Service recommendation method and electronic equipment

Abstract

The embodiment of the invention provides a service recommendation method and electronic equipment. The method is applied to terminal equipment. The method comprises the following steps: acquiring a first scene service combination comprising a first scene condition set and a first scene service set; service recommendation is carried out based on the first scene service combination; other scene conditions are collected, and / or a service starting condition is acquired; a second scene service combination is obtained, service recommendation is carried out based on the second scene service combination, and the second scene service combination comprises a second scene condition set and / or a second scene service set; the second scene condition set is a scene condition set generated according to the first scene condition set and the candidate scene conditions; the candidate scene conditions are scene conditions related to the first scene condition set and obtained according to other scene conditions; the second scene service set is a scene service set generated according to the first scene service set and the candidate service; the candidate service is a service related to the first scene condition set and obtained according to the service enabling condition. According to the method provided by the embodiment of the invention, the service matched with the user demand can be recommended to the user, and the user experience of service recommendation is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and electronic device for recommending services. Background Art

[0002] When a terminal device (e.g., a mobile phone) provides intelligent service recommendations to a user, the terminal device recommends services corresponding to the current scenario to the user. However, in many cases, the services recommended by the terminal device do not match the user's needs well.

[0003] Therefore, a service recommendation method is needed to recommend services that match user needs to users. Summary of the Invention

[0004] In order to solve the problem of how to recommend services that match user needs to users, the present application provides a method and electronic device for recommending services, and also provides a computer-readable storage medium.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, the present application provides a method for recommending services, the method being applied to a terminal device, the method comprising:

[0007] Acquire a first scenario service combination, where the first scenario service combination includes a first scenario condition set and a first scenario service set, where the first scenario condition set includes one or more scenario conditions, and the first scenario service set includes one or more services;

[0008] Recommending services based on the first scenario service combination includes recommending services in the first scenario service set to a user of the terminal device when the terminal device meets a scenario condition in the first scenario condition set;

[0009] If the terminal device satisfies a scenario condition in the first scenario condition set, collecting one or more scenario conditions other than the first scenario condition set on the terminal device; and / or, after recommending a service in the first scenario service set to a user of the terminal device, obtaining a service activation status based on an operation by the user to activate the service on the terminal device;

[0010] Obtain a second scenario service combination, and perform service recommendations based on the second scenario service combination, wherein:

[0011] The second scenario service combination includes a second scenario condition set and / or a second scenario service set;

[0012] The second scene condition set is a scene condition set generated according to the first scene condition set and one or more candidate scene conditions;

[0013] The one or more candidate scene conditions are scene conditions related to the first scene condition set obtained based on the one or more other scene conditions;

[0014] The second scenario service set is a scenario service set generated according to the first scenario service set and one or more candidate services;

[0015] The one or more candidate services are services related to the first scenario condition set acquired based on the service activation status.

[0016] According to the method of the first aspect, based on the data collected on-site by the terminal device, the pre-generated first scenario service combination is updated to obtain a second scenario service combination that better matches the user's actual scenario needs for service recommendation. Services that match the user's needs can be recommended to the user, thereby improving the user experience of the service recommendation.

[0017] In an implementation manner of the first aspect, the first scenario service combination is a scenario service combination generated according to intent sharing data.

[0018] According to the above implementation method, the second scenario service combination is generated by updating the first scenario service combination, wherein the scenario service combination generated based on the intent sharing data is used as the first scenario service combination, so that the first scenario service combination can be closer to the user's actual scenario needs, thereby reducing the update frequency of the first scenario service combination, saving project development efficiency and time, and improving user recommendation satisfaction.

[0019] In an implementation of the first aspect, the one or more other scene conditions include a first scene condition;

[0020] The acquiring, according to the one or more other scenario conditions, one or more candidate scenario conditions related to the first scenario condition set includes:

[0021] A first probability is calculated. When the first probability is greater than or equal to a first preset probability value, the first scene condition is the candidate scene condition, wherein:

[0022] The first probability is the probability of the first scene condition existing when the scene conditions in the first scene condition set are met.

[0023] In an implementation of the first aspect, the one or more other scene conditions include a first scene condition;

[0024] The acquiring, according to the one or more other scenario conditions, one or more candidate scenario conditions related to the first scenario condition set includes:

[0025] A second probability is calculated. When the second probability is greater than or equal to a second preset probability value, the first scene condition is the candidate scene condition, wherein:

[0026] The second probability is the probability of existence of the first scenario condition when the services in the first scenario service set are enabled after the services in the first scenario service set are recommended.

[0027] In an implementation of the first aspect, obtaining one or more candidate services related to the first scenario condition set according to the service activation status includes:

[0028] A third probability is calculated. When the first probability is greater than or equal to a third preset probability value, the first service is the candidate service, wherein:

[0029] The first service is a service other than the first scenario service set;

[0030] The third probability is the probability that the first service is enabled when a scenario condition in the first scenario condition set is met.

[0031] In an implementation of the first aspect, obtaining one or more candidate services related to the first scenario condition set according to the service activation status includes:

[0032] A fourth probability is calculated. When the first probability is greater than or equal to a fourth preset probability value, the first service is the candidate service, wherein:

[0033] The first service is a service other than the first scenario service set;

[0034] The fourth probability is the probability that the first service is enabled when the first scenario condition set and the candidate scenario condition are met.

[0035] In an implementation of the first aspect:

[0036] Generating a second scene condition set based on the first scene condition set and the one or more candidate scene conditions includes: performing a confidence assessment on the candidate scene conditions, and when the confidence of the candidate scene conditions reaches a preset first confidence threshold, adding the candidate scene conditions to the first scene condition set to generate the second scene condition set;

[0037] and / or,

[0038] The generating of the second scenario service set based on the first scenario service set and the one or more candidate services includes: performing confidence determination on the candidate services, and when the confidence of the candidate services reaches a preset second confidence threshold, filling the candidate services into the first scenario service set to generate the second scenario service set.

[0039] In an implementation of the first aspect, the one or more candidate services include a first candidate service;

[0040] Generating a second scenario service set according to the first scenario service set and the one or more candidate services includes:

[0041] When a scenario condition in the first scenario condition set or the second scenario condition set is met, recommending services in the first scenario service set and / or the first candidate service;

[0042] Collecting activation status of the first candidate service and / or activation status of services in the first scenario service set;

[0043] According to the activation status of the first candidate service and / or the activation status of the services in the first scenario service set, the first candidate service is added to the first scenario service set, or the first candidate service is not added to the first scenario service set to generate the second scenario service set.

