WO2024093967A1 - 一种推荐方法以及相关设备 - Google Patents

一种推荐方法以及相关设备 Download PDF

Info

Publication number
WO2024093967A1
WO2024093967A1 PCT/CN2023/128170 CN2023128170W WO2024093967A1 WO 2024093967 A1 WO2024093967 A1 WO 2024093967A1 CN 2023128170 W CN2023128170 W CN 2023128170W WO 2024093967 A1 WO2024093967 A1 WO 2024093967A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
matching rule
user
application
electronic device
Prior art date
Application number
PCT/CN2023/128170
Other languages
English (en)
French (fr)
Inventor
王瑞
盛立国
王翃宇
宁明印
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024093967A1 publication Critical patent/WO2024093967A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions

Definitions

  • the present application relates to the field of artificial intelligence, and in particular to a recommendation method and related equipment.
  • Artificial Intelligence is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
  • artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making. Using artificial intelligence technology for personalized recommendations is a common application of artificial intelligence.
  • the electronic device needs to collect detailed description data of the user and upload the description data of the user to the cloud.
  • the cloud determines the application or service recommended to the user based on the description data of the user and displays it to the user through the electronic device.
  • the embodiments of the present application provide a recommendation method and related devices, which obtain second information based on identification information of a first matching rule, and then obtain applications and/or services recommended to the user.
  • the first matching rule is a rule that matches the value of the user's characteristic information, which not only realizes personalized determination of applications and/or services recommended to the user, but also avoids sending detailed description data of the user to the first communication device, thereby avoiding the leakage of the user's privacy information.
  • the embodiment of the present application provides a recommendation method, which can apply artificial intelligence technology to the field of personalized recommendation.
  • the method includes: multiple matching rules and identification information of each matching rule can be deployed on the electronic device. After determining the value of the user's characteristic information, a first matching rule that matches the value of the user's characteristic information is determined from the multiple matching rules, and the identification information of the first matching rule is obtained; wherein each matching rule in the multiple matching rules is used to indicate the value range of each characteristic information in at least one characteristic information of the user.
  • the electronic device sends a first message to the server, wherein the first message includes the identification information of the first matching rule, and the first information is used for the server to obtain the second information.
  • the electronic device receives the second information sent by the server, the second information is used to indicate the first application and the first service, and recommends the first application and/or the first service on the display unit, for example, "recommending the first application and/or the first service on the display unit” can be understood as displaying the access interface of the first application and/or the first service on the display unit.
  • each application can provide one or more services to the user, and "service” can also be called “atomic service", "application service” or other names, etc.
  • a service refers to a service with an independent entrance in the application.
  • a shopping application may include "product browsing", “shopping cart", “payment” or other services; for another example, the "scan” function is also a service, etc., and the examples are not exhaustive here.
  • the electronic device can obtain the identification information of the first matching rule that matches the value of the user's characteristic information, and send the identification information of the first matching rule to the server, so that the server can obtain the second information based on the identification information of the first matching rule, and the electronic device determines the application and/or service recommended to the user based on the received second information. Since the first matching rule is a matching rule that matches the value of the user's characteristic information, personalized determination of the application and/or service recommended to the user is achieved, and only the identification information of the first matching rule needs to be sent to the second communication device, thereby avoiding sending the user's detailed description data to the server and avoiding the leakage of the user's privacy information.
  • the first matching rule includes at least one matching condition, each matching condition indicates a value range of a characteristic information of a user, and the value of the characteristic information of the user satisfies all the matching conditions in the first matching rule; or, the total number of matching conditions in the first matching rule is a first value, the number of matching conditions satisfied by the value of the characteristic information of the user in at least one matching condition included in the first matching rule is a second value, and the ratio between the second value and the first value is greater than or equal to a first threshold value, for example, the value of the first threshold may be 90%, 85%, 80% or other values.
  • the first information also includes identification information of a second matching rule
  • the second matching rule is included in the above-mentioned multiple matching rules
  • the second matching rule is a matching rule that does not match the value of the user's characteristic information.
  • the first information sent by the electronic device to the server includes not only the identification information of the first matching rule, but also the identification information of the second matching rule, so that the electronic device cannot determine which matching rule's identification information is hit by the server and which matching rule's identification information is not hit by the server, which is conducive to increasing the difficulty of the electronic device to reversely infer the characteristic information of the user of the server based on the identification information of the matching rule, so as to further protect the user's privacy data.
  • the second information is also used to indicate the correspondence between the identification information of the first matching rule and at least one application and/or service, and the correspondence between the identification information of the second matching rule and at least one application and/or service; for example, the second information may include the correspondence between the identification information of the first matching rule and the information of the application and/or service, and the correspondence between the identification information of the second matching rule and the information of the application and/or service.
  • the information of the application and/or service may include identification information of the application and/or service, for example, the identification information of the application and/or service may be the name of the application, the icon of the application, the name of the service, the icon of the service, the identification number of the application or service, or other identification information that can uniquely point to an application or service, etc.
  • the first application and/or the first service is the application and/or service corresponding to the identification information of the first matching rule among the multiple applications and/or services indicated by the second information.
  • the electronic device can also determine the first application and/or the first service recommended to the user based on the identification information of the first matching rule and the second information.
  • the electronic device can select one or more first applications and/or first service information corresponding to the identification information of the first matching rule from the information of the multiple applications and/or services included in the second information based on the identification information of the first matching rule.
  • the identification information of the second matching rule is added to the first information, and the server cannot determine which identification information in the first information is the identification information of the rule that matches the user's characteristic information, further increasing the difficulty for the server to reversely infer the user's characteristic information; since the identification information of the second matching rule is added to the first information, correspondingly, the second information includes information on applications and/or services corresponding to the identification information of the second matching rule, the electronic device can determine the applications and/or services that ultimately need to be recommended to the user based on the identification information of the first matching rule and the second information, thereby facilitating the accurate display of objects to the user while ensuring the security of the user's privacy data.
  • the method is applied to an electronic device, the matching rules deployed in the electronic device include a first matching rule, and the matching rules deployed in the electronic device and/or the identification information of the matching rules deployed in the electronic device are updateable.
  • the matching rules deployed in the electronic device and/or the identification information of the matching rules deployed in the electronic device are set to be updateable, which is not only conducive to more accurately recommending applications and/or services that may be of interest to users, but also conducive to improving the utilization rate of computer resources on the electronic device; for example, when the click rate of the application and/or service recommended based on a certain matching rule is too low, the matching rule can be deleted, which not only reduces the storage resources occupied by the matching rules, but also the electronic device no longer needs to perform matching operations on the deleted matching rules, reducing the consumption of processor resources.
  • the characteristic information of the user includes one or more of the following: the user's portrait information, the user's behavior information when using the application, the information of the electronic device used by the user, or the information of other electronic devices connected to the electronic device in communication, etc., which are not exhaustive here.
  • the user's portrait information may include any one or more of the following information: name, gender, age, birthday, current location, home location, company location, work and rest time, commuting method, sports hobbies or other information, etc.
  • the behavior information of the user when using the application may include any one or more of the following information: the user's commonly used applications, the average number of times each application in the n most used applications has been used in the last X days, the music application preferred by the user in multiple music applications, the video application preferred by the user in multiple video applications, the food application preferred by the user in multiple food applications, the shopping application preferred by the user in multiple shopping applications, etc., n is an integer greater than or equal to 1, and X is a positive number.
  • the information of the electronic device used by the user may include any one or more of the following information of the electronic device: device model, device type, operating system type, operating system version number, electronic device ID or other information, etc.
  • the information of other electronic devices connected to the electronic device in communication may include the information of other electronic devices connected to the electronic device in the near field, etc., which are not exhaustive here.
  • information on what the user's characteristic information specifically represents is provided, which is conducive to improving the feasibility of this solution.
  • the present application provides a recommendation method that can apply artificial intelligence technology to the field of personalized recommendation.
  • the method includes: The server receives first information sent by an electronic device, the first information includes identification information of a first matching rule, the first matching rule is one of multiple matching rules, wherein each matching rule of the multiple matching rules is used to indicate a value range of each characteristic information of at least one characteristic information of a user, and the first matching rule is used to indicate the value of the characteristic information of the user of the electronic device.
  • the server can determine second information based on the first information, and send the second information to the electronic device, wherein the second information is used to indicate the first application and/or the first service.
  • the server determines the second information based on the first information, which may include: the server may be configured with a correspondence between the identification information of each matching rule in the identification information of multiple matching rules and the information of the application and/or service, and the identification information of the aforementioned multiple matching rules includes the identification information of each matching rule in the first information.
  • the server obtains the information of the application and/or service corresponding to the identification information of at least one matching rule in the first information based on the identification information of each matching rule in the first information and the aforementioned correspondence; wherein the second information includes the information of the application and/or service corresponding to the identification information of the matching rule in the first information, and the information of the application and/or service corresponding to the identification information of the matching rule in the first information includes the information of the first application and/or the first service; for example, the information of the application and/or service may include the identification information of the application and/or service.
  • the method further includes: the server obtains fourth information, the fourth information including information associated with at least one application and/or service and/or group portrait information corresponding to the user.
  • the server may be configured with the type of information associated with at least one application and/or service, and the server may obtain information associated with the aforementioned at least one application and/or service according to the type of information associated with at least one application and/or service.
  • the server may determine the identification information of the user; the server may obtain group portrait information corresponding to the user according to the user's account information.
  • the information associated with the application and/or service may include weather information in the area where the user is located, express information of goods purchased by the user through one or more applications, preferential activity information or other information associated with the application and/or service.
  • the group portrait information includes portrait information of a class of users, for example, the group portrait information may include the age group of the user, the gender of the user, the type of consumption level of the user or other group portrait information.
  • the server determines the second information according to the first information, which may include: the server determines the second information according to the fourth information and the first information.
  • the server not only utilizes the first information in the process of determining the application and/or service recommended to the user, but also utilizes the information associated with the application and/or service and/or the group portrait information corresponding to the user, which is conducive to a fuller understanding of the object to be recommended and the current user, and is conducive to determining the object that the current user is interested in, thereby increasing the probability of accurately recommending the object to the user; in addition, when the electronic device has not yet collected the user's characteristic information, or when the electronic device can only collect a small amount of information about the user, then the acquired group portrait information can assist the server in determining an object that is more in line with the user's expectations.
  • the matching rule deployed in the electronic device includes a first matching rule
  • the matching rule deployed in the electronic device and/or identification information of the matching rule deployed in the electronic device is updateable.
  • the scenario in which the server updates the set of matching rules deployed on the electronic device may include any one or more of the following:
  • the electronic device updates the matching rule set on the server at a fixed time point; for example, after the matching rule set is initially deployed on the electronic device, the server may perform an update operation on the matching rule set on the electronic device at an interval of a first time period, and the number of types of information corresponding to the updated matching rule set is greater than the number of types of information corresponding to the initial matching rule set; or
  • the electronic device updates the matching rule set on the server at a preset frequency; or, when the object to be recommended changes, the electronic device updates the matching rule set on the server; or,
  • the electronic device obtains the click rate of the object that needs to be recommended based on each matching rule. If the click rate corresponding to a matching rule is lower than the second threshold, it is determined that the aforementioned matching rule needs to be deleted. In this scenario, the matching rule set on the electronic device will also be updated.
  • the matching rule set on the electronic device includes the matching rules deployed in the electronic device and/or identification information of the matching rules.
  • the initially configured matching rule set involves fewer types of information about the user. After the first time period has passed, the electronic device is able to collect more types of information about the user. In this way, the matching rule set on the electronic device can be updated.
  • the updated matching rule set involves more types of information about the user, so that the matching degree between the matching rule set deployed on the electronic device and the information currently obtained by the electronic device is conducive to improving the accuracy of the identification information process of the first matching rule.
  • an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored.
  • the computer-readable storage medium is run on a computer, the computer executes the recommendation method described in the first aspect or the second aspect above.
  • an embodiment of the present application provides an electronic device, including a processor and a memory, wherein the processor is coupled to the memory, the memory is used to store programs; the processor is used to execute the programs in the memory, so that the communication device executes the recommended method described in the first aspect above.
  • an embodiment of the present application provides a server, including a processor and a memory, wherein the processor is coupled to the memory, the memory is used to store programs; the processor is used to execute the programs in the memory, so that the communication device executes the recommended method described in the second aspect above.
  • an embodiment of the present application provides a computer program product, which includes a program.
  • the program When the program is run on a computer, the computer executes the recommendation method described in the first aspect or the second aspect above.
  • the present application provides a chip system, which includes a processor for supporting the implementation of the functions involved in the first aspect or the second aspect, for example, sending or processing the data and/or information involved in the above method.
  • the chip system also includes a memory, which is used to store program instructions and data necessary for the electronic device or communication device.
  • the chip system can be composed of chips, or it can include chips and other discrete devices.
  • FIG1 is a schematic diagram of a structure of an artificial intelligence main framework provided in an embodiment of the present application.
  • FIG2 is a diagram of an application scenario of the recommendation method provided in an embodiment of the present application.
  • FIG3 is a schematic diagram of a flow chart of a recommended method provided in an embodiment of the present application.
  • FIG4 is another schematic flow chart of a recommended method provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of an interface for displaying an object to a user provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of another interface for displaying an object to a user provided in an embodiment of the present application.
  • FIG7 is a schematic diagram of another interface for displaying an object to a user provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of a structure of a server provided in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
  • Figure 1 shows a structural diagram of the main framework of artificial intelligence.
  • the following is an explanation of the above artificial intelligence theme framework from the two dimensions of "intelligent information chain” (horizontal axis) and “IT value chain” (vertical axis).
  • the "intelligent information chain” reflects a series of processes from data acquisition to processing. For example, it can be a general process of intelligent information perception, intelligent information representation and formation, intelligent reasoning, intelligent decision-making, intelligent execution and output. In this process, the data has undergone a condensation process of "data-information-knowledge-wisdom".
  • the "IT value chain” reflects the value that artificial intelligence brings to the information technology industry from the underlying infrastructure of human intelligence, information (providing and processing technology implementation) to the industrial ecology process of the system.
  • the infrastructure provides computing power support for the artificial intelligence system, enables communication with the outside world, and is supported by the basic platform. It communicates with the outside world through sensors; computing power is provided by smart chips, which can specifically use hardware acceleration chips such as central processing unit (CPU), embedded neural network processor (NPU), graphics processing unit (GPU), application specific integrated circuit (ASIC) or field programmable gate array (FPGA);
  • the basic platform includes distributed computing frameworks and networks and other related platform guarantees and support, which can include cloud storage and computing, interconnected networks, etc.
  • sensors communicate with the outside world to obtain data, and these data are provided to the smart chips in the distributed computing system provided by the basic platform for calculation.
  • the data on the upper layer of the infrastructure is used to represent the data sources in the field of artificial intelligence.
  • the data involves graphics, images, voice, text, and IoT data of traditional devices, including business data of existing systems and perception data such as force, displacement, liquid level, temperature, and humidity.
  • Data processing usually includes data training, machine learning, deep learning, search, reasoning, decision-making and other methods.
  • machine learning and deep learning can symbolize and formalize data for intelligent information modeling, extraction, preprocessing, and training.
  • Reasoning refers to the process of simulating human intelligent reasoning in computers or intelligent systems, using formalized information to perform machine thinking and solve problems based on reasoning control strategies. Typical functions are search and matching.
  • Decision-making refers to the process of making decisions after intelligent information is reasoned, usually providing functions such as classification, sorting, and prediction.
  • some general capabilities can be further formed based on the results of the data processing, such as an algorithm or a general system, for example, translation, text analysis, computer vision processing, speech recognition, image recognition, etc.
  • Smart products and industry applications refer to the products and applications of artificial intelligence systems in various fields. They are the encapsulation of the overall artificial intelligence solution, which productizes intelligent information decision-making and realizes practical applications. Its application areas mainly include: smart terminals, smart manufacturing, smart transportation, smart homes, smart medical care, smart security, autonomous driving, smart cities, etc.
  • This application can be applied to application scenarios that require personalized recommendations in various fields.
  • the following will introduce multiple application scenarios that are implemented in products.
  • the smart terminal in the field of smart terminals, the smart terminal can select personalized recommended applications and/or services for users from multiple installed applications, and display the access interface of the aforementioned applications and/or services to the user. The user can quickly access the application and/or service through the aforementioned access interface.
  • each application can provide one or more services to the user, and "service” can also be called “atomic service”, "application service” or other names.
  • a service refers to a service with an independent entrance in the application.
  • a shopping application can include "product browsing”, “shopping cart", “payment” or other services; for example, the "scan” function is also a service; for example, the access interface of a coupon is also a service, etc.
  • the examples here are only for the convenience of understanding the concept of service and are not used to limit this solution.
  • FIG. 2 is an application scenario diagram of the recommended method provided in an embodiment of the present application.
  • the mobile phone displays three application access interfaces and one service access interface to the user in a personalized manner through the area shown in 201 on the display interface.
  • the three applications are music application A1, video application A2, and shopping application A3, and the one service is a “scan” function.
  • the example in FIG. 2 is only for the convenience of understanding the present solution and is not used to limit the present solution.
  • the video application when a user uses a video application, the video application can show the user videos that the user may be interested in in a personalized way; or, when a user uses a music application, the video application can recommend songs that the user may be interested in in a personalized way; or, when a user uses a shopping application, the shopping application can recommend products that the user may be interested in in a personalized way; or, when a user uses an application such as a game collection, the application can recommend games that the user may be interested in in a personalized way.
  • a refrigerator in the field of smart homes, can recommend recipes to the user in a personalized way, etc. All application scenarios of this application are not exhaustively listed here.
  • an embodiment of the present application provides a recommendation method.
  • the objects that need to be recommended to users may include any one or more of the following: applications, services, audio, video, commodities, recipes, games or other types of objects, etc., which are not exhaustive here; in the embodiment of the present application, a variety of specific manifestations of applications and/or services that need to be displayed to users are provided, and this solution is implemented in multiple specific application scenarios, thereby improving the feasibility of this solution.
  • the objects that need to be recommended to users are applications and/or services. When the objects that need to be recommended to users are other types of objects, please refer to the execution, and the embodiments of the present application will not be repeated.
  • the recommendation system provided in the present application may include a first communication device and a second communication device, the first communication device may be a network terminal device, and the network terminal device may be implemented by one or more servers, for example: one or more cloud servers; the second communication device may be an electronic device, for example, the second communication device may be a mobile phone, a tablet, a laptop computer, a desktop computer, a television or other types of electronic devices, etc., and the specific product forms of the first communication device and the second communication device are not exhaustively listed here.
  • multiple matching rules and identification information of each matching rule can be deployed on the electronic device. After the electronic device determines the values of multiple characteristic information of the user, it can determine at least one first matching rule that matches the value of the user's characteristic information from multiple matching rules based on the values of the multiple characteristic information of the user, and obtain the identification information of each first matching rule, wherein each matching rule in the multiple matching rules is used to indicate the value range of each characteristic information in at least one characteristic information of the user.
  • the electronic device may generate first information and send the first information to a server, where the first information includes the identifier information of the first matching rule.
  • the server can determine the second information based on the first information, where the second information includes information about at least one application and/or service; for example, a correspondence between identification information of a matching rule and information about an application and/or service can be deployed on the first communication device, and the first communication device can determine information about at least one application and/or service based on the identification information of the matching rule carried in the first information and the aforementioned correspondence.
  • the server may send the second information to the terminal device, where the second information is used to indicate the first application and/or the first service.
  • the electronic device may determine a first application and/or a first service to recommend to the user based on the second information, and recommend the first application and/or the first service on a display unit of the electronic device.
  • the server determines the second information based on the identification information of the matching rule, and the identification information of the aforementioned matching rule is determined by the electronic device based on the value of the user's characteristic information, it is possible to achieve personalized determination of the application and/or service displayed to the user; moreover, the electronic device sends the identification information of the matching rule to the server, avoiding sending the user's original information to the server, thereby avoiding the leakage of the user's privacy information.
  • the recommendation method provided in the embodiment of the present application may include:
  • the electronic device determines a value of characteristic information of a user, determines a first matching rule that matches the value of the characteristic information of the user from a plurality of matching rules, and obtains identification information of the first matching rule, wherein each matching rule of the plurality of matching rules is used to indicate a value range of each characteristic information of at least one characteristic information of the user.
  • the electronic device may obtain the value of N types of characteristic information of the user, where N is a positive integer greater than or equal to 1.
  • the N types of characteristic information of the user may include any one or more of the following types of information: user portrait information, user behavior information when using an application, information of the electronic device used by the user, information of other electronic devices connected to the electronic device for communication, or other characteristic information of the user, etc., which will not be elaborated here.
  • the user's portrait information may include any one or more of the following information: name, gender, age, birthday, current location, home location, company location, work schedule, commuting method, sports hobbies or other information, etc.
  • the user's behavior information when using applications may include any one or more of the following information: the user's frequently used applications, the average number of times each of the n most used applications has been used in the last X days, the user's preferred music applications among multiple music applications, the user's preferred video applications among multiple video applications, the user's preferred food applications among multiple food applications, the user's preferred shopping applications among multiple shopping applications, etc., where n is an integer greater than or equal to 1 and X is a positive number.
  • the information of the electronic device used by the user may include any one or more of the following information of the electronic device: device model, device type, type of operating system (OS), version number of the operating system, ID of the electronic device or other information, etc.
  • device model device model, device type, type of operating system (OS), version number of the operating system, ID of the electronic device or other information, etc.
  • OS operating system
  • version number of the operating system ID of the electronic device or other information, etc.
  • the information of other electronic devices that are communicatively connected to the electronic device may include other electronic devices that are near-field connected to the electronic device, such as other electronic devices that use near-field technology to achieve connection with the electronic device.
  • the aforementioned other electronic devices may include tablets, personal computers (PCs), smart screens, smart speakers, headphones, smart watches or other devices, etc. It should be noted that the examples of N types of feature information here are only for the convenience of understanding this solution and are not used to limit this solution.
  • the electronic device may be configured with a matching rule set, wherein the matching rule set includes a plurality of matching rules and a plurality of matching rules.
