Network recommendation method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a network recommendation method and device, equipment and a storage medium, which are used for performing network recommendation according to target update data and a target network recommendation model. The target network recommendation model is constructed by combining the historical update data of different terminal devices in the coverage range of the target space and the corresponding historical network, so that the convergence and accuracy of the target network recommendation strategy can be improved. The method provided by the embodiment of the invention comprises the following steps: acquiring target update data of target terminal equipment in a coverage range of a target space, wherein the target update data comprises at least one of use scene update data and network switching behavior data; determining a target network according to the target update data and a target network recommendation model; the target network recommendation model is constructed according to historical update data of different terminal devices in the coverage range of the target space and corresponding historical networks, and the historical update data comprises historical use scene update data and historical network switching behavior data.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a network recommendation method, device, equipment and storage medium. Background Art

[0002] In one implementation, data related to network selection is collected from terminal devices, and user preference information is constructed based on the network usage data, rules are constructed or models are constructed, and a network is selected as an access network or a target network for switching based on complex rules or model results. However, the problem is that only a single user is considered, and the behavior of other users in the same space is not considered. The obtained user preferences may be contradictory, resulting in the inability to construct the knowledge graph or the inability of the model to converge. Summary of the invention

[0003] The embodiments of the present application provide a network recommendation method, apparatus, device and storage medium for performing network recommendation based on target update data and a target network recommendation model. Because the target network recommendation model is constructed based on the historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, and the historical update data includes historical usage scenario update data and historical network switching behavior data, the convergence and accuracy of the target network recommendation strategy can be improved.

[0004] A first aspect of the present application provides a network recommendation method, which is applied to a terminal device, and the method comprises: obtaining target update data of target terminal devices within the coverage range of a target space, the target terminal devices comprising the terminal device and / or other terminal devices, the target update data comprising at least one of usage scenario update data and network switching behavior data; determining a target network according to the target update data and a target network recommendation model; wherein the target network recommendation model is constructed according to historical update data of different terminal devices within the coverage range of the target space and corresponding historical networks, the historical update data comprising historical usage scenario update data and historical network switching behavior data.

[0005] A second aspect of the present application provides a network recommendation device, the method being applied to a terminal device, the device comprising:

[0006] An acquisition module, configured to acquire target update data of a target terminal device within a coverage range of a target space, wherein the target terminal device includes the terminal device and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data;

[0007] A processing module is used to determine a target network based on the target update data and a target network recommendation model; wherein the target network recommendation model is constructed based on historical update data and corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data.

[0008] In a third aspect of the present application, a terminal device is provided, comprising a memory, one or more processors, and a transceiver, wherein the memory is coupled to the processor, the memory is used to store computer program code, the computer program code comprises computer instructions, and when the processor executes the computer instructions, the terminal device executes any one of the methods described in the first aspect.

[0009] On the other hand, the present application provides a chip, which includes a processor, a memory, and a display. The processor may be a logic circuit, an integrated circuit, or a general-purpose processor, etc. The memory stores instructions. The processor may implement any of the methods in the first aspect above by reading the software code stored in the memory. The memory may be integrated in the processor, or may be located outside the processor and exist independently.

[0010] On the other hand, the present application provides a chip system, which is applied to a terminal device, the chip system includes one or more interface circuits and one or more processors, and a display, the interface circuit and the processor are interconnected via a line, the interface circuit is used to receive a signal from the memory of the terminal device and send the signal to the processor, the signal includes computer instructions stored in the memory, when the processor executes the computer instructions, the terminal device executes any one of the methods described in the first aspect.

[0011] In yet another aspect of the present application, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code, or instruction), which enables a computer to execute any one of the methods described in the first aspect when the computer program is executed.

[0012] In yet another aspect of the present application, a computer-readable storage medium is provided, which stores a computer program (also referred to as code or instruction) which, when executed on a computer, enables the computer to execute any of the methods described in the first aspect.

[0013] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0014] In an embodiment of the present application, target update data of target terminal devices within the coverage range of the target space is obtained, the target terminal devices include the terminal devices and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data; the target network is determined according to the target update data and the target network recommendation model; wherein the target network recommendation model is constructed according to the historical update data and the corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data. Network recommendations can be made according to the target update data and the target network recommendation model, because the target network recommendation model is constructed in combination with the historical update data and the corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data, which can improve the convergence and accuracy of the target network recommendation strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments and the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained based on these drawings.

[0016] Figure 1 This is a system architecture diagram used in the embodiments of the present application;

[0017] Figure 2 A schematic diagram of an embodiment of the network recommendation method in the embodiment of the present application;

[0018] Figure 3 This is another schematic diagram of an embodiment of the network recommendation method in the embodiment of the present application;

[0019] Figure 4 A schematic diagram of a process used in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of a process flow of network recommendation in an embodiment of the present application;

[0021] Figure 6 A schematic diagram of an embodiment of a network recommendation device in an embodiment of the present application;

[0022] Figure 7 This is a schematic diagram of an embodiment of a terminal device in an embodiment of the present application;

[0023] Figure 8 This is another schematic diagram of a terminal device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiments of the present application provide a network recommendation method, apparatus, device and storage medium for performing network recommendation based on target update data and a target network recommendation model. Because the target network recommendation model is constructed based on the historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, and the historical update data includes historical usage scenario update data and historical network switching behavior data, the convergence and accuracy of the target network recommendation strategy can be improved.

[0025] In order to make the technical personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiment of the present application will be described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, they should all fall within the scope of protection of the present application.

[0026] The following is a brief description of some terms involved in this application, as follows:

[0027] Knowledge Graph is a structured semantic knowledge base that is used to describe concepts and their relationships in the physical world in symbolic form. Its basic components are "entity-relationship-entity" triples, as well as entities and their related attribute-value pairs. Entities are connected to each other through relationships to form a network of knowledge structures.

[0028] Wireless Local Area Network (WLAN) is a local area network that does not use any wires or transmission cables to connect, but uses radio waves or electric and magnetic fields as the medium for data transmission. The transmission distance is generally only a few dozen meters. The most common standards for wireless LANs are the 802.11 series of standards defined by IEEE, as well as a series of national network security standard structures (Wireless LAN Authentication and Privacy Infrastructure, WAPI) promulgated by the People's Republic of China since 2003.

[0029] The Institute of Electrical and Electronics Engineers (IEEE) is an international association of electrical and electronics engineers established on January 1, 1963. It is also one of the largest professional technical organizations in the world.

[0030] Mobile hotspot (Wi-Fi CERTIFIED), a technology of wireless LAN WALN, is a trademark of the Wi-Fi Alliance, a wireless LAN technology based on the IEEE 802.11 standard.

[0031] 3G / 4G / 5G / 6G, third / fourth / fifth / sixth generation mobile communication technology.

[0032] The Global System for Mobile Communications (GSM), also known as the pan-European digital mobile phone system, is the most widely used mobile phone standard.

[0033] Subscriber Identity Module (SIM), commonly known as "SIM card" or "phone card", is a smart card mainly used to store user identification information, text message data and phone numbers.

[0034] Reinforcement Learning (RL) is a field in machine learning that emphasizes how to act based on the environment to maximize expected benefits.

[0035] Quality of experience (QoE), also known as "user experience quality", refers to the user's subjective perception of the quality and performance of devices, networks, systems, applications or services.

[0036] Quality of Service (QoS) refers to a network's ability to use various basic technologies to provide better service capabilities for specified network communications. It is a network security mechanism and a technology used to solve problems such as network delays and congestion.

[0037] A network access point (AP), also known as an access point, allows wireless workstations within the coverage area of ​​the access point to communicate with each other.

[0038] Wireless Fidelity hotspot (Wi-Fi hotspot), including sharing the network through Wi-Fi hotspot and Wi-Fi hotspot for local use only. Users can turn on the hotspot on the device to share the device's network. AP mode means that the terminal turns on network sharing and is in a mode of providing wireless access services.

[0039] Station (STA), each terminal connected to the wireless network (such as laptops, personal digital assistants (PDA) and other user devices that can be connected to the network) can be called a station. STA mode (STA mode), the terminal is in the mode of accessing the wireless network.

[0040] Received Signal Strength Indication (RSSI), an optional part of the wireless transmission layer, is used to determine the link quality and whether to increase the broadcast transmission strength.

[0041] Basic Service Set Identifier (BSSID), BSSID refers to the Media Access Control Address (MAC) address of the station.

[0042] The Physical Cell Identifier (PCI) is used by 4G / 5G terminals to distinguish the wireless signals of different cells. It directly determines the location of the main synchronization signal and reference signal used by each cell. It is the first network-side information identified when the terminal is turned on or initially accesses a cell.

[0043] The cell identity (Cell Identity, CID) is obtained from the subsequent system broadcast message after the terminal completes synchronization with the base station and identifies the PCI. It is the basis for realizing terminal global roaming and mobility management.

[0044] Absolute Radio Frequency Channel Number (ARDCN) is a numbering scheme used to identify specific radio frequency channels in the GSM wireless system. It describes two physical radio system links and channels on the Um interface of the GSM wireless network system. One is used for uplink and the other is used for downlink.