[0044] In an implementation of the first aspect:

[0045] If the click-through rate of the application icon of the first candidate service is higher than the click-through rate of the application icons of the services in the first scenario service set, adding the first candidate service to the first scenario service set to generate the second scenario condition set;

[0046] or,

[0047] When the click rate of the application icon of the first candidate service is higher than a preset first click rate threshold, the first candidate service is added to the first scenario service set to generate the second scenario condition set.

[0048] In an implementation of the first aspect, generating a second scenario service set according to the first scenario service set and the one or more candidate services further includes:

[0049] calculating a first click-through rate, where the first click-through rate is a click-through rate of an application icon of the first candidate service when the first candidate service is not recommended when a scenario condition in the first scenario condition set or the second scenario condition set is met;

[0050] calculating a second click-through rate, where the second click-through rate is a click-through rate of an application icon of the first candidate service when the first candidate service is recommended when a scenario condition in the first scenario condition set or a scenario condition in the second scenario condition set is met;

[0051] When the improvement degree of the second click-through rate compared with the first click-through rate exceeds a preset improvement degree threshold, the first candidate service is added to the first scenario service set to generate the second scenario condition set.

[0052] In an implementation of the first aspect, the first scenario service set includes a second service;

[0053] The generating a second scenario service set according to the first scenario service set and the one or more candidate services further includes:

[0054] According to the activation status of the second service, the second service is deleted from the first scenario service set, or the second service in the first scenario service set is retained to generate the second scenario service set.

[0055] In an implementation of the first aspect:

[0056] When the click rate of the application icon of the second service is lower than a preset second click rate threshold, the second service in the first scenario service set is deleted, and the second scenario condition set is generated.

[0057] In a second aspect, the present application provides a method for generating a scene service combination, which is applied to an electronic device and includes:

[0058] Acquire a first scenario service combination, where the first scenario service combination includes a first scenario condition set and a first scenario service set, where the first scenario condition set includes one or more scenario conditions, and the first scenario service set includes one or more services;

[0059] Obtaining one or more other scenario conditions and / or service activation status, wherein: the other scenario conditions are scenario conditions other than the first scenario condition set collected on the terminal device when the terminal device satisfies the scenario conditions in the first scenario condition set; the service activation status is the service activation status obtained based on the user's operation of activating the service on the terminal device after recommending a service in the first scenario service set to the user of the terminal device when the terminal device satisfies the scenario conditions in the first scenario condition set;

[0060] Acquire one or more candidate scenario conditions related to the first scenario condition set based on the one or more other scenario conditions; and / or acquire one or more candidate services related to the first scenario condition set based on the service activation status;

[0061] Generate a second scenario condition set based on the first scenario condition set and the one or more candidate scenario conditions; and / or generate a second scenario service set based on the first scenario service set and the one or more candidate services;

[0062] A second scenario service combination is generated, where the second scenario service combination includes a second scenario condition set and / or a second scenario service set.

[0063] According to the method of the second aspect, the pre-generated scenario service combination is updated based on the data collected on-site by the terminal device, so that a scenario service combination that better matches the user's actual scenario needs can be obtained.

[0064] In a third aspect, the present application provides an electronic device, comprising a memory for storing computer program instructions and a processor for executing computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method steps described in the first aspect or the second aspect.

[0065] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method described in the first aspect or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 FIG2 is a structural block diagram of a scene service combination generating device according to an embodiment of the present application;

[0067] Figure 2 FIG2 is a flowchart of a method for recommending services according to an embodiment of the present application;

[0068] Figure 3 Shown is a schematic diagram of scenario and service pre-generation logic according to an embodiment of the present application;

[0069] Figure 4 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application;

[0070] Figure 5 FIG2 is a partial flow chart of a method for generating a scene service combination according to an embodiment of the present application;

[0071] Figure 6 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application;

[0072] Figure 7 Schematic diagram of data flow of a scenario service combination generation method according to an embodiment of the present application;

[0073] Figure 8 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application;

[0074] Figure 9 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application;

[0075] Figure 10 FIG. 1 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0076] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0077] The terms used in the implementation section of this application are only used to explain the specific embodiments of this application and are not intended to limit this application.

[0078] A scenario is a rule defined based on one or more conditions such as time, location, and device status. A scenario can contain one or more scenario conditions. When all scenario conditions are met, the scenario is triggered.

[0079] Specifically, in one embodiment, the scenario condition is to collect information about the user at a specific time, location, event, behavior, etc., and use one or a combination of these information as a condition for entering the scenario. For example, if a user frequently orders takeout during a certain period of time, this period can be considered as the scenario condition for the user to order takeout.

[0080] For example, a scenario includes the following conditions: Monday morning, at work, phone plugged into headphones, and phone vibration off. If a phone is at work on Monday morning, with vibration off and headphones plugged in, the phone triggers the scenario.

[0081] To implement intelligent service recommendations, the terminal device needs to define specific scenarios and associate scenario services with the defined scenarios. When the terminal device recognizes that it is currently in a defined scenario, the scenario services associated with the scenario are recommended to the user.

[0082] Specifically, in one embodiment, a scenario service is: when the application determines that the user meets the scenario conditions, it provides the user with information browsing or convenient access to some related functions. For example, when a user meets the scenario conditions for ordering takeout, the application provides the user with a takeout entrance or coupon information.

[0083] For example, define 5:00-11:30 as "Early Rising Scene" and associate "Early Rising Scene" with "Weather Service". Then, the terminal device will trigger the "Early Rising Scene" during 5:00-11:30 and recommend "Weather Service" to the user.

[0084] For example, define the action of plugging headphones into the device as "wearing headphones scene", and set the "wearing headphones scene" to be associated with "music services" and "video services". Then, when the headphones are plugged into the terminal device, the terminal device will recommend "music services" and "video services" to the user.

[0085] In the above-mentioned intelligent service recommendation process, the definition of the scenario is manually set by the user or technician. Since the user or technician cannot take all scenario conditions into consideration when defining the scenario, the scenario recommended by the intelligent service cannot cover all actual scenarios, and the definition of the scenario cannot accurately match the actual scenario.

[0086] For example, defining the action of plugging headphones into a device as "wearing headphones" doesn't take into account that connecting Bluetooth headphones also falls into this category. Another example is defining 5:00-11:30 as "early rising scene," but in some real-world scenarios, "early rising scene" corresponds to 5:00-7:30.

[0087] Furthermore, in the above-mentioned intelligent service recommendation process, the association relationship between the scene and the service is also manually set by the user or technician. Since the user or technician cannot take all services into consideration when setting the association relationship, nor does he consider the user's subsequent service usage, the service associated with the scene is not necessarily the service that the user expects to use.