  • the identification information of each matching rule, each matching rule includes one or more matching conditions, and each matching condition includes a value range of a characteristic information of the user.
  • the identification information of each matching rule may be a serial number, textual identification information, or other types of identification information, etc.; illustratively, the identification information of a matching rule may be 00000001, 00000002, or BB10000001, etc.
  • the examples given here are only for the convenience of understanding the present solution and are not used to limit the present solution.
  • Any matching condition in each matching rule may include one or more specific values; for example, the type of the user's characteristic information is gender, and the matching condition corresponding to the user's characteristic information of "gender” may be female; for another example, the type of the user's characteristic information is commuting mode, and the matching conditions corresponding to the user's characteristic information of "commuting mode” may include bus and subway; for another example, the user's characteristic information is current location, and the matching conditions corresponding to the characteristic information of "current location” may include at home, etc.
  • the target matching condition may also include continuous values; for example, the type of the user's characteristic information is the usage time of application D1, and the matching condition corresponding to the user's characteristic information "usage time of application D1" may include that the usage time of application D1 in the most recent day is greater than or equal to 2 hours; for another example, the type of the user's characteristic information is the average number of times application D2 is used in the past 3 days, and the matching condition corresponding to the user's characteristic information "the average number of times application D2 is used in the past 3 days” may include that the average number of times application D2 is used in the past 3 days is greater than or equal to 3 times, etc.
  • the examples of target matching conditions in the matching rules here are only for the convenience of understanding this solution and are not used to limit this solution. In order to more intuitively understand this solution, the following example of the set of matching rules configured on the electronic device is combined with Table 1.
  • Table 1 shows four matching rules and the identification information of each matching rule.
  • the matching rule pointed to by the identification information of the matching rule 0000000001 may include being in the company + the current time is the ordering time period + preference to use application C1 in food-related applications + the average number of times of ordering through food-related application C1 in the past three days is greater than or equal to three times.
  • the matching rule pointed to by the identification information of the matching rule 0000000001 includes four matching conditions, among which the matching condition "in the company” represents that the value range of the user's characteristic information "company location” needs to include the user's current location, and the "current time is the ordering time period”"
  • This matching condition means that the value range of the user characteristic information "dining time” needs to include the current time
  • the matching condition "preferring to use application C1 in food applications” means that the value range of the user information “preferring to use application C1 in food applications” needs to include application C1
  • the matching condition "the average number of times of ordering through food application C1 in the past 3 days is greater than or equal to 3 times” means that the value range of the user information "the average number of times of ordering through food application C1 in the past 3 days” needs to be greater than or equal to 3 times; for another example, referring to the second row in Table 1, the identification information of the matching rule 0000000002 points to the matching rule It can include the preference for using application C2 in mobile phone + at
  • the matching rule pointed to by the identification information of the matching rule 0000000002 includes 5 matching conditions, among which the matching condition "mobile phone” means that the value range of the user's characteristic information "device type” needs to include mobile phones, the matching condition “at home” means that the value range of the user's characteristic information "home location” needs to include the user's current location, the matching condition “rest” means that the value range of the user's characteristic information “rest time period” needs to include the current time, and the matching condition “shopping application” means that the value range of the user's characteristic information "rest time period” needs to include the current time.
  • the matching condition "preferring to use application C2 in the shopping category” means that the value range of the user information "preferring to use application C2 in shopping category applications” needs to include application C2, and the matching condition "the average number of times application C2 is used in the past three days is greater than or equal to 4 times” means that the value range of the user information "the average number of times application C2 is used in the past three days” needs to be greater than or equal to 4 times, etc.
  • the third and fourth rows in Table 1 please refer to the above explanation of the first and second rows of Table 1, which will not be repeated here. It should be noted that the examples in Table 1 are only for the convenience of understanding the two concepts of "matching rules” and “identification information of matching rules”. In actual applications, electronic Other matching rules and identification information of the matching rules can be configured on the device, which are not limited here.
  • the electronic device can determine at least one first matching rule from multiple matching rules based on the values of N types of characteristic information of the user, and obtain identification information of each first matching rule.
  • Each first matching rule may include a matching condition corresponding to at least one of the N types of characteristic information of the user, and each matching condition includes a value range of one type of characteristic information of the user; the first matching rule is a rule that successfully matches the value of the characteristic information of the user among multiple matching rules deployed by the electronic device, that is, the first matching rule is a rule that hits the value of the characteristic information of the user among multiple matching rules deployed by the electronic device.
  • the electronic device can obtain any one matching rule from multiple matching rules (hereinafter referred to as "target matching rule" for convenience of description), and judge whether the target matching rule matches the value of the user's characteristic information according to the values of the N types of characteristic information of the user. If the judgment result is yes, the target matching rule is determined as the first matching rule; if the judgment result is no, the next matching rule is obtained from the multiple matching rules, and the above judgment step is performed.
  • the electronic device can repeatedly perform the above operation to judge whether each matching rule in the multiple matching rules matches the value of the user's characteristic information one by one, so as to obtain at least one first matching rule from the multiple matching rules.
  • a target matching rule may include one or more matching conditions, and the electronic device may use a variety of methods to perform the judgment operation of "whether the target matching rule matches the value of the user's characteristic information".
  • the electronic device may judge whether the requirements of the matching conditions in the target matching rule are met based on the values of one or more characteristic information of the user. If the values of one or more characteristic information of the user all meet the requirements of the target matching rule, it is determined that the target matching rule matches the value of the user's characteristic information; if any of the values of one or more characteristic information of the user does not meet the requirements of the target matching rule, it is determined that the target matching rule does not match the value of the user's characteristic information.
  • the specific implementation process of the judgment operation of "judging whether the target matching rule matches the value of the user's characteristic information” is exemplified below in combination with the matching rules in Table 2.
  • the target matching rule (that is, any matching rule deployed on the electronic device) is taken as the matching rule pointed to by the identification information of the matching rule 0000000002 in Table 1.
  • Table 2 For the understanding of the matching rules in Table 2, please refer to the above explanation of Table 1, which will not be elaborated here.
  • the server can respectively obtain the values of 5 types of user feature information, namely "device type", “home location”, “rest time period”, "preferred application in shopping applications” and "average number of uses of application C2 in the past three days”; the server determines whether the user's device type is a mobile phone, and determines whether the user's home location includes the current location , determine whether the application preferred by the user in the shopping applications is application C2, and determine whether the average number of times the user uses application C2 in the past three days is greater than or equal to 4 times; if the judgment results of the aforementioned multiple judgment operations are all yes, the server can determine that the user's feature information meets the requirements of the matching rule 0000000002, that is, it can be determined that the matching rule 0000000002 matches the user's feature information; if the judgment result of any of the aforementioned multiple judgment operations is no, the server can determine that the user
  • the electronic device may determine that the total number of matching conditions in the target matching rule is a first value, and the electronic device may determine that the number of matching conditions satisfied by the value of the characteristic information of the user in at least one matching condition included in the target matching rule is a second value based on the value of the characteristic information of the user. If the ratio between the second value and the first value is greater than or equal to the first threshold, it may be determined that the target matching rule matches the value of the characteristic information of the user; if the ratio between the second value and the first value is less than the first threshold, it may be determined that the target matching rule does not match the value of the characteristic information of the user.
  • the value of the first threshold may be 90%, 85%, 80% or other values, etc., which are not limited here.
  • the electronic device may also implement "determining one or more first matching rules that match the value of the user's characteristic information from multiple matching rules" in other ways, which are not exhaustively listed here.
  • the multiple matching rules deployed in the electronic device and the identification information of each matching rule are generated by the server and sent to the electronic device.
  • the matching rules deployed in the electronic device and/or the identification information of the matching rules deployed in the electronic device are updateable.
  • the electronic device may update the matching rule set on the server in a variety of ways.
  • the server may send a matching rule set to the electronic device, the matching rule set including multiple matching rules and identification information of each matching rule;
  • the server may send a first indication message to the electronic device, where the first indication message is used to inform the electronic device to delete one or more matching rules and identification information of the matching rules from the aforementioned matching rule set, and/or to add one or more matching rules and identification information of the matching rules to the aforementioned matching rule set; based on the first indication message, the electronic device deletes one or more matching rules and identification information of the matching rules from the aforementioned matching rule set, and/or adds one or more matching rules and identification information of the matching rules to the aforementioned matching rule set, so as to obtain an updated matching rule set.
  • the first indication information may include at least one first identification information and second indication information, the second indication information is used to indicate that each first identification information is the identification information of the matching rule to be deleted; and/or, the first indication information may include at least one second identification information, the matching rule corresponding to each second identification information, and third indication information, the third information is used to indicate that each second identification information and the matching rule corresponding to each second identification information are added to the matching rule set.
  • the first identification information and the second identification information are both identification information of the matching rule, the difference is that the first identification information is the identification information of the matching rule in the matching rule set, and the second identification information does not exist in the matching rule set.
  • the second indication information and the third indication information are different, for example, the second indication information can be "delete”, and the third indication information can be “add”; for another example, the second indication information can be "0", the third indication information can be "1", and so on, which are not exhaustive here.
  • the first indication information may carry at least one identification information of a matching rule to be deleted, and/or, identification information of a matching rule to be added and the matching rule corresponding to each identification information; after obtaining the first indication information, the electronic device may determine whether the identification information of the matching rule in the matching rule set overlaps with the identification information of the matching rule carried in the first indication information; if there is overlapping identification information in the matching rule set and the first indication information, the electronic device may delete the aforementioned overlapping first identification information and the matching rule corresponding to the aforementioned overlapping first identification information from the matching rule set; if there is no overlapping identification information in the matching rule set and the first indication information, the electronic device may determine that there is no matching rule to be deleted.
  • the electronic device may also determine whether there is identification information outside the matching rule set in the first indication information; if there is second identification information outside the matching rule set in the first indication information, the electronic device may add each second identification information and the matching rule corresponding to each second identification information to the matching rule set; if there is no second identification information outside the matching rule set in the first indication information, the electronic device may determine that there is no need to add the matching rule to the matching rule set, etc. It should be noted that the electronic device may also use other methods to implement “deleting and/or adding matching rules based on the matching rule set according to the first indication information”. The example given here is only to prove the feasibility of this solution and is not used to limit this solution.
  • the server may send a matching rule set to the electronic device, where the matching rule set includes multiple matching rules and identification information of each matching rule.
  • the server needs to update the matching rule set on the electronic device, the server directly sends the updated matching rule set to the electronic device, where the updated matching rule set includes multiple matching rules and identification information of each matching rule.
  • the electronic device deletes the matching rule set before the update and stores the updated matching rule set.
  • the server can update the matching rule set deployed on the electronic device in a variety of scenarios.
  • the electronic device can update the matching rule set on the server at a fixed time point; for example, after the matching rule set is initially deployed on the electronic device, the server can perform an update operation on the matching rule set on the electronic device at an interval of a first time period, and the number of types of information corresponding to the updated matching rule set is greater than the number of types of information corresponding to the initial matching rule set; illustratively, the first time period can be one month, 50 days or other values.
  • the electronic device since the electronic device may collect less information about the user when the recommendation method provided in the embodiment of the present application is just started, the initially configured matching rule set involves less information about the user.
  • the electronic device can collect more information about the user, and the matching rule set on the electronic device can be updated.
  • the updated matching rule set involves more information about the user, so that the matching degree between the matching rule set deployed on the electronic device and the information currently acquired by the electronic device is conducive to improving the accuracy of the identification information process of the first matching rule.
  • the electronic device may also update the matching rule set on the server at a preset frequency; for example, the matching rule set on the electronic device may be updated once every month, etc., which is not limited here.
  • the electronic device can update the matching rule set on the server.
  • the applications and/or services that need to be recommended include applications and services as an example.
  • the matching rules corresponding to the aforementioned shopping application can change; for another example, when an application launches a new service, it is necessary to add matching rules corresponding to the newly released service; for another example, when an application no longer needs to be recommended, it is necessary to delete the matching rules corresponding to the aforementioned application, etc., which are not exhaustive here.
  • the electronic device may also obtain the application programs and/or services that need to be recommended based on each matching rule. If the click rate of a matching rule is lower than the second threshold, it is determined that the aforementioned matching rule needs to be deleted, and the matching rule set on the electronic device also needs to be updated in this scenario. It should be noted that the electronic device can also perform the update operation of the "matching rule set on the electronic device" in other scenarios. The examples given here are only for the convenience of understanding this solution and are not used to limit this solution.
  • the matching rules deployed in the electronic device and/or the identification information of the matching rules deployed in the electronic device are set to be updateable, which is not only conducive to more accurately displaying the applications and/or services that the user may be interested in, but also conducive to improving the utilization rate of computer resources on the electronic device; for example, when the click rate of the application and/or service recommended based on a certain matching rule is too low, the matching rule can be deleted, which not only reduces the storage resources occupied by the matching rule, but also the electronic device no longer needs to perform matching operations on the deleted matching rule, thereby reducing the consumption of processor resources.
  • the electronic device sends first information to the server, where the first information includes identification information of the first matching rule.
  • the electronic device may send first information to the server, and the server may receive the first information accordingly.
  • the first information includes at least identification information of each first matching rule, and the first information is used to request the server to determine one or more applications and/or services to be recommended based on the identification information of the matching rule carried in the first information.
  • the electronic device may use a variety of methods to determine which identification information of the first matching rules is carried in the first information.
  • the first information may include the identification information of all first matching rules determined in step 401. After the electronic device determines the identification information of at least one first matching rule in step 401, it may determine the identification information of all first matching rules determined in step 401 as the identification information of the first matching rule included in the first information. In another implementation, after the electronic device determines the identification information of at least one first matching rule in step 401, it may select one or more identification information of the first matching rules from the identification information of the first matching rules determined in step 401, that is, the first information may include the identification information of part of the first matching rules determined in step 401.
  • the electronic device may randomly select identification information of at least one second matching rule from identification information of multiple matching rules, and then generate the first information.
  • the first information may also include identification information of at least one second matching rule among multiple matching rules deployed on the electronic device.
  • the second matching rule and the first matching rule are different matching rules among the multiple matching rules, that is, the second matching rule is a rule that does not match the value of the user's characteristic information.
  • the meaning of "identification information of the second matching rule" is similar to that of "identification information of the first matching rule". For details, please refer to the description of the meaning of "identification information of the first matching rule" in step 401, which will not be repeated here.
  • the ratio between the number of identification information of the second matching rule in the first information and the number of identification information of the first matching rule may be greater than a third threshold.
  • the value of the third threshold may be 60%, 70%, 80% or other values, etc., which is not limited here.
  • the electronic device can be triggered to start executing steps 401 and 402 in a variety of scenarios.
  • the electronic device can be triggered to start executing steps 401 and 402 at a preset frequency.
  • the preset frequency can be performed every 2 hours, 3 hours, 4 hours, or other durations, etc., which is not limited here.
  • the electronic device can be triggered to start executing steps 401 and 402 at a fixed time point.
  • the fixed time points can include 7 am, 4 pm, and 8 pm every day, etc., which are not limited here.
  • the electronic device receives a display instruction for the aforementioned interface, thereby triggering the start of execution of steps 401 and 402; exemplarily, please refer to FIG. 2 , when the electronic device receives a display instruction for the interface shown in FIG. 2 , it may trigger the start of execution of steps 401 and 402.
  • each time the electronic device executes steps 401 and 402 it can obtain information of multiple applications and/or services.
  • the electronic device can display the aforementioned obtained applications and/or services multiple times, and can trigger the re-execution of steps 401 and 402 when the electronic device has displayed all the applications and/or services that need to be displayed to the user.
  • the electronic device executes steps 401 and 402 once to obtain information of 9 applications and/or services, and displays access interfaces of up to 4 applications and/or services to the user at one time.
  • the electronic device After the electronic device has displayed all the aforementioned 9 applications and/or services to the user, it can trigger the execution of steps 401 and 402 again, and so on.
  • the specific scenarios in which steps 401 and 402 are triggered can be flexibly set in combination with actual application scenarios, and are not limited here.
  • the server obtains fourth information, where the fourth information includes information associated with the application and/or service, and/or group portrait information corresponding to the user.
  • step 403 is an optional step.
  • the server may also obtain the fourth information.
  • the fourth information includes information associated with the application and/or service, and/or group portrait information corresponding to the user.
  • the server may be configured with information of multiple objects and the type of information associated with at least one of the multiple objects.
  • the server may obtain information associated with at least one of the multiple objects based on the type of information associated with at least one of the multiple objects.
  • the information associated with the applications and/or services may include weather information in the user's area, express delivery information of goods purchased by the user through one or more applications, promotional information, current news information or other information associated with applications and/or services, etc., which are not exhaustive here.
  • the weather information "a sharp drop in temperature occurred in the user's area” is associated with a shopping application, and the weather information "a sharp drop in temperature occurred in the user's area” is associated with the service "check weather”; for another example, the express delivery information of the goods purchased by the user and the user's location information are associated with the service "showing the user the express delivery to be picked up”; for another example, promotional event information and the user's location information are associated with the service "access interface for coupons", and so on. The examples are not exhaustive here.
  • audio of interest can be recommended to the user, that is, the object to be recommended is audio
  • the information associated with the application and/or service may include the style, author, release time, playback volume or other information of the audio.
  • a video of interest can be recommended to the user, that is, the object to be recommended is video
  • the information associated with the application and/or service may include the subject type of the video, the name of the leading actor in the video, the rating of the video, the playback volume of the video or other information.
  • the information associated with the application and/or service may include the cuisine to which the recipe belongs, the calories of the recipe, the vitamin content of the recipe, other information, etc., and the information associated with the application and/or service in all application scenarios is not exhaustively enumerated here.
  • the server can determine the user's identification information.
  • the user's identification information can be expressed as the user's account information, the user's mobile phone number or other types of identification information, etc., which is not limited here.
  • the server can obtain the group portrait information corresponding to the user based on the user's account information; wherein the group portrait information includes the portrait information of a class of users, for example, the group portrait information may include the age group of the user's age, the user's gender, the user's consumption level type or other group portrait information, etc.
  • the examples here are only for the convenience of understanding this solution and are not used to limit this solution.
  • the server can also obtain the group portrait information corresponding to the user, that is, it can obtain more information about the user, which is conducive to showing the user more in line with the expected application and/or service; in addition, when the electronic device has not yet collected the user's characteristic information, or when the electronic device can only collect a small amount of information about the user, the obtained group portrait information can assist the server in determining the application and/or service that is more in line with the user's expectations, which is conducive to improving the user stickiness of this solution.
  • the server determines second information according to the first information, where the second information is used to indicate the first application and/or the first service.
  • the second information may include information of at least one application and/or service; the information of the aforementioned at least one application and/or service is used for the electronic device to determine at least one application and/or service corresponding to the information of the at least one application and/or service. Since the information of the aforementioned at least one application and/or service includes information of the first application and/or the first service, the second information may indicate the first application and/or the first service. Exemplarily, in some application scenarios, the information of each application and/or service may include identification information of each application and/or service.
  • the identification information of each application and/or service may be the name of the application, the icon of the application, the name of the service, the icon of the service, the identification number of the application or service, or other identification information that can uniquely point to an application or service, etc., which are not exhaustive here.
  • the identification information of each object may be the name of the audio, the singer, and the name of the album to which it belongs, or the identification information of each object may be the identification number of the audio, or the identification information of each object may also be other information of the audio, etc., which are not limited here.
  • the information of applications and/or services recommended to users may also be the description information of the object.
  • the description information of each object may include the picture, name and access link of the commodity.
  • the description information of each object may include the picture of the recipe, the ingredients used or other information, etc.
  • the description information of each object may include the icon, name and access link of the game, etc.
  • the second information may include a first correspondence relationship
  • the first correspondence relationship may include each target identification information and the object identification
  • the correspondence between information, the target identification information is any identification information in the first information
  • each target identification information is the identification information of the first matching rule or the identification information of the second matching rule, that is, the second information is used to indicate the correspondence between the identification information of the first matching rule in the first information and at least one application and/or service, and the correspondence between the identification information of the second matching rule in the first information and at least one application and/or service.
  • the second information is used to inform the electronic device which applications and/or services can be displayed to the user, and which matching rule's identification information each application and/or service corresponds to, that is, to inform the electronic device based on which matching rule's identification information each application and/or service is recalled.
  • Step 403 is an optional step. If step 403 is not performed, the server can use multiple methods to implement "determining the second information according to the first information". Specifically, in one implementation method, a second corresponding relationship can be configured on the server, and the second corresponding relationship indicates the corresponding relationship between the identification information of each matching rule and the information of one or more applications and/or services. After receiving the first information, the server can obtain the identification information of multiple matching rules. Among them, the identification information of the aforementioned multiple matching rules includes the identification information of the first matching rule; optionally, the identification information of the aforementioned multiple matching rules also includes the identification information of the second matching rule.
  • the server can obtain the information of at least one application and/or service corresponding to the identification information of each matching rule according to the identification information of each matching rule in the first information and the second corresponding relationship, thereby obtaining the information of at least one application and/or service corresponding to the identification information of all matching rules in the first information.
  • the aforementioned "information of at least one application and/or service” includes the information of the application and/or service corresponding to the identification information of the first matching rule; optionally, the aforementioned "information of at least one application and/or service” also includes the information of the application and/or service corresponding to the identification information of the second matching rule.
  • the second correspondence may include the correspondence between the identification information of each matching rule and the identification information of the application and/or service; optionally, the second correspondence may also include the correspondence between the identification information of the application and/or service and the information of the application and/or service. It should be noted that the relationship between "identification information of matching rules" and "identification information of applications and/or services" in the second correspondence is many-to-many, and the identification information of one matching rule may correspond to the identification information of one or more applications and/or services, and the identification information of different matching rules may correspond to the identification information of the same application and/or service.
  • the server may store the second corresponding relationship in a table, array, or other data format.
  • Table 3 an example is given below in conjunction with Table 3, where the application and/or service is taken as an example.
  • Each row in Table 3 shows the identification information of the application and/or service corresponding to the identification information of a matching rule.
