance of the recommended route 3 is 3.0 kilometers. The electronic device 100 may receive a user's input operation (for example, click) on the recommended route 1 , and the electronic device 100 will enter a navigation interface based on the recommended route 1 . Alternatively, after the electronic device 100 receives the user's input operation (such as clicking) on the recommendation card 2507, the electronic device 100 does not display the user interface 2509 shown in FIG. 25D, but directly enters the navigation interface based on the recommended route 1.

If the user does not authorize the home service, such as the location of the user's home, and the electronic device 100 determines to enter the home scene, the electronic device 100 may recommend the home service in the home scene to the user, and generate a recommendation card based on the home service. The electronic device 100 displays a recommendation card on the desktop, such as the recommendation card 2507 shown in FIG. 25B . As shown in Figure 25B, the electronic device 100 receives the user's input operation (for example, click) on the recommendation card 2507. Since the user has not authorized the home service for the user's home location and other information, the electronic device 100 cannot navigate home for the user. For the route, the electronic device 100 may display a user interface 2509 as shown in FIG. 25D , and the user interface 2509 does not display any route information. The electronic device 100 may input the location of the user's home in the user interface 2509, and then the electronic device 100 may navigate the route home for the user based on the home location input by the user. However, in this case, the home service recommended by the electronic device 100 for the user loses the meaning of quick service, which affects user experience.

At present, in view of the above problems, the electronic device 100 may verify the service to be recommended, and recommend the service to the user after passing the service verification.

Fig. 26 exemplarily shows a schematic diagram of how the electronic device 100 checks the service to be recommended.

Operations such as service recall, service filtering and sorting, and service collection generation on the electronic device 100 are all completed by the recommendation system on the electronic device 100 , and the recommendation system can be understood as a system application on the electronic device 100 .

Before the recommendation system recommends a service set for users, it needs to verify one or more services in the recommended service set. The purpose of the verification is to ensure that one or more services in the service set can provide users with convenient functions. service, to prevent one or more services in the service set from having abnormal function of the recommendation card shown in FIG. 25A-FIG. 25D above.

As shown in Figure 26, after entering a certain scene, the recommender system can obtain one or more recommended services in the current scene. Before the recommender system recommends the one or more recommended services to the user, the recommender system needs to The one or more services to be recommended are verified so that the one or more services to be recommended are all services that can provide convenient services for users.

Specifically, firstly, the recommendation system obtains the recommendation data of the service to be recommended. The recommendation data includes information about the service to be recommended for the user to watch or use. For example, the service to be recommended can be a weather service, then the recommended data of the weather service includes the city where the user is located, the highest temperature of the city where the user is located, the lowest temperature of the city where the user is located, the current temperature of the city where the user is located, the air temperature of the city where the user is located situation etc. For example, the service to be recommended may be a home service, then the recommendation data of the home service includes the location of the user's home and route information from the current location to the location of the user's home.

After that, the recommendation system determines whether the recommended data based on the service to be recommended can realize the preset function of the service to be recommended based on the verification rules preset by the service to be recommended. The preset verification rules are used to verify whether the service to be recommended can realize the preset function. The preset verification rules limit that the preset function of the service to be recommended can only be realized after the preset data of the service to be recommended is obtained, and the preset data includes preset permissions and preset information. If the recommended data of the service to be recommended obtained by the recommendation system is less than the preset data defined in the preset verification rules, the service to be recommended cannot realize the preset function. If the recommendation system obtains that the recommended data of the service to be recommended meets the preset data defined in the preset verification rules, then the service to be recommended can realize the preset function.

When the recommendation system determines that the recommended data based on the service to be recommended can realize the preset function of the service to be recommended, then the recommendation system will recommend the service to be recommended to the user.

Exemplarily, the preset permission in the verification rule preset by the weather service includes the location permission, and the preset information in the verification rule preset by the home service includes the location of the user's home. If before, the recommendation system obtains the recommended data of the weather service does not include the user's city information, but the preset permission in the weather service's default verification rules includes the location permission, then the recommendation system determines that the current weather service cannot Provide the user with a preset function, that is, recommend the user the weather conditions in the city where the user is located. Or, if before, the recommendation system obtains that the recommended data of the home service does not include the location of the user's home, but the preset information in the verification rules preset by the home service includes the location of the user's home, then the recommendation system determines that The current home service cannot provide the user with a preset function, that is, to recommend route information from the current location to the user's home location for the user.

It can be seen from the above description that when the recommendation system verifies the service paper to be recommended, the recommendation system needs to obtain the preset verification rules of the service to be recommended, and the preset verification rules are different for different services to be recommended. When a new service is recalled, the recommendation system needs to obtain the preset verification rules of the new service. As the number of services to be recommended increases, the number of preset verification rules corresponding to the services to be recommended obtained by the recommendation system also increases. , which undoubtedly increases the workload of the recommendation system.

Based on this, this application provides a service verification method. Before recommending a set of services, the recommendation system does not need to do service verification work, but does the verification through the service itself. After that, the service returns the verification results to the recommendation system . In this way, the recommendation system does not need to obtain the verification rules preset for each service, which can reduce the huge workload generated by the recommendation system in the process of verifying services.

FIG. 27 exemplarily shows a software structural block diagram of an electronic device 100 provided by an embodiment of the present application.

In Fig. 27, the recommendation system determines to enter a certain scene, and determines the service to be recommended to the user in this scene. Before the recommendation system recommends the service to be recommended to the user, the recommendation system needs to verify the service to be recommended. The verification process includes the following steps:

Step 1: The recommendation system obtains the identification of the service to be recommended.

Step 2: The recommendation system sends the identification of the service to be recommended to the service management module.

Step 3: After the service management module receives the identification of the service to be recommended sent by the recommendation system, the service management module sends a verification instruction to the corresponding service to be recommended.

Step 4: The service to be recommended determines whether the service to be recommended can realize the preset function based on the preset verification rules of the service to be recommended and the recommendation data of the service to be recommended.

After receiving the verification instruction, the service to be recommended will perform self-verification based on the recommended data of the service to be recommended. The process of service verification can refer to the process of how the recommendation system verifies the recommended service shown in Figure 26. This application The embodiment will not be repeated here.

Step 5: After the verification of the service to be recommended is completed, the service to be recommended sends the verification result to the service management module.

Validation results include ready and not ready. Wherein, when the verification result is ready, it means that the service to be recommended can realize the preset function. When the verification result is not ready, it means that the service to be recommended cannot realize the preset function. When the recommendation system recommends the service to be recommended that is not ready for the user, the recommendation card shown in Figure 25A may be displayed incompletely , or the recommendation card shown in FIG. 25B is normally displayed, but the user cannot directly use the service set in the recommendation card.

It should be noted that since the service verification method provided by the embodiment of this application is self-verified by the service to be recommended, there may be some services to be recommended, which are currently not ready, but the service to be recommended The verification result sent by the service to the service management module is ready.

Step 6: After the service management module receives the verification result sent by the service to be recommended, the service management module sends the verification result to the recommendation system.

Step 7: After the recommendation system receives the verification result sent by the service management module, the recommendation system will confirm whether to recommend the service to be recommended to the user based on the verification result.

When the verification result is ready, the recommendation system recommends the service to be recommended to the user. When the verification result is not ready, the recommendation system will not recommend the service to be recommended to the user.

As shown in FIG. 28 , FIG. 28 exemplarily shows an interactive schematic diagram of a service review method provided by an embodiment of the present application.

The method steps of the verification process shown in FIG. 28 include S2801-S2807.

Wherein, S2801. The recommendation system obtains the identifier of the service to be recommended.

For the detailed description of S2801, refer to the detailed description of step 1 in the embodiment shown in FIG. 27 , which will not be repeated in this embodiment of the present application.

S2802. The recommendation system sends the identification of the service to be recommended to the service management module.

For the detailed description of S2802, refer to the detailed description of step 2 in the embodiment shown in FIG. 27 , which will not be repeated here in this embodiment of the present application.

S2803. After receiving the identification of the service to be recommended sent by the recommendation system, the service management module sends a verification instruction to the service to be recommended.

For the detailed description of S2803, refer to the detailed description of step 3 in the embodiment shown in FIG. 27 , which will not be repeated in this embodiment of the present application.

S2804. After receiving the verification instruction, the service to be recommended determines whether the service to be recommended can realize the preset function based on the verification rule preset by the service to be recommended and the recommendation data of the service to be recommended.

For the detailed description of S2804, refer to the detailed description of step 4 in the embodiment shown in FIG. 27 , which will not be repeated in this embodiment of the present application.

S2805. The service to be recommended sends the verification result to the service management module.

For the detailed description of S2805, refer to the detailed description of step 5 in the embodiment shown in FIG. 27 , which will not be repeated in this embodiment of the present application.

S2806. The service management module sends the verification result to the recommendation system.

For the detailed description of S2806, refer to the detailed description of step 6 in the embodiment shown in FIG. 27 , which will not be repeated here in this embodiment of the present application.

S2807. The recommendation system determines whether to recommend the service to be recommended to the user based on the verification result.

For a detailed description of S2807, refer to the detailed description of step 7 in the embodiment shown in FIG. 27 , which will not be repeated here in this embodiment of the application.

Fig. 29 exemplarily shows a schematic diagram of how the recommendation system checks the service to be recommended through the service management module.