[0088] For example, the "early morning scene" is associated with the "weather service," but in some scenarios, the user wants to use the "traffic service" in the morning. For another example, in one embodiment, the "video service" corresponds to opening a video playback application, but the user wants to open a short video application when entering the "headphones scene."

[0089] In view of the above situation, in order to improve the user experience of intelligent service recommendation and recommend services that meet user expectations to users, an embodiment of the present application provides a scene service combination generation device and a scene service combination generation method.

[0090] In one embodiment of the present application, the scenario service combination generation method is applied to an electronic device, or in other words, the scenario service combination generation method is applied to a scenario service combination generation device constructed on the electronic device.

[0091] The electronic device that implements the scenario service combination generation method can be a user's terminal device, or a server or other device connected to the terminal device.

[0092] For example, the electronic device may be a mobile phone, a tablet computer, a personal desktop computer, a notebook, a server, or a distributed server.

[0093] Furthermore, based on the scenario service combination generation method of the embodiment of the present application, an embodiment of the present application also provides a method for recommending services. The method for recommending services in the embodiment of the present application recommends services based on the scenario service combination generated by the scenario service combination generation method.

[0094] In one embodiment of the present application, the method for recommending services is applied to a terminal device. Alternatively, in another embodiment, the method for recommending services is partially applied to the terminal device and partially applied to a server or other device connected to the terminal device.

[0095] Figure 1 Shown is a structural block diagram of a scene service combination generation device according to an embodiment of the present application.

[0096] like Figure 1 As shown, the scene service combination generating device includes a scene service pre-generating module 310 and a scene and service association extending module 320. The scene and service association extending module 320 includes a condition collection and analysis submodule 321, a service association analysis submodule 322 and a click estimation feedback module 323.

[0097] In one embodiment, Figure 1 The scene service combination generating device shown can be built in the terminal device. In another embodiment, Figure 1 The scene service combination generating device shown can be built in a server or other device connected to the terminal device.

[0098] For example, Figure 2 Shown is a flow chart of a method for recommending services according to an embodiment of the present application.

[0099] In one embodiment, Figure 1 The scene service combination generating device shown is constructed in a server connected to a terminal device, and the scene service combination generating device and the terminal device execute Figure 2 The following process is shown to achieve service recommendation.

[0100] S400: The scenario and service pre-generation module 310 obtains a first scenario service combination corresponding to a first scenario, which includes a first scenario condition set (scenario conditions corresponding to the first scenario) and a first scenario service set (services corresponding to the first scenario).

[0101] The first scenario condition set includes one or more scenario conditions, and the first scenario service set includes one or more services. The scenario conditions in the first scenario condition set are independent of each other.

[0102] In an implementation of S400 , the first scenario service combination is manually set by a user or a technician.

[0103] For example, the first scenario condition set of the first scenario service combination is manually set by the user or the technician to include "5:00-8:30" and "mobile phone is awakened"; the first scenario service set of the first scenario service combination includes "weather service".

[0104] In another implementation of S400, the scenario and service pre-generation module 310 generates a first scenario service combination based on the intent sharing data provided by a third-party content provider (Content Provider). Specifically, the scenario and service pre-generation module 310 performs intent label training and conditional aggregation on the intent sharing data to generate a scenario service combination corresponding to the intent sharing data, where the scenario service combination corresponding to the intent sharing data includes at least the first scenario service combination.

[0105] According to the method of one embodiment of the present application, the final scenario service combination is generated by updating the basic scenario service combination, wherein the scenario service combination generated based on the intent sharing data is used as the basic scenario service combination, so that the basic scenario service combination can be closer to the user's actual scenario needs, thereby reducing the update frequency of the basic scenario service combination, saving project development efficiency and time, and improving user recommendation satisfaction.

[0106] In an embodiment of the present application, the intention sharing data is used to describe the user's service usage. The intention sharing data includes data such as the user's intention, the services used by the user, service usage conditions, and service details.

[0107] Specifically, in one embodiment, the intent data is: descriptive information about the behavior generated based on the user behavior, such as the information generated after the user orders takeout, including the order time, store name, cuisine type, etc.

[0108] For example, in one embodiment, a certain piece of intended sharing data provided by a food delivery platform A is shown in Table 1.

[0109] Table 1

[0110] Data Name Value intention Order takeout Order time 2023.08.25 11:15:18 Application APP Food delivery app A Store Name XX Hotel Store address No. XX, XX Street, XX District, XX City Cuisine Type fast food

[0111] In Table 1, the user's intention is to order takeout; the service usage condition is: order time (2023.08.25 11:15:18); the service used by the user is: takeout application A; the service usage details are: store name (XX Restaurant), store address (No. XX, XX Street, XX District, XX City), and cuisine type (fast food).

[0112] Figure 3 Shown is a schematic diagram of scenario and service pre-generation logic according to an embodiment of the present application.

[0113] like Figure 3 As shown, the intent sharing data (e.g., CP-1, CP-2, ..., CP-N) is input into the intent framework 500 for analysis. The analysis process includes:

[0114] S500: parse the externally input intention sharing data and extract the scenario conditions corresponding to the intention sharing data from the intention sharing data.

[0115] S501, calling a scene template, and according to the scene template, performing scene condition association on the scene conditions corresponding to the intended sharing data, and constructing a scene, wherein the constructed scene includes at least a first scene.

[0116] Specifically, in S501, the scenario and service pre-generation module 310 matches the scenario conditions extracted from the intention sharing data with the scenario template, and constructs the scenario corresponding to the intention sharing data according to the matching result.

[0117] For example, in one embodiment, the definition of the scenario template is shown in Table 2.

[0118] Table 2

[0119] Scene ID Condition 1 Condition 2 Condition 3 condition... Scenario 1 c1 c2 c3 ... Scenario 2 c1 c2 c4 Scenario 3 c1 c5 Scene 4 c1 ...

[0120] The scenario and service pre-generation module 310 analyzes the intended sharing data and extracts the scenario condition c1. The scenario condition c1 is matched with the scenario template shown in Table 1, and a first scenario condition set (c1) corresponding to the first scenario (scenario 4) is generated based on the matching result.

[0121] Furthermore, when the extracted scene conditions are matched with the scene template, there may be a situation where multiple scenes are matched. In view of the above situation, in one embodiment, the scene that matches the most scene conditions is the first scene.

[0122] For example, the scenario and service pre-generation module 310 analyzes the intended sharing data and extracts scenario conditions c1, c2, c4, and c5. Matching scenario condition c1 with the scenario templates shown in Table 1 yields the following matches: scenario 2 (c1, c2, c4), scenario 3 (c1, c5), and scenario 4 (c1). The scenario condition with the most matching conditions is selected, and based on the matching results, a first scenario condition set (c1, c2, c4) corresponding to the first scenario (scenario 2) is generated.