  • the identification information of the service corresponding to the identification number of the matching rule 0000000001 includes the ordering function of the food application D1.
  • the identification information of the application corresponding to the identification number of the matching rule 0000000002 includes the shopping application D2.
  • the identification information of the application corresponding to the identification number of the matching rule 0000000003 includes the music application D3 and the video application D4.
  • the identification information of the service corresponding to the identification number of the matching rule 0000000004 includes the scan function for scanning a QR code, etc.
  • Table 3 are only for the convenience of understanding this solution and are not used to limit this solution.
  • the server may input the identification information of each matching rule in the first information into the first neural network, and obtain the identification information of one or more applications and/or services output by the first neural network, and then obtain the identification information of one or more applications and/or services corresponding to the identification information of all matching rules in the first information through the first neural network.
  • the first neural network is a neural network that has performed a training operation, and illustratively, the first neural network may be a recurrent neural network, a convolutional neural network, a residual neural network, or other types of neural networks, etc., which are not exhaustive here.
  • step 404 may include: the server determines the second information based on the fourth information and the first information, wherein the first information includes identification information of at least one first matching rule; optionally, the first information also includes identification information of at least one second matching rule; the meaning of the "fourth information" and the method of obtaining it can be found in the description in step 403 and will not be repeated here.
  • a third correspondence may be configured on the server, and the third correspondence may include a correspondence between each first condition and identification information of at least one application and/or service.
  • Each first condition includes at least one identification information of a matching rule; optionally, the first condition may also include a first sub-condition, and the server may determine whether the first sub-condition is met based on information associated with the application and/or service and/or group portrait information corresponding to the user.
  • the server may store the second corresponding relationship in a table, array, or other data format.
  • Table 4 an example is given below in conjunction with Table 4, where the application and/or service is taken as an example.
  • Each row in Table 4 shows the identification information of one or more applications and/or services corresponding to a first condition.
  • the contents of the first and second rows in Table 4 can refer to the above description of Table 3, which will not be repeated here.
  • the identification of the matching rule included in the first condition is 0000000005, and the first sub-condition includes that the temperature drops by more than 8 degrees in the next day.
  • the identification information of the applications and services corresponding to the aforementioned first condition includes the shopping application D2 and the weather information viewing function.
  • the matching rule corresponding to the identification number of the matching rule 0000000005 may include the preference for using application D2 in the mobile phone + rest + shopping applications + the average number of times application D2 is used in the past three days is greater than or equal to 4 times.
  • the identification of the matching rule included in the first condition is 0000000006
  • the first sub-condition includes that the commodity d1 purchased through the shopping application D2 is delivered to the vicinity of the company
  • the identification information of the service corresponding to the aforementioned first condition includes the function of viewing the express information of the commodity d1 purchased through the shopping application D2.
  • the matching rule corresponding to the identification number of the matching rule 0000000006 may include being located near the company + non-commuting time period.
  • the identification of the matching rule included in the first condition is 0000000007
  • the first sub-condition includes that the food application D4 launches a coupon
  • the identification information of the service corresponding to the aforementioned first condition includes the access interface of the coupon of the food application D4.
  • the matching rule corresponding to the identification number of the matching rule 0000000007 may include that the user has purchased a coupon of the food application D4 + the current time is the meal time period.
  • the identification of the matching rule included in the first condition is 0000000008
  • the first sub-condition includes that the user's age range in the group portrait information corresponding to the user is between 25 and 35, and the user's gender is female
  • the identification information of the application corresponding to the aforementioned first condition includes the shopping application D2.
  • the matching rule corresponding to the identification number of the matching rule 0000000008 may include that the user's current location is at home + the current time is the user's rest time, etc.
  • Table 4 are only for the convenience of understanding this solution and are not used to limit this solution.
  • the server after the server deploys multiple matching rules and the identification information of each matching rule to the electronic device, it can delete the multiple matching rules and store the second corresponding relationship, that is, the corresponding relationship between the identification information of the matching rules and the identification information of the application and/or service, so as to further reduce the possibility of obtaining the user's privacy information.
  • the server after the server deploys multiple matching rules and the identification information of each matching rule to the electronic device, it can also store multiple matching rules and the identification information of each matching rule.
  • the server may obtain a second condition containing the target identification information from the multiple first conditions; if the second condition only includes the target identification information, the identification information of the application and/or service corresponding to the second condition is obtained, and the information of the application and/or service corresponding to the second condition is transmitted to the server.
  • the information is determined to be the identification information of the application and/or service included in the second information. If the second condition also includes the first sub-condition, the server can determine whether the first sub-condition in the second condition is met based on the information associated with the application and/or service and/or the group portrait information corresponding to the user.
  • the judgment result is yes, that is, it is determined that the first sub-condition in the second condition is met, the identification information of the application and/or service corresponding to the second condition is obtained, and the application and/or service information corresponding to the second condition is determined as the identification information of the application and/or service included in the second information; if the judgment result is no, the aforementioned operation is performed on the identification information of the next matching rule in the first information.
  • the server may input the identification information of each matching rule in the first information and the fourth information into the second neural network to obtain the identification information of one or more applications and/or services output by the first neural network, and then obtain the identification information of one or more applications and/or services corresponding to the identification information of all matching rules in the first information through the first neural network.
  • the second neural network is a neural network that has performed a training operation.
  • the second neural network can be a recurrent neural network, a convolutional neural network, a residual neural network or other types of neural networks, etc., which are not exhaustively listed here.
  • the server can also use other methods to determine the second information based on the fourth information and the first information, which can be determined in combination with the actual application scenario, and are not exhaustively listed here.
  • the server in the process of determining the applications and/or services to be displayed to the user, not only utilizes the first information, but may also utilize information associated with the applications and/or services and/or group portrait information corresponding to the user, which is conducive to a fuller understanding of the applications and/or services to be recommended and the current user, and is conducive to determining the applications and/or services that the current user is interested in, thereby increasing the probability of accurately recommending applications and/or services to the user.
  • the first information sent by the electronic device to the server includes not only the identification information of the first matching rule, but also the identification information of the second matching rule, so that the electronic device cannot determine which matching rule's identification information is hit by the server and which matching rule's identification information is not hit by the server. This helps to increase the difficulty for the electronic device to reversely infer the characteristic information of the server's user based on the identification information of the matching rules, so as to further protect the user's privacy data.
  • the server sends second information to the electronic device.
  • the server after the server determines the second information through step 404, it can send the second information to the electronic device.
  • the meaning of the "second information" can be found in the description of step 404 and will not be repeated here.
  • the electronic device recommends the first application and/or the first service on the display unit.
  • the electronic device after receiving the second information, can determine the information of the first application and/or the first service to be displayed to the user, and recommend the first application and/or the first service on the display unit; for example, "recommending the first application and/or the first service on the display unit" can be understood as displaying the access interface of the first application and/or the first service on the display unit. If the first information only includes the identification information of the first matching rule, the electronic device can determine all the applications and/or services in the second information as the first applications and/or the first services that need to be recommended to the user.
  • step 406 may include: the electronic device determines the first application and/or first service recommended to the user based on the identification information of the first matching rule and the second information.
  • the electronic device can select, based on the identification information of the first matching rule, one or more target applications and/or service information corresponding to the identification information of the first matching rule from the information of multiple applications and/or services included in the second information, that is, select one or more target applications and/or service information recalled by the identification information of the first matching rule, and determine the target application and/or service as the first application and/or first service that needs to be recommended to the user.
  • the identification information of multiple first matching rules included in the first information includes 0000000004, 0000000005 and 00000000006, and the identification information of multiple second matching rules includes 0000000011, 0000000023 and 00000000058.
  • the content included in the second information is shown in Table 5 below. It should be noted that the examples in Table 5 below are only for the convenience of understanding this solution and are not used to limit this solution.
  • the electronic device can obtain the identification information of the applications and/or services corresponding to 0000000004, 0000000005 and 00000000006 from the second information, that is, the “scan function for scanning the QR code”, “shopping application D2”, “weather information viewing function” and “express delivery information viewing function of product d1 purchased through shopping application D2” shown in Table 5.
  • the electronic device determines that the first application and/or first service that needs to be recommended to the user includes the “scan function”, “shopping application D2”, “weather information viewing function” and “express delivery information viewing function of product d1 purchased through shopping application D2”.
  • the identification information of the second matching rule is added to the first information, and the server cannot determine which identification information in the first information is the identification information of the rule that matches the user's characteristic information, further increasing the difficulty for the server to reversely infer the user's characteristic information; in addition, since the identification information of the second matching rule is added to the first information, correspondingly, the second information includes information on applications and/or services corresponding to the identification information of the second matching rule, the electronic device can determine the first application and/or first service that ultimately needs to be recommended to the user based on the identification information of the first matching rule and the second information, thereby facilitating the accurate display of applications and/or services to the user while ensuring the security of the user's privacy data.
  • the electronic device may also determine all applications and/or services in the second information as first applications and/or first services that need to be recommended to the user.
  • the electronic device After the electronic device has determined multiple applications and/or services that need to be displayed to the user, it can display all of the aforementioned applications and/or services to the user at one time; alternatively, the electronic device can display all of the aforementioned applications and/or services to the user at least twice, etc.
  • the specific display method can be flexibly determined in combination with the actual product form and is not limited here.
  • Figures 5 to 7 are three interface schematic diagrams for displaying applications and/or services to users provided by embodiments of the present application. Figures 5 to 7 all take the example of an electronic device displaying applications and/or services to users through the area indicated by 201. First, refer to Figure 5.
  • the characteristic information of the user collected by the electronic device includes: the user is located in city A, the current time is the morning commuting time period, the current time is the user's morning time period, the current location is near the company, and the user has purchased 3 coupons of the food application D4; the identification information of the two first matching rules obtained by the electronic device based on the collected user's characteristic information are 0000000004 and 0000000007, respectively, wherein the matching rule pointed to by the identification information of the matching rule 0000000004 may include being located in city A + the current time is the morning commuting time period + the current location is near the company, and the matching rule corresponding to the identification information of the matching rule 0000000007 may include the user has purchased a coupon of the food application D4 + the current time is the meal time period.
  • the electronic device can randomly select two identification information of the second matching rules 0000000058 and 0000000132 from the identification information of multiple matching rules stored locally, determine the identification information of the two first matching rules and the identification information of the two second matching rules as the identification information of the matching rules included in the first information, and send the first information to the server, the first information including 0000000004, 0000000007, 0000000058 and 0000000132.
  • the server obtains the information of applications and/or services corresponding to 0000000004, 0000000007, 0000000058 and 0000000132 respectively.
  • the application and/or service information corresponding to the identification information of the matching rule 0000000004 obtained by the server is "the scan function for scanning the QR code".
  • the server determines that the first condition including the identification information of the matching rule 0000000007 also includes the first sub-condition. According to the user's location information, it is determined that there is an offline store corresponding to the food application D4 within 50 meters of the user. That is, it is determined that the first condition is met, and the identification information of the matching rule 0000000007 can be obtained.
  • the information of the corresponding application and/or service i.e., "the access interface of the coupon of the food application D4").
  • the first sub-condition in the first condition containing the identification information of the matching rule 0000000058 is empty, and the information of the application and/or service corresponding to the identification information of the matching rule 0000000058 obtained by the server is the instant messaging application D7.
  • the first sub-condition in the first condition containing the identification information of the matching rule 0000000132 is empty, and the information of the application and/or service corresponding to the identification information of the matching rule 0000000132 obtained by the server is the food application D5.
  • the server sends second information to the electronic device, and the second information includes the correspondence between 0000000004 and the "scan function for scanning the QR code", the correspondence between 0000000007 and the "access interface of the coupon of the food application D4", the correspondence between 0000000058 and the “instant messaging application D7", and the correspondence between 0000000132 and the "food application D5".
  • the electronic device obtains the "scan function for scanning the QR code” corresponding to 0000000004 and the "access interface for the coupon of the food application D4" corresponding to 0000000007 from the second information, that is, it is determined that the first application and/or the first service to be recommended includes the "scan function for scanning the QR code” and the "access interface for the coupon of the food application D4".
  • the specific display method please refer to the content shown in the 201 area in Figure 5.
  • the access interface for displaying the coupon of the food application D4 is triggered (that is, the 3 purchased coupons of the store XXX shown in Figure 5). It should be understood that the example in Figure 5 is only for the convenience of understanding this solution and is not used to limit this solution.
  • the characteristic information of the user collected by the electronic device includes: the user is located in city A, the current time is the morning commuting time period, the current time is the user's morning time period, and the current location is near the company; the identification information of the two first matching rules obtained by the electronic device based on the collected characteristic information of the user are 0000000004 and 0000000020, respectively, wherein the matching rule pointed to by the identification information of the matching rule 0000000004 can include being located in city A + the current time is the morning commuting time period + the current location is near the company, and the matching rule corresponding to the identification information of the matching rule 0000000020 can include the current time is the meal time period.
  • the electronic device may randomly select two pieces of identification information of the second matching rules, 0000000058 and 0000000132, from identification information of multiple matching rules stored locally, and send first information to the server, where the first information includes 0000000004, 0000000020, 0000000058 and 0000000132.
  • the server respectively obtains the information of the application programs and/or services corresponding to 0000000004, 0000000020, 0000000058 and 0000000132.
  • the method of obtaining the information of the application programs and/or services corresponding to the identification information of the three matching rules 0000000004, 0000000058 and 0000000132 can refer to the above description of FIG5, which will not be repeated here.
  • the server determines that the first condition containing the identification information of the matching rule 0000000020 includes a first sub-condition, and the first sub-condition includes: there is store F1 within 20 meters of the user + store F1 is issuing coupons; the server determines that there is store F1 within 10 meters of the user based on the user's location information, and based on the information associated with the object "coupon for store F1", determines that store F1 is issuing coupons, and thus determines that the first condition is met, then the information of the application and/or service corresponding to the identification information of the matching rule 0000000020 (that is, the "access link for the coupon for store F1”) can be obtained.
  • the server sends second information to the electronic device, and the second information includes the correspondence between 0000000004 and the “Scan function for scanning the QR code”, the correspondence between 0000000020 and the “access link of the coupon of store F1”, the correspondence between 0000000058 and the “instant messaging application D7”, and the correspondence between 0000000132 and the “food application D5”.
  • the electronic device obtains the "scan function for scanning the QR code” corresponding to 0000000004 and the "access link for the coupon of store F1" corresponding to 0000000020 from the second information, that is, it is determined that the first application and/or the first service to be recommended includes the "scan function for scanning the QR code” and the "coupon of store F1".
  • the specific display method please refer to the content shown in the 201 area in Figure 6.
  • the access interface for displaying the coupon of store F1 is triggered. It should be understood that the example in Figure 6 is only for the convenience of understanding this solution and is not used to limit this solution.
  • the characteristic information of the user collected by the electronic device includes: the current time is the user's rest time, and there is a business circle within 20 meters of the current location; the identification information of a first matching rule obtained by the electronic device based on the collected characteristic information of the user is 0000000063, wherein the matching rule pointed to by the identification information of the matching rule 0000000063 may include rest time + a business circle within 50 meters nearby.
  • the electronic device can randomly select two second matching rule identification information 0000000132 from the identification information of multiple matching rules stored locally, and send the first information to the server, the first information including 0000000063 and 0000000132.
  • the server obtains the information of the application and/or service corresponding to 0000000063 and 0000000132 respectively.
  • the method of obtaining the "information of the application and/or service corresponding to the identification information of the matching rule 0000000132" can refer to the description of FIG. 5 above. No further details are given here.
  • the server determines that the first condition of the identification information containing the matching rule 0000000063 includes the first sub-condition, and the first sub-condition includes: there is at least one store in the business district where the user is located that is offering coupons; the server determines, based on the user's location information, that there is a business district within 20 meters of the user, and there are 6 stores in the aforementioned business district that are offering coupons, that is, it is determined that the first condition is met, and the information of the application and/or service corresponding to the identification information of the matching rule 0000000020 can be obtained (that is, "the access link to the coupons of the 6 stores in the aforementioned business district").
  • the server sends second information to the electronic device, where the second information includes a correspondence between 0000000063 and “access links to coupons for 6 stores”, and a correspondence between 0000000132 and “food application D5”.
  • the electronic device obtains the "access link for coupons of 6 stores" corresponding to 0000000063 from the second information, and determines that the first application and/or the first service to be recommended includes “coupons for 6 stores".
  • the specific display method please refer to the content shown in area 201 in Figure 7, where F2, F3 and F4 represent the access links for coupons of 3 stores.
  • F2, F3 and F4 represent the access links for coupons of 3 stores.
  • the access links for coupons of other 3 stores are triggered. It should be understood that the example in Figure 7 is only for the convenience of understanding of this solution and is not used to limit this solution.
  • the electronic device can obtain identification information of the first matching rule that matches the value of the user's characteristic information, and send the identification information of the first matching rule to the server, so that the server can obtain second information based on the identification information of the first matching rule, and the electronic device determines the first application and/or first service recommended to the user based on the received second information.
  • FIG. 8 is a structural schematic diagram of the server provided by the embodiment of the present application.
  • the server 800 is implemented by one or more servers.
  • the server 800 may have relatively large differences due to different configurations or performances. It may include one or more central processing units (CPU) 822 (for example, one or more processors) and memory 832, and one or more storage media 830 (for example, one or more mass storage devices) storing application programs 842 or data 844.
  • the memory 832 and the storage medium 830 can be short-term storage or permanent storage.
  • the program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server.
  • the central processor 822 can be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on the server 800.
  • the server 800 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input and output interfaces 858, and/or one or more operating systems 841, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • operating systems 841 such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the central processor 822 is used to execute the recommended method executed by the server in the embodiments corresponding to Figures 3 to 7. It should be noted that the specific manner in which the central processor 822 executes the aforementioned steps is based on the same concept as the various method embodiments corresponding to Figures 3 to 7 in the present application, and the technical effects brought about are the same as the various method embodiments corresponding to Figures 3 to 7 in the present application. For specific contents, please refer to the description in the method embodiments shown in the preceding description of the present application, which will not be repeated here.
  • FIG. 9 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
  • the electronic device 900 can be specifically manifested as a mobile phone, a tablet, a laptop computer, a smart wearable device, etc., which is not limited here.
  • the electronic device 900 includes: a receiver 901, a transmitter 902, a processor 903 and a memory 904 (wherein the number of processors 903 in the electronic device 900 can be one or more, and FIG. 9 takes one processor as an example), wherein the processor 903 may include an application processor 9031 and a communication processor 9032.
  • the receiver 901, the transmitter 902, the processor 903 and the memory 904 may be connected via a bus or other means.
  • the memory 904 may include a read-only memory and a random access memory, and provides instructions and data to the processor 903. A portion of the memory 904 may also include a non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the memory 904 stores processor and operation instructions, executable modules or data structures, or subsets thereof, or extended sets thereof, wherein the operation instructions may include various operation instructions for implementing various operations.
  • the processor 903 controls the operation of the electronic device.
  • the various components of the electronic device are coupled together through a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus, etc.
  • the bus system includes not only a data bus but also a power bus, a control bus, and a status signal bus, etc.
  • various buses are referred to as bus systems in the figure.
  • the method disclosed in the above embodiment of the present application can be applied to the processor 903, or implemented by the processor 903.
  • the processor 903 can It is an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 903.
  • the above-mentioned processor 903 can be a general-purpose processor, a digital signal processor (digital signal processing, DSP), a microprocessor or a microcontroller, and can further include an application specific integrated circuit (application specific integrated circuit, ASIC), a field programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • the processor 903 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application.
  • the general processor can be a microprocessor or the processor can also be any conventional processor.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor are combined and executed.
  • the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in the memory 904, and the processor 903 reads the information in the memory 904 and completes the steps of the above method in combination with its hardware.
  • the receiver 901 can be used to receive input digital or character information, and generate signal input related to the relevant settings and function control of the electronic device.
  • the transmitter 902 can be used to output digital or character information through the first interface; the transmitter 902 can also be used to send instructions to the disk group through the first interface to modify the data in the disk group; the transmitter 902 can also include a display device such as a display screen.
  • the processor 903 is used to execute the recommended method executed by the electronic device in the embodiments corresponding to Figures 3 to 7. It should be noted that the specific manner in which the application processor 9031 in the processor 903 executes the above steps is based on the same concept as the various method embodiments corresponding to Figures 3 to 7 in the present application, and the technical effects brought by it are the same as the various method embodiments corresponding to Figures 3 to 7 in the present application. For specific contents, please refer to the description in the method embodiments shown in the previous embodiment of the present application, which will not be repeated here.
  • a computer-readable storage medium is also provided in an embodiment of the present application, which stores a program for signal processing.
  • the computer executes the steps executed by the server in the method described in the embodiments shown in Figures 3 to 7 above, or the computer executes the steps executed by the electronic device in the method described in the embodiments shown in Figures 3 to 7 above.
  • Also provided in an embodiment of the present application is a computer program product, which, when executed on a computer, enables the computer to execute the steps executed by the server in the method described in the embodiments shown in the aforementioned Figures 3 to 7, or enables the computer to execute the steps executed by the electronic device in the method described in the embodiments shown in the aforementioned Figures 3 to 7.
  • the electronic device or server provided in the embodiment of the present application may specifically be a chip, and the chip includes: a processing unit and a communication unit, wherein the processing unit may be, for example, a processor, and the communication unit may be, for example, an input/output interface, a pin or a circuit, etc.
  • the processing unit may execute the computer execution instructions stored in the storage unit so that the chip executes the recommended method described in the embodiments shown in Figures 3 to 7 above.
  • the storage unit is a storage unit in the chip, such as a register, a cache, etc.
  • the storage unit may also be a storage unit located outside the chip in the wireless access device end, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), etc.
  • ROM read-only memory
  • RAM random access memory
  • the processor mentioned in any of the above places may be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the above-mentioned first aspect method.
  • the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.
  • the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.
  • the present application can be implemented by means of software plus necessary general-purpose hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc.
  • special hardware including special integrated circuits, special CPUs, special memories, special components, etc.
  • all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits.
  • software program implementation is a better implementation method in most cases.
  • the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art.
  • the computer software product is stored in a readable storage medium, such as a computer floppy disk, U disk, mobile hard disk, ROM, RAM, disk or CD, etc., and includes a number of instructions to enable
  • a computer device which may be a personal computer, a server, or a network device, etc. executes the methods described in each embodiment of the present application.
  • all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof.
  • all or part of the embodiments may be implemented in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the process or function described in the embodiment of the present application is generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integrations.
  • the available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
  • a magnetic medium e.g., a floppy disk, a hard disk, a tape
  • an optical medium e.g., a DVD
  • a semiconductor medium e.g., a solid-state drive (SSD)