First, the recommendation system includes but not limited to service recall module, service filtering module, service ranking module and service display module.

Wherein, the service recall module is used for recalling a plurality of services after entering a certain scene, and the plurality of services are the services to be recommended to the user by the recommendation system. After the service recall module acquires the service to be recommended, the service recall module sends the identifier of the service to be recommended to the service filtering module.

After the service filtering module receives the identification of the service to be recommended, the service filtering module will obtain the readiness status of the service to be recommended through the service management module. Services, only reserve the ready-to-recommend services.

Specifically, the service filtering module is used to send the identification of the service to be recommended to the service management module.

The service management module is configured to send a verification instruction to the corresponding service to be recommended based on the identifier of the service to be recommended after obtaining the identifier of the service to be recommended.

The service to be recommended is used to determine whether the preset function can be realized based on the current recommendation data and preset verification rules in response to the verification instruction after receiving the verification instruction, that is, to determine the verification result . When the service to be recommended can realize the preset function based on the current recommendation data, the verification result is ready. When the service to be recommended cannot realize the preset function based on the current recommendation data, the verification result is not ready.

After the service to be recommended determines the verification result, the service to be recommended sends the verification result to the service management module. There may be one or more services to be recommended. For example, the services to be recommended may be service one, service two and service three. The service management module sends verification instructions to service one, service two and service three respectively in turn. After service 1, service 2 and service 3 receive the verification instruction, service 1, service 2 and service 3 respectively determine whether the preset function can be realized based on the current recommended data and the preset verification rules, that is, determine the Check result. After the verification result is determined, service 1, service 2 and service 3 respectively send the verification results to the service management module.

The service management module is configured to send the verification result to the service filtering module after receiving the verification result sent by the service to be recommended.

The service filtering module is used to remove the services to be recommended whose verification results are not ready after receiving the verification results of the services to be recommended sent by the service management module. For example, if the verification result of service 1 and service 2 is ready, and the verification result of service 3 is not ready, then the service filtering module removes service 3 and only keeps service 2 and service 1. The services to be recommended finally obtained by the service filtering module are service one and service two.

The service filtering module sends the finally obtained identifiers of the services to be recommended to the service sorting module.

The service ranking module is used to sort the prepared services to be recommended, and obtain the services finally recommended to users.

In the embodiment of the present application, the service sorting module sorts the prepared services to be recommended based on the maintained service reputation table. The service reputation table may be periodically sent by the server to the electronic device 100 . The service reputation table describes the reputation of different services to be recommended. The higher the reputation of the service to be recommended, the higher the probability that the service to be recommended will be recommended to the user.

Table 17

待推荐服务服务To be recommended service	信誉度评分Reputation Score	服务的提供商service provider
服务一service one	9090	提供商一provider one
服务二service two	8080	提供商二provider two
服务三service three	7575	提供商三provider three

Table 17 exemplarily shows the reputation scores corresponding to different services. It should be noted that the reputation score of the service to be recommended changes in real time. How to update the reputation score of the service to be recommended will be described in detail in subsequent embodiments, and will not be described in detail in this embodiment of the present application.

Exemplarily, the reputation score of service one is 90 points, and the provider of service one is provider one. The reputation score of service two is 80 points, and the provider of service two is provider two. The credit score of service three is 75 points, and the provider of service three is provider three.

The service sorting module will determine the service to be recommended to the user from the plurality of services to be recommended based on the reputation score of the service to be recommended and the number of services finally pushed to the user.

Exemplarily, if the number of services finally pushed to the user is 1, the service sorting module determines that the service finally pushed to the user is Service 1 based on the reputation scores of Service 1, Service 2, and Service 3. If the number of services finally pushed to the user is 2, the service ranking module determines that the services finally pushed to the user are Service 1 and Service 2 based on the reputation scores of Service 1, Service 2, and Service 3. If the number of services finally pushed to the user is 3, the service ranking module determines that the services finally pushed to the user are service 1, service 2, and service 3 based on the reputation scores of service 1, service 2, and service 3.

After the service sorting module obtains the service finally recommended to the user, it sends the identification of the service finally recommended to the user to the service display module.

After the service display module receives the identification of the service finally recommended to the user sent by the service sorting module, based on the identification of the service finally recommended to the user, it generates a recommendation card for the service finally recommended to the user, and the service display module displays the recommendation card on the desktop superior.

Next, we will introduce how to update the reputation score of the service to be recommended.

After the service display module displays the recommended card on the desktop, the card information collection module will further examine the recommended card displayed on the desktop to further determine whether the recommended card can realize the preset function.

Fig. 30 exemplarily shows a schematic diagram of how to update the reputation score of the service to be recommended.

The card information collection module extracts the display content on the recommendation card, and the display content includes but not limited to text, icons, pictures and other information. Afterwards, the card information collection module sends the displayed content on the recommended card to the intent content matching module.

The intent content matching module is used to determine whether the display content on the recommendation card matches the recommendation intent after receiving the display content on the recommendation card sent by the card information collection module. If it does not match, the intent content matching module will display on the recommendation card The identification of the recommended service is sent to the server.

Specifically, the intent content matching module determines the matching degree between the displayed content on the recommended card and the preset displayed content based on the extracted displayed content on the recommended card. If the matching degree is lower than the preset value, the intent content matching module determines that the displayed content on the recommendation card does not match the recommendation intent, and the intent content matching module sends the identification of the recommended service displayed on the recommendation card to the server. If the matching degree is higher than the preset value, the intent content matching module determines that the displayed content on the recommendation card matches the recommendation intent.

After the server receives the identification of the recommended service sent by the intent content matching module, the server obtains the provider of the recommended service based on the identification of the recommended service, and the server reduces the reputation scores of all services provided by the provider of the recommended service.

In this way, it can prevent that some services to be recommended are currently not ready, but the verification result sent by some services to be recommended to the service management module is ready, so that the recommendation system will not prepare the service to be recommended recommended to users.

Exemplarily, if Service 1, Service 2, and Service 3 are ready after receiving the verification instruction, then the verification results sent by Service 1 and Service 3 to the service management module are ready. get ready. If the service 2 (identification of the first service function) is not ready, the verification result that the service 2 may send to the service management module is ready. Then the recommendation system may recommend the second service to the user.

After the recommendation system recommends service 2 to the user, that is, after the recommendation system displays the recommendation card generated by service 2 on the desktop, the card information collection module will extract the displayed content on the recommendation card of service 2, and the intent content matching module determines the Whether the display content on the recommendation card of service 2 includes the preset display content. Since service 2 is not ready, the intent content matching module determines that the display content on the recommendation card of service 2 does not include the preset display content. At this time, the intent content matching module sends the service 2 identifier to the server, And instruct the server to reduce the reputation score of service two, so that the recommendation system will reduce the probability of recommending service two to the user in the next recommendation.

Exemplarily, the recommendation card of service two may be the recommendation card 2502 shown in FIG. 25A. The recommendation card for service two can also be the recommendation card 2507 shown in FIG. 25B.

Table 18

待推荐服务服务To be recommended service	信誉度评分Reputation Score	服务的提供商service provider
服务一service one	9090	提供商一provider one
服务二service two	6565	提供商二provider two
服务三service three	7575	提供商三provider three

Table 18 exemplarily shows the reputation scores corresponding to different services obtained by reducing the reputation score of service two by the server. Exemplarily, the reputation score of service one is 90 points, and the provider of service one is provider one. The reputation score of service two is 65 points, and the provider of service two is provider two. The credit score of service three is 75 points, and the provider of service three is provider three.

After the server lowers the reputation score of service two, the server sends the reputation scores corresponding to different services to the service ranking module, and the service ranking module obtains the services finally recommended to the user based on the reputation scores corresponding to different services.

When the recommendation system recommends services for users next time, the service ranking module in the recommendation system will determine the final recommendation to the user from multiple services to be recommended based on the reputation score of the service to be recommended and the number of services that are finally pushed to the user. To be recommended for service.

Exemplarily, if the number of services finally pushed to the user is 1, the service sorting module determines that the service finally pushed to the user is Service 1 based on the reputation scores of Service 1, Service 2, and Service 3, and Service 1 can also be called For the second service function. If the number of services finally pushed to the user is 2, the service sorting module determines that the services finally pushed to the user are Service 1 and Service 3 based on the reputation scores of Service 1, Service 2, and Service 3, and Service 1 or Service 3 also Can be called the second service function. If the number of services finally pushed to the user is 3, the service ranking module determines that the services finally pushed to the user are Service 1, Service 2, and Service 3 based on the reputation scores of Service 1, Service 2, and Service 3, and Service 1 or Service 3 Service two or service three may also be referred to as the second service function.

Optionally, after the card information collection module extracts the displayed content on the recommended card and the intent content matching module determines the matching degree between the displayed content on the recommended card and the preset displayed content, the card information collection module will recommend the displayed content on the card. The display content is sent to the server, and the intent content matching module sends the matching degree between the display content on the recommendation card and the preset display content to the server. After the server receives the display content on the recommendation card and the matching degree between the display content on the recommendation card and the preset display content, the server based on the display content on the recommendation card, the preset display content and the display content on the recommendation card and The preset matching degree of displayed content is used as sample data to train the intent content matching model. Specifically, the server uses the display content on the recommendation card and the preset display content in the sample data as input to the intent content matching model, and the intent content matching model outputs a matching degree. The server calculates the difference between the matching degree output by the intended content matching model and the matching degree in the sample data, and when the difference between the two is greater than a preset value, the electronic device 100 modifies the parameters of the intended content matching model, and repeats the previous steps until The server confirms that the difference between the two is less than the preset value, and the training of the intent content matching model is completed.

