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, and the method comprises the steps: obtaining the state information of target equipment, the state information is used for indicating the network use preference of the target equipment, and the state information comprises at least one of network information, application information and environment perception information; and switching the target equipment to a target network, wherein the target network is matched with the state information of the target equipment. The accuracy of the network recommended to the equipment can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to network switching technology, including but not limited to a network recommendation method, device, equipment, and storage medium. Background Art

[0002] During the process of using a terminal device, a user usually needs to switch to different networks in different usage environments. Therefore, network switching needs to be performed according to the usage situation.

[0003] In the related art, during the process of implementing network switching, switching is performed based on historical switching records. However, performing network switching only based on the historical switching records of a terminal device has a certain lag, resulting in the determined switching network may not be accurate, and thus may lead to recommending a network with relatively low accuracy to the user. Summary of the Invention

[0004] In view of this, the network recommendation method, device, equipment, and storage medium provided by the embodiments of the present application can improve the accuracy of the network recommended to the device. The network recommendation method, device, equipment, and storage medium provided by the embodiments of the present application are implemented as follows:

[0005] On the one hand, an embodiment of the present application provides a network recommendation method, including:

[0006] Obtain the status information of a target device, where the status information is used to indicate the network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environmental perception information;

[0007] Switch the target device to a target network, where the target network matches the status information of the target device.

[0008] On the other hand, an embodiment of the present application further provides a network recommendation device, including: an information acquisition module and a network switching module;

[0009] The information acquisition module is used to obtain the status information of a target device, where the status information is used to indicate the network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environmental perception information;

[0010] The network switching module is used to switch the target device to a target network, where the target network matches the status information of the target device.

[0011] The computer equipment provided by the embodiments of the present application includes a memory and a processor, the memory stores a computer program that can run on the processor, and when the processor executes the program, the method of the embodiments of the present application is implemented.

[0012] The computer-readable storage medium provided by the embodiments of the present application stores a computer program, and when the computer program is executed by a processor, the method provided by the embodiments of the present application is implemented.

[0013] The network recommendation method, device, equipment, and storage medium provided by the embodiments of the present application can obtain the status information of the target device. The status information is used to indicate the network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environmental perception information; switch the target device to the target network, and the target network matches the status information of the target device. Among them, by obtaining the status information of the target device, a more suitable, accurate, and target device-matching target network can be obtained, and thus the network recommendation of the target device can be more accurately realized, improving the accuracy and rationality of the network recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0015] Figure 1 It is a schematic diagram of the application scenario provided in the embodiments of the present application;

[0016] Figure 2 It is a schematic flowchart of the network recommendation method provided in the embodiments of the present application;

[0017] Figure 3 It is a schematic flowchart of determining the target network based on personalized knowledge graph data provided in the embodiments of the present application;

[0018] Figure 4 It is a schematic flowchart of determining the target network from the recommended networks provided in the embodiments of the present application;

[0019] Figure 5 It is a schematic flowchart of determining the target network based on the network recommendation model provided in the embodiments of the present application;

[0020] Figure 6 It is a schematic flowchart of one of the network recommendations provided in the embodiments of the present application;

[0021] Figure 7 It is another schematic flowchart of the network recommendation provided in the embodiments of the present application;

[0022] Figure 8 It is another schematic flowchart of the network recommendation method provided in the embodiments of the present application;

[0023] Figure 9 It is a schematic flow chart for adjusting a recommendation strategy according to feedback information provided in an embodiment of the present application;

[0024] Figure 10 It is a schematic flow chart for constructing a personalized knowledge graph provided in an embodiment of the present application;

[0025] Figure 11 It is a schematic flow chart for collecting status information provided in an embodiment of the present application;

[0026] Figure 12 It is a schematic overall flow chart of the network recommendation method provided in an embodiment of the present application;

[0027] Figure 13 It is a schematic structural diagram of the network recommendation device provided in an embodiment of the present application;

[0028] Figure 14 It is a schematic structural diagram of the computer device provided in an embodiment of the present application. Detailed implementation manners

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will further describe the specific technical solutions of the present application in detail with reference to the accompanying drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0031] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0032] It should be noted that the terms "first / second / third" involved in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when permitted, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0033] To more clearly and accurately explain the network recommendation method provided in the embodiments of the present application, the following will illustrate the application scenarios of the network recommendation method provided in the embodiments of the present application.

[0034] Figure 1This is a schematic diagram of the application scenario provided in the embodiments of the present application. Please refer to Figure 1 , Figure 1 The scenario shown in Figure 1 is the application scenario of the network recommendation method provided in the embodiments of the present application. Among them, the target device can automatically perform network switching. For example, it can switch from Network 1 to Network 2. Here, Network 1 and Network 2 can be two different networks. For example, they can be two different wireless networks, two different mobile networks, or one wireless network and one mobile network. There is no specific limitation here and can be selected according to actual needs.

[0035] It should be noted that the target device may include, but is not limited to, mobile phones, wearable devices (such as smart watches, smart bracelets, smart glasses, etc.), tablet computers, laptop computers, vehicle-mounted terminals, PCs (Personal Computers), etc. The functions implemented by this method can be realized by the processor in the target device calling program code. Of course, the program code can be stored in a computer storage medium. It can be seen that the target device at least includes a processor and a storage medium.