[0123] S510: parse the externally input intention sharing data and extract services corresponding to the intention sharing data. The services corresponding to the intention sharing data include at least a first scenario service set.

[0124] For example, in one embodiment, in S511, the scenario and service pre-generation module 310 parses the external input intention sharing data, sorts the services according to the frequency of their appearance in the intention sharing data, and filters the top N services as the services corresponding to the intention sharing data (N is an integer greater than or equal to 1).

[0125] For example, a food delivery platform A provides 20 sets of intent sharing data (see Table 1). Among them, the application APP in 15 sets of intent sharing data is (food delivery application A), the application APP in 3 sets of intent sharing data is (food application A), and the application APP in 2 sets of intent sharing data is (small program of social application A). The scenario and service pre-generation module 310 parses the external input intent sharing data and sorts the services according to the frequency of their appearance in the intent sharing data: food delivery application A, food application A, social application A. The first scenario service set is finally generated as: (food delivery application A).

[0126] S520, associate and map the scene corresponding to the intention sharing data with the service to generate a scene service combination corresponding to the intention sharing data, where the scene service combination corresponding to the intention sharing data includes at least a first scene service combination.

[0127] After S400 , the first scenario service combination is sent to the user's terminal device, and the terminal device makes a service recommendation based on the first scenario service combination.

[0128] During the service recommendation process, the terminal device collects data, and the scene and service association extension module 320 obtains scene conditions other than the first scene condition set related to the first scene and other services other than the first scene service set based on the data collected by the terminal device, thereby increasing or decreasing scene conditions in the first scene condition set, and increasing or decreasing services in the first scene service set to optimize the first scene service combination.

[0129] Specifically, in one embodiment, after S400, the first scenario service combination is sent to the user's terminal device, and the user's terminal device executes S401.

[0130] S401: When a first scenario is triggered (all scenario conditions in a first scenario condition set are satisfied), the terminal device recommends services in the first scenario service set to the user.

[0131] Specifically, in one embodiment, in S401, the terminal device displays a recommendation card, which includes application icons and / or application cards of services in the first scenario service set.

[0132] Furthermore, in one embodiment, when recommending the first scenario service set, the terminal device also recommends services outside the first scenario service set. For example, the terminal device displays a recommendation card, which includes application icons and / or application cards for services in the first scenario service set and application icons and / or application cards for services outside the first scenario service set.

[0133] For example, in one embodiment, the first scene condition set of the first scene service combination includes "5:00-8:30", "mobile phone is awakened"; the first scene service set of the first scene service combination includes "weather service"

[0134] Figure 4 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application.

[0135] When the phone is woken up at 8:00 one day, it displays Figure 4 The screen shown.

[0136] like Figure 4 As shown, 601 is a recommendation card and 602 is an application card for "weather service". The recommendation card 601 also includes fixed recommended services that are not related to the scene: video, music, email and browser.

[0137] S402: The terminal device collects data.

[0138] Specifically, S402 includes:

[0139] When the first scene is triggered, the terminal device collects other scene conditions (scene conditions other than the first scene condition set) when the first scene is triggered. For example: time, event, device status, weather, etc.

[0140] When the first scenario is triggered and the terminal device recommends the first scenario service set, the terminal device collects the user's operation of enabling the service on the terminal device to obtain the service activation status. For example, the user clicks the icon of application S, opens application S and activates service S.

[0141] After S402, the terminal device sends the collected other scene conditions and service activation status to the scene service combination generating device.

[0142] S410 , the condition collection and analysis submodule 321 obtains one or more candidate scenario conditions related to the first scenario based on the first scenario condition set and other scenario conditions sent by the terminal device.

[0143] Specifically, in one embodiment, in S410, the condition collection and analysis submodule 321 performs statistical analysis based on the data collection results of the terminal device to obtain scene conditions (candidate scene conditions) that are highly correlated with the first scene. The candidate scene conditions are used to expand the current scene conditions of the first scene (the first scene condition set), thereby achieving scene conditions with higher correlation and more accurate triggering.

[0144] Furthermore, in one embodiment, the terminal device executes S401 multiple times and collects other scene conditions each time S401 is executed. The condition collection and analysis submodule 321 performs statistical analysis on the multiple collection results of other scene conditions of the terminal device to screen candidate scene conditions.

[0145] Specifically, in one embodiment, in S410 , the association relationship between the other scene conditions and the first scene condition set is evaluated by calculating the probability that the other scene conditions and the first scene condition set occur simultaneously.

[0146] For example, assume the first scenario condition set is scenario condition set A. When the first scenario is triggered, the terminal device detects scenario condition B. P(A) is the probability of scenario condition set A occurring. Given that the first scenario is triggered, the probability of scenario condition set A occurring is 100%. P(B) is the probability of scenario condition set B occurring, and P(AB) is the probability of scenario condition set A and scenario condition B occurring simultaneously. When P(AB) is greater than or equal to a first preset probability threshold, scenario condition B is considered to have a high correlation with the first scenario.

[0147] For example, suppose the scenario condition set for the first scenario service combination includes "5:00-8:30" and "phone is awakened," and the first scenario service set for the first scenario includes "weather service." Based on the first scenario service combination, when the phone is awakened between 5:00-8:30, the first scenario is triggered. When the first scenario is triggered, the phone recommends the "weather service" service and records the current time, weather, and other scenario conditions.

[0148] Assume that after the first scenario is triggered, the scenario conditions recorded by the mobile phone include "Monday to Friday" and "alarm off." The condition collection and analysis submodule 321 calculates the probability of "Monday to Friday," "5:00-8:30," and "mobile phone being woken up" occurring simultaneously. Based on whether the probability calculation result is greater than or equal to a preset probability threshold, it determines whether "Monday to Friday" can be classified as a candidate scenario condition.

[0149] In addition, the condition collection and analysis submodule 321 counts the probabilities of "turning off the alarm clock", "5:00-8:30", and "the phone being woken up" occurring at the same time, and determines whether "turning off the alarm clock" can be classified as a candidate scenario condition based on whether the probability calculation result is greater than or equal to the preset probability threshold.

[0150] Furthermore, in one embodiment, the probability of P(AB) is calculated based on the following formula.

[0151] P(AB)=num(AB) / num(I), (Formula 1)

[0152] In one implementation, in Formula 1: num(I) is the total number of times the first scene is triggered; num(AB) is the total number of times scene condition set A and scene condition B occur simultaneously (i.e., the total number of times scene condition B occurs when the first scene is triggered).