After the intent content matching model is trained, the server sends the intent content matching model to the intent content matching module, and the intent content matching module determines the matching degree between the display content on the recommendation card and the preset display content based on the intent content matching model. In this way, with more and more sample data, the accuracy of the matching degree between the display content on the recommendation card predicted by the intent content matching model and the preset display content is higher.

The service recommendations described in the foregoing embodiments are all performed on a single device. For example, when the electronic device 100 enters a certain scene, the service is recalled, the service is sorted, the service to be recommended is determined, a recommendation card is generated based on the service to be recommended, and the recommendation card is displayed on the desktop of the electronic device 100. Device 100 is complete.

Exemplarily, as shown in FIG. 31 , the electronic device 100 is a mobile phone as an example for description. The mobile phone triggers the recommendation process, and the mobile phone recalls multiple services, such as service one, service two, service three, service four, service five, service six, service seven, service eight, service nine, service ten, service eleven and service twelve. The mobile phone filters, screens, and sorts multiple services based on the recalled multiple services to obtain the services that are finally recommended to the user. The services that are finally recommended to the user can be service one, service three, service five, and service seven. The mobile phone generates recommendation cards based on service 1, service 3, service 5 and service 7, and the mobile phone displays the recommendation cards.

From the above analysis, it can be seen that the current service recommendation only realizes the service recommendation on a single device, and does not realize the cross-device recommendation service. If there are multiple devices around the user at the same time, the recommendation service is still only recommended to the user on a certain device. This recommendation experience may not be optimal, because the user may not pay attention to this device at the moment, resulting in the user not using this device. recommended services.

The following embodiments of the present application also provide a service filling method, which can realize service-based priority, user's current attention to each device, service capacity of each device, and matching degree of each service on each device Sort the recommended services based on factors such as to obtain the optimal distribution of services on each device, and then distribute and transfer services, and finally display each service on the most suitable device to achieve cross-device recommendation services.

Exemplarily, before the user goes out, the smart speakers in the home can broadcast the weather conditions of the day by voice. After the user goes out, for example, after the user gets in the car and starts the car, the car will no longer recommend weather services to the user. In this way, the user can be reminded in time, and the same service can be avoided repeatedly.

For another example, the user does not pay attention to the mobile phone while driving. However, among the courier information to be picked up by the user or the matters recorded in the memo of the mobile phone, there will be a meeting to attend. Then the car machine can recommend express service or schedule service to the user when the user is waiting for traffic lights or when the speed of the vehicle is slow. In this way, the mobile phone is prevented from recommending express service or schedule service to the user, and the recommended service does not meet the purpose of the user because the user does not use the mobile phone.

Fig. 32 exemplarily shows a schematic diagram of performing service loading on multiple devices.

In Figure 32, assuming that the mobile phone is a central control device, the mobile phone recalls multiple services and sorts the multiple services to obtain the most suitable device for each service to display. How to sort multiple services and obtain the most suitable device for displaying each service will be described in detail in subsequent embodiments, and will not be repeated here in this embodiment of the application.

Exemplarily, the services of mobile phone recall may include service one, service two, service three, service four, service five, service six, service seven, service eight, service nine, service ten, service eleven, service twelve, service ten Three, Service Fourteen, Service Fifteen and Service Sixteen.

Wherein, among the above sixteen services, except service twelve, service fourteen and service sixteen are virtual user interface (virtual user interface, VUI) services, the remaining services are graphic user interface (graphic user interface, GUI) services. VUI services can be understood as services that cannot be displayed in the form of graphics, that is, services without a user interface, and GUI services can be understood as services with a user interface.

If the devices that are currently connected to the mobile phone include large screens, tablets, watches, earphones, and cars. The mobile phone sorts the above-mentioned multiple services, and determines which of the above-mentioned multiple services is most suitable to be recommended on the above-mentioned device.

The mobile phone determines that service 1, service 3, service 5 and service 7 are most suitable for recommendation on the mobile phone, then the mobile phone displays service 1, service 3, service 5 and service 7 on the mobile phone. The mobile phone determines that service 2, service 4, service 6 and service 8 are most suitable for recommendation on the tablet, and then the mobile phone displays service 2, service 4, service 6 and service 8 on the tablet. The mobile phone determines that Service Nine and Service Eleven are the most suitable for recommendation on the large screen, and then the mobile phone displays Service Nine and Service Eleven on the large screen. The mobile phone determines that the service fifteen is the most suitable to be recommended on the watch, and then the mobile phone displays the service fifteen on the watch. The mobile phone determines that service twelve is the most suitable for recommending on the earphone, and then the mobile phone displays service twelve on the earphone. The mobile phone determines that the service ten is most suitable for recommendation on the car, and then the mobile phone will display the service ten on the car.

That is to say, after the electronic device associated with the user detects that the user enters a certain scene, the electronic device associated with the user will recommend services associated with the scene to the user. There are multiple electronic devices associated with the user, and the user pays different attention to different electronic devices. Based on this scheme, the priority of the service, the current attention of the user to each electronic device, the service capacity of each electronic device, As well as factors such as the matching degree of each service on each electronic device, each service to be recommended is displayed on the most suitable device.

After the electronic device associated with the user detects that the user enters a certain scene, one electronic device may trigger the service recommendation process, or multiple electronic devices may simultaneously trigger the service recommendation process.

If an electronic device triggers the service recommendation process, then the electronic device acts as a central control device, and the central control device completes the tasks of service recall, service filtering, service reordering, and service filling.

If multiple electronic devices trigger the service recommendation process at the same time, then the central control device can be determined from the multiple electronic devices that trigger the service recommendation process, and the central control device completes the tasks of service recall, service filtering, service reordering, and service loading matter.

Fig. 33A exemplarily shows a schematic framework diagram of a multi-device simultaneous triggering service recommendation process provided by an embodiment of the present application.

In this embodiment of the present application, how to load services on two electronic devices is taken as an example for illustration. In other embodiments, the method of how to load the service on more other electronic devices is similar to the method of how to load the service on two electronic devices.

Exemplarily, the two electronic devices are respectively the electronic device 100 and the electronic device 200 (the second electronic device).

If the electronic device 100 and the electronic device 200 trigger the recommendation process at the same time, it is first necessary to confirm the central control device. Optionally, the central control device may be determined based on the type of the device or the frequency of use of the device, assuming that the electronic device 100 is the central control device.

Both the electronic device 100 and the electronic device 200 have a service recall module, a service filtering module, a service rough sorting module, a service reordering module, a service joint sorting module, a service filling module, and a device status and data management module.

Wherein, for the electronic device 100, the service recall module is used to determine the current scene based on the preset trigger conditions of the scene, and recall the service, that is, to recommend related services in the current scene for the user.

The service recall module sends the recalled services to the service filtering module. The service filtering module is used to pre-screen the recalled services based on the filtering conditions and filter out services that do not meet the filtering conditions. The filtering conditions are preset. services used over time.

The service filtering module sends the recalled services obtained after filtering to the service rough sorting module, and the service rough sorting module is used to sort the recalled services obtained after filtering according to simple rules, and obtain services whose user usage probability is greater than a preset value.

The service rough sorting module sends the identifiers of the recalled services whose user usage probability is greater than the preset value to the service reordering module, and the service reordering module will further sort the recalled services based on the user's usage habits. Screening to get the service of the eventual electronic device 100 recall.

The service reordering module sends the services recalled by the electronic device 100 to the service reordering module.

For the electronic device 200, the electronic device 200 also triggers the service recommendation process, then the service recall module, the service filtering module, the service rough sorting module and the service reordering module in the electronic device 100 and the service recall module in the electronic device 100, The functions of the service filtering module, the service coarse sorting module and the service reordering module are similar, all of which are to obtain recalled services whose user usage probability is greater than a preset value.

After the service reordering module in the electronic device 200 receives the service recalled by the final electronic device 200, the service reordering module in the electronic device 200 sends the service recalled by the final electronic device 200 to the device status and data management module in the electronic device 200 .

After the device status and data management module in the electronic device 200 receives the service recalled by the electronic device 200, the device status and data management module in the electronic device 200 sends the service recalled by the electronic device 200 and the device status of the electronic device 200 to the electronic device 200. A device status and data management module in the device 100.

After the device status and data management module in the electronic device 100 receives the service recalled by the electronic device 200 and the device status of the electronic device 200, the device status and data management module in the electronic device 100 will recall the service and electronic device status of the electronic device 200 The device state of 200 is sent to the service association ordering module in the electronic device 100 .

After the service joint ranking module in the electronic device 100 obtains the service recalled by the electronic device 100 and the service recalled by the electronic device 200, the service joint ranking module in the electronic device 100 will base on the priority of the service, the user's current preference for the electronic device 100 and the electronic The attention degree of the device 200, the service capacity on the electronic device 100 and the electronic device 200, and the matching degree of each service on the electronic device 100 and the electronic device 200 are used to sort the services recalled by the electronic device 100 and the electronic device 200, Get the optimal distribution of services on each device, and then distribute and transfer services, and finally display each service on the most suitable device to achieve cross-device recommendation services. How the service joint ordering module determines the optimal distribution of services on each device will be described in detail in subsequent embodiments, and will not be repeated here in this embodiment of the application.