[0045] The existing network switching implementation scheme is usually between cellular cells. The terminal equipment changes to other cells through cell reselection, switching, redirection, etc., and switches to another network when there is a poor signal between the cellular and WLAN or within the WLAN. Network selection based on user preferences usually uses historical statistical data collected over a short period of time, such as collection time, location, network quality, application (application, APP) used, user usage time, etc., and then uses certain simple rules to find the network that best meets the rules in the historical records, and selects a network as the access network or switching target network.

[0046] In one implementation, an access network selection device and method based on a hidden Markov model are proposed. Based on the user's service characteristic sensitive needs and network status characteristics, optimized access network selection is performed for users in the common coverage area of ​​heterogeneous wireless networks, thereby achieving user service quality (QoS) guarantee and network performance optimization. Among them, the user's service characteristic sensitive needs are determined based on application status and usage preference analysis, and the optimized access network selection is to optimize the hidden Markov model modeling of each access network based on the user's historical data and current network status information, and then select the access network. It supports network integration mode, is suitable for heterogeneous wireless network environments, and can effectively realize adaptive and intelligent network access based on network steady-state information and user service needs.

[0047] In another implementation, a method and device for determining a network selection strategy are provided, specifically, a first network device obtains first network selection preference information, and determines a network selection strategy based on the information. The first network selection preference information is the network selection preference information of the first terminal, and the information includes a learning result obtained after learning data related to the terminal network selection, and the network selection strategy is used to determine the wireless management strategy of the first terminal. The core network device can determine the network selection strategy for the terminal based on the network selection preference information of the terminal, and globally consider various influencing factors, so that the network finally selected by the terminal can ensure user experience and avoid negative impact on the entire network.

[0048] In another implementation, a network preference prediction method, apparatus, device, medium, and program product are proposed. First, a network preference prediction model constructed based on network preference parameters is obtained, wherein the network preference parameters include operation data related to network usage performed by the user. Then, the network usage parameters of the target user are obtained, and the network preference prediction results are determined according to the network usage parameters and the network preference prediction model. The network currently preferred to be used by the target user is determined according to the network preference prediction results. The method can take into account the operation data related to network usage performed by the user and the network usage parameters of the user in the process of determining the network currently preferred to be used by the user, thereby improving the accuracy of the prediction of the network currently preferred to be used by the user.

[0049] However, no matter whether the above scheme is obtained from the terminal device or directly learned and obtained based on the user's network selection related data on the network device side, the network selection related data is collected from the terminal device, and user preference information is constructed based on the network usage data, rules are constructed or models are constructed, and based on complex rules or model results, a network is selected as an access network or a switching target network.

[0050] However, the problem is that when considering the preferences of a single user, the behaviors of other users in the same space are not considered, and the obtained user preferences may be contradictory, resulting in the inability to construct the graph or the failure of the model to converge.

[0051] In this application, if Figure 1 As shown, it is a system architecture diagram used in the embodiment of the present application. The target space can also be called a trusted space, and users using terminal devices in the trusted space are associated. Taking the target space as a home space as an example, a home space includes four devices, namely a mobile phone, a tablet, a smart watch and a TV.

[0052] In an embodiment of the present application, target update data of target terminal devices within the coverage range of the target space is obtained, the target terminal devices include the terminal devices and / or other terminal devices, and the target update data include at least one of usage scenario update data and network switching behavior data; the target network is determined according to the target update data and the target network recommendation model; wherein the target network recommendation model is constructed based on historical update data and corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data include historical usage scenario update data and historical network switching behavior data; because the target network recommendation model is constructed based on historical update data and corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data include historical usage scenario update data and historical network switching behavior data, the convergence and accuracy of the target network recommendation strategy can be improved, making network recommendation and optimization more effective and personalized.

[0053] In the embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a television, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0054] As an example but not limitation, in the embodiment of the present application, the terminal device can also be a wearable device with a display interface. Wearable devices can also be called wearable smart devices, which are a general term for wearable devices that use wearable technology to intelligently design and develop wearable devices for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and independent of smartphones to achieve complete or partial functions, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.

[0055] The technical solution of the present application is further described below by way of embodiments. Figure 2 As shown, it is a schematic diagram of an embodiment of a network recommendation method in an embodiment of the present application. The method is applied to a current terminal device. The embodiment of the method may include:

[0056] 201. Obtain target update data of target terminal devices within the coverage range of the target space, where the target terminal devices include the terminal device and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data.

[0057] For example, one of the devices within the coverage of the target space is taken as an example, and the current terminal device is in a network connection state, and the connected network can be referred to as the current network. The current network here can refer to mobile data, wireless fidelity (WiFi), or mobile data hotspot, or WiFi hotspot, etc.

[0058] The target space can also be called the trusted space. The trusted space can be understood as a network environment with a trust relationship between devices and users within a specific geographical range. The trusted space is a data sharing environment based on consensus rules, which aims to connect multiple parties to achieve secure sharing and efficient use of data resources. It uses a series of technical means (such as privacy computing, data sandbox, smart contracts, etc.) to ensure the security, compliance and privacy of data during circulation.

[0059] For example, it can be applied to the following application scenarios:

[0060] (1) Family Space

[0061] Multi-device trust environment: Terminal devices in the home (such as smart TVs, mobile phones, tablets, etc.) are connected through a unified user account to form a trust network. Users can seamlessly switch and share data between these devices while ensuring privacy.

[0062] Device learning and automatic configuration: The device automatically identifies and connects to the home network by learning the user's usage habits, forming a secure device space.

[0063] Family Sharing: With Family Sharing, family members can share apps, music, movies and more, while parents can manage their children’s devices and content.

[0064] In a home environment, a trusted space can be achieved by:

[0065] Unified user accounts: With a family sharing account, multiple devices can connect to the same network, forming a trusted device space.

[0066] Automatic device learning and configuration: The device automatically identifies and connects to the home network by learning the user's usage habits and network environment, reducing manual configuration.

[0067] Privacy protection: Ensure that the privacy of family members is not violated through device permission management and data encryption technology.

[0068] (2) Enterprise and Industrial Scenarios

[0069] Enterprise trusted data space: Enterprises can work with upstream and downstream partners to build a trusted data space to achieve secure sharing of sensitive information such as design drawings and production data.

[0070] Industrial Internet: Through a trusted data space, enterprises can achieve efficient data circulation and coordination within the industrial chain and improve production efficiency.

[0071] Urban trusted data space: By integrating data from multiple departments such as transportation, energy, and environmental protection, we can achieve intelligent urban management and improve the level of public services.

[0072] Authorized operation of public data: Relevant departments can use trusted data space to achieve secure sharing and authorized operation of public data.

[0073] (4) Personal data management

[0074] Personal trusted data space: Individuals can manage their own medical, financial and other data and independently decide which institutions to share with while ensuring data privacy.

[0075] In this technical solution, the target space, also known as the trusted space, realizes the trust relationship between devices and users through technical means and rules, and has broad application prospects in scenarios such as families, enterprises and cities. This space not only improves the efficiency of data sharing, but also ensures the security and privacy of data.

[0076] In some possible implementations, obtaining target update data of target terminal devices within the coverage of the target space may include: obtaining target update data of target terminal devices within the coverage of the target space when a network recommendation trigger condition is met, and the network recommendation trigger condition includes a change in the usage scenario of the target terminal device within the coverage of the target space, and / or a change in the network connection.

[0077] In this technical solution, when the network recommendation triggering conditions are met, the target update data of the target terminal device within the coverage range of the target space is obtained, which improves the feasibility of the solution and facilitates determining the target network based on the target update data and the target network recommendation model.

[0078] 1. Update data on usage scenarios of target terminal devices

[0079] In some possible implementations, the usage scenario update data of the target terminal device includes: update data of at least one of application usage data, environment data, and network usage information.

[0080] Optionally, obtaining usage scenario update data of a target terminal device within the coverage area of ​​the target space includes at least one of the following:

[0081] 1) Obtain update data from the first application usage data to the second application usage data of the target terminal device within the coverage of the target space, wherein the first application usage data and the second application usage data include at least one of the type of application running in the foreground, the number of different types of applications running in the foreground, the usage time of the application running in the foreground, and the number of applications running in the background.

[0082] The update data of the application usage data of the target terminal device may include: when the target terminal device updates from the application usage of the first data to the application usage of the second data, obtaining the update data of the target terminal device from the application usage of the first data to the application usage of the second data.

[0083] Optionally, the application usage data may include: the type of application APP running in the foreground, the number of different application APP types running in the foreground, the usage time of the application running in the foreground, the number of applications running in the background, etc.

[0084] (1) Update data of the application APP type running in the foreground includes: update data from a first APP type running in the foreground to a second APP type running in the foreground.