[0153] For example, assuming that the first preset probability threshold is 60%, and assuming that among the 100 times the first scene is triggered ("5:00-8:30", "the phone is woken up"), the scene condition "Monday to Friday" is recorded 75 times, then the probability of the scene condition "Monday to Friday" and the first scene condition set occurring at the same time is 75% (greater than 60%), and the scene condition "Monday to Friday" is determined to be a candidate scene condition related to the first scene.

[0154] Furthermore, considering that after S401 is executed, the user may ignore the service recommendation, and the other recorded scenario conditions at this time cannot be used as a reference for the first scenario to a large extent. Therefore, in another implementation, the candidate scenario conditions are only screened for the case where the user activates the recommended service after S401 is executed.

[0155] Specifically, in Formula 1: num(I) is the total number of times the user activates the services in the first scene service set after the first scene is triggered multiple times; num(AB) is the total number of times scene condition set A and scene condition B occur simultaneously when the user activates the services in the first scene service set.

[0156] For example, assuming the first preset probability threshold is 80%, and assuming that after the first scenario ("5:00-8:30", "Phone is awakened") is triggered 100 times, it is recorded that the user activated the "Weather Service" 80 times. Furthermore, it is recorded that the user turned off the alarm 40 times out of the 80 times (i.e., the scenario condition "Turn off the alarm") exists. Then, the probability of the scenario condition "Turn off the alarm" occurring simultaneously with the first scenario condition set is 50% (less than 80%), and the scenario condition "Turn off the alarm" is determined not to be a candidate scenario condition related to the first scenario.

[0157] S420, the service association analysis submodule 322 obtains one or more candidate services related to the first scenario based on the service activation status collected by the terminal device, where the candidate services are services outside the first scenario service set.

[0158] Specifically, in one embodiment, in S410 , the service association analysis submodule 322 obtains services (candidate services) that are highly associated with the first scenario according to the service activation status.

[0159] Specifically, the service activation situation includes: after the terminal device recommends the first scenario service set, the user activates the operation of the services in the first scenario service set (for example, the user clicks the application icon on the recommendation card), and / or the user activates the operation of other services outside the first scenario service set (for example, the user clicks the application icon outside the recommendation card on the mobile phone interface, or the user clicks the application icon of other services outside the first scenario service set on the recommendation card).

[0160] Furthermore, in one embodiment, the terminal device executes S401 multiple times, and executes 402 after each execution of S401 to collect service activation information. The conditional collection and analysis submodule 321 performs statistical analysis on the multiple collection results of the terminal device's service activation information to obtain candidate services. The candidate services include one or more services outside the first scenario service set.

[0161] Specifically, in one embodiment, in S410 , the association relationship between the service and the first scenario is evaluated by calculating the probability that the service is enabled after the first scenario is triggered.

[0162] For example, when the first scenario is triggered, the terminal device detects that the user has activated service C, which does not belong to the first scenario service set. The activation probability of service C is P(C). When P(C) is greater than or equal to a second preset probability threshold (for example, 10%), service C is considered to have a high correlation with the first scenario.

[0163] Furthermore, in one embodiment, when the first scenario is triggered, the probability of service C being enabled is calculated based on the following formula.

[0164] P(C)=num(C) / num(I), (Formula 2)

[0165] In Formula 2: num(I) is the total number of times the first scenario is triggered; num(C) is the total number of times service C is enabled when the first scenario is triggered.

[0166] For example, assuming that after the first scenario ("5:00-8:30", "mobile phone is woken up") is triggered 100 times, it is recorded that the user clicks the calendar icon 20 times to enable the "calendar service", then the probability of the "calendar service" being enabled is 20% (greater than the preset probability threshold of 10%), and the "calendar service" is determined to be a candidate service related to the first scenario.

[0167] Furthermore, in another embodiment, the probability of the service being enabled is calculated with reference to the screened candidate scenario conditions.

[0168] Specifically, assuming that the first scenario condition set is scenario condition set A. In S410, scenario condition B is determined as a candidate scenario condition. The probability P(C|AB) of service C being activated with reference to candidate scenario condition B is calculated based on the following formula.

[0169] P(C|AB)=P(ABC) / P(AB), (Equation 3)

[0170] In Formula 3: P(AB) is the probability that scenario condition set A and scenario condition B occur simultaneously; P(ABC) is the probability that scenario condition set A, scenario condition B, and enabled service C occur simultaneously.

[0171] S430 , the click estimation feedback module 323 updates the first scenario service combination according to the candidate scenario conditions obtained in S410 and the candidate services obtained in S420 , and generates a second scenario service combination.

[0172] The second scenario service combination corresponds to the second scenario, which is a subordinate scenario of the first scenario. The second scenario service combination includes a second scenario condition set (scenario conditions corresponding to the second scenario) and a second scenario service set (services corresponding to the second scenario).

[0173] The second scenario condition set includes one or more scenario conditions, and the second scenario service set includes one or more services. The scenario conditions in the second scenario condition set are independent of each other.

[0174] In one embodiment, in S430, updating the first scenario service combination may be updating only the first scenario condition set of the first scenario service combination to generate the second scenario condition set, that is, the second scenario service combination includes the second scenario condition set and the first scenario service set.

[0175] In another embodiment, in S430, updating the first scenario service combination may be updating only the first scenario service set of the first scenario service combination to generate the second scenario service set. That is, the second scenario service combination includes the first scenario condition set and the second scenario service set.

[0176] In another embodiment, in S430, updating the first scenario service combination may be updating the first scenario service set and the first scenario service set of the first scenario service combination to generate the second scenario service set and the second scenario service set. That is, the second scenario service combination includes the second scenario condition set and the second scenario service set.

[0177] Specifically, in one embodiment, S430 includes:

[0178] S431 : Generate a second scene condition set based on the first scene condition set according to the candidate scene conditions acquired in S410 .

[0179] and / or,

[0180] S432: Generate a second scenario service set based on the first scenario service set according to the candidate services acquired in S420.

[0181] Specifically, in an implementation of S431 , the candidate scene conditions acquired in S410 are added to the first scene condition set to generate a second scene condition set.

[0182] In an implementation of S432, the candidate services acquired in S420 are added to the first scenario service set to generate a scenario service set.

[0183] In another implementation of S431, a confidence determination is performed on the candidate scene conditions. When the confidence of the candidate scene conditions reaches a preset first confidence threshold, the candidate scene conditions are added to the first scene condition set.

[0184] Confidence is a statistical concept. In the present invention, confidence means that a limited number of conditional association analysis results can accurately represent / predict the probability that relevant scenario conditions will occur when a user uses a certain service.