FIG. 33B exemplarily shows a schematic framework diagram of a single-device-triggered service recommendation process provided by an embodiment of the present application.

If only the electronic device 100 triggers the service recommendation process, and the electronic device 200 does not trigger the service recommendation process, the difference between the electronic device 100 and the electronic device 200 triggering the service recommendation process at the same time is that the difference between Figure 33B and Figure 33A is that the electronic The service recalled by the device 200 is empty, and the electronic device 100 only needs to be based on the priority of the service, the user's current attention to the electronic device 100 and the electronic device 200, the service capacity on the electronic device 100 and the electronic device 200, and each service's The factors such as the matching degree on the electronic device 100 and the electronic device 200 sort the services recalled by the electronic device 100, obtain the optimal distribution of the services on each device, and then carry out the distribution and circulation of the services, and finally display each service in the most suitable to implement cross-device recommendation services. For a specific description, refer to the detailed introduction in FIG. 33A , which will not be repeated in this embodiment of the present application.

Next, the specific implementation of how the service joint ordering module determines the optimal distribution of services on each device is introduced.

The service joint sorting module will collect the device status of the electronic devices associated with the user in the current scenario, based on the priority of the service, the user's attention to each device, the service capacity of each device and the matching degree of the service and each device. A comprehensive score is given for the degree of matching between a service and each device, and the optimal distribution of each service on each device is obtained.

First, the service joint ranking module obtains the priority normalization coefficient of each service preset based on the preset priority of each service.

Table 19

服务的标识Service ID	优先级归一化系数Priority Normalization Factor
服务一service one	P ¹ ^P1
服务二service two	P ² ^P2
服务三service three	P ³ P ³
服务四service four	P ⁴ P ⁴

Table 19 exemplarily shows that the service joint ranking module obtains the preset priority normalization coefficient of each service based on the preset priority of each service. Among them, the priority normalization coefficient corresponding to service one is P ¹ , the priority normalization coefficient corresponding to service two is P ² , the priority normalization coefficient corresponding to service three is P ³ , and the priority normalization coefficient corresponding to service four is The normalization coefficient is P ⁴ . Wherein, P ¹ , P ² , P ³ and P ⁴ are all constants, for example, P ¹ is 0.8, P ² is 0.6, P ³ is 0.7, and P ⁴ is 0.5.

Secondly, based on the device status and the device status obtained by the data management module, the service joint ranking module obtains the user's attention degree score for each device. For how the service joint ranking module obtains the user's attention score for each device based on the device status, you can refer to the embodiments introduced in FIG. 14 and FIG. 15 , and the embodiments of the present application will not be repeated here.

Table 20

Table 20 exemplarily shows that the service joint ranking module obtains the user's attention score for each device based on the status of each device. Among them, the user's attention to the mobile phone is rated as δ ¹ , the user's attention to the tablet is δ ² , the user's attention to the large screen is δ ³ , the user's attention to the car machine is δ 4 , and the user's attention to the mobile phone is δ ⁴ . The watch's attention score is δ ⁵ , and the user's attention score to earphones is δ ⁶ . Among them, δ ¹ , δ ² , δ ³ , δ ⁴ , δ ⁵ and δ ⁶ are all constants, for example, δ ¹ is 0.8, δ ² is 0.1, δ ³ is 0.1, δ ⁴ is 0.9, δ ⁵ is 0.1, δ ⁶ is 0.1.

Finally, the service joint ranking module records the degree of matching between each service and each different electronic device.

Table 21

服务Serve	手机cell phone	平板flat	大屏Big screen	车机car machine	手表watch	耳机earphone
服务一service one	R ₁ ¹ R ₁ ¹	R ₁ ² R ₁ ²	R ₁ ³ R ₁ ³	R ₁ ⁴ R ₁ ⁴	R ₁ ⁵ R ₁ ⁵	R ₁ ⁶ R ₁ ⁶
服务二service two	R ₂ ¹ R ₂ ¹	R ₂ ² R ₂ ²	R ₂ ³ R ₂ ³	R ₂ ⁴ R ₂ ⁴	R ₂ ⁵ R ₂ ⁵	R ₂ ⁶ R ₂ ⁶
服务三service three	R ₃ ¹ R ₃ ¹	R ₃ ² R ₃ ²	R ₃ ³ R ₃ ³	R ₃ ⁴ R ₃ ⁴	R ₃ ⁵ R ₃ ⁵	R ₃ ⁶ R ₃ ⁶
服务四service four	R ₄ ¹ R ₄ ¹	R ₄ ² R ₄ ²	R ₄ ³ R ₄ ³	R ₄ ⁴ R ₄ ⁴	R ₄ ⁵ R ₄ ⁵	R ₄ ⁶ R ₄ ⁶

Table 21 exemplarily shows the matching coefficients of recalled services and various electronic devices. Among them, the matching coefficient of service 1 and mobile phone is R ₁ ¹ , the matching coefficient of service 2 and mobile phone is R ₂ ¹ , the matching coefficient of service 3 and mobile phone is R ₃ ¹ , and the matching coefficient of service 4 and mobile phone is R ₄ ¹ .

The matching coefficient between service 1 and the tablet is R ₁ ² , the matching coefficient between service 1 and the tablet is R ₂ ² , the matching coefficient between service 3 and the tablet is R ₃ ² , and the matching coefficient between service 4 and the tablet is R ₄ ² . The matching coefficient of service 1 and large screen is R ₁ ³ , the matching coefficient of service 2 and large screen is R ₂ ³ , the matching coefficient of service 3 and large screen is R ₃ ³ , and the matching coefficient of service 4 and large screen is R ₄ ³ . The matching coefficient of service 1 and vehicle-machine is R ₁ ⁴ , the matching coefficient of service 2 and vehicle-machine is R ₂ ⁴ , the matching coefficient of service 3 and vehicle-machine is R ₃ ⁴ , and the matching coefficient of service 4 and vehicle-machine is R ₄ ⁴ . The matching coefficient of service 1 and watch is R ₁ ⁵ , the matching coefficient of service 2 and watch is R ₂ ⁵ , the matching coefficient of service 3 and watch is R ₃ ⁵ , and the matching coefficient of service 4 and watch is R ₄ ⁵ . The matching coefficient of service 1 and earphones is R ₁ ⁶ , the matching coefficient of service 2 and earphones is R ₂ ⁶ , the matching coefficient of service 3 and earphones is R ₃ ⁶ , and the matching coefficient of service 4 and earphones is R ₄ ⁶ .

It should be noted that the matching coefficients shown in Table 21 are all constants. For example, if Service 1 is a GUI service, then the matching coefficient R ₁ ¹ between Service 1 and mobile phone is 1, and the matching coefficient R ₁ ⁶ between Service 1 and earphones is 0. If Service 2 is a VUI service, then the matching coefficient R ₂ ¹ between Service 2 and the mobile phone is 0, and the matching coefficient R ₂ ⁶ between Service 2 and the headset is 1.

After the service joint ranking module obtains the degree of matching between each service and different electronic devices, the user's attention score to each device and the preset priority normalization coefficient of each service, the service joint ranking module based on the above parameters Score the degree of correspondence between each service and each electronic device.

Optionally, the service joint ranking module can obtain the correspondence degree score between each service and each electronic device based on the following formula (3).

In formula (3), j represents the label of the service, m represents a total of m services, i represents the label of the electronic device, R _j ⁱ represents the matching coefficient between the service and each electronic device, and P ^j represents the normalized priority of the service coefficient, ^δi represents the user's attention score to the device, and S represents the correspondence score between each service and each electronic device.

Not limited to the formula (3), the service joint ranking module can also obtain the correspondence degree score between each service and each electronic device based on other formulas, which is not limited in this embodiment of the present application.

Table 22

服务Serve	手机cell phone	平板flat	大屏Big screen	车机car machine	手表watch	耳机earphone
服务一service one	A1A1	B1B1	C1C1	D1D1	E1E1	F1F1
服务二service two	A2A2	B2B2	C2C2	D2D2	E2E2	F2F2
服务三service three	A3A3	B3B3	C3C3	D3D3	E3E3	F3F3
服务四service four	A4A4	B4B4	C4C4	D4D4	E4E4	F4F4

Table 22 exemplarily shows the correspondence score between each service and each electronic device obtained by the service joint ranking module. Among them, the correspondence between service one and mobile phone is A1, the correspondence between service one and tablet is B1, the correspondence between service one and large screen is C1, the correspondence between service one and car machine is D1, and the correspondence between service one and large screen is D1. The correspondence degree score with the watch is E1, and the correspondence degree score between service one and earphone is F1. The correspondence between Service 2 and mobile phones is A2, the correspondence between Service 2 and tablets is B2, the correspondence between Service 2 and large screens is C2, the correspondence between Service 2 and cars is D2, and the correspondence between Service 2 and watches is The correspondence degree score of service 2 is E2, and the correspondence degree score of service 2 and earphone is F2. The correspondence between Service 3 and mobile phones is A3, the correspondence between Service 3 and tablets is B3, the correspondence between Service 3 and large screens is C3, the correspondence between Service 3 and cars is D3, and the correspondence between Service 3 and watches is The corresponding score of the service three and the earphone is F3. The correspondence between Service 4 and mobile phones is A4, the correspondence between Service 4 and tablets is B4, the correspondence between Service 4 and large screens is C4, the correspondence between Service 4 and cars is D4, and the correspondence between Service 4 and watches is The correspondence score of the service four and the earphone is F4. It should be noted that the correspondence scores between the above-mentioned services and each electronic device are constant. For example, the correspondence score A1 between service one and mobile phones is 0.4, the correspondence score B1 between service one and tablets is 0.5, and the correspondence score between service one and large screens is 0.4. The correspondence score C1 of service 1 is 0.5, the correspondence score D1 of service 1 and car machine is 0.9, the correspondence score E1 of service 1 and watch is 0.2, and the correspondence score F1 of service 1 and earphone is 0.2, then the service can be determined If one has the highest correspondence score with the vehicle, then the service should be optimally displayed on the vehicle.