[0036] It should be noted that the execution subject of the network recommendation method in the embodiments of the present application can be the above-mentioned target device, or it can also be other devices communicatively connected to the target device. For example, when the target device is a mobile terminal such as a mobile phone or a tablet computer, the execution subject can be a router, a CPE (Customer Premises Equipment, network conversion device), or a network access device (such as a base station) communicatively connected to the target device. If the execution subject is the above-mentioned target device, the relevant data required can be obtained by the target device itself. If the execution subject is other devices communicatively connected to the target device, the relevant data required can be obtained by other devices from the target device. There is no specific limitation here and can be selected according to actual needs.

[0037] In Figure 1 the application scenario shown in Figure 1 , when the user is using the target device, it is usually necessary to switch to different networks in different usage environments. Therefore, network switching needs to be performed according to the usage situation.

[0038] In the related art, during the process of implementing network switching, it is switched according to the historical switching records. However, simply performing network switching based on the historical switching records of the target device has a certain lag, resulting in the determined switching network may not be accurate, thus possibly leading to a relatively low-accuracy network recommended to the user.

[0039] Moreover, in the related art, it needs to be driven according to the data volume. When building a model or statistical data, a certain amount of data accumulation is required, and the data update process is complex.

[0040] To solve the above problems existing in the related art, an embodiment of the present application provides a network recommendation method, and the following will explain the specific implementation process of the network recommendation method.

[0041] Figure 2 For the flowchart of the network recommendation method provided in the embodiment of the present application, please refer to Figure 2 , the method includes:

[0042] S210: Obtain the status information of the target device.

[0043] It should be noted that the execution subject of this method can be the above-mentioned target device, or it can also be other electronic devices communicatively connected to the target device, and no specific limitation is made here.

[0044] Among them, the status information is used to indicate the network usage preference of the target device.

[0045] It should be noted that the status information can refer to the usage status of the target device, and these status information can represent the network usage preference of the target device. Among them, the network usage preference refers to the bias of the network used by the target device under different status information. For example: in the first status information, the target device prefers to use a wireless network; in the second status information, the target device prefers to use a mobile network.

[0046] Optionally, the status information includes at least one of the following: network information, application information, and environment perception information.

[0047] Among them, the network information refers to the current network of the target device. For example: it can be a wireless network, a mobile network, or no network, etc. And, the specific information of the network can also be recorded in the network information. For example: the frequency band, bandwidth, and BSSID (Basic Service Set Identifier) of the wireless network, or it can also be the bandwidth, network mode, CID (Cell Identity), PCI (Physical Cell Identifier), and ARFCN (Absolute Radio Frequency Channel Number) of the corresponding cell of the mobile network.

[0048] The application information refers to the applications currently running on the target device. For example: it can be the application being displayed in the foreground, or it can also be the application running in the background, and no specific limitation is made here. Among them, during the process of recording the application information, the APP information before and after network switching can be recorded at the same time. If there are multiple foreground APPs, optionally: record 2 APPs, record the APP opened later, or record the APP with a higher network priority.

[0049] The environmental perception information may include location-related information and time-related information. Among them, the location-related information may refer to the environment where the target device is currently located. For example, it may be the positioning result obtained through the positioning module or the location perception information obtained through the location perception module. There is no specific limitation here. That is to say, the location of the target device can be represented by the positioning result or the location perception information; the time-related information may include information such as the current time and date.

[0050] It should be noted that the above status information can be obtained once every certain period of time, or it can also be obtained after meeting the corresponding status acquisition conditions. There is no specific limitation here, and one of the methods can be selected according to actual needs to obtain the status information.

[0051] S220: Switch the target device to the target network.

[0052] It should be noted that after obtaining the status information, the target network corresponding to the status information can be determined. Among them, the target network can be a network that matches the status information of the target device.

[0053] Optionally, a calculation model or a mapping relationship table can be preset in the target device. After obtaining the corresponding status information, the target network corresponding to the status information can be determined according to the above calculation model or mapping relationship table.

[0054] In one embodiment, after determining the target network, the target device can be controlled to switch to the target network.

[0055] Among them, if the execution entity is the target device itself, the network can be directly switched through the network switch, so as to realize the switching from the current network to the target network; if the execution entity is other electronic devices communicatively connected to the target device, the target device can be controlled to perform network switching by sending a network switching instruction to the target device. There is no specific limitation here.

[0056] In the network recommendation method provided by the embodiments of the present application, the status information of the target device can be obtained. The status information is used to indicate the network usage preference of the target device. The status information includes at least one of the following: network information, application information, and environmental perception information; the target device is switched to the target network, and the target network matches the status information of the target device. Among them, by obtaining the status information of the target device, a more suitable, accurate, and target device-matching target network can be obtained, and thus the network recommendation of the target device can be realized more accurately, improving the accuracy and rationality of the network recommendation.

[0057] It should be noted that after obtaining the status information, the corresponding target network can be determined according to the status information. The following explains one feasible implementation manner for determining the target network in the embodiments of the present application.