[0085] The types of applications running in the foreground can be divided into: social type, shopping type, office type, learning type, life service type, entertainment type, etc. They can also be simply divided by bandwidth requirements, among which the first bandwidth requirement type APP (referred to as high bandwidth requirement type APP), the second bandwidth requirement type APP (referred to as medium bandwidth requirement type APP), and the third bandwidth requirement type APP (referred to as low bandwidth requirement type APP). The bandwidth corresponding to the first bandwidth requirement type APP is greater than the bandwidth corresponding to the second bandwidth requirement type APP, and the bandwidth corresponding to the second bandwidth requirement type APP is greater than the bandwidth corresponding to the third bandwidth requirement type APP. For example: the type of application running in the foreground is updated from the low bandwidth requirement APP type to the high bandwidth requirement APP type.

[0086] (2) Update data of the number of different types of application programs APP running in the foreground includes: update data of the number of different types of application programs APP running in the foreground being updated from a first number range to a second number range.

[0087] Exemplarily, the number of different APP types running in the foreground can be understood as the number of APP types used by the terminal device in the same time period. The number of high-bandwidth demand APP types running in the foreground changes from a first number range (e.g., 0-2) to a second number range (e.g., 3-7).

[0088] (3) The update data of the usage time of the application program running in the foreground includes: the update data of the usage time of the application program running in the foreground being updated from the first time range to the second time range.

[0089] Exemplarily, the usage time of the foreground application can be understood as the usage time of the foreground application of the terminal device today, or the usage time this time, etc. The usage time of the foreground application is greater than the first preset time.

[0090] (4) Update data of the number of applications running in the background includes: update data of the number of applications running in the background being updated from a third number range to a fourth number range.

[0091] Exemplarily, the number of applications running in the background can be understood as the total number of applications running in the background of the terminal device. The number of applications running in the background exceeds a preset number (eg, 10) of update data, etc.

[0092] 2) Obtain update data of a target terminal device within the coverage of the target space from first environment data to second environment data, wherein the first environment data and the second environment data include at least one of a time period identifier, a date type, a space identifier, and a user identifier.

[0093] That is, the update data of the environment data of the target terminal device may include, but is not limited to, update data of a time period identifier, a date type, a space identifier, and a user identifier.

[0094] (1) The updated data of the time period identifier may include: the updated data from the first time period identifier to the second time period identifier. Exemplarily, the time period identifier may be understood as the identifier corresponding to the working time period, the off-get off work time period, and the evening rest time period. A more detailed time period division may also be performed according to actual needs, and the embodiments of the present application do not make specific limitations. For example: the updated data of the time period identifier may include the updated data from the working time period identifier to the off-get off work time period identifier. Exemplarily, the terminal device may determine the corresponding time period identifier through a timestamp.

[0095] (2) The date type update data may include: update data updated from a first date type to a second date type. Exemplarily, the date type may be understood as a working day, a non-working day, a statutory holiday, etc. For example: the date type update data may include update data updated from a working day to a non-working day.

[0096] (3) The updated data of the space identification may include: the updated data from the first space identification to the second space identification. Exemplarily, the space identification is understood to mean that the target space can be divided into different space areas, and each space area has a corresponding identification, which is called the space identification. Taking the target space of home as an example, each room corresponds to a space identification and the living room corresponds to a space identification. For example: the updated data of the space identification includes the updated data from the master bedroom identification to the living room identification. Exemplarily, the terminal device may have a collection module, such as a positioning sensor, and the space identification may be collected through the positioning sensor.

[0097] (4) The updated data of the user identification may include: updated data from the first user identification to the second user identification. Exemplarily, the user identification is the user account of the terminal device logged in. For example: the updated data of the user identification includes updated data from user identification A to user identification B.

[0098] 3) Updated data on the target terminal device’s network usage information, which may include but is not limited to the current network to which the target terminal device is connected, the duration of WiFi usage on that day, the duration of mobile data (also referred to as cellular data) usage on that day, the current network speed, the amount of mobile data used, the remaining amount of mobile data, and updated data on the number of terminal devices currently connected to WiFi.

[0099] 2. Network switching behavior data of the target terminal device

[0100] In some possible implementations, the network switching behavior data of the target terminal device may include, but is not limited to: behavior data of the target terminal device switching from a first network to a second network.

[0101] The types of the first network and the second network are the same or different. Exemplarily, the behavior data of the target terminal device switching from the first network to the second network may include: behavior data of switching between WiFi data and mobile data, behavior data of switching between the first WiFi data and the second WiFi data, and behavior data of switching between the first mobile data and the second mobile data. That is, behavior data of switching between WiFi data and cellular data, behavior data of switching between different cellular data, behavior data of switching between different WiFi data, etc. The triggering operation of this switching may be triggered by the user or by the system, and is not limited to the specific embodiments of the present application. For example: behavior data of a terminal device switching from the default current network to the first network.

[0102] In the present technical solution, the usage scenario update data and the network switching behavior data included in the target update data of the target terminal device are respectively described, so as to facilitate a better understanding of the usage scenario update data and the network switching behavior data and improve the feasibility of the solution.

[0103] In some possible implementations, the usage scenario update data of the target terminal device may carry at least one of a device identification and a device type of the corresponding terminal device.

[0104] The device identifier may be a serial number (Serial Number, SN).

[0105] Device types can be divided into mobile phones, tablets, laptops, smart watches, etc.

[0106] In this technical solution, the usage scenario update data of the target terminal device also includes at least one of the device identification and the device type, and an example is given to improve the feasibility of the solution.

[0107] In some possible implementations, the method may further include: when the target update data is the target update data of the terminal device, synchronizing the target update data to other terminal devices within the coverage range of the target space.

[0108] In some possible implementations, when the target update data is the target update data of the terminal device, synchronizing the target update data to other terminal devices within the coverage range of the target space may include: when the target update data is the target update data of the terminal device, synchronizing the target update data to other online terminal devices within the coverage range of the target space.

[0109] The description of online terminal devices is the terminal devices currently connected to the target space. For example: a total of 8 terminal devices have been connected within the coverage of the target space, and the current terminal device obtains the target update data. The target update data is the target update data of the current terminal device. However, in addition to the current terminal device, there are 5 other terminal devices online. Then, the current terminal device only needs to synchronize the target update data to these 5 online terminal devices. The other two terminal devices that are not online will be automatically synchronized after they come online.

[0110] In this technical solution, when the target update data is the target update data of the current terminal device, the target update data also needs to be synchronized to other online terminal devices within the coverage of the target space. Because the update of the target update data of the current terminal device may lead to network recommendations of other online terminal devices within the coverage of the target space, it is necessary to synchronize the target update data of the current terminal device to other online terminal devices within the coverage of the target space.

[0111] In some possible implementations, synchronizing the target update data to other online terminal devices within the coverage of the target space may include:

[0112] Synchronize the target update data to the target space database, and synchronize to other online terminal devices within the coverage of the target space through the target space database; or,

[0113] The target update data is synchronized to other online terminal devices within the coverage of the target space through broadcast or point-to-point mode.

[0114] Exemplarily, when the current terminal device detects target update data, that is, usage scenario update data, and / or network switching behavior data (also referred to as data path change data), it is recorded in the database of the current terminal device, and the target update data of the current terminal device can also be synchronized to other online terminal devices within the coverage of the target space. One of the following methods can be selected for synchronization: 1) Synchronize to the trusted space database, and synchronize to all online terminal devices within the coverage of the trusted space via the trusted space database (such as cloud disk, edge cloud, router, etc.); 2) Directly broadcast or point-to-point communicate in the trusted space to synchronize the target update data of the current terminal device to other online terminal devices within the coverage of the trusted space.

[0115] In the present technical solution, several specific implementation methods are provided for synchronizing the target update data of the current terminal device to other online terminal devices within the coverage range of the target space. Users can choose a synchronization method according to their needs, or use the default synchronization method. Because the update of the target update data of the current terminal device may result in network recommendations for other terminal devices within the coverage range of the target space, it is necessary to synchronize the target update data of the current terminal device to other online terminal devices within the coverage range of the target space.

[0116] In some possible implementations, the terminal device obtaining the target update data may include: when the target update data is the target update data of other terminal devices within the coverage range of the target space, receiving the target update data of other terminal devices synchronized by the other terminal devices.

[0117] Exemplarily, when the target update data is the target update data of other terminal devices within the coverage of the target space, the other terminal devices need to synchronize the corresponding target update data to the current terminal device, so the current terminal device receives the target update data synchronized by the other terminal devices. The method for synchronizing the target update data from other terminal devices to the current terminal device can refer to the synchronization method described above, which will not be repeated here.

[0118] In this technical solution, when the target update data is the target update data of other terminal devices within the coverage of the target space, the current terminal device receives the target update data synchronized by the other terminal devices. This ensures that the target update data of each terminal device within the coverage of the target space can be synchronized to other online terminal devices in a timely manner, and more accurate network recommendations can be made in a timely manner to provide users with better network services.

[0119] 202. Determine a target network according to the target update data and the target network recommendation model.

[0120] The target network recommendation model is constructed based on historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, wherein the historical update data includes historical usage scenario update data and historical network switching behavior data.

[0121] 1. The historical networks of different terminal devices within the coverage of the target space may include network identifiers. Optionally, the historical networks of the terminal devices may also include network types.