The service association sorting module also needs to record the displayable service capacity of each record based on the device status and the displayable service capacity of the device obtained by the data management module. The service federation ordering module determines which services to distribute to which devices based on the service capacity that can be displayed on each device.

The service capacity can be understood as the number of services that can be displayed in the service recommendation area on the device. For different electronic devices, the service recommendation area may have multiple specifications, and for each specification of the service recommendation area, there may be multiple service display formats of different specifications.

It can be understood that different services have different sizes, and the size of a service can be measured by size 1, size 2, size 3 and size 4, and a service with a larger size occupies more area of the service recommendation area. The service recommendation area can display multiple different services at the same time, so the service recommendation area can be composed of service display layouts of different sizes. For example, the service recommendation area can consist of two service display formats of size 2, and the service recommendation area of this rule can display two services of size 2 at the same time.

Fig. 34 exemplarily shows a schematic diagram of service recommendation areas of several different specifications.

The first line in Figure 34 shows the service recommendation area of the first specification. The service recommendation area of the first specification is composed of four service display formats of size 1. The service recommendation area of the first specification can simultaneously display four sizes of 1. services. The second line in Figure 34 shows the service recommendation area of the second specification. The service recommendation area of the second specification is composed of two service display formats of size 1 and one size 2. The service recommendation area of the second specification can be displayed at the same time. Showing 2 servings of

size

1 and 1 serving of size 2. The third line in Figure 34 shows the service recommendation area of the third specification. The service recommendation area of the third specification is composed of two service display formats of size 2. The service recommendation area of the third specification can display two sizes of 2 at the same time. services. The fourth line in Figure 34 shows the service recommendation area of the fourth specification. The service recommendation area of the fourth specification is composed of a service display format of size 3. The service recommendation area of the fourth specification can display a size 3 at the same time. services.

It should be noted that FIG. 34 is an example showing several service display areas with different specifications, and the service display area may also be composed of other service display formats with different specifications, which is not limited in this embodiment of the present application.

Table 23

Electronic equipment

cell phone

flat

Big screen

car machine

watch

earphone

service capacity

ε ¹

ε ²

ε ³

ε ⁴

ε ⁵

ε ⁶

Table 23 exemplarily shows the service capacities that can be displayed on several different electronic devices. Among them, the service capacity that can be displayed on the mobile phone is ε ¹ , the service capacity that can be displayed on the tablet is ε ² , the service capacity that can be displayed on the large screen is ε ³ , the service capacity that can be displayed on the car is ε ⁴ , and the service capacity that can be displayed on the watch is ε 3 . The displayed service capacity is ε ⁵ , and the service capacity that can be displayed on the headset is ε ⁶ . It should be noted that ε ¹ , ε ² , ε ³ , ε ⁴ , ε ⁵ and ε ⁶ are all constants, and the specific explanations for ε ¹ , ε ² , ε ³ , ε ⁴ , ε ⁵ and ε ⁶ can be Refer to the relevant description in FIG. 34 above.

Exemplarily, based on the correspondence degree scores of each service and each device obtained in Table 22, if service 1 has the highest matching degree with the car and machine, followed by the mobile phone. Service 2 has the highest matching degree with car and machine, followed by mobile phone. Service 3 has the highest degree of matching with mobile phones, followed by car phones. Service 4 has the highest matching degree with car and machine, followed by mobile phone.

If only three services can be displayed on the car at the same time, and only two services can be displayed on the mobile phone at the same time, then service 1, service 2 and service 4 will be displayed on the car first, and service 3 will be displayed on the mobile phone first.

Next, take the driving scene as an example to illustrate how to determine the optimal distribution of each service on the device.

First, in the driving scene, the user is navigating the route through the car and playing music on the mobile phone through the earphones. At a certain moment, such as waiting for a stop at a red light at a traffic light intersection, the user’s mobile phone and car machine both trigger the service recommendation process. The services recalled on the mobile phone are courier services and WeChat services, and the services recalled on the car machine are calendar services and navigation services. .

Currently, both the mobile phone and the car machine have triggered the service recommendation process, but the user is driving and the priority of the car machine is higher than that of the mobile phone, so the car machine is determined to be the central control device.

The car machine sends a request to the mobile phone, which requests the user to obtain the recalled service data and mobile phone status data on the mobile phone. In response to the request sent by the car, the mobile phone sends the mobile phone recall service to the car, namely express service and WeChat service.

First, the car and machine get the priority normalization coefficient of each service.

Table 24

服务Serve	优先级归一化系数Priority Normalization Factor
快递服务Delivery Service	0.80.8
日程服务Schedule service	0.60.6
微信服务WeChat service	0.30.3
导航服务navigation service	0.10.1

Table 24 exemplarily shows the priority normalization coefficients obtained for the vehicle-to-vehicle recall service and the mobile phone recall service. Among them, the priority normalization coefficient of express service is 0.8, the priority normalization coefficient of calendar service is 0.6, the priority normalization coefficient of WeChat service is 0.3, and the priority normalization coefficient of navigation service is 0.1.

Secondly, based on the device status data of the car, headset and mobile phone, the car machine can obtain the user's attention score for each device.

Table 25

设备equipment	车机car machine	手机cell phone	耳机earphone
用户对设备的关注度评分Score of user interest in the device	0.80.8	0.30.3	0.50.5

Table 25 exemplarily shows the user's attention score for each device in the driving scene. Among them, the user's attention score for the car machine is 0.8, the user's attention score for the mobile phone is 0.3, and the user's attention score for the earphone is 0.5.

Finally, the car machine gets the matching degree of the car machine recall service and the mobile phone recall service on each device.

Table 26

服务Serve	车机car machine	手机cell phone	耳机 earphone

快递服务Delivery Service	11	11	0.30.3

日程服务 Schedule service	11	11	0.30.3
微信服务 WeChat service	11	11	0.30.3
导航服务 navigation service	11	11	0.30.3

Table 26 exemplarily shows the matching degree of the service recalled by the car and the recalled mobile phone on each device in the driving scene. Among them, the matching degree of the courier service on the car is 1, the matching degree of the courier service on the mobile phone is 1, and the matching degree of the courier service on the headset is 0.3. The matching degree of the schedule service on the car is 1, the matching degree of the schedule service on the mobile phone is 1, and the matching degree of the schedule service on the headset is 0.3. The matching degree of the WeChat service on the car machine is 1, the matching degree of the WeChat service on the mobile phone is 1, and the matching degree of the calendar service on the headset is 0.3. The matching degree of the navigation service on the car is 1, the matching degree of the navigation service on the mobile phone is 1, and the matching degree of the navigation service on the headset is 0.3.

The car machine will be based on the priority normalization coefficient of each service, the user's attention score for each device, and the matching degree of the service on each device. Get the correspondence score between each service and each device.

Table 27

服务Serve	车机car machine	手机cell phone	耳机earphone
快递服务Delivery Service	0.80.8	0.50.5	00
日程服务Schedule service	0.70.7	0.60.6	00
微信服务WeChat service	0.40.4	0.50.5	00
导航服务navigation service	0.30.3	0.30.3	00

Table 27 exemplarily shows the correspondence score between each service obtained by the vehicle and each device. Among them, the correspondence score between express service and car machine is 0.8, the correspondence score between express service and mobile phone is 0.5, and the correspondence score between express service and earphone is 0. The correspondence score between schedule service and car machine is 0.7, the correspondence score between express service and mobile phone is 0.6, and the correspondence score between schedule service and earphone is 0. The correspondence score between WeChat service and car machine is 0.4, the correspondence score between WeChat service and mobile phone is 0.5, and the correspondence score between WeChat service and earphone is 0. The correspondence degree score between navigation service and car machine is 0.3, the correspondence degree score between navigation service and mobile phone is 0.3, and the correspondence degree score between navigation service and earphone is 0.

The car machine will also combine the service capacity that can be accommodated on the car machine and the service capacity that can be accommodated on the mobile phone at the same time, and distribute each service to different devices.

Table 28

电子设备Electronic equipment	车机car machine	手机cell phone	耳机 earphone

服务容量service capacity	11	33	11

Table 28 exemplarily shows the service capacity that can be displayed on each device at the same time. Among them, only one service can be displayed on the car at the same time, a maximum of three services can be displayed on the mobile phone, and only one service can be displayed on the headset at the same time.