[0185] It should be noted here that those skilled in the art can set the decision logic for performing confidence determination on candidate scene conditions according to actual needs, and the embodiments of the present application do not make specific limitations on this.

[0186] For example, in one embodiment, the association analysis of scene conditions is not performed only once, but multiple association analyses of scene conditions are performed based on the user's clicks and operation behaviors; each scene condition association analysis calculates the correlation degree for the permutations and combinations of multiple scene conditions; if the correlation degree of a certain scene condition permutation and combination exceeds the correlation degree threshold of the existing scene conditions, it is recorded once and accumulated.

[0187] The number of times the scene condition permutation combination correlation exceeds the existing scene condition correlation threshold is set as the confidence value of the scene condition permutation combination. When the confidence value reaches a preset first confidence threshold, the scene condition permutation combination is added to the first scene condition set.

[0188] In another implementation of S432, a confidence determination is performed on the candidate service, and when the confidence of the candidate service reaches a preset second confidence threshold, the candidate service is added to the first scenario service set.

[0189] The confidence determination in S432 may refer to S431.

[0190] Specifically, in one embodiment, the confidence value of the candidate service is generated based on the overall click usage, location reporting, information feedback of the candidate service, and the estimated training of the model.

[0191] In another implementation of S432, service recommendations are made using the first scenario condition set or the second scenario condition set as scenario trigger conditions, and the first scenario service set and the candidate services obtained in S420 as recommendation content (the service recommendation can be performed online by the server, or offline by the terminal device). During the service recommendation process, data collection is performed, and the estimated feedback module 323 is clicked to eliminate and update the services in the first scenario service set based on the collected data (the candidate services obtained in S420 are added to the first scenario service set, and / or the original services in the first scenario service set are eliminated) to generate a second scenario service combination.

[0192] Specifically, Figure 5 Shown is a partial method flow chart of a scene service combination generation method according to an embodiment of the present application.

[0193] In one embodiment, S432 includes:

[0194] S700: When the first scenario condition set or the second scenario condition set is satisfied, recommend services in the first scenario service set and the candidate services obtained in S420.

[0195] S710: Collect activation status of services in the first scenario service set and candidate services obtained in S420.

[0196] For example, a user clicks on a service application icon in a recommendation card.

[0197] S711 , based on the collected service activation status, the candidate services acquired in S420 are added to the first scenario service set, and / or the original services in the first scenario service set are eliminated to generate a second scenario service combination.

[0198] Specifically, in one embodiment, the click prediction feedback module 323 determines whether to add the candidate service obtained in S420 to the first scenario service set and / or eliminate the original service in the first scenario service set based on the click rate of the service application icon in the recommendation card.

[0199] For example, when the click rate of a candidate service is higher than a preset first click rate threshold, the candidate service is added to the first scenario service set.

[0200] For another example, when the click rate of the candidate service is higher than that of the original services in the first scenario service set, the candidate service is added to the first scenario service set.

[0201] For another example, when the click rate of a certain service originally in the first scenario service set is lower than a preset first click rate threshold, the service is removed from the first scenario service set.

[0202] For another example, when the click rate of a certain service in the first scenario service set is lower than that of the candidate service, the service is removed from the first scenario service set.

[0203] Furthermore, in one embodiment, in order to exclude candidate services that have a higher click-through rate than the original services in the first scenario service set (i.e., are irrelevant to the scenario), the improvement in the click-through rate after recommending the candidate service compared to the click-through rate of the non-recommended candidate service is calculated. If the improvement is < 2 times, it is considered small, and the candidate service is not added to the first scenario service set.

[0204] After S430, the scene service combination generating apparatus sends the second scene service combination to the terminal device, and the terminal device executes S403.

[0205] S403: Recommend services based on the second scenario service combination.

[0206] For example, in one embodiment, a first scenario service combination includes: a first scenario condition set: "5:00-8:30", "Mobile phone is awakened", and the first scenario service set of the first scenario service combination includes "Weather service". A second scenario service combination generated based on the first scenario service combination includes: a second scenario condition set ("5:00-8:30", "Mobile phone is awakened", "At home", "Workday") and a second scenario service set ("Weather service", "News service").

[0207] Figure 6 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application.

[0208] When the mobile phone is at the user's home and is woken up at 8:00 on a weekday, it displays the following Figure 6 The screen shown.

[0209] like Figure 6 As shown, 801 is a recommendation card, 802 is an application card for "weather service", and 803 is an application icon for "news service". The recommendation card 801 also includes fixed recommended services that are not related to the scene: video, music, email, and browser.

[0210] According to the scenario service combination generation method of the embodiment of the present application, the pre-generated scenario service combination is updated based on the data collected on-site by the terminal device, so that a scenario service combination that better matches the user's actual scenario needs can be obtained.

[0211] According to the service recommendation method of the embodiment of the present application, the pre-generated scenario service combination is updated based on the data collected on-site by the terminal device, and a scenario service combination that better matches the user's actual scenario needs is obtained for service recommendation. Services that match the user's needs can be recommended to the user, thereby improving the user experience of service recommendation.

[0212] Figure 7 Shown is a data flow diagram of a scenario service combination generation method according to an embodiment of the present application.

[0213] The first scenario service combination is generated based on the sharing intention data 800 of the third party.

[0214] The first scenario service combination corresponds to the first scenario, and includes a first scenario condition set (scenario conditions corresponding to the first scenario) and a first scenario service set (services corresponding to the first scenario).

[0215] The first scenario service combination 801 is saved to the database 811 .

[0216] The first scenario service combination 801 in the database 811 is called to perform service recommendation. Specifically, the scenario changes are monitored, and when the first scenario is triggered, the service 802 in the first scenario service set is recommended.

[0217] When the first scene is triggered, scene condition data 803 is collected.

[0218] After recommending the services 802 in the first scenario service set, the service activation status 804 is collected based on the user's click.

[0219] The scene condition data 803 and the service activation status 804 are saved to the database 812 .

[0220] Periodic data mining is performed on the scenario condition data 803 and the service activation status 804 in the database 812 to determine candidate scenario conditions and candidate services 805.

[0221] The candidate scenario conditions and candidate services 805 are saved in the database 813 .

[0222] Based on the candidate scenario conditions in the database 813 and the candidate services 805 , online recommendations are made, and application click rates 806 are collected.

[0223] According to the candidate scenario conditions and candidate services 805 in the database 813 , and the application click rate 806 , a second scenario service combination 807 is generated.

[0224] Taking a specific application scenario as an example, takeaway platform A shares the intention sharing data (see Table 1). Based on the intention sharing data, the first scenario service combination is generated: the first scenario condition set (11:00-12:00); the first scenario service set (takeaway A application).