[0122] Network identifier, such as BSSID (Basic Service Set Identifier), CID (Cell Identity), etc.

[0123] Network type, which may include operator, frequency band, etc.

[0124] 2. Historical update data of different terminal devices within the coverage area of ​​the target space

[0125] The historical usage scenario update data of different terminal devices includes: update data of at least one of historical application usage data, historical environment data, and historical network usage information.

[0126] 1) Update data of historical application usage data of different terminal devices may include: when different terminal devices update from historical application usage first data to historical application usage second data, obtaining update data of different terminal devices from updating from historical application usage first data to historical application usage second data.

[0127] Optionally, historical application usage data may include: the types of applications running in the historical foreground, the number of different types of applications running in the historical foreground, the usage time of applications running in the historical foreground, the number of applications running in the historical background, etc.

[0128] (1) The update data of the application APP type running in the historical foreground includes: the update data from the first APP type running in the historical foreground to the second APP type running in the historical foreground.

[0129] The types of applications running in the historical foreground can be divided into: social type, shopping type, office type, learning type, life service type, entertainment type, etc. They can also be simply divided by bandwidth requirements, among which the first bandwidth requirement type APP (referred to as high bandwidth requirement type APP), the second bandwidth requirement type APP (referred to as medium bandwidth requirement type APP), and the third bandwidth requirement type APP (referred to as low bandwidth requirement type APP). The bandwidth corresponding to the first bandwidth requirement type APP is greater than the bandwidth corresponding to the second bandwidth requirement type APP, and the bandwidth corresponding to the second bandwidth requirement type APP is greater than the bandwidth corresponding to the third bandwidth requirement type APP. For example: the update data of the application type running in the historical foreground is updated from the low bandwidth requirement APP type to the high bandwidth requirement APP type.

[0130] (2) The update data of the number of different application APP types running in the historical foreground includes: the update data of the number of different application APP types running in the historical foreground is updated from a first number range to a second number range.

[0131] For example, the number of different APP types running in the historical foreground can be understood as the number of APP types used by the terminal device in the same time period. The number of high-bandwidth demand APP types running in the historical foreground changes from a first number range (e.g., 0-2) to a second number range (e.g., 3-7).

[0132] (3) The update data of the usage time of the application program running in the foreground in history includes: the update data of the usage time of the application program running in the foreground in history being updated from the first time range to the second time range.

[0133] Exemplarily, the usage time of the historical foreground application can be understood as the usage time of the application currently running in the foreground of the terminal device today, or the usage time this time, etc. The usage time of the historical foreground application is greater than the first preset time.

[0134] (4) Update data of the number of historical background-running applications includes: update data of the number of historical background-running applications being updated from a third number range to a fourth number range.

[0135] Exemplarily, the number of historical background running applications can be understood as the total number of background running applications of the terminal device, the number of historical background running applications exceeding a preset number (eg, 10) of update data, etc.

[0136] 2) The update data of the historical environment data of different terminal devices may include, but are not limited to, the update data of the historical time period identifier, the historical date type, the historical space identifier, and the historical user identifier.

[0137] (1) The updated data of the historical time period identifier may include: the updated data from the first historical time period identifier to the second historical time period identifier. Exemplarily, the time period identifier may be understood as the identifier corresponding to the working time period, the off-get off work time period, and the evening rest time period. A more detailed time period division may also be performed according to actual needs, and the embodiments of the present application do not make specific limitations. For example: the updated data of the time period identifier may include the updated data from the working time period identifier to the off-get off work time period identifier. Exemplarily, the terminal device may determine the corresponding time period identifier through a timestamp.

[0138] (2) The update data of the historical date type may include: the update data updated from the first historical date type to the second historical date type. Exemplarily, the date type may be understood as a working day, a non-working day, a statutory holiday, etc. For example, the update data of the date type may include the update data updated from a working day to a non-working day.

[0139] (3) The update data of the historical space identification may include: the update data from the first historical space identification to the second historical space identification. Exemplarily, the space identification is understood to mean that the target space can be divided into different space areas, and each space area has a corresponding identification, which is called the space identification. Taking the target space as a home as an example, each room corresponds to a space identification and the living room corresponds to a space identification. For example: the update data of the historical space identification includes the update data from the master bedroom identification to the living room identification. Exemplarily, the terminal device may have a collection module, such as a positioning sensor, through which the space identification can be collected.

[0140] (4) The update data of the historical user identification may include: update data from the first historical user identification to the second historical user identification. Exemplarily, the user identification is the user account of the terminal device logged in. For example: the update data of the user identification includes update data from user identification A to user identification B.

[0141] 3) Updated data on historical network usage information of different terminal devices, which may include but is not limited to historical current networks connected to different terminal devices, historical daily WiFi usage duration, historical daily mobile data (also known as cellular data) usage duration, historical current network speed, historical mobile data usage, historical mobile data remaining amount, and updated data on the historical number of terminal devices currently connected to WiFi.

[0142] 3. Historical network switching behavior data of different terminal devices

[0143] In some possible implementations, the historical network switching behavior data of different terminal devices may include but is not limited to: behavior data of different terminal devices switching from a first historical network to a second historical network, where the first historical network and the second historical network are of the same or different types.

[0144] Exemplarily, the behavior data of different terminal devices switching from the first historical network to the second historical network may include: the behavior data of switching between WiFi data and mobile data, the behavior data of switching between the first WiFi data and the second WiFi data, and the behavior data of switching between the first mobile data and the second mobile data. That is, the behavior data of switching between WiFi data and cellular data, the behavior data of switching between different cellular data, the behavior data of switching between different WiFi data, etc. The triggering operation of this switching may be triggered by the user or by the system, and is not limited to the specific embodiments of the present application. For example: the behavior data of a terminal device switching from the default historical current network to the historical first network.

[0145] In this technical solution, the historical update data of different terminal devices, including the historical usage scenario update data and the historical network switching behavior data, are explained separately to facilitate a better understanding of the historical usage scenario update data and the historical network switching behavior data, thereby improving the feasibility of the solution.

[0146] In some possible implementations, the historical usage scenario update data of different terminal devices may carry at least one of the device identification and device type of the corresponding terminal device.

[0147] The device identifier may be a serial number (Serial Number, SN).

[0148] Device types can be divided into mobile phones, tablets, laptops, smart watches, etc.

[0149] In this technical solution, historical usage scenario update data for different terminal devices also includes at least one of a device identification and a device type, and an example is provided to improve the feasibility of the solution.

[0150] In some possible implementations, determining the target network according to the target update data and the target network recommendation model may include:

[0151] When the ping-pong switching suppression timer corresponding to the terminal device has not timed out, wait for the ping-pong switching suppression timer to time out, and then determine the target network according to the target update data and the target network recommendation model; or

[0152] When the ping-pong switching suppression timer corresponding to the terminal device times out, the target network is determined according to the target update data and the target network recommendation model.

[0153] Exemplarily, after the current terminal device obtains the target update data, in order to prevent the network switching between multiple terminal devices within the coverage of the target space from coupling each other and causing ping-pong switching, a ping-pong switching inhibition timer can be added. The timer time is not specifically limited, for example, it can be 30s. It is determined whether the current terminal device is in the ping-pong switching inhibition time range, that is, the ping-pong inhibition stage. If it is in the ping-pong inhibition stage, wait until the timer times out before executing the subsequent process, otherwise directly execute the subsequent process.

[0154] In this technical solution, in order to prevent the network switching between multiple terminal devices within the coverage of the target space from being coupled to each other and causing ping-pong switching, after the current terminal device obtains the target update data, the ping-pong switching suppression timer can be used to coordinate the network switching between multiple terminal devices to avoid ping-pong switching and optimize the user experience. That is, a ping-pong switching suppression module can be added during the recommendation process to avoid the continuous ping-pong switching phenomenon, and multiple terminal devices within the coverage of the trusted space can trigger cyclic mutual detection, and can execute the network switching of the current terminal device based on the network switching request sent by other terminal devices.

[0155] In some possible implementations, the target network recommendation model may include a target knowledge graph and / or a target model.

[0156] In the process of building the target knowledge graph, data preprocessing is required first, that is, cleaning and formatting the historical update data and the corresponding historical network; then entity relationship identification is required, that is, extracting entities and relationships from the historical update data and the corresponding historical network; finally, graph database storage is performed, and a suitable graph database (such as Neo4j or ArangoDB) is selected to store the knowledge graph data. The nodes of the knowledge graph include user behavior, device status, application usage, etc., and the edges represent the relationships between these entities.

[0157] Alternatively, instead of building a knowledge graph, you can choose to use a large model or some machine learning models with memory, such as the Echo State Network (ESN), the Long Short Term Memory (LSTM), etc., to learn historical update data and the corresponding historical network for training, and perform subsequent network prediction and recommendation. Compared with the knowledge graph solution, the process is complex, requires a large amount of data, and the model interpretability is low.

[0158] In the present technical solution, the target network recommendation model may include a target knowledge graph and / or a target model; examples are given for the target knowledge graph and the target model, which improves the feasibility of the solution and provides a basis for determining the target network of the current terminal device based on the target update data and the target network recommendation model.