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种推荐方法以及相关设备，该方法可将人工智能技术应用于个性化推荐领域中，方法包括：电子设备从多个匹配规则中确定与用户的特征信息的取值匹配的第一匹配规则，并向服务器发送第一信息，第一信息包括第一匹配规则的标识信息，第一信息用于供服务器得到第二信息；电子设备接收服务器发送的第二信息，该第二信息用于指示第一应用程序和/或第一服务，在显示单元上推荐第一应用程序和/或第一服务；由于每个匹配规则指示用户的至少一种特征信息的取值范围，而第一匹配规则与用户的特征信息的取值匹配，也即实现了向用户个性化的推荐应用程序和/或服务；且向服务器发送第一匹配规则的标识信息，避免了用户的隐私信息的泄露。

Description

一种推荐方法以及相关设备
本申请要求于2022年11月01日提交国家知识产权局、申请号为202211372446.8、发明名称为“一种推荐方法以及相关设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及人工智能领域，尤其涉及一种推荐方法以及相关设备。
背景技术
人工智能(Artificial Intelligence，AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个分支，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式作出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。利用人工智能技术进行个性化推荐是人工智能常见的一个应用方式。
为了实现向用户个性化的推荐，电子设备侧需要收集用户详细的描述数据，将前述用户的描述数据上传至云端，云端根据用户的描述数据，确定向用户推荐的应用程序或服务，并由电子设备展示给用户。
但是，将用户详细的描述数据上传至云端服务器，会造成用户的隐私信息的泄露。
发明内容
本申请实施例提供了一种推荐方法以及相关设备，根据第一匹配规则的标识信息得到第二信息，进而得到向用户推荐的应用程序和/或服务，第一匹配规则为与用户的特征信息的取值匹配的规则，不仅实现了个性化的确定向用户推荐的应用程序和/或服务，而且避免了将用户详细的描述数据发送至第一通信设备，避免了用户的隐私信息的泄露。
为解决上述技术问题，本申请实施例提供以下技术方案：
第一方面，本申请实施例提供一种推荐方法，可将人工智能技术应用于个性化推荐领域中，方法包括：电子设备上可以部署多个匹配规则和每个匹配规则的标识信息，在确定用户的特征信息的取值之后，从多个匹配规则中确定与用户的特征信息的取值匹配的第一匹配规则，并获取第一匹配规则的标识信息；其中，多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围。电子设备向服务器发送第一信息，其中，第一信息中包括第一匹配规则的标识信息，第一信息用于供服务器得到第二信息。电子设备接收服务器发送的第二信息，第二信息用于指示第一应用程序和第一服务，并在显示单元上推荐第一应用程序和/或第一服务，例如，“在显示单元上推荐第一应用程序和/或第一服务”可以理解为在显示单元上展示第一应用程序和/或第一服务的访问接口。其中，每个应用程序可以向用户提供一个或多个服务，“服务”也可以称为“原子化服务”、“应用服务”或其他名称等，一个服务指的是应用程序中具有独立入口的服务。例如，一个购物类的应用程序可以包括“商品浏览”、“购物车”、“支付”或其他服务等；又例如，“扫一扫”功能也是一个服务等，此处不做穷举。
本实现方式中，电子设备可以获取与用户的特征信息的取值匹配的第一匹配规则的标识信息，并将第一匹配规则的标识信息发送给服务器，从而服务器可以根据第一匹配规则的标识信息得到第二信息，电子设备根据接收到的第二信息确定向用户推荐的应用程序和/或服务，由于第一匹配规则是与用户的特征信息的取值匹配的匹配规则，因此实现了个性化的确定向用户推荐的应用程序和/或服务，且仅需要向第二通信设备发送第一匹配规则的标识信息，避免了将用户详细的描述数据发送至服务器，避免了用户的隐私信息的泄露。
在第一方面的一种可能实现方式中，第一匹配规则包括至少一个匹配条件，每个匹配条件指示用户的一种特征信息的取值范围，用户的特征信息的取值满足第一匹配规则中所有的匹配条件；或者，第一匹配规则中匹配条件的总数量为第一数值，第一匹配规则包括的至少一个匹配条件中该用户的特征信息的取值所满足的匹配条件的个数为第二数值，第二数值和第一数值之间的比值大于或等于第一阈值，例 如，第一阈值的取值可以为百分之九十、百分之八十五、百分之八十或其他取值等。
在第一方面的一种可能实现方式中，第一信息还包括第二匹配规则的标识信息，第二匹配规则包含于上述多个匹配规则，且第二匹配规则为与用户的特征信息的取值不匹配的匹配规则。本实现方式中，电子设备向服务器发送的第一信息中不仅包括第一匹配规则的标识信息，还包括第二匹配规则的标识信息，从而电子设备无法确定哪个匹配规则的标识信息是服务器命中的，哪个匹配规则的标识信息不是服务器命中的，有利于提高电子设备根据匹配规则的标识信息反向推理出服务器的用户的特征信息的难度，以进一步保护用户的隐私数据。
在第一方面的一种可能实现方式中，第二信息还用于指示第一匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系，以及第二匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系；例如，第二信息可以包括第一匹配规则的标识信息与应用程序和/或服务的信息之间的对应关系，以及，第二匹配规则的标识信息与应用程序和/或服务的信息之间的对应关系。进一步地，应用程序和/或服务的信息可以包括应用程序和/或服务的标识信息，例如，应用程序和/或服务的标识信息可以为应用程序的名称、应用程序的图标、服务的名称、服务的图标、应用程序或服务的标识号或其他可以唯一指向一个应用程序或服务的标识信息等。
其中，第一应用程序和/或第一服务为所述第二信息指示的多个应用程序和/或服务中与所述第一匹配规则的标识信息对应的应用程序和/或服务，则电子设备在接收到服务器发送的第二信息之后，还可以根据第一匹配规则的标识信息和第二信息，确定向用户推荐的第一应用程序和/或第一服务。可选地，电子设备可以根据第一匹配规则的标识信息，从第二信息包括的多个应用程序和/或服务的信息中选取与第一匹配规则的标识信息对应的一个或多个第一应用程序和/或第一服务的信息。
本实现方式中，由于第一匹配规则是与用户的特征信息匹配的规则，第二匹配规则是与用户的特征信息不匹配的规则，在第一信息中加入了第二匹配规则的标识信息，服务器无法确定第一信息中哪些标识信息是与用户的特征信息匹配的规则的标识信息，进一步加大了服务器反向推理出用户的特征信息的难度；由于在第一信息中加入了第二匹配规则的标识信息，对应的，第二信息中包括与第二匹配规则的标识信息对应的应用程序和/或服务的信息，电子设备能够根据第一匹配规则的标识信息和第二信息，确定最终需要向用户推荐的应用程序和/或服务，从而在保证用户的隐私数据安全度的前提下，有利于实现向用户精准的展示客体。
在第一方面的一种可能实现方式中，方法应用于电子设备，电子设备中部署的匹配规则包括第一匹配规则，电子设备中部署的匹配规则和/或电子设备中部署的匹配规则的标识信息为可更新的。本实现方式中，将电子设备中部署的匹配规则和/或电子设备中部署的匹配规则的标识信息设置为可更新的，不仅有利于更为精准的向用户推荐可能感兴趣的应用程序和/或服务，而且有利于提高电子设备上计算机资源的利用率；例如，当基于某个匹配规则推荐的应用程序和/或服务的点击率过低时，可以删除该匹配规则，不仅减少了匹配规则所占用的存储资源，且电子设备不再需要对删除掉的匹配规则执行匹配操作，减少了对处理器资源的消耗。
在第一方面的一种可能实现方式中，用户的特征信息包含以下一种或多种：用户的画像信息、用户使用应用程序时的行为信息、用户所使用的电子设备的信息或者与电子设备通信连接的其他电子设备的信息等，此处不做穷举。示例性地，用户的画像信息可以包括如下任一种或多种信息：姓名、性别、年龄、生日、当前位置、家的位置、公司的位置、作息时间、通勤方式、运动爱好或其他信息等。用户使用应用程序时的行为信息可以包括如下任一种或多种信息：用户常用的应用程序、使用率最高的n个应用程序中每个应用程序在最近X天的平均使用次数、在多个音乐类应用程序中用户偏好的音乐类应用程序、在多个视频类应用程序中的用户偏好的视频类应用程序、在多个美食类应用程序中用户偏好的美食类应用程序、在多个购物类应用程序中用户偏好的购物类应用程序等，n为大于等于1的整数，X为正数。用户所使用的电子设备的信息可以包括电子设备的如下任一种或多种信息：设备型号、设备类型、操作系统的类型、操作系统的版本号、电子设备的ID或其他信息等。与电子设备通信连接的其他电子设备的信息可以包括与电子设备近场连接的其他电子设备的信息等，此处不做穷举。本实现方式中，提供了用户的特征信息具体表现为哪些信息，有利于提高本方案的可实现性。
第二方面，本申请实施例提供一种推荐方法，可将人工智能技术应用于个性化推荐领域中，方法包 括：服务器接收电子设备发送的第一信息，第一信息包括第一匹配规则的标识信息，第一匹配规则为多个匹配规则中的一个，其中，多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围，第一匹配规则用于指示电子设备的用户的特征信息的取值。服务器可以根据第一信息确定第二信息，向电子设备发送第二信息，其中，第二信息用于指示第一应用程序和/或第一服务。
在第二方面的一种可能实现方式中，服务器根据第一信息确定第二信息，可以包括：服务器上可以配置有多个匹配规则的标识信息中每个匹配规则的标识信息与应用程序和/或服务的信息之间的对应关系，前述多个匹配规则的标识信息包括第一信息中的每个匹配规则的标识信息。服务器根据第一信息中每个匹配规则的标识信息以及前述对应关系，获取到与第一信息中的至少一个匹配规则的标识信息对应的应用程序和/或服务的信息；其中，第二信息包括前述与第一信息中的匹配规则的标识信息对应的应用程序和/或服务的信息，前述与第一信息中的匹配规则的标识信息对应的应用程序和/或服务的信息包括第一应用程序和/或第一服务的信息；例如，应用程序和/或服务的信息可以包括应用程序和/或服务的标识信息。
在第二方面的一种可能实现方式中，方法还包括：服务器获取第四信息，第四信息包括与至少一个应用程序和/或服务具有关联关系的信息和/或与用户对应的群体画像信息。例如，服务器上可以配置有与至少一个应用程序和/或服务具有关联关系的信息的类型，则服务器可以根据与至少一个应用程序和/或服务具有关联关系的信息的类型，获取与前述至少一个应用程序和/或服务具有关联关系的信息。服务器在接收到电子设备发送的第一信息之后，可以确定用户的标识信息；服务器可以根据用户的账号信息获取与用户对应的群体画像信息。其中，与应用程序和/或服务具有关联关系的信息可以包括用户所在区域的天气信息、用户通过一个或多个应用程序购买的商品的快递信息、优惠活动信息或其他与应用程序和/或服务具有关联关系的信息等。群体画像信息包括的为一类用户的画像信息，例如，群体画像信息可以包括用户的年龄所在的年龄段、用户的性别、用户的消费水平类型或其他群体画像信息等。则服务器根据第一信息确定第二信息，可以包括：服务器根据第四信息和第一信息，确定第二信息。
本实现方式中，服务器在确定向用户推荐的应用程序和/或服务的过程中，不仅利用了第一信息，还可以利用与应用程序和/或服务具有关联关系的信息和/或与用户对应的群体画像信息，有利于更为充分的了解待推荐的客体以及当前用户，有利于确定出当前用户感兴趣的客体，从而提高向用户精准推荐客体的概率；此外，当电子设备尚未收集到用户的特征信息时，或者，电子设备仅能收集到用户少量的信息时，则电子设备仅能收集到用户少量的信息时，则获取到的群体画像信息能够辅助服务器确定出较为符合用户期望的客体。
在第二方面的一种可能实现方式中，电子设备中部署的匹配规则包括第一匹配规则，电子设备中部署的匹配规则和/或电子设备中部署的匹配规则的标识信息为可更新的。可选地，服务器更新电子设备上部署的匹配规则集合的场景可以包括如下任一种或多种：
电子设备在固定时间点更新服务器上的匹配规则集合；例如，服务器可以在初次在电子设备上部署了匹配规则集合之后，间隔第一时间段，对电子设备上的匹配规则集合执行一次更新操作，与更新后的匹配规则集合对应的信息的种类的数量大于与初始的匹配规则集合对应的信息的种类的数量；或者，
电子设备按照预设频率更新服务器上的匹配规则集合；或者，当需要推荐的客体发生变化时，电子设备更新服务器上的匹配规则集合；或者，
电子设备获取基于每个匹配规则确定的需要推荐的客体的点击率，若某个匹配规则所对应的点击率低于第二阈值时，确定需要删除前述匹配规则，在该场景中也会更新电子设备上的匹配规则集合，电子设备上的匹配规则集合包括电子设备中部署的匹配规则和/或匹配规则的标识信息。
本实现方式中，由于在刚刚开始执行本申请实施例提供的推荐方法时，电子设备可能采集到用户较少的信息，则初始配置的匹配规则集合涉及用户较少种类的信息，在经过了第一时间段之后，电子设备能够采集到用户更多种类的信息，则可以对电子设备上的匹配规则集合进行更新，更新后的匹配规则集合涉及用户更多种类的信息，使得电子设备上部署的匹配规则集合和电子设备当前获取到的信息之间的匹配度，有利于提高第一匹配规则的标识信息过程的准确度。
本申请第二方面中，第二方面的各个可能实现方式中的步骤的具体实现方式、名词的含义以及所带来的有益效果，均可以参阅第一方面，此处不再赘述。
第三方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面或第二方面所述的推荐方法。
第四方面，本申请实施例提供了一种电子设备，包括处理器和存储器，处理器与存储器耦合，存储器，用于存储程序；处理器，用于执行存储器中的程序，使得通信设备执行上述第一方面所述的推荐方法。
第五方面，本申请实施例提供了一种服务器，包括处理器和存储器，处理器与存储器耦合，存储器，用于存储程序；处理器，用于执行存储器中的程序，使得通信设备执行上述第二方面所述的推荐方法。
第六方面，本申请实施例提供了一种计算机程序产品，计算机程序产品包括程序，当该程序在计算机上运行时，使得计算机执行上述第一方面或第二方面所述的推荐方法。
第七方面，本申请提供了一种芯片系统，该芯片系统包括处理器，用于支持实现上述第一方面或第二方面中所涉及的功能，例如，发送或处理上述方法中所涉及的数据和/或信息。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存电子设备或通信设备必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
附图说明
图1为本申请实施例提供的人工智能主体框架的一种结构示意图；
图2为本申请实施例提供的推荐方法的一种应用场景图；
图3为本申请实施例提供的推荐方法的一种流程示意图；
图4为本申请实施例提供的推荐方法的另一种流程示意图；
图5为本申请实施例提供的向用户展示客体的一种界面示意图；
图6为本申请实施例提供的向用户展示客体的另一种界面示意图；
图7为本申请实施例提供的向用户展示客体的又一种界面示意图；
图8为本申请实施例提供的服务器一种结构示意图；
图9为本申请实施例提供的电子设备的一种结构示意图。
具体实施方式
下面结合附图，对本申请的实施例进行描述。本领域普通技术人员可知，随着技术的发展和新场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，这仅仅是描述本申请的实施例中对相同属性的对象在描述时所采用的区分方式。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，以便包含一系列单元的过程、方法、系统、产品或设备不必限于那些单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它单元。
首先对人工智能系统总体工作流程进行描述，请参见图1，图1示出的为人工智能主体框架的一种结构示意图，下面从“智能信息链”(水平轴)和“IT价值链”(垂直轴)两个维度对上述人工智能主题框架进行阐述。其中，“智能信息链”反映从数据的获取到处理的一列过程。举例来说，可以是智能信息感知、智能信息表示与形成、智能推理、智能决策、智能执行与输出的一般过程。在这个过程中，数据经历了“数据—信息—知识—智慧”的凝练过程。“IT价值链”从人智能的底层基础设施、信息(提供和处理技术实现)到系统的产业生态过程，反映人工智能为信息技术产业带来的价值。
(1)基础设施
基础设施为人工智能系统提供计算能力支持，实现与外部世界的沟通，并通过基础平台实现支撑。通过传感器与外部沟通；计算能力由智能芯片提供，该智能芯片具体可以采用中央处理器(central processing unit，CPU)、嵌入式神经网络处理器(neural-network processing unit，NPU)、图形处理器(graphics processing unit，GPU)、专用集成电路(application specific integrated circuit，ASIC)或现场可编程门阵列(field programmable gate array，FPGA)等硬件加速芯片；基础平台包括分布式计算框架及网络等相关的平台保障和支持，可以包括云存储和计算、互联互通网络等。举例来 说，传感器和外部沟通获取数据，这些数据提供给基础平台提供的分布式计算系统中的智能芯片进行计算。
(2)数据
基础设施的上一层的数据用于表示人工智能领域的数据来源。数据涉及到图形、图像、语音、文本，还涉及到传统设备的物联网数据，包括已有系统的业务数据以及力、位移、液位、温度、湿度等感知数据。
(3)数据处理
数据处理通常包括数据训练，机器学习，深度学习，搜索，推理，决策等方式。
其中，机器学习和深度学习可以对数据进行符号化和形式化的智能信息建模、抽取、预处理、训练等。
推理是指在计算机或智能系统中，模拟人类的智能推理方式，依据推理控制策略，利用形式化的信息进行机器思维和求解问题的过程，典型的功能是搜索与匹配。
决策是指智能信息经过推理后进行决策的过程，通常提供分类、排序、预测等功能。
(4)通用能力
对数据经过上面提到的数据处理后，进一步基于数据处理的结果可以形成一些通用的能力，比如可以是算法或者一个通用系统，例如，翻译，文本的分析，计算机视觉的处理，语音识别，图像的识别等等。
(5)智能产品及行业应用
智能产品及行业应用指人工智能系统在各领域的产品和应用，是对人工智能整体解决方案的封装，将智能信息决策产品化、实现落地应用，其应用领域主要包括：智能终端、智能制造、智能交通、智能家居、智能医疗、智能安防、自动驾驶、智慧城市等。