Combining the current car recall service and mobile phone recall service, as well as the device status of the mobile phone, the car machine first makes the following assumptions:

(1) The mobile phone is in the charging state; (2) The schedule starts in 3 hours; (3) The car is driving towards home, which is relatively close to home; (4) The car is using navigation software; (5) The user has never used WeChat and payment codes on the car.

According to the above conditions, make a simple joint sort statement:

(1) It is currently inconvenient for the user to use the mobile phone; (2) The user is about to arrive home, so the user is more eager to use the courier service than the user to use the schedule service; (3) The car is currently navigating, so the user is more interested in the navigation service (4) The user has only used WeChat on a mobile phone, and it is inconvenient for the user to use the mobile phone at this time, so the user's demand for WeChat services is relatively low.

Based on the above conditions, it can be obtained that the joint ranking result is that the usage probability of the express service is greater than that of the schedule service, the usage probability of the schedule service is greater than that of the WeChat service, and the usage probability of the WeChat service is greater than that of the navigation service.

Based on Table 27 and Table 28, the car-machine finally determines that the correspondence between the express service and the car-machine has the highest score, and only one service can be displayed on the car-machine at the same time, then the car-machine will display the express service on the car-machine. Afterwards, the correspondence between the schedule service, WeChat service and navigation service and the mobile phone has the highest score, and a maximum of 3 services can be displayed on the mobile phone at the same time, then the vehicle will send the schedule service logo, WeChat service logo and navigation service logo to the mobile phone, The mobile phone displays the schedule service, WeChat service and navigation service on the mobile phone.

S3501. The first electronic device (electronic device 100) generates a first service set based on the personal data of the first user, the first service set includes multiple service functions, and the personal data of the first user includes historical usage data of the first user.

The first service set may be the service set shown in the card 801 shown in FIG. 9A . The first service set may also be the service set shown in the card 802 shown in FIG. 9C. The first service set may also be the service set shown in the card 803 shown in FIG. 9I. The first service set may also be the service set shown in the card 807 shown in FIG. 9J . The first service set may also be the service set shown in the card 810 shown in FIG. 9K . The first service set may also be the service set shown in the card 813 shown in FIG. 9L. The first service set may also be the service set shown in the card 1202 shown in FIG. 12 . The first service set may also be the service set shown in the card 1302 shown in FIG. 13 . The first service set may also be the service set shown in the card 1602 shown in FIG. 16 . The first service set may also be the service set shown in the card 1702 shown in FIG. 17 .

Through the provided method, the convenience and accuracy of service recommendation are realized.

S3502. When it is detected that the trigger condition of the first service set is satisfied, the first electronic device executes multiple functional operations corresponding to the first service set.

Optionally, after the first electronic device generates the first service set based on the first user's personal data, before the first electronic device executes multiple functional operations corresponding to the first service set, the method further includes: , the first electronic device displays the first recommendation card corresponding to the first service set; when it is detected that the trigger condition of the first service set is met, the first electronic device executes multiple functional operations corresponding to the first service set, specifically including: When a trigger operation for the first recommended card is detected, the first electronic device executes multiple functional operations corresponding to the first service set.

The first recommendation card may be the card 801 shown in FIG. 9A . The first recommendation card may also be the card 802 shown in FIG. 9C. The first recommendation card may also be the card 803 shown in FIG. 9I. The first recommendation card may also be the card 807 shown in FIG. 9J . The first recommendation card may also be the card 810 shown in FIG. 9K . The first recommendation card may also be the card 813 shown in FIG. 9L. The first recommendation card may also be the card 1202 shown in FIG. 12 . The first recommendation card may also be the card 1302 shown in FIG. 13 . The first recommendation card may also be the card 1602 shown in FIG. 16 . The first recommendation card may also be the card 1702 shown in FIG. 17 .

The triggering condition can also be a voice command, the identity information of the first user, a gesture, etc., so that the first electronic device can be triggered to execute multiple services in the first service set without manual operation by the user, which is convenient and quick.

Optionally, multiple service functions in the first service set correspond to multiple service functions of different applications, or multiple service functions in the first service set correspond to control of multiple different devices. In this way, different applications are controlled simultaneously or different devices are controlled simultaneously.

Optionally, the multiple service function types in the first service set include any one or more of the following: application services, system services, and services for controlling working states of other electronic devices. The first electronic device executes multiple functional operations corresponding to the first service set, specifically including: the first electronic device controls the first electronic device to work with a first working parameter, where the first working parameter includes any one or more of the following: The setting state of the system of the first electronic device, the setting state of the application installed on the first electronic device, and the opening/closing of the application installed on the first electronic device. And/or, the first electronic device controls the third electronic device to work with the second working parameter, wherein the second working parameter includes any one or more of the following: on/off of the third electronic device, setting state of the third electronic device .

Specifically, for the introduction of the trigger conditions of the first service set and how to execute multiple functional operations corresponding to the first service set, you can refer to the embodiments shown in Figures 9A-9H, and the embodiments of this application are not repeated here. repeat.

Optionally, the first electronic device generates a second service set based on the personal data of the first user. The second service set includes multiple service functions, and the multiple functional operations corresponding to the second service set are the same as the multiple service functions corresponding to the first service set. The functional operations are different; when it is detected that the trigger condition of the second service set is satisfied, the first electronic device executes multiple functional operations corresponding to the second service set. In this way, for the same user, in different scenarios, the first electronic device can automatically generate different service sets for the user, reflecting the intelligence of service recommendation.

Optionally, the first electronic device generates a third service set based on the personal data of the second user, the third service set includes multiple service functions, and the personal data of the second user includes historical usage data of the second user; When the trigger condition of the third service set is met, the first electronic device executes multiple functional operations corresponding to the third service set. If the personal data of the first user is different from the personal data of the second user, the multiple functional operations corresponding to the third service set are different from the multiple functional operations corresponding to the first service set. In this way, in the same scene, for different users, the service sets generated by the electronic device are also different, which reflects the differences of users and the intelligence of service recommendation.

Optionally, the first electronic device executes multiple functional operations corresponding to the first service set, specifically including: the first electronic device executes multiple functional operations corresponding to the first service set based on the execution relationship of multiple services in the first service set . Wherein, the execution relationship of multiple services in the first service set includes but not limited to sequential execution, simultaneous execution and so on. Regarding the sequence of execution, for example, in a navigation scenario, the first electronic device first acquires location information, and then acquires route information, and then the first electronic device broadcasts the route information through the earphone.

Optionally, before the first electronic device generates the first service set based on the personal data of the first user, the method further includes: when the first condition is met, the first electronic device acquires multiple candidate service functions; the first electronic device Generating the first service set based on the personal data of the first user specifically includes: the first electronic device generating the first service set based on multiple candidate service functions based on the personal data of the first user. That is, before generating the first service set, the first electronic device needs to acquire multiple candidate service functions. The first condition is the trigger condition of the scenario.

Optionally, the first condition includes any one or more of the following: the current time meets the first time, the location of the first electronic device meets the preset location, and the device status of the electronic device associated with the first user meets the preset status , wherein the device status includes the current battery level of the electronic device, whether the electronic device is connected to WiFi, whether the electronic device is connected to Bluetooth, whether the screen of the electronic device is on, whether the electronic device outputs audio, and whether the electronic device is turned on/off.

Optionally, before the first electronic device generates the first service set based on the personal data of the first user, the method further includes: the first electronic device acquires multiple service sets in the first scene; Generating the first service set from the personal data specifically includes: the first electronic device determines the first service set from multiple service sets based on the first user's personal data. That is, the first electronic device may not filter out a single service and generate a service set based on multiple individual services, but directly select a service set that may be used by the user from multiple service sets.

Optionally, the multiple service sets are service sets whose similarity with the service function used by the first user in the first scenario is greater than a preset value; the first electronic device selects from the multiple service sets based on the personal data of the first user Determining the first service set specifically includes: the first electronic device determines the type of device that the first user cares about in the first scenario; Determine the first service set that is similar to the device type that the first user cares about from the service sets. That is to say, the first electronic device may recommend to the user a set of services used by similar users that are close to the type of device that the first user cares about.

Optionally, the first electronic device determines the type of device that the first user pays attention to in the first scenario, specifically including: the first electronic device detects based on the working status of the device associated with the first user and the device associated with the first user. The obtained state of the first user determines the device type that the first user is concerned about.

Specifically, for how the first electronic device recommends to the user a set of services used by similar users whose device types are close to each other, reference may be made to the embodiments introduced in FIG. 10-FIG.

Optionally, the first electronic device obtains the first time when the user history uses the first service set and the second time when the first electronic device history displays the first recommended card; when the first electronic device determines that the first time is earlier than the second time time, or when the first time is later than the second time and the difference between the first time and the second time is greater than a preset value, the first electronic device adjusts the preset trigger condition of the first service set; After an electronic device adjusts the preset triggering condition of the first service set, the first electronic device displays the first recommendation card at a third time, wherein the third time is before the first time, and the third time and the first time The difference is less than the preset value. That is to say, the first electronic device can dynamically adjust the time for the first electronic device to display the first service set based on the time when the user uses the first service set and the time for displaying the first service set, so as to prevent the first electronic device from displaying the first service set. There is a large deviation between the time of the service set and the time when the user uses the first service set.