[0058] Figure 3 For the schematic flow chart of determining the target network based on the personalized knowledge graph data provided in the embodiments of the present application, please refer to Figure 3 , before switching the target device to the recommended network, the method further includes:

[0059] S310: Determine at least one recommended network corresponding to the status information according to the status information of the target device and the personalized knowledge graph data.

[0060] It should be noted that the personalized knowledge graph data can be relationship data pre-stored in the target device or other devices communicatively connected to the target device. The content in the personalized knowledge graph data can be composed of data such as pre-collected status information.

[0061] In the actual implementation process, the personalized knowledge graph may include: the mapping relationship between the preset status information and the preset recommended network.

[0062] Among them, each preset status information is the status information obtained when the target device executes a preset operation.

[0063] It should be noted that the preset operation may refer to an operation of switching networks, such as: an operation of turning on / off Wi-Fi, an operation of turning on / off the cellular network, an operation of changing the Wi-Fi access AP, an operation of inputting the Wi-Fi password, an operation of turning on / off 5G, an operation of manually switching the SIM card, an operation of turning on / off the flight mode of the target device, an operation of turning on / off the power-saving mode, etc., which is not specifically limited herein.

[0064] Among them, the operation of turning Wi-Fi on or off refers to the user manually turning on / off the Wi-Fi button in the settings; the operation of turning cellular data on or off refers to the user manually turning on / off the data traffic in the settings; the operation of changing the Wi-Fi access point (AP) refers to the user manually modifying the Wi-Fi access point in the settings, such as switching from one Wi-Fi to another; the operation of entering the Wi-Fi password refers to the user manually entering the password of a new AP and successfully connecting; the operation of turning 5G on or off refers to the user turning on / off the 5G option in the settings. When it is turned off, the terminal device cannot access the 5G cellular network; the operation of manually switching the SIM card refers to the user having more than one SIM card and manually selecting the SIM card for data traffic usage; the operation of turning the flight mode of the target device on or off refers to the user manually turning on / off the flight mode. In the case of turning off the flight mode, if the user does not turn on the Wi-Fi switch, both Wi-Fi and the cellular network are unavailable. If the user chooses to turn on the Wi-Fi switch or the device's default flight mode does not affect the Wi-Fi connection, the Wi-Fi network is available. The operation of turning the power-saving mode on or off refers to that on some mobile phones, when the power-saving mode is turned on, the 5G cellular network is turned off and only the 4G cellular network can be accessed.

[0065] It should be noted that the status information can be collected when the above preset operations are executed. For example, network information, application information, environmental perception information, etc. can be collected.

[0066] Among them, after multiple status information is collected, these status information can be integrated and processed, sorted into the above personalized knowledge graph data according to the preset rules, and the personalized knowledge graph data can be stored.

[0067] It should be noted that each set of collected status information can be used as a set of data. When the number of data meets a certain quantity threshold, or when the collection time meets a certain time threshold, the construction of personalized knowledge graph data can be carried out.

[0068] In the process of constructing the above personalized knowledge graph data, for the above application information, considering that when the user manually triggers a network change, the foreground display will switch to the settings page or the drop-down menu page, and there may be a situation of misidentifying the application program. Therefore, if the application information to be obtained is the foreground application and the foreground is the system page, the APP that appeared last within the first M1 seconds, or / and the APP that appeared M2 seconds after the network change is used as the APP at the time of switching. Among them, M1 and M2 can be set according to actual needs, and the example can both be taken as 10s.

[0069] In one embodiment, if there is no application in the foreground of the target device, it is optional to record that the foreground APP discards this type of data, or use a special identifier for marking, and no specific restrictions are imposed here.

[0070] In the process of constructing the above personalized knowledge graph data, for the positioning result / position perception information in the above environmental perception, considering that switching the network may cause a change in positioning, while the actual positioning result / position perception information may not have changed. Therefore, the matching of the positioning result / position perception information and the network before and after switching is optimized, and one or more of the following methods can be selected to obtain the positioning result / position perception information:

[0071] Method 1: The data within N1 seconds after the network switch is also constructed into the positioning space before the switch. The value of N1 can be dynamically allocated through the system configuration file or fixed in the code, and no specific restrictions are imposed here. For example, the example of N1 can be 10s.

[0072] Method 2: The data within N2 seconds before the network switch is recorded into the positioning space after the switch. The value of N2 can be dynamically allocated through the system configuration file or fixed in the code, and no specific restrictions are imposed here. For example, the example of N2 can be 3s.

[0073] In the process of constructing the above personalized knowledge graph data, for the time / date in the environmental perception information, the date types can be optionally divided into the following several types, and it is possible to flexibly select to remove one item or combine multiple items: Monday to Friday, Saturday and Sunday, legal working days, legal compensatory leave days, legal holidays, winter vacation, summer vacation, etc.

[0074] In addition, the time division can be selected as follows: (1) Divide by natural hours; (2) Divide by time periods such as morning, noon, afternoon, evening, night, early morning, etc.; (3) Distinguish different time periods according to the user's real activity behavior, such as it can be distinguished as before going to work, after work, etc.; (4) Combine the positioning result / position perception result, and divide the time periods with large differences in the positioning result / position perception result for similar positions.