本申请可以应用于各个领域中需要个性化推荐的应用场景中，下面将对多个落地到产品的多个应用场景进行介绍。在一种应用场景中，在智能终端领域中，智能终端可以从已经安装的多个应用程序中，选取向用户个性化的推荐应用程序和/或服务，并向用户展示前述应用程序和/或服务的访问接口，用户可以通过前述访问接口快速的访问应用程序和/或服务。其中，每个应用程序可以向用户提供一个或多个服务，“服务”也可以称为“原子化服务”、“应用服务”或其他名称等，一个服务指的是应用程序中具有独立入口的服务。例如，一个购物类的应用程序可以包括“商品浏览”、“购物车”、“支付”或其他服务等；又例如，“扫一扫”功能也是一个服务；又例如，某个优惠券的访问接口也是一个服务等，此处举例仅为方便理解服务的概念，不用于限定本方案。
为更直观地理解本方案，请参阅图2，图2为本申请实施例提供的推荐方法的一种应用场景图，如图2所示，手机通过展示界面上201示出的区域向用户个性化的展示了3个应用程序的访问接口和1个服务的访问接口，3个应用程序分别为音乐类应用程序A1、视频类应用程序A2和购物类应用程序A3，1个服务为“扫一扫”功能，应理解，图2中的示例仅为方便理解本方案，不用于限定本方案。
在另一种应用场景中，在智能终端领域中，用户在使用视频类的应用程序时，视频类的应用程序可以向用户个性化的展示用户可能感兴趣的视频；或者，用户在使用音乐类的应用程序时，视频类的应用程序可以向用户个性化的推荐用户可能感兴趣的歌曲；或者，用户在使用购物类的应用程序时，购物类的应用程序可以向用户个性化的推荐用户可能感兴趣的商品；或者，用户在使用游戏大全这种应用程序时，可以向用户个性化的推荐可能感兴趣的游戏。在另一种应用场景中，在智能家居领域中，冰箱可以向用户个性化地推荐食谱等等，此处不对本申请的所有应用场景进行穷举。
在上述种种应用场景中，为了在不泄露用户的隐私信息的前提下，个性化的确定向用户推荐的客体，本申请实施例提供了一种推荐方法。其中，需要向用户推荐的客体可以包括如下任一项或多项：应用程序、服务、音频、视频、商品、食谱、游戏或其他类型的客体等等，此处不做穷举；本申请实施例中，提供了需要向用户展示的应用程序和/或服务的多种具体表现形式，将本方案落实到多个具体的应用场景中，提高了本方案的可实现性。需要说明的是，本申请及后续实施例中以需要向用户推荐的客体为应用程序和/或服务为例进行说明，当需要向用户推荐的客体表现为其他类型的客体时，可参阅执行，本申请实施例中不再赘述。
可选的，请参阅图3，图3为本申请实施例提供的推荐方法的一种流程示意图。本申请提供的推荐系统可以包括第一通信设备和第二通信设备，第一通信设备可以为网络端设备，网络端设备可以由一个或多个服务器实现，例如：一个或多个云端服务器；第二通信设备可以表现为电子设备，例如，第二通信设备可以表现为手机、平板、笔记本电脑、台式电脑、电视或其他类型的电子设备等等，此处不对第一通信设备和第二通信设备的具体产品形态进行穷举。
其中，301、电子设备上可以部署有多个匹配规则以及每个匹配规则的标识信息，电子设备可以确定用户的多种特征信息的取值之后，根据用户的多种特征信息的取值，从多个匹配规则中确定与用户的特征信息的取值匹配的至少一个第一匹配规则，并获取每个第一匹配规则的标识信息，其中，多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围。
302、电子设备在获取到至少一个第一匹配规则的标识之后，可以生成第一信息，并向服务器发送第一信息，前述第一信息包括第一匹配规则的标识信息。
303、服务器在接收到第一信息之后，可以根据第一信息确定第二信息，第二信息包括至少一个应用程序和/或服务的信息；例如，第一通信设备上可以部署有匹配规则的标识信息与应用程序和/或服务的信息之间的对应关系，则第一通信设备可以根据第一信息中携带的匹配规则的标识信息和前述对应关系，确定至少一个应用程序和/或服务的信息。
304、服务器在生成第二信息之后，可以向终端设备发送第二信息，第二信息用于指示第一应用程序和/或第一服务。
305、电子设备在接收到第二信息之后，可以根据第二信息确定向用户推荐的第一应用程序和/或第一服务，并在电子设备的显示单元上推荐第一应用程序和/或第一服务。
本申请实施例中，由于服务器是根据匹配规则的标识信息确定第二信息的，而前述匹配规则的标识信息是电子设备根据用户的特征信息的取值确定的，因此能够实现个性化的确定向用户展示的应用程序和/或服务；而且，电子设备向服务器发送的是匹配规则的标识信息，避免了将用户的原始信息发送给服务器，从而避免了用户的隐私信息的泄露。
结合上述描述，下面开始对本申请实施例提供的推荐方法的具体实现流程进行描述。具体的，请参阅图4，图4为本申请实施例提供的推荐方法的另一种流程示意图，本申请实施例提供的推荐方法可以包括：
401、电子设备确定用户的特征信息的取值，从多个匹配规则中确定与用户的特征信息的取值匹配的第一匹配规则，获取第一匹配规则的标识信息，多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围。
本申请实施例中，电子设备可以获取用户的N种特征信息的取值，N为大于或等于1的正整数。例如，用户的N种特征信息可以包括如下任一类或多类信息：用户的画像信息、用户使用应用程序时的行为信息、用户所使用的电子设备的信息、与电子设备通信连接的其他电子设备的信息或者用户的其他特征信息等，此处不做赘述。
其中，用户的画像信息可以包括如下任一种或多种信息：姓名、性别、年龄、生日、当前位置、家的位置、公司的位置、作息时间、通勤方式、运动爱好或其他信息等。用户使用应用程序时的行为信息可以包括如下任一种或多种信息：用户常用的应用程序、使用率最高的n个应用程序中每个应用程序在最近X天的平均使用次数、在多个音乐类应用程序中用户偏好的音乐类应用程序、在多个视频类应用程序中的用户偏好的视频类应用程序、在多个美食类应用程序中用户偏好的美食类应用程序、在多个购物类应用程序中用户偏好的购物类应用程序等，n为大于等于1的整数，X为正数。
用户所使用的电子设备的信息可以包括电子设备的如下任一种或多种信息：设备型号、设备类型、操作系统(Operating System，OS)的类型、操作系统的版本号、电子设备的ID或其他信息等。
与电子设备通信连接的其他电子设备的信息可以包括与电子设备近场连接的其他电子设备，例如采用近场技术实现与电子设备连接的其他电子设备，例如，前述其他电子设备可以包括平板、个人计算机(personal computer，PC)、智慧屏、智能音箱、耳机、智能手表或其他设备等等，需要说明的是，此处对N种特征信息的举例仅为方便理解本方案，不用于限定本方案。
电子设备上可以配置有匹配规则集合，前述匹配规则集合中包括多个匹配规则以及多个匹配规则中 每个匹配规则的标识信息，每个匹配规则包括一个或多个匹配条件，每个匹配条件包括用户的一种特征信息的取值范围。
例如，每个匹配规则的标识信息可以为序列号、文字形式的标识信息或其他类型的标识信息等；示例性地，一个匹配规则的标识信息可以为00000001、00000002或BB10000001等，此处举例仅为方便理解本方案，不用于限定本方案。
每个匹配规则中的任意一个匹配条件(为方便描述，后续称为“目标匹配条件”)可以包括一个或多个特定的值；例如，用户的特征信息的类型为性别，与“性别”这一用户的特征信息对应的匹配条件可以为女；又例如，用户的特征信息的类型为通勤方式，与“通勤方式”这一用户的特征信息对应的匹配条件可以包括公交和地铁；又例如，用户的特征信息为当前位置，与“当前位置”这一特征信息对应的匹配条件可以包括在家等等。
目标匹配条件也可以包括连续的值；例如，用户的特征信息的类型为应用程序D1的使用时长，与“应用程序D1的使用时长”这一用户的特征信息对应的匹配条件可以包括最近一天内应用程序D1的使用时长大于或等于2小时；又例如，用户的特征信息的类型为应用程序D2在近3天内的平均使用次数，与“应用程序D2在近3天内的平均使用次数”这一用户的特征信息对应的匹配条件可以包括应用程序D2在近3天内的平均使用次数大于或等于3次等，应理解，此处对匹配规则中目标匹配条件的举例仅为方便理解本方案，不用于限定本方案。为更直观地理解本方案，以下结合表1对电子设备上配置的匹配规则集合进行举例。
表1
表1中示出了4个匹配规则以及每个匹配规则的标识信息，例如，参阅表1中的第一行，0000000001这一匹配规则的标识信息指向的匹配规则可以包括在公司+当前时间为点餐时间段+美食类的应用程序中偏好使用应用程序C1+近3天内通过美食类应用程序C1点餐的平均次数大于或等于3次，0000000001这一匹配规则的标识信息指向的匹配规则包括了4个匹配条件，其中，“在公司”这一匹配条件代表“公司位置”这一用户的特征信息的取值范围需要包括用户的当前位置，“当前时间为点餐时间段”这一匹配条件代表“就餐时间”这一用户的特征信息的取值范围需要包括当前时刻，“美食类的应用程序中偏好使用应用程序C1”这一匹配条件代表“美食类的应用程序中偏好使用应用程序”这一用户信息的取值范围需要包括应用程序C1，“近3天内通过美食类应用程序C1点餐的平均次数大于或等于3次”这一匹配条件代表“近3天内通过美食类应用程序C1点餐的平均次数”这一用户信息的取值范围需要大于或等于3次；又例如，参阅表1中的第二行，0000000002这一匹配规则的标识信息指向的匹配规则可以包括手机+在家+休息+购物类的应用程序中偏好使用应用程序C2+近三天内对应用程序C2的平均使用次数大于或等于4次，0000000002这一匹配规则的标识信息指向的匹配规则包括了5个匹配条件，其中，“手机”这一匹配条件代表“设备类型”这一用户的特征信息的取值范围需要包括手机，“在家”这一匹配条件代表“家的位置”这一用户的特征信息的取值范围需要包括用户的当前位置，“休息”这一匹配条件代表“休息时间段”这一用户的特征信息的取值范围需要包括当前时刻，“购物类的应用程序中偏好使用应用程序C2”这一匹配条件代表“购物类的应用程序中偏好使用应用程序”这一用户信息的取值范围需要包括应用程序C2，“近三天内对应用程序C2的平均使用次数大于或等于4次”这一匹配条件代表“近三天内对应用程序C2的平均使用次数”这一用户信息的取值范围需要大于或等于4次等；对于表1中第三行和第四行的解释可以参阅上述对表1的第一行和第二行的解释，此处不做赘述，需要说明的是，表1中的示例仅为方便理解“匹配规则”和“匹配规则的标识信息”这两个概念，在实际应用中，电子 设备上可以配置其他的匹配规则以及匹配规则的标识信息，此处不做限定。
电子设备可以根据用户的N种特征信息的取值，从多个匹配规则中确定至少一个第一匹配规则，并获取每个第一匹配规则的标识信息。其中，每个第一匹配规则可以包括与用户的N种特征信息中至少一种特征信息对应的匹配条件，每个匹配条件包括用户的一种特征信息的取值范围；第一匹配规则为电子设备部署的多个匹配规则中与用户的特征信息的取值匹配成功的规则，也即第一匹配规则为电子设备部署的多个匹配规则中用户的特征信息的取值命中的规则。
具体的，电子设备可以从多个匹配规则中获取任意一个匹配规则(为方便描述，后续称为“目标匹配规则”)，根据用户的N种特征信息的取值，判断目标匹配规则是否与用户的特征信息的取值匹配，若判断结果为是，则将目标匹配规则确定为第一匹配规则；若判断结果为否，则从多个匹配规则中获取下一个匹配规则，并执行前述判断步骤。电子设备可以重复执行前述操作，以逐个判断多个匹配规则中的每个匹配规则是否与用户的特征信息的取值匹配，以从多个匹配规则中获取到至少一个第一匹配规则。
一个目标匹配规则可以包括一个或多个匹配条件，电子设备可以采用多种方式执行“目标匹配规则是否与用户的特征信息的取值匹配”的判断操作。在一种实现方式中，电子设备可以根据用户的一种或多种特征信息的取值，判断是否满足目标匹配规则中的匹配条件的要求，若用户的一种或多种特征信息的取值均满足目标匹配规则的要求，则确定目标匹配规则与用户的特征信息的取值匹配；若用户的一种或多种特征信息的取值中存在任意一种特征信息的取值不满足目标匹配规则的要求，则确定目标匹配规则与用户的特征信息的取值不匹配。为更直观地理解本方案，以下结合表2中的匹配规则对“判断目标匹配规则是否与用户的特征信息的取值匹配”这一判断操作的具体实现过程进行举例。
表2
表2中以目标匹配规则(也即电子设备上部署的任意一个匹配规则)为表1中0000000002这一匹配规则的标识信息指向的匹配规则为例，对于表2中的匹配规则的理解，可以参阅上述对表1的解释，此处不做赘述，示例性地，由于0000000002这一匹配规则的标识信息指向的匹配规则包括了与用户的5种信息对应的5个匹配条件，则服务器可以分别获取“设备类型”、“家的位置”、“休息时间段”、“购物类的应用程序中偏好使用应用程序”以及“近三天内对应用程序C2的平均使用次数”这5种用户的特征信息的取值；服务器判断用户的设备类型是否为手机，判断用户的家的位置是否包括当前位置，判断用户在购物类的应用程序中偏好的应用程序是否为应用程序C2，以及判断用户近三天内对应用程序C2的平均使用次数是否大于或等于4次；若前述多个判断操作的判断结果均为是，则服务器可以确定用户的特征信息满足0000000002这一匹配规则的要求，也即可以确定0000000002这一匹配规则与用户的特征信息匹配；若前述多个判断操作中任一个判断操作的判断结果为否，则服务器可以确定用户的特征信息不满足0000000002这一匹配规则的要求，也即可以确定0000000002这一匹配规则与用户的特征信息不匹配；应理解，此处举例仅为方便理解本方案，不用于限定本方案。
在另一种实现方式中，电子设备可以确定目标匹配规则中匹配条件的总数量为第一数值，电子设备根据用户的特征信息的取值，确定目标匹配规则包括的至少一个匹配条件中该用户的特征信息的取值所满足的匹配条件的个数为第二数值，若第二数值和第一数值之间的比值大于或等于第一阈值，则可以确定目标匹配规则与用户的特征信息的取值匹配；若第二数值和第一数值之间的比值小于第一阈值，则可以确定目标匹配规则与用户的特征信息的取值不匹配。例如，第一阈值的取值可以为百分之九十、百分之八十五、百分之八十或其他取值等等，此处不做限定。
需要说明的是，电子设备还可以通过其他方式实现“从多个匹配规则中确定与用户的特征信息的取值匹配的一个或多个第一匹配规则”，此处不做穷举。
可选地，电子设备中部署的多个匹配规则以及每个匹配规则的标识信息由服务器生成并发送至电子设备上。可选地，电子设备中部署的匹配规则和/或电子设备中部署的匹配规则的标识信息为可更新的。
电子设备可以采用多种方式来更新服务器上的匹配规则集合。在一种实现方式中，服务器可以向电子设备发送匹配规则集合，匹配规则集合中包括多个匹配规则以及每个匹配规则的标识信息；当服务器 需要更新电子设备上的匹配规则集合时，服务器可以向电子设备发送第一指示信息，第一指示信息用于告知电子设备从前述匹配规则集合中删除一个或多个匹配规则以及该匹配规则的标识信息，和/或，向前述匹配规则集合中增加一个或多个匹配规则以及该匹配规则的标识信息；电子设备根据第一指示信息，从前述匹配规则集合中删除一个或多个匹配规则以及该匹配规则的标识信息，和/或，向前述匹配规则集合中添加一个或多个匹配规则以及该匹配规则的标识信息，以得到更新后的匹配规则集合。
具体的，在一种实现方式中，第一指示信息可以包括至少一个第一标识信息以及第二指示信息，第二指示信息用于指示每个第一标识信息为需要删除的匹配规则的标识信息；和/或，第一指示信息可以包括至少一个第二标识信息、与每个第二标识信息对应的匹配规则以及第三指示信息，第三信息用于指示将每个第二标识信息以及每个第二标识信息所对应的匹配规则添加至匹配规则集合中。其中，第一标识信息和第二标识信息均为匹配规则的标识信息，区别在于，第一标识信息为匹配规则集合中的匹配规则的标识信息，匹配规则集合中不存在第二标识信息。第二指示信息和第三指示信息不同，例如，第二指示信息可以为“删除”，第三指示信息可以为“添加”；又例如，第二指示信息可以为“0”，第三指示信息可以为“1”等等，此处不做穷举。
在另一种实现方式中，第一指示信息中可以携带至少一个需要删除的匹配规则的标识信息，和/或，指示一个需要添加的匹配规则的标识信息以及每个标识信息所对应的匹配规则；电子设备在获取到第一指示信息之后，可以判断匹配规则集合中的匹配规则的标识信息是否与第一指示信息中携带的匹配规则的标识信息存在重合；若匹配规则集合和第一指示信息中存在重合的标识信息，则电子设备可以从匹配规则集合中删除前述重合的第一标识信息以及前述重合的第一标识信息所对应的匹配规则；若匹配规则集合和第一指示信息中不存在重合的标识信息，则电子设备可以确定不存在需要删除的匹配规则。电子设备还可以判断第一指示信息中是否存在匹配规则集合之外的标识信息，若第一指示信息中存在匹配规则集合之外的第二标识信息，则电子设备可以将每个第二标识信息以及每个第二标识信息所对应的匹配规则添加至匹配规则集合中；若第一指示信息中不存在匹配规则集合之外的第二标识信息，则电子设备可以确定不需要向匹配规则集合中添加匹配规则等。需要说明的是，电子设备还可以采用其他方式实现“根据第一指示信息，在匹配规则集合的基础上删除和/或添加匹配规则”，此处举例仅为证明本方案的可实现性，不用于限定本方案。
在另一种实现方式中，服务器可以向电子设备发送匹配规则集合，匹配规则集合中包括多个匹配规则以及每个匹配规则的标识信息。当服务器需要更新电子设备上的匹配规则集合时，直接向电子设备发送更新后的匹配规则集合，更新后的匹配规则集合中包括多个匹配规则以及每个匹配规则的标识信息。电子设备将更新前的匹配规则集合删除，并存储更新后的匹配规则集合。
服务器可以在多种场景下更新电子设备上部署的匹配规则集合。在一种应用场景中，电子设备可以在固定时间点更新服务器上的匹配规则集合；例如，服务器可以在初次在电子设备上部署了匹配规则集合之后，间隔第一时间段，对电子设备上的匹配规则集合执行一次更新操作，与更新后的匹配规则集合对应的信息的种类的数量大于与初始的匹配规则集合对应的信息的种类的数量；示例性地，第一时间段可以为一个月、50天或其他数值等。本申请实施例中，由于在刚刚开始执行本申请实施例提供的推荐方法时，电子设备可能采集到用户较少的信息，则初始配置的匹配规则集合涉及用户较少种类的信息，在经过了第一时间段之后，电子设备能够采集到用户更多种类的信息，则可以对电子设备上的匹配规则集合进行更新，更新后的匹配规则集合涉及用户更多种类的信息，使得电子设备上部署的匹配规则集合和电子设备当前获取到的信息之间的匹配度，有利于提高第一匹配规则的标识信息过程的准确度。
在另一种应用场景中，电子设备也可以按照预设频率更新服务器上的匹配规则集合；例如，每隔一个月对电子设备上的匹配规则集合执行一次更新操作等，此处不做限定。
在另一种应用场景中，当需要推荐的应用程序和/或服务发生变化时，电子设备可以更新服务器上的匹配规则集合。此处以需要推荐的应用程序和/或服务包括应用程序和服务为例，例如，当某个购物类的应用程序推出了一项优惠活动时，与前述购物类的应用程序所对应的匹配规则可以发生改变；又例如，当某个应用程序推出新的服务时，则需要增加与新出的服务对应的匹配规则；又例如，当某个应用程序不再需要被推荐时，则需要删除与前述应用程序对应的匹配规则等等，此处不做穷举。