[0159] In an embodiment of the present application, target update data of target terminal devices within the coverage range of the target space is obtained, the target terminal devices include the terminal devices and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data; the target network is determined according to the target update data and the target network recommendation model; wherein the target network recommendation model is constructed according to the historical update data and the corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data. Network recommendations can be made according to the target update data and the target network recommendation model, because the target network recommendation model is constructed in combination with the historical update data and the corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data, which can improve the convergence and accuracy of the target network recommendation strategy.

[0160] like Figure 3 As shown, it is a schematic diagram of another embodiment of the network recommendation method in the embodiment of the present application, which may include:

[0161] 301. Obtain historical update data and corresponding historical networks of different terminal devices within the coverage area of ​​the target space.

[0162] The construction of the target network recommendation model is based on the historical update data of different terminal devices within the coverage of the target space and the corresponding historical networks. The historical update data includes historical usage scenario update data and historical network switching behavior data. The historical usage scenario update data and historical network switching behavior data can be referred to the above description and will not be repeated here.

[0163] The target network recommendation model may include a target knowledge graph and / or a target model.

[0164] Among them, the historical network may include a network ID (such as CID, BSSID, etc.). Furthermore, factors such as network type (operator, frequency band, etc.) may also be considered. The embodiment of the present application further refines the network access scenarios of each terminal device in the target space by adding usage scenario update data and network switching behavior data of different terminal devices, so that the target network recommendation model can more accurately identify and distinguish network recommendations corresponding to different terminal devices, different terminal device types, different users, different application types, usage time of different application types, different numbers of background applications, different space identifiers, different time period identifiers, different date types, etc.

[0165] Exemplary factors considered in building a personalized knowledge graph are as follows:

[0166] 1) In the network access binding scenario of the target knowledge graph / target model, it is considered that different user behaviors within the coverage of the trusted space affect the network recommendations of different terminal devices. Therefore, in the process of building the target network recommendation model, segmented user behavior data needs to be considered.

[0167] (1) Adding the behavior information of other users when using different types of APPs may result in different final access networks of the current terminal device.

[0168] For the same terminal device, different types of apps running in the foreground, accessing / leaving the network, are considered different scenarios, and network access is differentiated. For example: accessing the network when using app X, and / or, leaving the network when using app Y.

[0169] For different terminal devices and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0170] For the same user ID and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0171] For different user IDs, different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0172] For the same terminal device, different user IDs, and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0173] For different terminal devices, different user IDs, and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0174] For the same terminal device, the same user ID, and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0175] For different terminal devices, the same user ID, and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0176] It should be noted that for the descriptions of different APP types, you can also add time period identifiers, date types and other conditions, which will not be repeated here.

[0177] (2) In the target space, the number of different APP types used is different, which may result in different final access networks of the current terminal device.

[0178] In the target space, when there are N1 users using APP type M1 on other terminal devices, the current terminal device accesses the network; when there are N2 users using APP type M2 on other terminal devices, the current terminal device accesses the network. This granularity is also regarded as different scenarios to distinguish network access.

[0179] For example, if there are 5 users using a video app and 6 users using a music app in the trusted space, they are considered different scenarios. Different user combinations and app usage will lead to different network access scenarios.

[0180] (3) Adding device types, such as mobile phones, tablets, watches, etc. Different types of devices may result in different final access networks for the current terminal devices.

[0181] Optionally, the number of devices accessing the WiFi network, the type of APP running in the foreground, at least one of the number of uses of different APP types, etc. may be added to differentiate network access.

[0182] For different types of terminal devices, accessing / exiting the network is considered as different scenarios and network access is differentiated.

[0183] For different types of terminal devices and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0184] For different types of terminal devices and the same type of APP running in the foreground, accessing / exiting the network are considered different scenarios and network access is differentiated.

[0185] For different terminal device types, the same user ID, and different APP types running in the foreground, accessing / exiting the network are considered different scenarios and network access is differentiated.

[0186] For different terminal device types, different user IDs, and different types of apps running in the foreground, accessing / leaving the network are considered different scenarios and network access is differentiated.

[0187] For different terminal device types, the same user ID, and the same APP type running in the foreground, accessing / exiting the network are considered different scenarios and network access is differentiated.

[0188] For different terminal device types, different user IDs, and the same APP type running in the foreground, accessing / exiting the network are considered different scenarios and network access is differentiated.

[0189] Take the example of combining the device type (such as mobile phone, tablet, watch, etc.) and the type of APP running in the foreground, the number of devices, the number of APP types, etc. to further subdivide the access network scenario. For example: In the target space, there are 3 mobile phones using APPX access and 2 tablets using APP Y access. This combination is regarded as a unique access scenario. If the device type or the type of APP used changes, or the number of devices increases or decreases, the network access scenario will be redefined.

[0190] 2) In the network access binding scenario of the target knowledge graph / target model, it is considered that the network demand information of different users within the coverage of the trusted space affects the network recommendation of the terminal device. Therefore, in the process of building the target network recommendation model, it is necessary to consider the current user's current network demand information being affected by the environment, or the influence of other users' behaviors in the trusted space. Therefore, in this application, by adding environmental influences or other users' behavior information, the current user's current network demand is more accurately evaluated and distinguished.

[0191] (1) When using different APP types, the current network requirements of the current terminal device change.

[0192] For the same terminal device, different types of apps running in the foreground are considered different scenarios to distinguish changes in network requirements. For example, the current user's network requirements change when using app X, and / or the current user's network requirements change when using app Y.

[0193] Different terminal devices and different types of apps running in the foreground are considered as different scenarios to distinguish changes in network requirements.

[0194] For the same user ID and different types of apps running in the foreground, they are considered as different scenarios to distinguish changes in network requirements.

[0195] Different user IDs and different types of apps running in the foreground are considered as different scenarios to distinguish changes in network requirements.

[0196] The same terminal device, different user IDs, and different types of apps running in the foreground are considered different scenarios to differentiate changes in network requirements.

[0197] Different terminal devices, different user IDs, and different types of apps running in the foreground are considered different scenarios to differentiate changes in network requirements.

[0198] For the same terminal device, the same user ID, and different types of apps running in the foreground, they are considered to be different scenarios and the changes in network requirements are distinguished.

[0199] Different terminal devices, the same user ID, and different types of apps running in the foreground are considered different scenarios to distinguish changes in network requirements.

[0200] It should be noted that for the descriptions of different APP types, you can also add time period identifiers, date types and other conditions, which will not be repeated here.

[0201] (2) In the target space, the number of different APP types used is different, resulting in different current network requirements of the current terminal device.

[0202] In the target space, when N1 users of other terminal devices use APP type M1, the current terminal device accesses the network; when N2 users of other terminal devices use APP type M2, the current terminal device accesses the network. This granularity is also regarded as different scenarios to distinguish the current network demand of the current user.

[0203] For example, if there are 5 users in the trusted space using APP type M1 and 6 users using APP type M2, this combination will affect the current network demand assessment of the current user. Different user combinations and APP usage will lead to different network demands of the current user, thus affecting the final access network.

[0204] (3) Add device types, such as mobile phones, tablets, watches, etc., and re-evaluate and differentiate the current network needs of current users based on the different device types.

[0205] Optionally, at least one of the number of devices connected to the WiFi network, the type of APPs running in the foreground, and the number of different APP types used may be added to re-evaluate and differentiate the current network demand of the current user.

[0206] Different terminal device types are considered as different scenarios to differentiate current network requirements.

[0207] Different types of terminal devices and different types of apps running in the foreground are considered as different scenarios to differentiate the current network requirements.

[0208] Different types of terminal devices and the same type of APP running in the foreground are considered as different scenarios to distinguish the current network requirements.

[0209] Different terminal device types, the same user ID, and different APP types running in the foreground are considered different scenarios to distinguish current network requirements.

[0210] Different terminal device types, different user IDs, and different types of apps running in the foreground are considered different scenarios to differentiate current network requirements.

[0211] Different terminal device types, the same user ID, and the same APP type running in the foreground are considered different scenarios to distinguish the current network requirements.

[0212] Different terminal device types, different user IDs, and the same APP type running in the foreground are considered different scenarios to distinguish the current network requirements.

[0213] Take the example of combining device type (such as mobile phone, tablet, watch, etc.) and the type of APP running in the foreground, the number of devices, the number of APP types, etc. to further subdivide the network demand scenario. For example: In the target space, there are 3 mobile phones using APPX access and 2 tablets using APP Y access. This combination is regarded as a unique access scenario. If the device type or the type of APP used changes, or the number of devices increases or decreases, the current network demand of the current user will be re-evaluated.

[0214] In this technical solution, the core of this personalized target knowledge graph / target model construction method is to further subdivide the access and demand scenarios by adding user behavior information (such as application usage data, device type, number of users, etc.). That is, when collecting historical update data and corresponding historical networks, the current user behavior triggered by other user behaviors in the environment, as well as the current user behavior triggered by objective factors and environmental changes, are comprehensively considered. This enables the target knowledge graph / target model to more accurately identify the behavior patterns and network demand changes of different users in different environments, thereby providing richer data support and more accurate decision-making basis for personalized services.