[0075] It should be noted that after recording the above three types of information in the status information, a set of relationship chains can be formed, for example: foreground application + positioning result / position perception information + time + date. In addition, the network information before and after the network switch can also be recorded, for example: switching from a wireless network to a mobile network or from a mobile network to a wireless network, etc.

[0076] S320: Determine the target network from at least one recommended network.

[0077] It should be noted that, based on the personalized knowledge graph data constructed above and the obtained status information, a recommended network corresponding to the status information can be determined. Furthermore, multiple recommended networks can be determined, and one network can be selected from the multiple recommended networks as the target network.

[0078] In the network recommendation method provided by the embodiments of the present application, at least one recommended network corresponding to the status information can be determined according to the status information of the target device and the personalized knowledge graph data; and a target network can be determined from the at least one recommended network. Among them, through the mapping relationship in the personalized knowledge graph data, a target network that matches the current usage situation of the target device can be determined more quickly, accurately, and reasonably, and thus the switching of the target network can be realized more accurately and quickly.

[0079] In one embodiment, the personalized knowledge graph data further includes the scores of the preset recommended networks corresponding to each group of preset status information.

[0080] It should be noted that each group of preset status information can be one of the above-mentioned relationship chains, and each relationship chain corresponds to a recommended network, and the confidence score of this recommended network is the above-mentioned score.

[0081] In one embodiment, the scores of the preset recommended networks in the personalized knowledge graph data are determined according to the scores of all network switching behaviors performed by the target device, the scores of network switching behaviors performed by the target device within a preset time interval, and the scores of the frequencies of network switching performed by the target device within a preset time interval.

[0082] The specific formula is as follows:

[0083]

[0084] Among them, S1 refers to the score of all network switching behaviors performed by the target device, S2 refers to the score of network switching behaviors performed by the target device within a preset time interval, and S3 refers to the score of the frequencies of network switching performed by the target device within a preset time interval.

[0085] Among them, a1, b1, c1, d1, a2, b2, c2, d2, a3, b3, c3, d3, etc. are all preset coefficients and can be set according to actual needs.

[0086] SI0 refers to the total number of times the system automatically switches in, SI refers to the number of times the system automatically switches in this time, UI0 refers to the total number of times the user manually switches in, UI refers to the number of times the user manually switches in this time, SO0 refers to the total number of times the system automatically switches out, SO refers to the number of times the system automatically switches out this time, UO0 refers to the total number of times the user manually switches out, and UO refers to the number of times the user manually switches out this time.

[0087] SIC0 refers to the total number of automatic system cut-ins within D days, SIC refers to the number of times of the current automatic system cut-in within D days, UIC0 refers to the total number of manual user cut-ins within D days, UIC refers to the number of times of the current manual user cut-in within D days, SOC0 refers to the total number of automatic system cut-outs within D days, SOC refers to the number of times of the current automatic system cut-out within D days, UOC0 refers to the total number of manual user cut-outs within D days, and UOC refers to the number of times of the current manual user cut-out within D days.

[0088] SIN refers to the number of days of automatic system cut-ins within D days, UIN refers to the number of days of manual user cut-ins within D days, SON refers to the number of days of automatic system cut-outs within D days, UON refers to the number of days of manual user cut-outs within D days, and D is the set number of days.

[0089] S1 - S3 can be calculated through the above formulas. After obtaining S1 - S3, the confidence score can be determined:

[0090] Score = min(110, max(0, R1×S1 + R2×S2 + R3×S3));

[0091] Among them, R1, R2, and R3 are preset coefficients, and R1 + R2 + R3 = 1. The specific values are not limited. For example: R1 = 0.8, R2 = 0.1, R3 = 0.1. The obtained Score is the above-mentioned confidence score, that is, the score for a recommendation result.

[0092] In the network recommendation method provided by the embodiments of the present application, the score of the preset recommended network corresponding to each group of preset status information can be determined according to the score of all network switching behaviors performed by the target device, the score of the network switching behaviors performed by the target device within a preset time interval, and the score of the frequency of network switching performed by the target device within a preset time interval, improving the accuracy and rationality of each score.

[0093] In one embodiment, determining at least one recommended network corresponding to the status information according to the status information of the target device and the personalized knowledge graph data includes: determining the wireless network with the highest score and the mobile network with the highest score from the preset recommended networks.

[0094] It should be noted that in the actual implementation process, the wireless network with the highest score and the mobile network with the highest score can be determined according to the status information.

[0095] In one embodiment, the above-mentioned set of preset status information and the scores of the corresponding preset recommendation networks can be stored in an offline recommendation table, and then the wireless network with the highest score and the mobile network with the highest score can be obtained by querying the offline recommendation table.

[0096] It should be noted that the above content can be stored in an offline prediction table, or it can also be obtained by real-time calculation during the recommendation process, and no specific limitation is made here.

[0097] Correspondingly, determining the target network from at least one recommendation network includes: determining the target network according to the scores of the wireless network and the mobile network.