在另一种应用场景中，电子设备还可以获取基于每个匹配规则确定的需要推荐的应用程序和/或服 务的点击率，若某个匹配规则所对应的点击率低于第二阈值时，确定需要删除前述匹配规则，在该场景中也需要更新电子设备上的匹配规则集合等，需要说明的是，电子设备还可以在其他场景中执行“电子设备上的匹配规则集合”的更新操作，此处举例仅为方便理解本方案，不用于限定本方案。
本申请实施例中，将电子设备中部署的匹配规则和/或电子设备中部署的匹配规则的标识信息设置为可更新的，不仅有利于更为精准的展示用户可能感兴趣的应用程序和/或服务，而且有利于提高电子设备上计算机资源的利用率；例如，当基于某个匹配规则推荐的应用程序和/或服务的点击率过低时，可以删除该匹配规则，不仅减少了匹配规则所占用的存储资源，且电子设备不再需要对删除掉的匹配规则执行匹配操作，减少了对处理器资源的消耗。
402、电子设备向服务器发送第一信息，第一信息包括第一匹配规则的标识信息。
本申请实施例中，电子设备在获取至少一个第一匹配规则的标识信息之后，可以向服务器发送第一信息，对应的，服务器可以接收到第一信息。其中，第一信息至少包括每个第一匹配规则的标识信息，第一信息用于请求服务器根据第一信息中携带的匹配规则的标识信息确定一个或多个待推荐的应用程序和/或服务。
电子设备可以采用多种方式确定第一信息中携带哪些第一匹配规则的标识信息。具体的，在一种实现方式中，第一信息可以包括步骤401中确定的所有第一匹配规则的标识信息，则电子设备在通过步骤401确定了至少一个第一匹配规则的标识信息之后，可以将步骤401中确定的所有第一匹配规则的标识信息，确定为第一信息中包括的第一匹配规则的标识信息。在另一种实现方式中，电子设备在通过步骤401确定了至少一个第一匹配规则的标识信息后，可以从步骤401确定的第一匹配规则的标识信息中选取一个或多个第一匹配规则的标识信息，也即第一信息可以包括步骤401中确定的部分第一匹配规则的标识信息。
可选地，电子设备可以从多个匹配规则的标识信息中随机选择至少一个第二匹配规则的标识信息，进而生成第一信息，第一信息还可以包括电子设备上部署的多个匹配规则中的至少一个第二匹配规则的标识信息。其中，第二匹配规则和第一匹配规则为多个匹配规则中不同的匹配规则，也即第二匹配规则为与用户的特征信息的取值不匹配的规则，“第二匹配规则的标识信息”的含义与“第一匹配规则的标识信息”的含义类似，具体可参阅步骤401中对“第一匹配规则的标识信息”的含义的描述，此处不做赘述。
进一步可选地，第一信息中第二匹配规则的标识信息的数量与第一匹配规则的标识信息的数量之间的比值可以大于第三阈值，例如，第三阈值的取值可以为百分之六十、百分之七十、百分之八十或其他数值等等，此处不做限定。
电子设备可以在多种场景中触发开始执行步骤401和402，在一种场景中，电子设备可以按照预设频率触发开始执行步骤401和402，例如，预设频率可以为每隔2个小时、3个小时、4个小时或其他时长执行一次等，此处不做限定。在另一种场景中，电子设备可以在固定时间点触发开始执行步骤401和402，例如，固定时间点可以包括每天早上7点、下午4点和晚上8点等，此处不做限定。
在另一种场景中，也可以为用户每次访问需要向用户展示的应用程序和/或服务所在的界面时，电子设备接收到对前述界面的展示指令，从而触发开始执行步骤401和402；示例性地，请参阅图2，当电子设备接收到对图2示出的界面的展示指令时，可以触发开始执行步骤401和402。
在另一种场景中，电子设备每执行一次步骤401和402，能够获取到多个应用程序和/或服务的信息，电子设备可以分多次展示前述获取到的应用程序和/或服务，可以为电子设备在将需要向用户展示的应用程序和/或服务全部展示完毕时，触发重新执行步骤401和402；例如，电子设备执行一次步骤401和402获取到了9个应用程序和/或服务的信息，一次性最多向用户展示4个应用程序和/或服务的访问接口，则可以在电子设备将前述9个应用程序和/或服务向用户全部展示完毕后，再次触发执行步骤401和402等等，具体在哪些场景中触发开始执行步骤401和402可以结合实际应用场景灵活设定，此处不做限定。
403、服务器获取第四信息，第四信息包括与应用程序和/或服务具有关联关系的信息，和/或与用户对应的群体画像信息。
本申请实施例中，步骤403为可选步骤，服务器在接收到第一信息之后，还可以获取第四信息，第 四信息包括与应用程序和/或服务具有关联关系的信息，和/或，与用户对应的群体画像信息。
例如，服务器上可以配置有多个客体的信息，以及与多个客体中至少一个客体具有关联关系的信息的类型，则服务器可以根据与多个客体中至少一个客体具有关联关系的信息的类型，获取与前述至少一个客体具有关联关系的信息。为更直观地理解本方案，以下结合的实际应用场景进行举例。在一种应用场景中，若需要展示用户可能会访问的应用程序和服务，也即需要推荐的客体包括应用程序和服务，与应用程序和/或服务具有关联关系的信息可以包括用户所在区域的天气信息、用户通过一个或多个应用程序购买的商品的快递信息、优惠活动信息、当前时刻的新闻信息或其他与应用程序和/或服务具有关联关系的信息等等，此处不做穷举。例如，“用户所在区域出现剧烈降温”这一天气信息与购物类应用程序具有关联关系，且“用户所在区域出现剧烈降温”这一天气信息与“查看天气”这一服务具有关联关系；又例如，用户购买的商品的快递信息和用户所在的位置信息与“向用户展示待取快递”这一服务具有关联关系；又例如，优惠活动信息和用户所在的位置信息与“优惠券的访问接口”这一服务具有关联关系等等，此处不做穷举。
在另一种应用场景中，当用户访问音乐类的应用程序时，可以向用户推荐感兴趣的音频，也即需要推荐的客体为音频，与应用程序和/或服务具有关联关系的信息可以包括音频的风格、作者、发布时间、播放量或其他信息等。在另一种应用场景中，当用户访问视频类的应用程序时，可以向用户推荐感兴趣的视频，也即需要推荐的客体为视频，与应用程序和/或服务具有关联关系的信息可以包括视频的题材类型、视频中主演的名字、视频的评分、视频的播放量或其他信息等。在另一种应用场景中，若需要推荐的应用程序和/或服务为食谱，与应用程序和/或服务具有关联关系的信息可以包括食谱所属菜系、食谱的热量、食谱中维生素的含量其他信息等等，此处不对所有应用场景中与应用程序和/或服务具有关联关系的信息进行穷举。
针对“服务器获取与用户对应的群体画像信息”的具体实现方式，服务器在接收到电子设备发送的第一信息之后，可以确定用户的标识信息，用户的标识信息可以表现为用户的账号信息、用户的手机号或其他类型的标识信息等，此处不做限定。服务器可以根据用户的账号信息获取与用户对应的群体画像信息；其中，群体画像信息包括的为一类用户的画像信息，例如，群体画像信息可以包括用户的年龄所在的年龄段、用户的性别、用户的消费水平类型或其他群体画像信息等，此处举例仅为方便理解本方案，不用于限定本方案。本申请实施例中，服务器还可以获取与用户对应的群体画像信息，也即能够获得用户更多的信息，有利于向用户展示更符合期望的应用程序和/或服务；此外，当电子设备尚未收集到用户的特征信息时，或者，电子设备仅能收集到用户少量的信息时，则获取到的群体画像信息能够辅助服务器确定出较为符合用户期望的应用程序和/或服务，有利于提高本方案的用户粘度。
404、服务器根据第一信息确定第二信息，第二信息用于指示第一应用程序和/或第一服务。
本申请实施例中，第二信息可以包括至少一个应用程序和/或服务的信息；前述至少一个应用程序和/或服务的信息用于供电子设备确定与至少一个应用程序和/或服务的信息对应的至少一个应用程序和/或服务，由于前述至少一个应用程序和/或服务的信息包括第一应用程序和/或第一服务的信息，则第二信息可以指示第一应用程序和/或第一服务。示例性地，在一些应用场景中，每个应用程序和/或服务的信息可以包括每个应用程序和/或服务的标识信息，例如，若应用程序和/或服务为应用程序或服务，每个应用程序和/或服务的标识信息可以为应用程序的名称、应用程序的图标、服务的名称、服务的图标、应用程序或服务的标识号或其他可以唯一指向一个应用程序或服务的标识信息等，此处不做穷举。此外，若向用户推荐的应用程序和/或服务表现为音频，每个客体的标识信息可以为音频的名称、演唱者以及所归属的专辑名称，或者，每个客体的标识信息可以为音频的标识号，或者，每个客体的标识信息也可以为音频的其他信息等，此处不做限定。
在另一些应用场景中，向用户推荐的应用程序和/或服务的信息也可以为客体的描述信息，例如，若客体为商品，每个客体的描述信息可以包括该商品的图片、名称以及访问链接。又例如若客体为食谱，每个客体的描述信息可以包括该食谱的图片、使用到的食材或其他信息等。又例如，若客体为游戏，每个客体的描述信息可以包括游戏的图标、名称以及访问链接等等，需要说明的是，此处举例仅为方便理解“至少一个客体的信息”的概念，不用于限定本方案。
可选地，第二信息可以包括第一对应关系，第一对应关系可以包括每个目标标识信息和客体的标识 信息之间的对应关系，目标标识信息为第一信息中的任意一个标识信息，每个目标标识信息为第一匹配规则的标识信息或第二匹配规则的标识信息，也即，第二信息用于指示第一信息中的第一匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系，以及第一信息中的第二匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系。例如，当向用户推荐的应用程序和/或服务为应用程序和/或服务时，第二信息用于告知电子设备可以向用户展示的应用程序和/或服务有哪些，以及电子设备每个应用程序和/或服务与哪个匹配规则的标识信息对应，也即用于告知电子设备每个应用程序和/或服务是基于哪个匹配规则的标识信息召回的。
步骤403为可选步骤，若不执行步骤403，服务器可以采用多种方式实现“根据第一信息确定第二信息”，具体的，在一种实现方式中，服务器上可以配置有第二对应关系，第二对应关系指示每个匹配规则的标识信息与一个或多个应用程序和/或服务的信息之间的对应关系。服务器在接收到第一信息之后，能够得到多个匹配规则的标识信息。其中，前述多个匹配规则的标识信息包括第一匹配规则的标识信息；可选地，前述多个匹配规则的标识信息还包括第二匹配规则的标识信息。服务器可以根据第一信息中每个匹配规则的标识信息和第二对应关系，获取到与每个匹配规则的标识信息对应的至少一个应用程序和/或服务的信息，从而得到与第一信息中所有匹配规则的标识信息对应的至少一个应用程序和/或服务的信息。其中，前述“至少一个应用程序和/或服务的信息”包括与第一匹配规则的标识信息对应的应用程序和/或服务的信息；可选地，前述“至少一个应用程序和/或服务的信息”还包括与第二匹配规则的标识信息对应的应用程序和/或服务的信息。
其中，第二对应关系可以包括每个匹配规则的标识信息与应用程序和/或服务的标识信息之间的对应关系；可选地，第二对应关系还可以包括应用程序和/或服务的标识信息与应用程序和/或服务的信息之间的对应关系。需要说明的是，第二对应关系中“匹配规则的标识信息”和“应用程序和/或服务的标识信息”之间是多对多的关系，一个匹配规则的标识信息可以对应一个或多个应用程序和/或服务的标识信息，不同的匹配规则的标识信息可以和相同的应用程序和/或服务的标识信息对应。
服务器可以通过表格、数组或其他数据格式存储第二对应关系，为了更直观地理解本方案，以下结合表3进行举例，表3中以应用程序和/或服务为应用程序或服务为例。
表3
表3中每行示出了一个匹配规则的标识信息所对应的应用程序和/或服务的标识信息，参阅表3第一行，与0000000001这一匹配规则的标识号对应的服务的标识信息包括美食类应用程序D1的点餐功能。参阅表3第二行，与0000000002这一匹配规则的标识号对应的应用程序的标识信息包括购物类应用程序D2。参阅表3第三行，与0000000003这一匹配规则的标识号对应的应用程序的标识信息包括音乐类应用程序D3和视频类应用程序D4。参阅表3的第四行，与0000000004这一匹配规则的标识号对应的服务的标识信息包括对二维码进行扫描的扫一扫功能等，表3中的示例仅为方便理解本方案，不用于限定本方案。
在另一种实现方式中，服务器可以将第一信息中的每个匹配规则的标识信息输入第一神经网络，得到第一神经网络输出的一个或多个应用程序和/或服务的标识信息，则可以通过第一神经网络得到与第一信息中所有匹配规则的标识信息对应的一个或多个应用程序和/或服务的标识信息。其中，第一神经网络为执行过训练操作的神经网络，示例性地，第一神经网络可以为循环神经网络、卷积神经网络、残差神经网络或其他类型的神经网络等等，此处不做穷举。
可选地，若执行步骤403，则步骤404可以包括：服务器根据第四信息和第一信息，确定第二信息，其中，第一信息包括至少一个第一匹配规则的标识信息；可选地，第一信息还包括至少一个第二匹配规则的标识信息；“第四信息”的含义以及获取方式可以参阅步骤403中的描述，此处不做赘述。
服务器可以通过多种方式执行“根据第四信息和第一信息，确定第二信息”的操作。在一种实现方 式中，服务器上可以配置第三对应关系，第三对应关系可以包括每个第一条件与至少一个应用程序和/或服务的标识信息之间的对应关系。其中，每个第一条件至少包括一个匹配规则的标识信息；可选地，第一条件还可以包括第一子条件，服务器可以基于与应用程序和/或服务具有关联关系的信息和/或与用户对应的群体画像信息来判断是否满足第一子条件。
服务器可以通过表格、数组或其他数据格式存储第二对应关系，为了更直观地理解本方案，以下结合表4进行举例，表4中以应用程序和/或服务为应用程序或服务为例。
表4
表4中每行示出了一个第一条件所对应的一个或多个应用程序和/或服务的标识信息，表4中的第一行和第二行的内容可以参阅上述对表3中的描述，此处不做赘述。参阅表4第三行，第一条件包括的匹配规则的标识为0000000005，第一子条件包括未来一天的温度下降超过8度，与前述第一条件对应的应用程序以及服务的标识信息包括购物类应用程序D2和天气信息的查看功能，例如，0000000005这一匹配规则的标识号所对应的匹配规则可以包括手机+休息+购物类的应用程序中偏好使用应用程序D2+近三天内对应用程序D2的平均使用次数大于或等于4次。参阅表4第四行，第一条件包括的匹配规则的标识为0000000006，第一子条件包括通过购物类应用程序D2购买的商品d1被派送至公司附近，与前述第一条件对应的服务的标识信息包括通过购物类应用程序D2购买的商品d1的快递信息的查看功能，又例如，0000000006这一匹配规则的标识号所对应的匹配规则可以包括位于公司附近+非通勤时间段。参阅表4第五行，第一条件包括的匹配规则的标识为0000000007，第一子条件包括美食类应用程序D4推出优惠券，与前述第一条件对应的服务的标识信息包括美食类应用程序D4的优惠券的访问接口，又例如，0000000007这一匹配规则的标识号所对应的匹配规则可以包括用户已经购买了美食类应用程序D4的优惠券+当前时间为吃饭时间段。参阅表4第六行，第一条件包括的匹配规则的标识为0000000008，第一子条件包括用户所对应的群体画像信息中用户的年龄段在25至35之间，且用户的性别为女，与前述第一条件对应的应用程序的标识信息包括购物类应用程序D2，又例如，0000000008这一匹配规则的标识号所对应的匹配规则可以包括用户当前位置为在家+当前时间为用户的休息时间等等，表4中的示例仅为方便理解本方案，不用于限定本方案。
需要说明的是，上述对与表4中的匹配规则的标识号对应的匹配规则的举例仅为方便理解本方案，在实际应用场景中，在一种实现方式中，服务器在将多个匹配规则以及每个匹配规则的标识信息部署至电子设备之后，可以删除多个匹配规则，存储第二对应关系，也即存储匹配规则的标识信息和应用程序和/或服务的标识信息之间的对应关系，以进一步降低获取到用户的隐私信息的可能性。在另一种实现方式中，服务器在将多个匹配规则以及每个匹配规则的标识信息部署至电子设备之后，还可以存储多个匹配规则以及每个匹配规则的标识信息。
具体的，针对第一信息中的任意一个匹配规则的标识信息(为方便描述，后续称为“目标标识信息”)，服务器可以从多个第一条件中获取存在目标标识信息的第二条件；若第二条件中只包括目标标识信息，则获取第二条件所对应的应用程序和/或服务的标识信息，将第二条件所对应的应用程序和/或服务的信 息确定为第二信息中包括的应用程序和/或服务的标识信息。若第二条件中还包括第一子条件，则服务器可以基于与应用程序和/或服务具有关联关系的信息和/或与用户对应的群体画像信息来判断是否满足第二条件中的第一子条件，若判断结果为是，也即确定满足第二条件中的第一子条件，则获取第二条件所对应的应用程序和/或服务的标识信息，将第二条件所对应的应用程序和/或服务信息确定为第二信息中包括的应用程序和/或服务的标识信息；若判断结果为否，则对第一信息中的下一个匹配规则的标识信息执行前述操作。
在另一种实现方式中，服务器可以将第一信息中的每个匹配规则的标识信息和第四信息输入第二神经网络，得到第一神经网络输出的一个或多个应用程序和/或服务的标识信息，则可以通过第一神经网络得到与第一信息中所有匹配规则的标识信息对应的一个或多个应用程序和/或服务的标识信息。其中，第二神经网络为执行过训练操作的神经网络，示例性地，第二神经网络可以为循环神经网络、卷积神经网络、残差神经网络或其他类型的神经网络等等，此处不做穷举。需要说明的是，服务器根据第四信息和第一信息，还可以采用其他方式来确定第二信息，具体可以结合实际应用场景确定，此处不做穷举。
本申请实施例中，服务器在确定向用户展示的应用程序和/或服务的过程中，不仅利用了第一信息，还可以利用与应用程序和/或服务具有关联关系的信息和/或与用户对应的群体画像信息，有利于更为充分的了解待推荐的应用程序和/或服务以及当前用户，有利于确定出当前用户感兴趣的应用程序和/或服务，从而提高向用户精准推荐应用程序和/或服务的概率。
电子设备向服务器发送的第一信息中不仅包括第一匹配规则的标识信息，还包括第二匹配规则的标识信息，从而电子设备无法确定哪个匹配规则的标识信息是服务器命中的，哪个匹配规则的标识信息不是服务器命中的，有利于提高电子设备根据匹配规则的标识信息反向推理出服务器的用户的特征信息的难度，以进一步保护用户的隐私数据。
405、服务器向电子设备发送第二信息。
本申请实施例中，服务器在通过步骤404确定了第二信息之后，可以向电子设备发送第二信息，“第二信息”的含义可以参阅步骤404中的描述，此处不做赘述。
406、电子设备在显示单元上推荐第一应用程序和/或第一服务。
本申请实施例中，电子设备在接收到第二信息之后，可以确定向用户展示的第一应用程序和/或第一服务的信息，并在显示单元上推荐第一应用程序和/或第一服务；例如，“在显示单元上推荐第一应用程序和/或第一服务”可以理解为在显示单元上展示第一应用程序和/或第一服务的访问接口。其中，若第一信息中仅包括第一匹配规则的标识信息，则电子设备可以将第二信息中的所有的应用程序和/或服务确定为需要向用户推荐的第一应用程序和/或第一服务。