[0225] The service recommendation is made based on the service combination of the first scenario. When the time is between 11:00 and 12:00, the takeaway A application is recommended.

[0226] Figure 8 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application.

[0227] At 11:20 on a certain day, the phone displays Figure 8 The screen shown.

[0228] like Figure 8 As shown, 1001 is a recommendation card, and 1002 is the application icon of "Takeaway A Application". The recommendation card 1001 also includes fixed recommended services that are not related to the scene: video, music, email, and browser.

[0229] When recommending takeaway A app between 11:00 and 12:00, scenario condition data and service activation status data are collected.

[0230] By analyzing the scenario condition data and the service activation data, after the takeaway app A is recommended and the takeaway app A is activated, the probability of the scenario condition (at the company) being present is higher than the first preset probability value. Therefore, the scenario condition (at the company) is determined to be a candidate scenario condition.

[0231] By analyzing the scenario condition data and the service activation data, the probability that the food delivery app B is activated after the food delivery app A is recommended is a second preset probability value. Therefore, the scenario condition (at the company) is determined as a candidate scenario condition.

[0232] Make service recommendations. When the time is met (11:00-12:00, at the company), recommend takeaway app A and takeaway app B, and collect service click-through rate data.

[0233] The click-through rate of Takeaway B app is higher than that of Takeaway A app, so Takeaway A app is eliminated. Generate the second scenario service combination: the second scenario condition set (11:00-12:00, at the company); the second scenario service set (Takeaway B app).

[0234] Figure 9 Shown is a schematic diagram of a mobile phone interface according to an embodiment of the present application.

[0235] At 11:10 one day at the company, the phone displayed the following Figure 9 The screen shown.

[0236] like Figure 9 As shown, 1101 is a recommendation card, and 1102 is the application icon of "Takeaway B Application". The recommendation card 1101 also includes fixed recommended services that are not related to the scene: video, music, email, and browser.

[0237] In the description of the embodiments of the present application, for the convenience of description, the device is described as being divided into various modules according to their functions. The division of each module is merely a division of logical functions. When implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0238] Specifically, the device proposed in the embodiment of the present application can be fully or partially integrated into a physical entity during actual implementation, or it can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the detection module can be a separately established processing element, or it can be integrated in a chip of an electronic device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. During the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0239] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0240] An embodiment of the present application also proposes an electronic device. The electronic device may be a terminal device, a server device connected to the terminal device, or other device connected to the terminal device. For example, the electronic device may be a device for constructing Figure 1 The device of the scene service combination generating device shown. For another example, the electronic device may be Figure 2 The terminal device in the method flow shown. For another example, the electronic device may be Figure 2 In the method flow shown, it is used to construct Figure 1 The server device of the scene service combination generating device shown.

[0241] Figure 10 FIG. 1 is a structural diagram of an electronic device according to an embodiment of the present application.

[0242] like Figure 10 As shown, the electronic device 2500 includes a memory 2502 for storing computer program instructions and a processor 2501 for executing program instructions, wherein, when the computer program instructions are executed by the processor 2501, the electronic device 2500 is triggered to execute the method steps as described in the embodiments of the present application.

[0243] Specifically, in one embodiment of the present application, the above-mentioned one or more computer programs are stored in the above-mentioned memory 2502, and the above-mentioned one or more computer programs include instructions. When the above-mentioned instructions are executed by the above-mentioned electronic device 2500, the above-mentioned electronic device 2500 executes the method steps described in the embodiment of the present application.

[0244] It is understood that the structural description of the electronic device 2500 in the embodiment of the present application does not constitute a specific limitation on the electronic device 2500. In other embodiments of the present application, the electronic device 2500 may include other components besides the processor 2501 and the memory 2502.

[0245] The processor 2501 may be a device on a chip (SOC), and the processor 2501 may include a central processing unit (CPU), and may further include other types of processors.

[0246] The processor involved in processor 2501 may include, for example, a CPU, a DSP, a microcontroller, or a digital signal processor, and may also include a GPU, an embedded neural network processor (NPU), and an image signal processor (ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as ASICs, or one or more integrated circuits for controlling the execution of the program of the technical solution of this application. In addition, the processor may have the function of operating one or more software programs, and the software programs may be stored in a storage medium.

[0247] The processor 2501 may include one or more processing units. For example, the processor may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent components or integrated into one or more processors. In some embodiments, the electronic device 2500 may also include one or more processors 2501. The controller may generate an operation control signal based on the instruction opcode and the timing signal to complete the control of instruction fetching and execution.

[0248] In some embodiments, the processor 2501 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM card interface, and / or a USB interface, etc. Among them, the USB interface is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface can be used to connect a charger to charge the electronic device, and can also be used to transmit data between the electronic device and peripheral devices.

[0249] Electronic device 2500 may also include an external memory interface for connecting an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device. The external memory card communicates with processor 2501 via the external memory interface to implement data storage. For example, files such as music and videos can be stored on the external memory card.

[0250] Memory 2502 may include a code storage area and a data storage area. The code storage area may store an operating system. The data storage area may store data created during the use of electronic device 2500. Furthermore, memory 2502 may include high-speed random access memory and non-volatile memory, such as one or more disk storage components, flash memory components, and universal flash storage (UFS).

[0251] The memory 2502 may be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any computer-readable medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0252] The processor 2501 and the memory 2502 may be combined into one processing device, or more commonly, they may be independent components.

[0253] Optionally, the devices, apparatuses, and modules described in the embodiments of the present application may be implemented by computer chips or entities, or by products having certain functions.

[0254] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0255] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of this application.

[0256] Specifically, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer-readable storage medium is run on a computer, the computer executes the method provided in the embodiment of the present application.

[0257] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program product is run on a computer, it enables the computer to execute the method provided in the embodiment of the present application.

[0258] The description of the embodiments in this application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), and computer program products according to the embodiments of the application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0259] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0260] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0261] It should also be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0262] In the embodiments of the present application, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, commodity, or apparatus comprising the element.

[0263] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0264] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiments.