[0098] It should be noted that after determining the wireless network and the mobile network with the highest scores, the target network can be determined from the wireless network and the mobile network.

[0099] In the network recommendation method provided by the embodiments of the present application, the wireless network with the highest score and the mobile network with the highest score can be determined from the preset recommendation networks; the target network is determined according to the scores of the wireless network and the mobile network. Among them, a more suitable target network can be determined according to the specific scores of the wireless network and the mobile network, thereby improving the accuracy of determining the target network.

[0100] Next, the specific implementation process of determining the target network will be explained.

[0101] Figure 4 For the schematic flowchart of determining the target network from the recommendation network provided in the embodiments of the present application, please refer to Figure 4 , first, the current network of the target device can be determined. For example, it can be a wireless network or a mobile network.

[0102] In different situations, different methods can be used to determine the target network.

[0103] In one embodiment, when the current network of the target device is a wireless network, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to the first threshold, the wireless network is determined as the target network.

[0104] It should be noted that the first threshold can be a threshold set according to actual needs. For example: 20, and no specific limitation is made here.

[0105] Among them, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to the first threshold, it can be determined that the wireless network is more suitable, the wireless network can be used as the target network, and the target network is recommended to the target device.

[0106] In one embodiment, when the current network of the target device is a wireless network, if the score of the wireless network is less than a second threshold, and the difference between the score of the mobile network and the score of the wireless network is greater than or equal to a first threshold, the mobile network is determined as the target network.

[0107] It should be noted that the second threshold can be a threshold set according to actual needs. For example: 60, and no specific limitation is made here.

[0108] Among them, if the score of the wireless network is less than the second threshold, and the difference between the score of the mobile network and the score of the wireless network is greater than or equal to the first threshold, it can be determined that the mobile network is more suitable. The mobile network can be used as the target network, and the current network can be switched from the wireless network to the mobile network.

[0109] In one embodiment, when the current network of the target device is a mobile network, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to a third threshold, and the score of the wireless network is greater than or equal to a fourth threshold, the wireless network is determined as the target network; if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to a fifth threshold, the wireless network is determined as the target network, where the fifth threshold is greater than the third threshold.

[0110] It should be noted that the third threshold, the fourth threshold, and the fifth threshold can all be thresholds set according to actual needs. For example: the third threshold is 0, the fourth threshold is 60, and the fifth threshold is 20, and no specific limitation is made here.

[0111] In the above two cases, the current network of the target device is already a mobile network, but the wireless network is significantly better than the mobile network. In these two cases, the wireless network can be used as the target network, and the above target network is recommended to the target device.

[0112] It should be noted that except for the above situations, the corresponding recommendation work may not be carried out. It should be noted that during the process of recommending the target network, it can be generated and recommended once every once in a while.

[0113] In the network recommendation method provided by the embodiments of the present application, a more suitable recommended network can be determined according to the current network of the target device and the score difference between the mobile network and the wireless network, and then a more accurate target network can be determined, thereby improving the accuracy of the target network recommended to the target device.

[0114] In one embodiment, before determining the wireless network with the highest score and the mobile network with the highest score from the preset recommended networks, the method further includes: when multiple groups of preset status information correspond to the same preset recommended network, using the score with the smallest score among them as the score of the preset recommended network.

[0115] It should be noted that, in order to ensure the rationality of the recommendation network, if there are multiple groups of preset status information corresponding to the same preset recommendation network, then the smallest score among the scores corresponding to the recommendation network is selected as the score of the recommendation network.

[0116] For example: According to the currently obtained status information, it can be determined that the matched preset status information is preset status information A and preset status information B. Among them, the recommendation network corresponding to preset status information A is the mobile network, and the score is 80. The recommendation network corresponding to preset status information B is the mobile network, and the score is 90. Then, the score of the recommendation network corresponding to the preset status information A with the lower score can be selected as the score of the mobile network, that is, the above 80 points.

[0117] In the network recommendation method provided by the embodiments of the present application, when multiple groups of preset status information correspond to the same preset recommendation network, the smallest score among them is used as the score of the preset recommendation network. Among them, by using the smallest score as the score of the preset recommendation network, the accuracy of network recommendation can be ensured, avoiding misjudgment of recommendations caused by a relatively high network recommendation score, and improving the accuracy of target network recommendation.

[0118] It should be noted that, in the process of obtaining the status information of the target device, the corresponding method can be adopted to obtain it. The following explains the specific implementation process of obtaining the status information of the target device provided in the embodiments of the present application.

[0119] In one embodiment, obtaining the status information of the target device includes: obtaining the location of the target device through the positioning module of the target device; when the location of the target device changes, obtaining the status information of the target device. The situations where the location changes include: the target device enters or leaves the fence area.

[0120] It should be noted that the positioning module of the target device can be a navigation positioning module, such as GPS, or it can also be a fence positioning module. For example: Multiple fences can be pre-divided, and the location of the target device can be determined according to the action of the user's target device entering or leaving the fence.

[0121] Exemplarily, the space where the target device is located can be divided into multiple areas, each area is separated by a fence, the initial location of the target device can be determined, and after the target device passes through the fence and arrives at area B from area A, it can be determined that the location where the target device is located has become area B.