The first time may be the time T _P when the scenario introduced in the foregoing embodiments is entered, and the second time may be the time Tq when the user uses the service set in the scenario introduced in the foregoing embodiments.

Optionally, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset trigger condition, and the preset trigger condition includes one or more sub-conditions, The maximum constraint condition is the last executed subcondition among one or more subconditions; the first electronic device delays the execution time of the maximum constraint condition of the preset trigger condition by a first duration; the first electronic device determines the first newly added subcondition, Wherein, the execution time of the first newly added sub-condition is earlier than the execution time after the maximum constraint condition of the preset trigger condition is delayed by a first duration. In this way, the first electronic device can adjust the preset trigger condition that triggers the scene too early.

Optionally, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset trigger condition; the first electronic device determines the second new sub-set The condition, wherein the execution time of the second newly added subcondition is earlier than the execution time of the maximum constraint condition of the preset trigger condition; the first electronic device replaces the maximum constraint condition of the preset trigger condition with the second newly added subcondition. In this way, the first electronic device can adjust the preset trigger condition that the scene is triggered too late.

Specifically, for how the first electronic device adjusts the conditions of triggering the scene too early or too late, reference may be made to the embodiments introduced in FIG. 21-FIG. 22 , which will not be repeated here in the embodiments of the present application.

Optionally, the method further includes: the first electronic device acquires the first time when the user history uses the first service set and the second time when the first electronic device stops displaying the first recommendation card in the history; When the time is later than the second time, or the first time is earlier than the second time and the difference between the first time and the second time is greater than a preset value, the preset exit condition of the first electronic device for the first service set Adjustment; after the first electronic device adjusts the preset exit condition of the first service set, the first electronic device stops displaying the first recommendation card at a third time, wherein the third time is after the first time, and the first time The difference between the third time and the first time is less than a preset value. That is to say, the first electronic device can dynamically adjust the time when the first electronic device stops displaying the first service set based on the time when the user uses the first service set and the time when the user stops displaying the first service set, so as to prevent the first electronic device from stopping There is a large deviation between the time when the first service set is displayed and the time when the user uses the first service set.

Optionally, the first electronic device adjusts the preset exit condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset exit condition, and the preset exit condition includes one or more subconditions, The maximum constraint condition is the last executed subcondition among one or more subconditions; the first electronic device delays the execution time of the maximum constraint condition of the preset exit condition by a first duration;

Optionally, the first electronic device adjusts the preset trigger condition of the first service set, which specifically includes: the first electronic device determines the maximum constraint condition of the preset exit condition; the first electronic device determines the second new sub-set The condition, wherein the execution time of the second newly added subcondition is earlier than the execution time of the maximum constraint condition of the preset exit condition; the first electronic device replaces the maximum constraint condition of the preset exit condition with the first newly added subcondition. In this way, the first electronic device can adjust the preset trigger condition that the scene exits too late.

Specifically, for how the first electronic device adjusts the conditions of triggering the scene too early and too late, reference may be made to the embodiments introduced in FIGS. 23-24 , and details will not be repeated here in the embodiments of the present application.

Optionally, the method further includes, after the first electronic device displays the first recommendation card, and the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements, the first electronic device based on the first user personal data to generate a fourth service set, the fourth service set does not include the first service function in the first service set; the first electronic device displays the second recommendation card corresponding to the fourth service set, and the display on the second recommendation card The elements are the same as the default display elements. In this way, the first electronic device can avoid displaying incomplete services recommended for the user.

Optionally, after the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements, the method further includes: the first electronic device sends the identifier of the first service function in the first service set to the server , the identification of the first service function is used by the server to lower the reputation of the first service function; the first electronic device receives the reputation information sent by the server after reducing the reputation of the first service function, and the reputation information is used to indicate multiple Reputation of different service functions. In this way, the first electronic device avoids recommending and displaying incomplete services for the user by reducing the credibility of displaying incomplete services.

Optionally, the first electronic device generates the fourth service set based on the first user's personal data, which specifically includes: the first electronic device generates the fourth service set based on the first user's personal data from a plurality of different service functions based on the reputation information sent by the server. In the fourth service set, the reputation of the second service function in the fourth service set is higher than the reputation of the first service function in the first service set.

Optionally, before the first electronic device displays the first recommendation card, the method further includes: the first electronic device acquires a verification result generated by the first service function in the first service set, and the verification result is used to represent the first service Whether the function has obtained preset permission information and preset data information. Displaying the first recommendation card by the first electronic device specifically includes: displaying the first recommendation card by the first electronic device when the verification result is that the first service function has acquired preset authority information and preset data information. In this way, the first electronic device determines whether to recommend the service to the user through service self-verification, which improves the efficiency of service verification.

Specifically, for how the first electronic device provides verification services, reference may be made to the embodiments introduced in FIG. 25A-FIG. 30 , and details will not be repeated here in the embodiments of the present application.

Optionally, before the first electronic device displays the first recommendation card corresponding to the first service set, the method further includes: establishing a communication connection between the first electronic device and the second electronic device; The first degree of attention of the electronic device, the second degree of attention of the first user to the second electronic device; the first electronic device determines the device displaying the first set of services based on the first degree of attention and the second degree of attention; the first electronic device Displaying the first recommendation card corresponding to the first service set specifically includes: when the device displaying the first service set is the first electronic device, the first electronic device displays the first recommendation card corresponding to the first service set. In this way, the first electronic device may recommend services on devices that the user cares about based on the user's current degree of attention to each device.

Optionally, the method further includes: when the device displaying the first service set is the second electronic device, the first electronic device sends the identifier of the service function in the first service set to the second electronic device, and the service function in the first service set The identification of the function is used for the second electronic device to display the first recommendation card.

Optionally, before the first electronic device determines the device displaying the first service set based on the first degree of attention and the second degree of attention, the method further includes: the first electronic device obtains the service functions in the first service set and the first The matching degree of the electronic device, the matching degree of the service function in the first service set and the second electronic device, the priority of the service function in the first service set, the service function capacity that can be displayed on the first electronic device, and the service function capacity on the second electronic device. Displayable service function capacity; the first electronic device determines the device displaying the first service set based on the first degree of attention and the second degree of attention, specifically including: the first electronic device determines the device based on the first degree of attention, the second degree of attention, the second degree of The degree of matching between the service functions in a service set and the first electronic device, the matching degree between the service functions in the first service set and the second electronic device, the priority of the service functions in the first service set, and the displayable information on the first electronic device The service function capacity and the service function capacity that can be displayed on the second electronic device determine the device displaying the first service set.

Specifically, for the first electronic device to recommend services on multiple devices, reference may be made to the embodiments introduced in FIG. 32-FIG. 34 , and the embodiments of the present application will not be repeated here.

Various implementation modes of the present application can be combined arbitrarily to achieve different technical effects.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the present application are generated in whole or in part. A computer can be a general purpose computer, special purpose computer, computer network, or other programmable device. Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g. Coaxial cable, optical fiber, digital subscriber line) or wireless (such as infrared, wireless, microwave, etc.) to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server, a data center, etc. integrated with one or more available media. The usable medium may be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (solid state disk, SSD)), etc.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments are realized. The processes can be completed by computer programs to instruct related hardware. The programs can be stored in computer-readable storage media. When the programs are executed , may include the processes of the foregoing method embodiments. The aforementioned storage medium includes: ROM or random access memory RAM, magnetic disk or optical disk, and other various media that can store program codes.

In a word, the above are only examples of the technical solutions of the present invention, and are not intended to limit the protection scope of the present invention. All modifications, equivalent replacements, improvements, etc. made according to the disclosure of the present invention shall be included in the protection scope of the present invention.

Claims

A service recommendation method, characterized in that the method comprises:

The first electronic device generates a first service set based on the personal data of the first user, the first service set includes a plurality of service functions, and the personal data of the first user includes historical usage data of the first user;

When it is detected that the trigger condition of the first service set is met, the first electronic device executes multiple functional operations corresponding to the first service set.
The method according to claim 1, characterized in that, after the first electronic device generates the first service set based on the personal data of the first user, the first electronic device executes the corresponding service set of the first service set. Before multiple functional operations, the method also includes:

When the first condition is met, the first electronic device displays a first recommendation card corresponding to the first service set;

When it is detected that the trigger condition of the first service set is met, the first electronic device executes multiple functional operations corresponding to the first service set, specifically including:

When a trigger operation for the first recommended card is detected, the first electronic device executes a plurality of functional operations corresponding to the first service set.
The method according to claim 1 or 2, characterized in that the method further comprises:

The first electronic device generates a second service set based on the personal data of the first user, the second service set includes multiple service functions, and the multiple functional operations corresponding to the second service set are the same as the first The multiple functional operations corresponding to the service collection are different;

When it is detected that the trigger condition of the second service set is satisfied, the first electronic device executes multiple functional operations corresponding to the second service set.
The method according to any one of claims 1-3, wherein the method further comprises:

The first electronic device generates a third service set based on the personal data of the second user, the third service set includes a plurality of service functions, and the personal data of the second user includes historical usage data of the second user;

When it is detected that the trigger condition of the third service set is met, the first electronic device executes multiple functional operations corresponding to the third service set.
The method according to claim 4, wherein if the personal data of the first user is different from the personal data of the second user, the multiple functional operations corresponding to the third service set are the same as those of the first user. The multiple functional operations corresponding to the service collection are different.
The method according to any one of claims 1-5, wherein the first electronic device executes multiple functional operations corresponding to the first service set, specifically including:

The first electronic device executes multiple functional operations corresponding to the first service set based on the execution relationship of multiple services in the first service set.
The method according to any one of claims 1-6, wherein the multiple service functions in the first service set correspond to multiple service functions of different applications, or the multiple service functions in the first service set Corresponding to the control of multiple different devices.
The method according to any one of claims 1-7, wherein the first electronic device executes multiple functional operations corresponding to the first service set, specifically including:

The first electronic device controls the first electronic device to work with a first working parameter, wherein the first working parameter includes any one or more of the following: the setting state of the system of the first electronic device, the first The setting state of the application installed on the electronic device, and the opening/closing of the application installed on the first electronic device;

and / or,

The first electronic device controls the third electronic device to work with a second working parameter, wherein the second working parameter includes any one or more of the following: the third electronic device is turned on/off, the third electronic device The device's provisioning state.
The method according to any one of claims 1-8, wherein before the first electronic device generates the first service set based on the personal data of the first user, the method further comprises:

When the first condition is met, the first electronic device acquires multiple candidate service functions;

The first electronic device generates a first service set based on the personal data of the first user, specifically including:

The first electronic device generates the first service set based on the plurality of candidate service functions based on personal data of the first user.
The method according to claim 9, wherein before the first electronic device obtains multiple candidate service functions, the method further comprises:

The first electronic device obtains a candidate service set, and the service functions in the candidate service set include any one or more of the following: service functions sent by the server, service functions sent by other electronic devices, and service functions sent by the first electronic device The preset service functions in

The first electronic device obtains multiple candidate service functions, specifically including:

The first electronic device acquires the plurality of candidate service functions from the set of candidate services based on the personal data of the first user.
The method according to claim 10, wherein the first electronic device obtains the plurality of candidate service functions from the candidate service set based on the personal data of the first user, specifically comprising:

The first electronic device obtains the probability that the first user uses each service function in the candidate service set based on the personal data of the first user;

The first electronic device screens out a plurality of service functions whose usage probability is greater than a preset value, and obtains the candidate service functions.
The method according to any one of claims 9-11, wherein the first condition includes any one or more of the following: the current time meets the first time, the location of the first electronic device meets the predetermined Set the location and the device state of the electronic device associated with the first user to meet the preset state, wherein the device state includes the current battery level of the electronic device, whether the electronic device is connected to WiFi, whether the electronic device is connected to Bluetooth, whether the electronic device is on, electronic Whether the device outputs audio, whether the electronics are turned on/off.
The method according to claim 1, wherein before the first electronic device generates the first service set based on the personal data of the first user, the method further comprises:

The first electronic device acquires multiple service sets in the first scene;

The first electronic device generates a first service set based on the personal data of the first user, specifically including;

The first electronic device determines the first service set from the plurality of service sets based on the personal data of the first user.
The method according to claim 13, wherein the multiple service sets are service sets whose similarity with the service function used by the first user in the first scene is greater than a preset value; the The first electronic device determines the first service set from the plurality of service sets based on the personal data of the first user, specifically including:

The first electronic device determines the device type that the first user pays attention to in the first scenario;

The first electronic device determines, based on the device type concerned by the first user and the personal data of the first user, the first device similar to the device type concerned by the first user from the plurality of service sets. A collection of services.
The method according to claim 14, wherein the first electronic device determines the device type that the first user pays attention to in the first scene, specifically comprising:

The first electronic device determines the type of device concerned by the first user based on the working state of the device associated with the first user and the state of the first user detected by the device associated with the first user .
The method according to claim 15, wherein the first electronic device is based on the working status of the device associated with the first user, the first user detected by the device associated with the first user The status determines the device type that the first user is concerned about, specifically including:

The first electronic device determines, based on the working state of the device associated with the first user, and the state of the first user detected by the device associated with the first user, that the first user is responsible for multiple devices. degree of attention;

The first electronic device uses the top M devices with the first user's degree of attention to multiple devices as the type of device that the first user is concerned about.
The method according to claim 2, further comprising:

The first electronic device obtains the first time when the user history uses the first service set and the second time when the first electronic device historically displays the first recommended card;

When the first electronic device determines that the first time is earlier than the second time, or the first time is later than the second time and the difference between the first time and the second time When the value is greater than a preset value, the first electronic device adjusts a preset trigger condition of the first service set;

After the first electronic device adjusts the preset trigger condition of the first service set, the first electronic device displays the first recommendation card at a third time, wherein the third time is at the before the first time, and the difference between the third time and the first time is smaller than the preset value.
The method according to claim 17, wherein the first time is an average value of time the user uses the first set of services within a first time period;

The second time is an average value of time during which the first electronic device displays the first service set within the first time period.
The method according to claim 2, characterized in that the method comprises:

The first electronic device obtains the first time when the user history uses the first service set and the second time when the first electronic device stops displaying the first recommendation card in the history;

When the first electronic device determines that the first time is later than the second time, or the first time is earlier than the second time and the difference between the first time and the second time is When the value is greater than a preset value, the first electronic device adjusts the preset exit condition of the first service set;

After the first electronic device adjusts the preset exit condition of the first service set, the first electronic device stops displaying the first recommendation card at a third time, wherein the third time is at After the first time, and the difference between the third time and the first time is smaller than the preset value.
The method according to claim 19, wherein the first time is an average value of time the user uses the first set of services within a first time period;

The second time is an average value of time during which the first electronic device stops displaying the first set of services within the first time period.
The method according to claim 2, characterized in that the method comprises:

After the first electronic device displays the first recommendation card, and the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements, the first electronic device based on the The personal data of the first user is used to generate a fourth service set, and the fourth service set does not include the first service function in the first service set;

The first electronic device displays a second recommendation card corresponding to the fourth service set, and display elements on the second recommendation card are the same as preset display elements.
The method according to claim 21, wherein after the first electronic device determines that the display elements on the first recommendation card are different from the preset display elements, the method further comprises:

The first electronic device sends an identifier of a first service function in the first service set to a server, where the identifier of the first service function is used by the server to reduce the credibility of the first service function;

The first electronic device receives reputation information sent by the server after reducing the reputation of the first service function, where the reputation information is used to indicate the reputation of multiple different service functions.
The method according to claim 22, wherein the first electronic device generates a fourth service set based on the personal data of the first user, specifically comprising:

The first electronic device generates the fourth service set based on the personal data of the first user from a plurality of different service functions based on the reputation information sent by the server, and the second service function in the fourth service set The reputation of is higher than the reputation of the first service function in the first service set.
The method according to any one of claims 21-23, wherein before the first electronic device displays the first recommendation card, the method further comprises:

The first electronic device obtains a verification result generated by the first service function in the first service set, and the verification result is used to indicate whether the first service function has obtained preset permission information and preset data information;

The first electronic device displays a first recommendation card, specifically including:

If the verification result is that the first service function has acquired the preset authority information and the preset data information, the first electronic device displays the first recommendation card.
The method according to claim 2, further comprising: before the first electronic device displays the first recommendation card corresponding to the first service set:

The first electronic device establishes a communication connection with the second electronic device;

The first electronic device obtains the first degree of attention of the first user on the first electronic device, and the second degree of attention of the first user on the second electronic device;

determining, by the first electronic device, a device displaying the first set of services based on the first degree of attention and the second degree of attention;

The first electronic device displays the first recommendation card corresponding to the first service set, specifically including:

When the device displaying the first service set is the first electronic device, the first electronic device displays a first recommendation card corresponding to the first service set.
The method according to claim 25, further comprising:

When the device displaying the first service set is the second electronic device, the first electronic device sends the identifier of the service function in the first service set to the second electronic device, and the first electronic device The identifiers of the service functions in the service set are used by the second electronic device to display the first recommendation card.
The method according to claim 25 or 26, wherein, before the first electronic device determines a device displaying the first set of services based on the first degree of attention and the second degree of attention, the The method also includes:

The first electronic device acquires the degree of matching between the service functions in the first service set and the first electronic device, the matching degree between the service functions in the first service set and the second electronic device, the The priority of service functions in the first service set, the capacity of service functions that can be displayed on the first electronic device, and the capacity of service functions that can be displayed on the second electronic device;

The first electronic device determines, based on the first degree of attention and the second degree of attention, a device displaying the first set of services, specifically including:

The first electronic device is based on the first attention degree, the second attention degree, the matching degree of the service function in the first service set and the first electronic device, and the service function in the first service set The degree of matching with the second electronic device, the priority of service functions in the first service set, the capacity of service functions that can be displayed on the first electronic device, and the service functions that can be displayed on the second electronic device Capacities determine devices that exhibit the first set of services.
An electronic device, which is a first electronic device, is characterized in that the first electronic device includes: one or more processors, one or more memories; the one or more memories and the one or more The processors are coupled, the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and the one or more processors call the computer instructions to make the first electronic device execute the above-mentioned The method of any one of claims 1-27.
A computer-readable storage medium for storing computer instructions, when the computer instructions are run on the first electronic device, the first electronic device is made to perform the method described in any one of claims 1-27 .
A computer program product, characterized in that, when the computer program product is run on the first electronic device, the first electronic device is made to execute the method described in any one of claims 1-27.