[0215] 302. Construct the target network recommendation model according to the historical update data and the corresponding historical network.

[0216] In some possible implementations, the target network recommendation model may include a target knowledge graph and / or a target model.

[0217] In the process of building the target knowledge graph, data preprocessing is required first, that is, cleaning and formatting the historical update data and the corresponding historical network; then entity relationship identification is required, that is, extracting entities and relationships from the historical update data and the corresponding historical network; finally, graph database storage is performed, and a suitable graph database (such as Neo4j or ArangoDB) is selected to store the knowledge graph data. The nodes of the knowledge graph include user behavior, device status, application usage, etc., and the edges represent the relationships between these entities.

[0218] In the process of building the target model, the historical update data and the corresponding historical network are divided into training data and reference data. The model is trained according to the training data to obtain the training model. Then, it is determined whether the error between the output data of the model and the reference data is less than the error threshold. If it is less than the error threshold, it is determined that the error rate of the model is within an acceptable range, and the training model can be used as the target model for network recommendation.

[0219] 303. Obtain target update data of target terminal devices within the coverage range of the target space, where the target terminal devices include the terminal device and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data.

[0220] 304 determines a target network according to the target update data and the target network recommendation model.

[0221] It should be noted that in the embodiment of the present application, steps 303 and 304 are Figure 2 Steps 201 and 202 in the illustrated embodiment are similar and will not be described in detail herein.

[0222] In some possible implementations, the method may further include: acquiring current usage data of the terminal device and / or other terminal devices, the current usage data including at least one of current usage scenario data and current usage network information;

[0223] Determining the target network according to the target update data and the target network recommendation model may include: determining current network demand information according to the target update data, the current usage data and a first target network recommendation model, wherein the first target network recommendation model is constructed according to the historical update data, the historical usage data and the historical network demand information, wherein the historical usage data includes historical usage scenario data and historical network usage information; obtaining the target network according to the current network demand information and a second target network recommendation model, wherein the second target network recommendation model is constructed according to the historical network demand information and the corresponding historical network;

[0224] The target network recommendation model includes the first target network recommendation model and the second target network recommendation model.

[0225] Exemplarily, after obtaining the target update data, for example, the target update data is the update data from the bedroom ID to the living room ID, at this time, the corresponding current usage data can also be obtained, and the current usage data includes at least one of the current usage scenario data and the current usage network information.

[0226] Optionally, the current usage scenario data includes current usage scenario data of the terminal device and / or current usage scenario data of other terminal devices.

[0227] The current usage scenario data may include: the type of APP running in the foreground, the number of different APP types running in the foreground, the usage time of the APP running in the foreground, the number of APP running in the background, the time period identifier, the date type, and at least one of the user identifiers.

[0228] Optionally, the currently used network information includes the currently used network information of the terminal device and / or the currently used network information of other terminal devices.

[0229] The currently used network information may include: the current network ID of the connection, the usage time of WiFi on that day, the usage time of mobile data (also called cellular data) on that day, the speed of the current network, the usage of mobile data, the remaining amount of mobile data, and at least one of the updated data of the number of terminal devices currently connected to WiFi.

[0230] Among them, the first target network recommendation model is constructed based on the historical update data, historical usage data and historical network demand information. The historical usage data includes historical usage scenario data and historical network usage information. Regarding the historical usage scenario data and historical network usage information, refer to the description of the current usage scenario data and the current network usage information in the above text, which will not be repeated here.

[0231] The current network demand information includes at least one of the current network frequency band demand, the current network rate demand and the current network type demand. The current network demand information can characterize the user's quality of experience, which refers to the user's subjective feeling about the quality and performance of the device, network and system, application or service. The current network demand information can also be understood as the current network demand level. The second target network recommendation model is constructed based on the historical network demand information and the corresponding historical network. The historical network demand information can refer to the description of the current network demand information, which will not be repeated here.

[0232] Exemplarily, current usage data and target update data are input into a first target network recommendation model to obtain corresponding current network demand information, and then the current network demand information is input into a second target network recommendation model to obtain a recommended target network.

[0233] If the first target network recommendation model is a knowledge graph, then the second target network recommendation model is also a knowledge graph; if the first target network recommendation model is an algorithm model, then the second target network recommendation model is also an algorithm model.

[0234] In this technical solution, the current network demand information can be determined based on the target update data and the current usage data, as well as the first target network recommendation model, and then the target network can be determined based on the current network information and the second target network recommendation model. This provides a specific implementation method for determining the target network and improves the feasibility of the solution.

[0235] In some possible implementations, obtaining the target network according to the current network demand information and the second target network recommendation model may include: obtaining available networks according to the current network demand information and the second target network recommendation model; and determining the best network among the available networks as the target network.

[0236] Exemplarily, when the second target network recommendation model is the second target knowledge graph, the current network demand information is input into the second target knowledge graph to match the available networks; the available networks are sorted according to their scores in the second knowledge graph, and the best network among the available networks can be used as the target network.

[0237] When the second target network recommendation model is the second target model, the current network demand information is input into the second target model, the available networks are matched and sorted according to the communication quality of the available networks, and the best network among the available networks can be used as the target network.

[0238] In this technical solution, available networks that meet current network demand information can be matched according to the second target network recommendation model, and then the best network among the available networks is used as the target network, which provides a specific implementation method for determining the target network and improves the feasibility of the solution.

[0239] In some possible implementations, the method may further include: when no available network is matched according to the current network demand information and the second target network recommendation model, network adjustment is performed according to the network demand information of different terminal devices within the coverage range of the target space to obtain the target network, and the network demand information of the different terminal devices includes the current network demand information.

[0240] Exemplarily, based on the first target knowledge graph / first target model, the current demand information corresponding to the current usage data and the target update data is matched, and then based on the second target knowledge graph / second target model, and the current demand information, if there is no available network to meet the current demand information, a network switching request (also referred to as a network adjustment request) can be generated, and according to the network switching request, the network is adjusted according to the network demand information of different terminal devices within the coverage of the target space to obtain the target network. For example: submit a network switching request to the management module of the trusted space, and the management module of the trusted space adjusts the network according to the network demand information of all terminal devices, triggering network switching of other terminal devices to obtain a target network that meets the current network demand information.

[0241] In the present technical solution, the current network demand information can be determined based on the current usage data and target update data, as well as the first target network recommendation model. Then, after matching the available networks that do not meet the current network demand information according to the second target network recommendation model, the network is adjusted according to the network demand information of different terminal devices within the coverage range of the target space to obtain the target network. This provides a specific implementation method for determining the target network, thereby improving the feasibility of the solution.

[0242] Optionally, the method may also include: when receiving target update data from other terminal devices within the coverage range of the target space and no available network is matched, triggering a network switching request of the terminal device; and executing network switching of the terminal device according to the network switching request of the terminal device to obtain an available network for other terminal devices.

[0243] In this technical solution, personalized knowledge graphs and / or models are used to dynamically adjust the binding scenarios of network access and terminal devices corresponding to user network demand information, and the optimal network is matched according to the knowledge graphs and / or models as the target network. A specific implementation method for determining the target network based on current usage data and target update data, as well as knowledge graphs and / or models is provided.

[0244] 305. Perform network switching according to the target network.

[0245] In some possible implementations, performing network switching according to the target network may include:

[0246] If the current terminal device is connected to a current network, the current network is switched to the target network for communication. For example, if the first terminal device is connected to a current network, it is necessary to disconnect the current network first and then connect to the target network, or to connect to the target network first and then disconnect the current network. Or,

[0247] When the current terminal device is connected to a current network, if the communication quality of the target network is higher than that of the current network, the current network is switched to the target network for communication. Exemplarily, when the current terminal device is connected to a current network, if the communication quality of the target network is higher than that of the current network, it is necessary to disconnect the current network first and then connect to the target network, or to connect to the target network first and then disconnect the current network.

[0248] In some possible implementations, the method may further include: when the current terminal device has a current network to which it is connected, if the communication quality of the target network is lower than the communication quality of the current network, not performing a network switching operation. Exemplarily, when the current terminal device has a current network to which it is connected, if the communication quality of the target network is lower than the communication quality of the current network, not performing a network switching operation.

[0249] The current terminal device can switch networks according to the target network. If the current terminal device is not connected to any network, then after obtaining the target network, the network connection is directly performed. If the current terminal device is connected to the current network, then after obtaining the target network, the communication quality of the current network and the target network is compared. If the communication quality of the target network is better than that of the current network, the current network is connected to the target network through network switching; if the communication quality of the target network is worse than that of the current network, the network switching operation is not performed and the current network continues to be used.

[0250] In this technical solution, the network switching is performed on the current terminal device according to the target network, a specific implementation method is provided, and the feasibility of the solution is improved.

[0251] The technical solution of this application can be divided into three parts: data collection and synchronization, personalized knowledge graph construction, network recommendation and network switching. Optionally, it can also include a trusted space database. Optionally, it can also include a trusted space network management module. Figure 4 The figure is a schematic diagram of the process used in the embodiment of the present application.