[0122] Among them, the status information can be obtained when the location of the target device has changed. For example: When the target device arrives at another area where a fence is located from the current area, the status information can be obtained.

[0123] Optionally, in addition to obtaining status information in the above cases, it is also possible to determine whether the target device meets the status acquisition condition, such as determining whether the target device is in a state of being lit and unlocked, etc. In this case, status information can be obtained.

[0124] It should be noted that, in addition to obtaining status information in the above manner, status information can also be obtained once every preset time, and no specific limitation is made here.

[0125] In the network recommendation method provided by the embodiments of the present application, the location of the target device can be obtained through the positioning module of the target device; when the location of the target device changes, the status information of the target device is obtained. Among them, when the location of the target device changes, it is possible to more quickly and timely determine that the target device may need network recommendation, and then the corresponding status information can be obtained and the target network can be determined based on the status information, improving the timeliness of the target network recommendation.

[0126] In one embodiment, the method further includes: when the positioning module of the target device is updated, updating the personalized knowledge graph data.

[0127] It should be noted that the positioning module can be a location determination module or a location perception module. Such modules may be updated. If an update occurs, the location information recorded in the personalized knowledge graph may be different. To avoid location differences caused by version updates, monitor the update of the positioning module. If the positioning module is updated, the updated version number can be obtained, and the environmental perception information in the preset status information in the personalized knowledge graph data can be updated. For example: use the updated positioning module to update the location, so as to realize the update of the personalized knowledge graph data.

[0128] Among them, the personalized knowledge graph data can be directly updated, or alternatively, the source data constituting the personalized knowledge graph can be updated, and the personalized knowledge graph data can be reconstructed based on the updated source data.

[0129] In the network recommendation method provided by the embodiments of the present application, the personalized knowledge graph data can be updated when the positioning module of the target device is updated. By updating the personalized knowledge graph data, the error of the location information caused by the update of the positioning module can be avoided, so as to ensure the accuracy of the determination of the target network.

[0130] In one embodiment, the method further includes: if the positioning module of the target device has not been updated for more than the preset time, clearing the personalized knowledge graph data.

[0131] It should be noted that the positioning module is usually updated at regular intervals. If the update exceeds the preset duration, it may lead to positioning errors. To avoid such events, the update of the positioning module can be monitored. If the positioning module of the target device has not been updated for more than the preset time, the personalized knowledge graph data can be cleared.

[0132] Among them, the personalized knowledge graph data can be reconstructed. For example, the source data constituting the personalized knowledge graph can be adjusted. For example, the source data N days ago can be deleted. N can be 90, for example. Furthermore, the personalized knowledge graph data can be reconstructed again. For example, only the data within the most recent X days is used during construction. X can be 70, for example.

[0133] In the network recommendation method provided by the embodiments of the present application, if the positioning module of the target device has not been updated for more than the preset time, clearing the personalized knowledge graph data can ensure that the content in the personalized knowledge graph data is relatively new data, and the new data is more in line with the user's preferences for using the target device, thereby improving the accuracy of the target network recommendation to a certain extent.

[0134] Next, another feasible implementation manner for determining the target network in the embodiments of the present application will be explained.

[0135] Figure 5 For the flow diagram of determining the target network provided in the embodiments of the present application, please refer to Figure 5 , before switching the target device to the recommended network, the method further includes:

[0136] S510: Input the status information of the target device into a pre-trained network recommendation model to obtain at least one recommended network.

[0137] Among them, the network recommendation model is a model obtained by training based on sample status information and sample recommended networks.

[0138] It should be noted that in addition to using the personalized knowledge graph to implement the determination of the recommended network, it can also be implemented based on the network recommendation model.

[0139] Among them, the network recommendation model can be, for example, an Echo State Network (ESN), a Long Short Term Memory (LSTM), etc., which learn user behaviors and are trained to perform subsequent network prediction and recommendation.

[0140] Among them, the sample status information may be the aforementioned preset status information collected, and the sample recommendation network may be the preset recommendation network corresponding to the preset status information. These data can be used to train the initial model to obtain the above-mentioned network recommendation model.

[0141] After obtaining the network recommendation model, the status information of the target device can be input into the model, and then at least one recommendation network can be obtained through the output of the model.

[0142] S520: Determine the target network from at least one recommendation network.

[0143] It should be noted that after obtaining the recommendation network, the target network can be determined from multiple recommendation networks in a manner similar to the aforementioned S320.

[0144] In the network recommendation method provided in the embodiments of the present application, the status information of the target device is input into a pre-trained network recommendation model to obtain at least one recommendation network; the target network is determined from at least one recommendation network. Among them, the determination of the recommendation network can also be realized through the network recommendation model, which improves the accuracy and rapidity of obtaining the target network.

[0145] Next, one implementation process of the network recommendation provided in the embodiments of the present application will be explained.

[0146] Figure 6 For one of the flow diagrams of the network recommendation provided in the embodiments of the present application, please refer to Figure 6 During the process of network recommendation, it is possible to first monitor whether the target device meets the status acquisition condition. For example, it is determined whether the target device is in the state of being lit and unlocked. If so, it can be determined that the status acquisition condition is met, the status information of the target device can be obtained, and it can be determined whether the status information has changed. If so, the target network can be recommended to the target device. If not, the network may not be recommended.