可选地，若第一信息包括第一匹配规则的标识信息和第二匹配规则的标识信息，在一种实现方式中，第二信息包括每个第一标识信息和应用程序和/或服务的信息之间的对应关系，每个第一标识信息为第一匹配规则的标识信息或第二匹配规则的标识信息；步骤406可以包括：电子设备根据第一匹配规则的标识信息和第二信息，确定向用户推荐的第一应用程序和/或第一服务。
具体的，电子设备可以根据第一匹配规则的标识信息，从第二信息包括的多个应用程序和/或服务的信息中选取与第一匹配规则的标识信息对应的一个或多个目标应用程序和/或服务的信息，也即选取由第一匹配规则的标识信息召回的一个或多个目标应用程序和/或服务的信息，并将目标应用程序和/或服务确定为需要向用户推荐的第一应用程序和/或第一服务。
示例性地，第一信息中包括的多个第一匹配规则的标识信息包括0000000004、0000000005以及0000000006，多个第二匹配规则的标识信息包括0000000011、0000000023和0000000058，第二信息包括的内容通过如下表5进行展示，需要说明的是，如下表5中的示例仅为方便理解本方案，不用于限定本方案。
表5
电子设备可以从第二信息中，获取与0000000004、0000000005以及0000000006对应的应用程序和/或服务的标识信息，也即表5中示出的“对二维码进行扫描的扫一扫功能”、“购物类应用程序D2”、“天气信息的查看功能”以及“通过购物类应用程序D2购买的商品d1的快递信息的查看功能”，电子设备确定需要向用户推荐的第一应用程序和/或第一服务包括“扫一扫功能”、“购物类应用程序D2”、“天气信息的查看功能”以及“通过购物类应用程序D2购买的商品d1的快递信息的查看功能”。
本申请实施例中，由于第一匹配规则是与用户的特征信息匹配的规则，第二匹配规则是与用户的特征信息不匹配的规则，在第一信息中加入了第二匹配规则的标识信息，服务器无法确定第一信息中哪些标识信息是与用户的特征信息匹配的规则的标识信息，进一步加大了服务器反向推理出用户的特征信息的难度；此外，由于在第一信息中加入了第二匹配规则的标识信息，对应的，第二信息中包括与第二匹配规则的标识信息对应的应用程序和/或服务的信息，电子设备能够根据第一匹配规则的标识信息和第二信息，确定最终需要向用户推荐的第一应用程序和/或第一服务，从而在保证用户的隐私数据安全度的前提下，有利于实现向用户精准的展示应用程序和/或服务。
在另一种实现方式中，若第一信息包括第一匹配规则的标识信息和第二匹配规则的标识信息，电子设备也可以将第二信息中的所有的应用程序和/或服务确定为需要向用户推荐的第一应用程序和/或第一服务。
电子设备在确定了需要向用户展示的多个应用程序和/或服务之后，可以一次性的向用户展示前述确定的全部应用程序和/或服务；或者，电子设备也可以分至少两次向用户展示前述确定的全部应用程序和/或服务等，具体展示方式可以结合实际产品形态灵活确定，此处不做限定。
为了更直观地理解本方案，以下结合实际的应用场景进行举例说明，先参阅图5至图7，图5至图7为本申请实施例提供的向用户展示应用程序和/或服务的三种界面示意图。图5至图7中均以电子设备通过201指示的区域向用户展示应用程序和/或服务为例，先参阅图5，电子设备采集到的用户的特征信息包括：用户位于A城市、当前时间为早上通勤时间段、当前时间为用户的早晨时间段、当前位置位于公司附近、用户已经购买了美食类应用程序D4的3张优惠券；电子设备根据采集到的用户的特征信息获取到的两个第一匹配规则的标识信息分别为0000000004和0000000007，其中，0000000004这一匹配规则的标识信息指向的匹配规则可以包括位于A城市+当前时间为早上通勤时间段+当前位置位于公司附近，0000000007这一匹配规则的标识信息所对应的匹配规则可以包括用户已经购买了美食类应用程序D4的优惠券+当前时间为吃饭时间段。
电子设备可以从本地存储的多个匹配规则的标识信息中随机选取两个第二匹配规则的标识信息0000000058和0000000132，将两个第一匹配规则的标识信息和两个第二匹配规则的标识信息确定为第一信息中包括的匹配规则的标识信息，并向服务器发送第一信息，第一信息包括0000000004、0000000007、0000000058和0000000132。
服务器分别获取与0000000004、0000000007、0000000058以及0000000132对应的应用程序和/或服务的信息。例如，服务器获取到与0000000004这一匹配规则的标识信息对应的应用程序和/或服务的信息为“对二维码进行扫描的扫一扫功能”。又例如，服务器确定包含0000000007这一匹配规则的标识信息的第一条件中还包括第一子条件，根据用户的位置信息，确定用户的50米以内有美食类应用程序D4所对应的线下门店，也即确定满足第一条件，则能够获取到与0000000007这一匹配规则的标识信息 对应的应用程序和/或服务的信息(也即“美食类应用程序D4的优惠券的访问接口”)。又例如，包含0000000058这一匹配规则的标识信息的第一条件中的第一子条件为空，服务器获取到与0000000058这一匹配规则的标识信息对应的应用程序和/或服务的信息为即时通讯类应用程序D7。又例如，包含0000000132这一匹配规则的标识信息的第一条件中的第一子条件为空，服务器获取到与0000000132这一匹配规则的标识信息对应的应用程序和/或服务的信息为美食类应用程序D5。
服务器向电子设备发送第二信息，第二信息包括0000000004与“对二维码进行扫描的扫一扫功能”之间的对应关系、0000000007与“美食类应用程序D4的优惠券的访问接口”之间的对应关系、0000000058与“即时通讯类应用程序D7”之间的对应关系以及0000000132与“美食类应用程序D5”之间的对应关系。
电子设备从第二信息中获取与0000000004对应的“对二维码进行扫描的扫一扫功能”，以及与0000000007对应的“美食类应用程序D4的优惠券的访问接口”，也即确定了需要推荐的第一应用程序和/或第一服务包括“对二维码进行扫描的扫一扫功能”和“美食类应用程序D4的优惠券的访问接口”，具体展示方式可以参阅图5中的201区域示出的内容。当用户点击附近美食旁边的箭头时，触发展示美食类应用程序D4的优惠券的访问接口(也即图5中示出的门店XXX的已购3张券)，应理解，图5中的示例仅为方便理解本方案，不用于限定本方案。
再参阅图6，电子设备采集到的用户的特征信息包括：用户位于A城市、当前时间为早上通勤时间段、当前时间为用户的早晨时间段、当前位置位于公司附近；电子设备根据采集到的用户的特征信息获取到的两个第一匹配规则的标识信息分别为0000000004和0000000020，其中，0000000004这一匹配规则的标识信息指向的匹配规则可以包括位于A城市+当前时间为早上通勤时间段+当前位置位于公司附近，0000000020这一匹配规则的标识信息所对应的匹配规则可以包括当前时间为吃饭时间段。
电子设备可以从本地存储的多个匹配规则的标识信息中随机选取两个第二匹配规则的标识信息0000000058和0000000132，向服务器发送第一信息，第一信息包括0000000004、0000000020、0000000058和0000000132。
服务器分别获取与0000000004、0000000020、0000000058和0000000132对应的应用程序和/或服务的信息。“与0000000004、0000000058和0000000132这三个匹配规则的标识信息对应的应用程序和/或服务的信息”的获取方式可以参阅上述对图5的描述，此处不做赘述。又例如，服务器确定包含0000000020这一匹配规则的标识信息的第一条件中包括第一子条件，第一子条件包括：用户的20米以内有门店F1+门店F1在推出优惠券；服务器根据用户的位置信息，确定用户的10米以内有门店F1，且根据与“门店F1的优惠券”这一客体具有关联的信息，确定门店F1在推出优惠券，也即确定了满足第一条件，则能够获取到与0000000020这一匹配规则的标识信息对应的应用程序和/或服务的信息(也即“门店F1的优惠券的访问链接”)。
服务器向电子设备发送第二信息，第二信息包括0000000004与“对二维码进行扫描的扫一扫功能”之间的对应关系、0000000020与“门店F1的优惠券的访问链接”之间的对应关系、0000000058与“即时通讯类应用程序D7”之间的对应关系以及0000000132与“美食类应用程序D5”之间的对应关系。
电子设备从第二信息中获取与0000000004对应的“对二维码进行扫描的扫一扫功能”，以及与0000000020对应的“门店F1的优惠券的访问链接”，也即确定了需要推荐的第一应用程序和/或第一服务包括“对二维码进行扫描的扫一扫功能”和“门店F1的优惠券”，具体展示方式可以参阅图6中的201区域示出的内容。当用户点击附近美食旁边的箭头时，触发展示门店F1的优惠券的访问接口，应理解，图6中的示例仅为方便理解本方案，不用于限定本方案。
再参阅图7，电子设备采集到的用户的特征信息包括：当前时间为用户的休息时间、当前位置的20米以内是某个商业圈；电子设备根据采集到的用户的特征信息获取到的一个第一匹配规则的标识信息为0000000063，其中，0000000063这一匹配规则的标识信息指向的匹配规则可以包括休息时间+附近50米内存在商业圈。电子设备可以从本地存储的多个匹配规则的标识信息中随机选取两个第二匹配规则的标识信息0000000132，向服务器发送第一信息，第一信息包括0000000063和0000000132。
服务器分别获取与0000000063和0000000132对应的应用程序和/或服务的信息。“与0000000132这一匹配规则的标识信息对应的应用程序和/或服务的信息”的获取方式可以参阅上述对图5的描述， 此处不做赘述。又例如，服务器确定包含0000000063这一匹配规则的标识信息的第一条件中包括第一子条件，第一子条件包括：用户所在商圈中存在至少一个门店在推出优惠券；服务器根据用户的位置信息，确定用户的20米以内有某个商业圈，且前述商业圈内存在6个门店正在推出优惠券，也即确定了满足第一条件，则能够获取到与0000000020这一匹配规则的标识信息对应的应用程序和/或服务的信息(也即“上述商业圈内6个门店的优惠券的访问链接”)。
服务器向电子设备发送第二信息，第二信息包括0000000063与“6个门店的优惠券的访问链接”之间的对应关系，以及0000000132与“美食类应用程序D5”之间的对应关系。
电子设备从第二信息中获取与0000000063对应的“6个门店的优惠券的访问链接”，也即确定了需要推荐的第一应用程序和/或第一服务包括“6个门店的优惠券”，具体展示方式可以参阅图7中的201区域示出的内容，其中，F2、F3和F4代表了3个门店的优惠券的访问链接，当用户点击图7中的“+3”按钮时，触发展示其他3个门店的优惠券的访问链接，应理解，图7中的示例仅为方便理解本方案，不用于限定本方案。
本申请实施例中，电子设备可以获取与用户的特征信息的取值匹配的第一匹配规则的标识信息，并将第一匹配规则的标识信息发送给服务器，从而服务器可以根据第一匹配规则的标识信息得到第二信息，电子设备根据接收到的第二信息确定向用户推荐的第一应用程序和/或第一服务，通过前述方案，不仅实现了个性化的确定向用户推荐的第一应用程序和/或第一服务，而且避免了将用户详细的描述数据发送至服务器，避免了用户的隐私信息的泄露。
接下来介绍本申请实施例提供的服务器，请参阅图8，图8为本申请实施例提供的服务器一种结构示意图，具体的，服务器800由一个或多个服务器实现，服务器800可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上中央处理器(central processing units，CPU)822(例如，一个或一个以上处理器)和存储器832，一个或一个以上存储应用程序842或数据844的存储介质830(例如一个或一个以上海量存储设备)。其中，存储器832和存储介质830可以是短暂存储或持久存储。存储在存储介质830的程序可以包括一个或一个以上模块(图示没标出)，每个模块可以包括对服务器中的一系列指令操作。更进一步地，中央处理器822可以设置为与存储介质830通信，在服务器800上执行存储介质830中的一系列指令操作。
服务器800还可以包括一个或一个以上电源826，一个或一个以上有线或无线网络接口850，一个或一个以上输入输出接口858，和/或，一个或一个以上操作系统841，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等等。
本申请实施例中，中央处理器822，用于执行图3至图7对应实施例中的服务器执行的推荐方法。需要说明的是，中央处理器822执行前述各个步骤的具体方式，与本申请中图3至图7对应的各个方法实施例基于同一构思，其带来的技术效果与本申请中图3至图7对应的各个方法实施例相同，具体内容可参见本申请前述所示的方法实施例中的叙述，此处不再赘述。
再参阅图9，图9为本申请实施例提供的电子设备的一种结构示意图，电子设备900具体可以表现为手机、平板、笔记本电脑、智能穿戴设备等，此处不做限定。具体的，电子设备900包括：接收器901、发射器902、处理器903和存储器904(其中电子设备900中的处理器903的数量可以一个或多个，图9中以一个处理器为例)，其中，处理器903可以包括应用处理器9031和通信处理器9032。在本申请的一些实施例中，接收器901、发射器902、处理器903和存储器904可通过总线或其它方式连接。
存储器904可以包括只读存储器和随机存取存储器，并向处理器903提供指令和数据。存储器904的一部分还可以包括非易失性随机存取存储器(non-volatile random access memory，NVRAM)。存储器904存储有处理器和操作指令、可执行模块或者数据结构，或者它们的子集，或者它们的扩展集，其中，操作指令可包括各种操作指令，用于实现各种操作。
处理器903控制电子设备的操作。具体的应用中，电子设备的各个组件通过总线系统耦合在一起，其中总线系统除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都称为总线系统。
上述本申请实施例揭示的方法可以应用于处理器903中，或者由处理器903实现。处理器903可以 是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器903中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器903可以是通用处理器、数字信号处理器(digital signal processing，DSP)、微处理器或微控制器，还可进一步包括专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field-programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。该处理器903可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器904，处理器903读取存储器904中的信息，结合其硬件完成上述方法的步骤。
接收器901可用于接收输入的数字或字符信息，以及产生与电子设备的相关设置以及功能控制有关的信号输入。发射器902可用于通过第一接口输出数字或字符信息；发射器902还可用于通过第一接口向磁盘组发送指令，以修改磁盘组中的数据；发射器902还可以包括显示屏等显示设备。
本申请实施例中，处理器903，用于执行图3至图7对应实施例中的电子设备执行的推荐方法。需要说明的是，处理器903中的应用处理器9031执行上述各个步骤的具体方式，与本申请中图3至图7对应的各个方法实施例基于同一构思，其带来的技术效果与本申请中图3至图7对应的各个方法实施例相同，具体内容可参见本申请前述所示的方法实施例中的叙述，此处不再赘述。
本申请实施例中还提供一种计算机可读存储介质，该计算机可读存储介质中存储有用于进行信号处理的程序，当其在计算机上运行时，使得计算机执行如前述图3至图7所示实施例描述的方法中服务器所执行的步骤，或者，使得计算机执行如前述图3至图7所示实施例描述的方法中电子设备所执行的步骤。
本申请实施例中还提供一种包括计算机程序产品，当其在计算机上运行时，使得计算机执行如前述图3至图7所示实施例描述的方法中服务器所执行的步骤，或者，使得计算机执行如前述图3至图7所示实施例描述的方法中电子设备所执行的步骤。
本申请实施例提供的电子设备或服务器具体可以为芯片，芯片包括：处理单元和通信单元，所述处理单元例如可以是处理器，所述通信单元例如可以是输入/输出接口、管脚或电路等。该处理单元可执行存储单元存储的计算机执行指令，以使芯片执行上述图3至图7所示实施例描述的推荐方法。可选地，所述存储单元为所述芯片内的存储单元，如寄存器、缓存等，所述存储单元还可以是所述无线接入设备端内的位于所述芯片外部的存储单元，如只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)等。
其中，上述任一处提到的处理器，可以是一个通用中央处理器，微处理器，ASIC，或一个或多个用于控制上述第一方面方法的程序执行的集成电路。
另外需说明的是，以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。另外，本申请提供的装置实施例附图中，模块之间的连接关系表示它们之间具有通信连接，具体可以实现为一条或多条通信总线或信号线。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到本申请可借助软件加必需的通用硬件的方式来实现，当然也可以通过专用硬件包括专用集成电路、专用CPU、专用存储器、专用元器件等来实现。一般情况下，凡由计算机程序完成的功能都可以很容易地用相应的硬件来实现，而且，用来实现同一功能的具体硬件结构也可以是多种多样的，例如模拟电路、数字电路或专用电路等。但是，对本申请而言更多情况下软件程序实现是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在可读取的存储介质中，如计算机的软盘、U盘、移动硬盘、ROM、RAM、磁碟或者光盘等，包括若干指令用以使得 一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。
所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存储的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘(Solid State Disk，SSD))等。