[0252] like Figure 5As shown, it is a flowchart of network recommendation in an embodiment of the present application. For example, a terminal device within the coverage of the trusted space is monitored, and the current terminal device is used as an example to explain whether the foreground APP type, space ID, and default network of the current terminal device have changed, and whether the foreground APP type, space ID, and default network of other terminal devices have changed. If there is a change, it can be called target update data, and then it can be determined whether it is within the ping-pong switching inhibition time range? If it is within the ping-pong switching inhibition time range, you can wait for the ping-pong switching inhibition timer to time out, that is, the ping-pong switching inhibition timer ends, and execute according to the target update data, as well as the knowledge graph and / or model, to determine the target network, which can also be called a recommended network, and then perform network switching according to the target network.

[0253] If the target network is not obtained according to the target update data, knowledge graph and / or model, a network switching request can be generated, and the network switching can be performed through the trusted space network management module to trigger other devices to perform network switching, obtain the target network, and then execute the network switching of the current terminal device. Optionally, the current terminal device can also receive a network switching request sent by other devices in the trusted space and execute the network switching.

[0254] In an embodiment of the present application, the historical update data and the corresponding historical network are obtained; the target network recommendation model is constructed based on the historical update data and the corresponding historical network; the target update data of the target terminal device within the coverage range of the target space is obtained, the target terminal device includes the terminal device and / or other terminal devices, and the target update data includes at least one of the usage scenario update data and the network switching behavior data; the target network is determined based on the target update data and the target network recommendation model; and the network is switched based on the target network. The operation data of multiple users and multiple devices in the trusted space can be combined, and when constructing a personalized knowledge graph / model, it can effectively identify and process user conflicting behavior scenarios caused by the operation of other devices with the same other conditions, avoiding the problem of non-convergence or statistical errors of the knowledge graph and / or model. This method significantly improves the accuracy of the knowledge graph and / or model, making network recommendation and optimization more effective and personalized.

[0255] like Figure 6 FIG. 1 is a schematic diagram of an embodiment of a network recommendation device in an embodiment of the present application, wherein the device is applied to a terminal device, and the device includes:

[0256] An acquisition module 601 is used to acquire target update data of a target terminal device within the coverage range of a target space, wherein the target terminal device includes the terminal device and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data;

[0257] A processing module 602 is used to determine a target network according to the target update data and the target network recommendation model;

[0258] The target network recommendation model is constructed based on historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, wherein the historical update data includes historical usage scenario update data and historical network switching behavior data.

[0259] Optionally, in some possible implementations, obtaining usage scenario update data of a target terminal device within the coverage area of ​​the target space includes at least one of the following:

[0260] Acquire update data of a target terminal device within the coverage of the target space from first application usage data to second application usage data, wherein the first application usage data and the second application usage data include at least one of a type of application running in the foreground, a number of different types of application running in the foreground, a usage time of an application running in the foreground, and a number of applications running in the background;

[0261] Acquire update data of a target terminal device within the coverage range of the target space from first environment data to second environment data, where the first environment data and the second environment data include at least one of a time period identifier, a date type, a space identifier, and a user identifier;

[0262] Obtain the network switching behavior data of the target terminal device within the coverage area of ​​the target space, including:

[0263] Acquire update data of a target terminal device within the coverage area of ​​the target space from the first network to the second network.

[0264] Optionally, in some possible implementations, the acquisition module 601 is further configured to acquire current usage data of the terminal device and / or other terminal devices, where the current usage data includes at least one of current usage scenario data and current usage network information;

[0265] The processing module 602 is specifically configured to determine the current network demand information according to the target update data, the current usage data and the first target network recommendation model, wherein the first target network recommendation model is constructed according to the historical update data, the historical usage data and the historical network demand information, wherein the historical usage data includes historical usage scenario data and historical network usage information; obtain the target network according to the current network demand information and the second target network recommendation model, wherein the second target network recommendation model is constructed according to the historical network demand information and the corresponding historical network;

[0266] The target network recommendation model includes the first target network recommendation model and the second target network recommendation model.

[0267] Optionally, in some possible implementations, the processing module 602 is further configured to obtain available networks according to the current network demand information and the second target network recommendation model; and determine the best network among the available networks as the target network.

[0268] Optionally, in some possible implementations, the processing module 602 is specifically used to adjust the network according to the network demand information of different terminal devices within the coverage of the target space to obtain the target network when no available network is matched according to the current network demand information and the second target network recommendation model, and the network demand information of the different terminal devices includes the current network demand information.

[0269] Optionally, in some possible implementations, the processing module 602 is specifically configured to, when the ping-pong switching suppression timer corresponding to the terminal device has not timed out, wait for the ping-pong switching suppression timer to time out, and determine the target network according to the target update data and the target network recommendation model; or,

[0270] The processing module 602 is specifically configured to determine a target network according to the target update data and the target network recommendation model when the ping-pong switching suppression timer corresponding to the terminal device times out.

[0271] Optionally, in some possible implementations, the processing module 602 is further used to synchronize the target update data to other online terminal devices within the coverage range of the target space when the target update data is the target update data of the terminal device.

[0272] Optionally, in some possible implementations, the processing module 602 is specifically configured to synchronize the target update data to a target space database, and synchronize the target update data to other online terminal devices within the coverage of the target space through the target space database; or,

[0273] The processing module 602 is specifically used to synchronize the target update data to other online terminal devices within the coverage range of the target space through broadcast or point-to-point mode.

[0274] Optionally, in some possible implementations, the acquisition module 601 is specifically used to receive the target update data synchronized by other terminal devices when the target update data is the target update data of other terminal devices within the coverage range of the target space.

[0275] Optionally, in some possible implementations, the acquisition module 601 is further configured to acquire the historical update data and the corresponding historical network;

[0276] The processing module 602 is further configured to construct the target network recommendation model according to the historical update data and the corresponding historical network.

[0277] like Figure 7 As shown, it is a schematic diagram of an embodiment of a terminal device in an embodiment of the present application, which may include: Figure 6 Recommended devices for the network shown.

[0278] like Figure 8 FIG. 1 is another schematic diagram of a terminal device in an embodiment of the present application. Figure 8 A detailed introduction to the various components of the mobile phone in the terminal device:

[0279] The RF circuit 810 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is sent to the processor 880 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit 810 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the RF circuit 810 can also communicate with the network and other devices through wireless communication. The above wireless communication can use any communication standard or protocol, including but not limited to the Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0280] The memory 820 can be used to store software programs and modules. The processor 880 executes various functional applications and data processing of the mobile phone by running the software programs and modules stored in the memory 820. The memory 820 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 820 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0281] The input unit 830 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the mobile phone. Specifically, the input unit 830 may include a touch panel 831 and other input devices 832. The touch panel 831, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 831 or near the touch panel 831 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. Optionally, the touch panel 831 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 880, and can receive and execute commands sent by the processor 880. In addition, the touch panel 831 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 831, the input unit 830 may also include other input devices 832. Specifically, the other input devices 832 may include but are not limited to one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, etc.

[0282] The display unit 840 can be used to display information input by the user or information provided to the user and various menus of the mobile phone. The display unit 840 may include a display panel 841. Optionally, the display panel 841 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. Further, the touch panel 831 may cover the display panel 841. When the touch panel 831 detects a touch operation on or near it, it is transmitted to the processor 880 to determine the type of touch event. Subsequently, the processor 880 provides a corresponding visual output on the display panel 841 according to the type of touch event. Although in Figure 8 In the embodiment, the touch panel 831 and the display panel 841 are used as two independent components to realize the input and output functions of the mobile phone, but in some embodiments, the touch panel 831 and the display panel 841 can be integrated to realize the input and output functions of the mobile phone.

[0283] The mobile phone may also include at least one sensor 850, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 841 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 841 and / or the backlight when the mobile phone is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can be configured in the mobile phone, such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0284] The audio circuit 860, the speaker 861, and the microphone 862 can provide an audio interface between the user and the mobile phone. The audio circuit 860 can transmit the received audio data to the speaker 861 after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone 862 converts the collected sound signal into an electrical signal, which is received by the audio circuit 860 and converted into audio data, and then the audio data is output to the processor 880 for processing, and then sent to another mobile phone through the RF circuit 810, or the audio data is output to the memory 820 for further processing.

[0285] Wi-Fi is a short-range wireless transmission technology. The mobile phone can help users send and receive emails, browse web pages and access streaming media through the Wi-Fi module 870. It provides users with wireless broadband Internet access. Figure 8A Wi-Fi module 870 is shown, but it is understandable that it is not an essential component of the mobile phone and can be omitted as needed without changing the essence of the invention.

[0286] The processor 880 is the control center of the mobile phone. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 820, and calling data stored in the memory 820, it executes various functions of the mobile phone and processes data, thereby monitoring the mobile phone as a whole. Optionally, the processor 880 may include one or more processing units; preferably, the processor 880 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 880.

[0287] The mobile phone also includes a power supply 890 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 880 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions.

[0288] Although not shown, the mobile phone may also include a camera, a Bluetooth module, etc., which will not be described in detail here.