[0147] It should be noted that Figure 6 This is only one feasible implementation manner. In the actual implementation process, if the target network corresponding to the current status information is already the current network, the recommendation of the target network may not be performed.

[0148] Next, another implementation process of the network recommendation provided in the embodiments of the present application will be explained.

[0149] Figure 7 For another flow diagram of the network recommendation provided in the embodiments of the present application, please refer to Figure 7, during the process of network recommendation, the current status information of the target device can be obtained, and then the wireless network and mobile network with the highest score can be determined according to the personalized knowledge graph data; moreover, according to the recommendation strategy, it can be determined whether to recommend the wireless network, the mobile network, or not to recommend, and then the target device can be controlled to perform network switching according to the recommended target network. Additionally, the feedback information of the network switching can be obtained and the recommendation strategy can be adjusted.

[0150] Among them, the recommendation strategy is the strategy for recommending the target network according to the above-mentioned personalized knowledge graph data.

[0151] After the recommendation of the target network is realized, the above-mentioned recommendation strategy can be adjusted according to the feedback information of the target network switching. The specific method is as follows:

[0152] Figure 8 This is another flowchart of the network recommendation method provided in the embodiments of the present application. Please refer to Figure 8 , after determining the target network from at least one recommended network, the method further includes:

[0153] S810: Obtain the feedback information for the target network switching.

[0154] Among them, the feedback information can be obtained in the form of a feedback code. For example, the feedback code can be obtained based on the result of whether the target device has switched to the target network, and the feedback information can be determined based on the specific content of the feedback code. Among them, different feedback codes can represent different feedback information. For example, when the feedback code is 0, it can be determined that the target device has realized network switching according to the recommended target network, and other feedback codes can represent that the target device has not realized network switching according to the recommended target network.

[0155] S820: Adjust the recommendation strategy for the target network according to the feedback information.

[0156] In one embodiment, after obtaining the above-mentioned feedback information, the recommendation strategy can be adjusted according to the specific content of the feedback information. For example, if the recommendation is successful, it means that the recommendation is reasonable; if the recommendation is not successful, it means that there may be something unreasonable in the recommendation, and the recommendation logic in the recommendation strategy can be adjusted. For example, adjust the threshold, replace the recommendation result, or do not continue to recommend within a certain period of time. There is no specific limitation here.

[0157] In the network recommendation method provided by the embodiments of the present application, the feedback information for the target network switching can be obtained; the recommendation strategy for the target network can be adjusted according to the feedback information. Among them, by feedback-regulating the recommendation strategy of the target network through the feedback information, the accuracy and reasonableness of the recommendation for the target network can be further improved, and the recommendation logic can be continuously improved based on the feedback result of the recommendation.

[0158] Next, the specific implementation process of adjusting the recommendation strategy according to the feedback information provided in the embodiments of the present application will be explained.

[0159] Figure 9 The flowchart for adjusting the recommendation strategy according to the feedback information provided in the embodiments of the present application is shown in Figure 9 , first, it is possible to determine whether the target device has completed the handover to the target network according to the feedback information. If the target network has been switched to the target network and there is no handover back within a certain period of time, it can be determined that the handover has been completed; otherwise, it can be determined that the target device has not completed the handover. For the case where the handover has not been completed, the following steps can be executed:

[0160] In one embodiment, when the feedback information indicates that the handover back to the target network is triggered, or when the handover to the target network fails, the network recommendation for the target device is stopped.

[0161] It should be noted that when the feedback information indicates that the handover back to the target network is triggered, it can mean that the user manually switches back to the original network, that is, the current recommendation is not satisfied, and the network recommendation for the target device can be stopped until the application is updated or the positioning module is updated.

[0162] Among them, stopping the network recommendation for the target device can be that the recommendation results are not sent to the target device for M consecutive times, or that the determination of the target network is not performed for M consecutive times. There is no specific limitation here, and one of the two methods can be selected according to actual needs for implementation.

[0163] It should be noted that when the feedback information indicates that the handover to the target network fails, it can be determined that the handover to the target network cannot be achieved. For such a situation, the recommendation can also be stopped until the application is updated or the positioning module is updated.

[0164] In one embodiment, when the feedback information indicates that the target device cannot perform the handover to the target network at the current time, a handover instruction is generated at preset time intervals. The handover instruction is used to instruct the target device to switch the current network to the target network.

[0165] It should be noted that when the feedback information indicates that the target device cannot perform the handover to the target network at the current time, it can be determined that a handover instruction that needs to be executed with a delay is required. In this case, a handover instruction can be generated once every preset time and sent to the target device. If the handover is successful, it will not be sent continuously. If the handover fails, it can be sent continuously.

[0166] Among them, the generated interval time can be set according to actual requirements. Position perception can be performed again every once in a while. If the position has not changed, the sending of the switching instruction can continue to be executed. If the position changes before the switching is successful, the steps of determining and recommending the target network can be executed again, and the switching instruction is no longer generated.