Claims (13)

  1. 一种推荐方法，应用于电子设备，其特征在于，所述方法包括：
    确定用户的特征信息的取值；
    从多个匹配规则中确定与所述用户的特征信息的取值匹配的第一匹配规则，获取所述第一匹配规则的标识信息，其中，所述多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围；
    向服务器发送第一信息，所述第一信息包括所述第一匹配规则的标识信息，所述第一信息用于供所述服务器得到第二信息；
    接收所述服务器发送的第二信息，所述第二信息用于指示第一应用程序和/或第一服务；
    在所述电子设备的显示单元上推荐所述第一应用程序和/或第一服务。
  2. 根据权利要求1所述的方法，其特征在于，所述第一信息还包括第二匹配规则的标识信息，所述第二匹配规则为与所述用户的特征信息的取值不匹配的匹配规则。
  3. 根据权利要求2所述的方法，其特征在于，所述第二信息还用于指示所述第一匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系，以及所述第二匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系；
    所述第一应用程序和/或第一服务为所述第二信息指示的多个应用程序和/或服务中与所述第一匹配规则的标识信息对应的应用程序和/或服务。
  4. 根据权利要求1至3任一项所述的方法，其特征在于，所述电子设备中部署的匹配规则包括所述第一匹配规则，所述电子设备中部署的匹配规则和/或所述电子设备中部署的匹配规则的标识信息为可更新的。
  5. 根据权利要求1至3任一项所述的方法，其特征在于，所述用户的特征信息包含以下一种或多种：所述用户的画像信息、所述用户使用应用程序时的行为信息、所述用户所使用的所述电子设备的信息或者与所述电子设备通信连接的其他电子设备的信息。
  6. 一种推荐方法，其特征在于，应用于服务器，所述方法包括：
    接收电子设备发送的第一信息，所述第一信息包括第一匹配规则的标识信息，所述第一匹配规则为多个匹配规则中的一个，其中，所述多个匹配规则中的每个匹配规则用于指示用户的至少一种特征信息中每种特征信息的取值范围，所述第一匹配规则用于指示所述电子设备的用户的特征信息的取值；
    根据所述第一信息确定第二信息，所述第二信息用于指示第一应用程序和/或第一服务；
    向所述电子设备发送所述第二信息。
  7. 根据权利要求6所述的方法，其特征在于，所述第一信息还包括第二匹配规则的标识信息，所述第二匹配规则为与所述用户的特征信息的取值不匹配的匹配规则。
  8. 根据权利要求7所述的方法，其特征在于，所述第二信息还用于指示所述第一匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系，以及所述第二匹配规则的标识信息与至少一个应用程序和/或服务之间的对应关系；
    所述第一应用程序和/或第一服务为所述第二信息指示的多个应用程序和/或服务中与所述第一匹配规则的标识信息对应的应用程序和/或服务。
  9. 根据权利要求6至8任一项所述的方法，其特征在于，所述电子设备中部署的匹配规则包括所述 第一匹配规则，所述电子设备中部署的匹配规则和/或所述电子设备中部署的匹配规则的标识信息为可更新的。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有程序，当所述程序在计算机上运行时，使得计算机执行如权利要求1至5中任一项所述的方法，或者，使得计算机执行如权利要求6至9中任一项所述的方法。
  11. 一种电子设备，其特征在于，包括处理器和存储器，所述处理器与所述存储器耦合，
    所述存储器，用于存储程序；
    所述处理器，用于执行所述存储器中的程序，使得所述电子设备执行如权利要求1至5中任一项所述的方法。
  12. 一种服务器，其特征在于，包括处理器和存储器，所述处理器与所述存储器耦合，
    所述存储器，用于存储程序；
    所述处理器，用于执行所述存储器中的程序，使得所述服务器执行如权利要求6至9中任一项所述的方法。
  13. 一种计算机程序产品，其特征在于，所述计算机程序产品包括程序，当所述程序在计算机上运行时，使得计算机执行如权利要求1至5中任一项所述的方法，或者，使得计算机执行如权利要求6至9中任一项所述的方法。
PCT/CN2023/128170 2022-11-01 2023-10-31 一种推荐方法以及相关设备 WO2024093967A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211372446.8A CN118037373A (zh) 2022-11-01 2022-11-01 一种推荐方法以及相关设备
CN202211372446.8 2022-11-01

Publications (1)

Publication Number Publication Date
WO2024093967A1 true WO2024093967A1 (zh) 2024-05-10

Family

ID=90929786

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/128170 WO2024093967A1 (zh) 2022-11-01 2023-10-31 一种推荐方法以及相关设备

Country Status (2)

Country Link
CN (1) CN118037373A (zh)
WO (1) WO2024093967A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107249016A (zh) * 2017-04-28 2017-10-13 北京小米移动软件有限公司 推送信息的方法及装置
CN110782289A (zh) * 2019-10-28 2020-02-11 方文珠 一种基于用户画像的业务推荐方法和系统
CN111125497A (zh) * 2018-10-29 2020-05-08 北京国双科技有限公司 一种信息推荐方法、装置、处理器以及存储介质
CN111882399A (zh) * 2020-07-31 2020-11-03 平安国际融资租赁有限公司 服务信息推荐方法、装置、计算机系统及可读存储介质
US20210042720A1 (en) * 2018-09-04 2021-02-11 Advanced New Technologies Co., Ltd. Service recommendation method, apparatus, electronic device, and computer-readable storage media
WO2021139701A1 (zh) * 2020-01-06 2021-07-15 宇龙计算机通信科技(深圳)有限公司 一种应用推荐方法、装置、存储介质及电子设备
CN115114515A (zh) * 2021-03-23 2022-09-27 华为技术有限公司 一种基于用户兴趣的内容推荐方法与终端设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107249016A (zh) * 2017-04-28 2017-10-13 北京小米移动软件有限公司 推送信息的方法及装置
US20210042720A1 (en) * 2018-09-04 2021-02-11 Advanced New Technologies Co., Ltd. Service recommendation method, apparatus, electronic device, and computer-readable storage media
CN111125497A (zh) * 2018-10-29 2020-05-08 北京国双科技有限公司 一种信息推荐方法、装置、处理器以及存储介质
CN110782289A (zh) * 2019-10-28 2020-02-11 方文珠 一种基于用户画像的业务推荐方法和系统
WO2021139701A1 (zh) * 2020-01-06 2021-07-15 宇龙计算机通信科技(深圳)有限公司 一种应用推荐方法、装置、存储介质及电子设备
CN111882399A (zh) * 2020-07-31 2020-11-03 平安国际融资租赁有限公司 服务信息推荐方法、装置、计算机系统及可读存储介质
CN115114515A (zh) * 2021-03-23 2022-09-27 华为技术有限公司 一种基于用户兴趣的内容推荐方法与终端设备

Also Published As

Publication number Publication date
CN118037373A (zh) 2024-05-14

Similar Documents

Publication Publication Date Title
CN109002490B (zh) 用户画像生成方法、装置、服务器及存储介质
CN106357517B (zh) 定向标签生成方法及装置
CN107087235B (zh) 媒体内容推荐方法、服务器及客户端
US10454863B2 (en) Data processing device and data processing method based on user emotion icon activity
KR102230342B1 (ko) 뉴스피드에서 소셜 네트워킹 시스템 사용자에게 제시하기 위한 컨텐츠 아이템의 선택
CN109347722B (zh) 交互系统、方法、客户端及后台服务器
JP6352274B2 (ja) 通知中のスポンサー記事
US10115017B2 (en) Electronic device and image display method thereof
CN106663032A (zh) 跨设备任务连续性
US20160062732A1 (en) Method for providing additional functions based on information
CN105009024A (zh) 节省电池和数据使用
CN105103105A (zh) 社交封面信息流界面
EP2590130A1 (en) Similarity and relatedness of content
US20230092475A1 (en) Information processing method, apparatus and device, and storage medium
CN112783592A (zh) 信息发布方法、装置、设备和存储介质
US20140164132A1 (en) Client-Side Advertising Decisions
JP7463286B2 (ja) 高速かつ安全なコンテンツ提供のためのシステム
US20190012219A1 (en) Method for providing content to user according to user's preference and electronic device therefor
WO2024093967A1 (zh) 一种推荐方法以及相关设备
US11113617B1 (en) Ranking of user contacts to facilitate efficient user interfaces
US10812437B1 (en) Ranking items using a unified model
EP3374860B1 (en) Communicating information about an update of an application
CN115525834A (zh) 筛选并显示消息的方法、计算机装置及记录介质
TW202133093A (zh) 即時通訊應用程式內容評價方法、系統以及電腦可讀取記錄媒體
CN112348614A (zh) 用于推送信息的方法和装置