[0289] In the embodiment of the present application, the processor 880 is configured to obtain target update data of a target terminal device within the coverage range of the target space, the target terminal device including the terminal device and / or other terminal devices, the target update data including at least one of usage scenario update data and network switching behavior data; determine the target network according to the target update data and the target network recommendation model;

[0290] The target network recommendation model is constructed based on historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, wherein the historical update data includes historical usage scenario update data and historical network switching behavior data.

[0291] Optionally, in some possible implementations, obtaining usage scenario update data of a target terminal device within the coverage area of ​​the target space includes at least one of the following:

[0292] Acquire update data of a target terminal device within the coverage of the target space from first application usage data to second application usage data, wherein the first application usage data and the second application usage data include at least one of a type of application running in the foreground, a number of different types of application running in the foreground, a usage time of an application running in the foreground, and a number of applications running in the background;

[0293] Acquire update data of a target terminal device within the coverage range of the target space from first environment data to second environment data, where the first environment data and the second environment data include at least one of a time period identifier, a date type, a space identifier, and a user identifier;

[0294] Obtain the network switching behavior data of the target terminal device within the coverage area of ​​the target space, including:

[0295] Acquire update data of a target terminal device within the coverage area of ​​the target space from the first network to the second network.

[0296] Optionally, in some possible implementations, the processor 880 is further used to obtain current usage data of the terminal device and / or other terminal devices, the current usage data including at least one of current usage scenario data and current network usage information; determine current network demand information according to the target update data, the current usage data and a first target network recommendation model, the first target network recommendation model is constructed according to the historical update data, historical usage data and historical network demand information, the historical usage data including historical usage scenario data and historical network usage information; obtain a target network according to the current network demand information and a second target network recommendation model, the second target network recommendation model is constructed according to the historical network demand information and the corresponding historical network; wherein the target network recommendation model includes the first target network recommendation model and the second target network recommendation model.

[0297] Optionally, in some possible implementations, the processor 880 is further configured to obtain an available network according to the current network demand information and the second target network recommendation model; and determine an optimal network among the available networks as the target network.

[0298] Optionally, in some possible implementations, the processor 880 is specifically used to adjust the network according to the network demand information of different terminal devices within the coverage of the target space to obtain the target network when no available network is matched according to the current network demand information and the second target network recommendation model, and the network demand information of the different terminal devices includes the current network demand information.

[0299] Optionally, in some possible implementations, the processor 880 is specifically configured to, when the ping-pong switching suppression timer corresponding to the terminal device has not timed out, wait for the ping-pong switching suppression timer to time out, and determine the target network according to the target update data and the target network recommendation model; or,

[0300] The processor 880 is specifically configured to determine a target network according to the target update data and the target network recommendation model when the ping-pong switching inhibition timer corresponding to the terminal device times out.

[0301] Optionally, in some possible implementations, the processor 880 is further configured to synchronize the target update data to other online terminal devices within the coverage range of the target space when the target update data is the target update data of the terminal device.

[0302] Optionally, in some possible implementations, the processor 880 is specifically configured to synchronize the target update data to a target space database, and synchronize the target update data to other online terminal devices within the coverage of the target space through the target space database; or,

[0303] The processor 880 is specifically used to synchronize the target update data to other online terminal devices within the coverage range of the target space through broadcast or point-to-point mode.

[0304] Optionally, in some possible implementations, the processor 880 is specifically configured to receive the target update data synchronized by other terminal devices when the target update data is target update data of other terminal devices within the coverage range of the target space.

[0305] Optionally, in some possible implementations, the processor 880 is further configured to obtain the historical update data and the corresponding historical network; and construct the target network recommendation model according to the historical update data and the corresponding historical network.

[0306] The embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a terminal device, the terminal device executes the above method embodiment.

[0307] The above-mentioned computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (Random Access Memory, RAM), a read-only memory (read only memory, ROM), an erasable programmable read-only memory (erasableprogrammable read only memory, EPROM) or flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0308] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0309] The program code embodied on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

[0310] Computer program code for performing the operations of this specification may be written in one or more programming languages ​​or a combination thereof, including resource-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0311] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute part or all of the steps in the above method embodiment.

[0312] The embodiment of the present application provides a chip system, which includes a processor and may also include a memory, for implementing the functions of the terminal device in the above method. The chip system may be composed of a chip, or may include a chip and other discrete devices.

[0313] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0314] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0315] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0316] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0317] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0318] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A network recommendation method, characterized in that: The method is applied to a terminal device, and the method comprises: Acquire target update data of target terminal devices within the coverage range of the target space, the target terminal devices including the terminal device and / or other terminal devices, the target update data including at least one of usage scenario update data and network switching behavior data; Determine a target network according to the target update data and the target network recommendation model; The target network recommendation model is constructed based on historical update data of different terminal devices within the coverage area of ​​the target space and the corresponding historical networks, wherein the historical update data includes historical usage scenario update data and historical network switching behavior data.

2. The method according to claim 1, characterized in that: Obtaining usage scenario update data of target terminal devices within the coverage area of ​​the target space includes at least one of the following: Acquire update data of a target terminal device within the coverage of the target space from first application usage data to second application usage data, wherein the first application usage data and the second application usage data include at least one of a type of application running in the foreground, a number of different types of application running in the foreground, a usage time of an application running in the foreground, and a number of applications running in the background; Acquire update data of a target terminal device within the coverage range of the target space from first environment data to second environment data, where the first environment data and the second environment data include at least one of a time period identifier, a date type, a space identifier, and a user identifier; Obtain the network switching behavior data of the target terminal device within the coverage area of ​​the target space, including: Acquire update data of a target terminal device within the coverage area of ​​the target space from the first network to the second network.

3. The method according to claim 1, characterized in that The method further comprises: Acquire current usage data of the terminal device and / or other terminal devices, wherein the current usage data includes at least one of current usage scenario data and current usage network information; The determining the target network according to the target update data and the target network recommendation model includes: Determining current network demand information according to the target update data, the current usage data and a first target network recommendation model, wherein the first target network recommendation model is constructed according to the historical update data, the historical usage data and the historical network demand information, wherein the historical usage data includes historical usage scenario data and historical usage network information; Obtaining a target network according to the current network demand information and a second target network recommendation model, wherein the second target network recommendation model is constructed according to the historical network demand information and the corresponding historical network; The target network recommendation model includes the first target network recommendation model and the second target network recommendation model.

4. The method according to claim 3, characterized in that The obtaining of the target network according to the current network demand information and the second target network recommendation model comprises: Obtaining an available network according to the current network demand information and the second target network recommendation model; An optimal network among the available networks is determined as a target network.

5. The method according to claim 4, characterized in that The method further comprises: When no available network is matched according to the current network demand information and the second target network recommendation model, network adjustment is performed according to the network demand information of different terminal devices within the coverage range of the target space to obtain the target network, and the network demand information of the different terminal devices includes the current network demand information.

6. The method according to any one of claims 1 to 4, characterized in that The determining the target network according to the target update data and the target network recommendation model includes: When the ping-pong switching suppression timer corresponding to the terminal device has not timed out, wait for the ping-pong switching suppression timer to time out, and then determine the target network according to the target update data and the target network recommendation model; or When the ping-pong switching suppression timer corresponding to the terminal device times out, the target network is determined according to the target update data and the target network recommendation model.

7. The method according to any one of claims 1 to 4, characterized in that The method further comprises: In a case where the target update data is the target update data of the terminal device, the target update data is synchronized to other online terminal devices within the coverage of the target space.

8. The method according to claim 6, characterized in that The step of synchronizing the target update data to other online terminal devices within the coverage of the target space includes: Synchronize the target update data to the target space database, and synchronize to other online terminal devices within the coverage of the target space through the target space database; or, The target update data is synchronized to other online terminal devices within the coverage of the target space through broadcast or point-to-point mode.

9. The method according to any one of claims 1 to 4, characterized in that: The obtaining of target update data includes: In a case where the target update data is target update data of other terminal devices within the coverage range of the target space, the target update data synchronized by the other terminal devices is received.

10. The method according to any one of claims 1 to 4, characterized in that Before obtaining the target update data, the method further includes: Obtaining the historical update data and the corresponding historical network; The target network recommendation model is constructed according to the historical update data and the corresponding historical network.

11. A network recommendation device, characterized in that: The device is applied to a terminal device, and the device includes: An acquisition module, configured to acquire target update data of a target terminal device within a coverage range of a target space, wherein the target terminal device includes the terminal device and / or other terminal devices, and the target update data includes at least one of usage scenario update data and network switching behavior data; A processing module is used to determine a target network based on the target update data and a target network recommendation model; wherein the target network recommendation model is constructed based on historical update data and corresponding historical networks of different terminal devices within the coverage range of the target space, and the historical update data includes historical usage scenario update data and historical network switching behavior data.

12. A terminal device, characterized in that: include: A memory, a processor, and a transceiver, wherein the memory stores a computer program that can be run on the processor, and when the terminal device executes the program, the method according to any one of claims 1 to 10 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images