[0265] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments of the present application can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0266] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0267] The above description is merely a specific embodiment of the present application. Any person skilled in the art may easily conceive of variations or substitutions within the technical scope disclosed in this application, and such variations or substitutions shall be within the scope of protection of this application. The scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. A method for recommending services, characterized in that: The method is applied to a terminal device, and the method includes: Acquire a first scenario service combination, where the first scenario service combination includes a first scenario condition set and a first scenario service set, where the first scenario condition set includes one or more scenario conditions, and the first scenario service set includes one or more services; Recommending services based on the first scenario service combination includes recommending services in the first scenario service set to a user of the terminal device when the terminal device meets a scenario condition in the first scenario condition set; If the terminal device satisfies a scenario condition in the first scenario condition set, collecting one or more scenario conditions other than the first scenario condition set on the terminal device; and / or, after recommending a service in the first scenario service set to a user of the terminal device, obtaining a service activation status based on an operation by the user to activate the service on the terminal device; Obtain a second scenario service combination, and perform service recommendations based on the second scenario service combination, wherein: The second scenario service combination includes a second scenario condition set and / or a second scenario service set; The second scene condition set is a scene condition set generated according to the first scene condition set and one or more candidate scene conditions; The one or more candidate scene conditions are scene conditions related to the first scene condition set obtained based on the one or more other scene conditions; The second scenario service set is a scenario service set generated according to the first scenario service set and one or more candidate services; The one or more candidate services are services related to the first scenario condition set acquired based on the service activation status.

2. The method according to claim 1, characterized in that The first scenario service combination is a scenario service combination generated according to the intention sharing data.

3. The method according to claim 1, characterized in that The one or more other scene conditions include a first scene condition; The acquiring, according to the one or more other scenario conditions, one or more candidate scenario conditions related to the first scenario condition set includes: A first probability is calculated. When the first probability is greater than or equal to a first preset probability value, the first scene condition is the candidate scene condition, wherein: The first probability is the probability of the first scene condition existing when the scene conditions in the first scene condition set are met.

4. The method according to claim 1, wherein The one or more other scene conditions include a first scene condition; The acquiring, according to the one or more other scenario conditions, one or more candidate scenario conditions related to the first scenario condition set includes: A second probability is calculated. When the second probability is greater than or equal to a second preset probability value, the first scene condition is the candidate scene condition, wherein: The second probability is the probability of existence of the first scenario condition when the services in the first scenario service set are enabled after the services in the first scenario service set are recommended.

5. The method according to claim 1, characterized in that The acquiring, according to the service activation status, one or more candidate services related to the first scenario condition set includes: A third probability is calculated. When the first probability is greater than or equal to a third preset probability value, the first service is the candidate service, wherein: The first service is a service other than the first scenario service set; The third probability is the probability that the first service is enabled when a scenario condition in the first scenario condition set is met.

6. The method according to claim 1, characterized in that The acquiring, according to the service activation status, one or more candidate services related to the first scenario condition set includes: A fourth probability is calculated. When the first probability is greater than or equal to a fourth preset probability value, the first service is the candidate service, wherein: The first service is a service other than the first scenario service set; The fourth probability is the probability that the first service is enabled when the first scenario condition set and the candidate scenario condition are met.

7. The method according to claim 1, wherein: Generating a second scene condition set based on the first scene condition set and the one or more candidate scene conditions includes: performing a confidence assessment on the candidate scene conditions, and when the confidence of the candidate scene conditions reaches a preset first confidence threshold, adding the candidate scene conditions to the first scene condition set to generate the second scene condition set; and / or, The generating of the second scenario service set based on the first scenario service set and the one or more candidate services includes: performing confidence determination on the candidate services, and when the confidence of the candidate services reaches a preset second confidence threshold, filling the candidate services into the first scenario service set to generate the second scenario service set.

8. The method according to any one of claims 1 to 7, characterized in that The one or more candidate services include a first candidate service; Generating a second scenario service set according to the first scenario service set and the one or more candidate services includes: When a scenario condition in the first scenario condition set or the second scenario condition set is met, recommending services in the first scenario service set and / or the first candidate service; Collecting activation status of the first candidate service and / or activation status of services in the first scenario service set; According to the activation status of the first candidate service and / or the activation status of the services in the first scenario service set, the first candidate service is added to the first scenario service set, or the first candidate service is not added to the first scenario service set to generate the second scenario service set.

9. The method according to claim 8, characterized in that: If the click-through rate of the application icon of the first candidate service is higher than the click-through rate of the application icons of the services in the first scenario service set, adding the first candidate service to the first scenario service set to generate the second scenario condition set; or, When the click rate of the application icon of the first candidate service is higher than a preset first click rate threshold, the first candidate service is added to the first scenario service set to generate the second scenario condition set.

10. The method according to claim 8 or 9, characterized in that The generating a second scenario service set according to the first scenario service set and the one or more candidate services further includes: calculating a first click-through rate, where the first click-through rate is a click-through rate of an application icon of the first candidate service when the first candidate service is not recommended when a scenario condition in the first scenario condition set or the second scenario condition set is met; calculating a second click-through rate, where the second click-through rate is a click-through rate of an application icon of the first candidate service when the first candidate service is recommended when a scenario condition in the first scenario condition set or a scenario condition in the second scenario condition set is met; When the improvement degree of the second click-through rate compared with the first click-through rate exceeds a preset improvement degree threshold, the first candidate service is added to the first scenario service set to generate the second scenario condition set.

11. The method according to claim 8, characterized in that The first scenario service set includes a second service; The generating a second scenario service set according to the first scenario service set and the one or more candidate services further includes: According to the activation status of the second service, the second service is deleted from the first scenario service set, or the second service in the first scenario service set is retained to generate the second scenario service set.

12. The method according to claim 11, wherein: When the click rate of the application icon of the second service is lower than a preset second click rate threshold, the second service in the first scenario service set is deleted, and the second scenario condition set is generated.

13. A method for generating a scene service combination, characterized in that: The method is applied to an electronic device, and includes: Acquire a first scenario service combination, where the first scenario service combination includes a first scenario condition set and a first scenario service set, where the first scenario condition set includes one or more scenario conditions, and the first scenario service set includes one or more services; Obtaining one or more other scenario conditions and / or service activation status, wherein: the other scenario conditions are scenario conditions other than the first scenario condition set collected on the terminal device when the terminal device satisfies the scenario conditions in the first scenario condition set; the service activation status is the service activation status obtained based on the user's operation of activating the service on the terminal device after recommending a service in the first scenario service set to the user of the terminal device when the terminal device satisfies the scenario conditions in the first scenario condition set; Acquire one or more candidate scenario conditions related to the first scenario condition set based on the one or more other scenario conditions; and / or acquire one or more candidate services related to the first scenario condition set based on the service activation status; Generate a second scenario condition set based on the first scenario condition set and the one or more candidate scenario conditions; and / or generate a second scenario service set based on the first scenario service set and the one or more candidate services; A second scenario service combination is generated, where the second scenario service combination includes a second scenario condition set and / or a second scenario service set.

14. An electronic device, characterized in that: The electronic device comprises a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to perform the method steps of any one of claims 1 to 12 or claim 13.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 12 or claim 13.

Images