[0167] It should be noted that Figure 9 The shown implementation process can also be implemented based on a Reinforcement Learning from Reflective Feedback (RLRF) model.

[0168] Among them, the state of reinforcement learning can be selected as the accessed target network, and the action of forced learning is recommendation. Combining the recommendation result and the feedback information as feedback, the reinforcement learning mode is adjusted in real time.

[0169] In the network recommendation method provided by the embodiments of the present application, according to the feedback information, it can be determined that when the switching is not completed, the recommendation strategy for the target device is adjusted, so as to avoid repeated unreasonable recommendations, and it can ensure that the delayed recommendation continues, improving the accuracy and reasonableness of the network recommendation.

[0170] For the case where the switching has been completed, the following steps can be executed:

[0171] In one embodiment, adjusting the recommendation strategy for the target network according to the feedback information includes: when the feedback information indicates that the target device switches the current network to the target network, obtaining the network change situation and position change situation of the target device within a preset time; generating a recommendation failure instruction when the target device meets the recommendation failure condition.

[0172] Among them, the recommendation failure conditions include: no position information of the target device is obtained within the preset time, the position information of the target device is not in the personalized knowledge graph data, the target device does not meet the network backhaul condition, and the target device is in the screen-off state; the recommendation failure instruction is used to indicate that the recommendation for the target network has expired.

[0173] It should be noted that not obtaining the position information of the target device within the preset time can be that there is no positioning result for a continuous T1 seconds, or for a continuous T2 seconds, the feedback of the positioning result / position perception result is -1, where the feedback of the positioning result / position perception result being -1 means that no positioning result is obtained.

[0174] The location information of the target device not being in the personalized knowledge graph data means that the recommendation result triggers the wireless network to switch to the mobile network, but during the subsequent process of the system switching to the mobile network, the serving cell corresponding to the mobile network during positioning is not in the personalized knowledge graph data.

[0175] The target device not meeting the network fallback condition means that the recommendation result triggers the wireless network to switch to the mobile network. Subsequently, during positioning, the serving cell corresponding to the mobile network is in the personalized knowledge graph data, but the difference between the score of the current wireless network and the score of the mobile network is greater than or equal to the third threshold, and the wireless network is less than the fourth threshold. In this case, the network has not fallen back to the wireless network.

[0176] In the above multiple cases, it can be determined that the recommendation for the target network has failed, and a recommendation failure instruction can be generated.

[0177] In the network recommendation method provided by the embodiments of the present application, when the feedback information indicates that the target device switches the current network to the target network, the network change situation and location change situation of the target device within a preset time can be obtained; when the target device meets the recommendation failure condition, a recommendation failure instruction is generated. Among them, since the recommendation for the target network is a continuous process, after the recommendation, if it is determined that the target device meets the recommendation failure situation, a recommendation failure instruction can be generated, thereby indicating that the recommendation result of the target network has failed.

[0178] Next, the implementation process of constructing the personalized knowledge graph provided in the embodiments of the present application will be explained.

[0179] Figure 10 For the flow diagram of constructing the personalized knowledge graph provided in the embodiments of the present application, please refer to Figure 10 , the method includes:

[0180] S1010: Collect corresponding status information when the target device performs corresponding behavior operations.

[0181] S1020: Establish personalized knowledge graph data according to each group of status information.

[0182] S1030: Store the personalized knowledge graph data in the database.

[0183] It should be noted that the target device performing corresponding behavior operations can be one of the aforementioned multiple network switching operations, corresponding status information can be collected, and the above-mentioned personalized knowledge graph data can be established based on these status information and stored in the database.

[0184] Next, the implementation process of collecting status information provided in the embodiments of the present application will be explained.

[0185] Figure 11 This is a schematic flowchart of the process for collecting status information provided in the embodiments of the present application. Please refer to Figure 11 , which can monitor the target device in real time to determine whether there is a network switching operation. If not, it can continue to monitor. If so, it can record the status information of the target device within a preset time interval.

[0186] Next, the overall implementation process of the network recommendation provided in the embodiments of the present application will be explained.

[0187] Figure 12 This is a schematic flowchart of the overall process of the network recommendation method provided in the embodiments of the present application. Please refer to Figure 12 , first, it can collect the status information generated by the target device when performing a network switching operation, then establish personalized knowledge graph data based on the status information, and then perform target network recommendation based on the personalized knowledge graph data; finally, it can control the target device to switch to the target network, generate feedback information according to the switching result, and use the status information corresponding to the switching as the new status information generated by the target device when performing the network switching operation.

[0188] It should be noted that through the above method, the number of ineffective collections can be reduced, personalized knowledge graph data can be constructed according to historical user behaviors, the user's network preferences can be predicted in real time, the network switching action can be output before the user manually switches the network, reducing the user's manual operations. At the same time, according to the real-time network status and the user's possible re-switching behaviors, ineffective recommendations or incorrect recommendations can be avoided, making the network switching closer to the user's true intention.

[0189] It should be understood that although the steps in the above flowcharts are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0190] Based on the foregoing embodiments, the embodiments of the present application provide a network recommendation device. The device includes each module included and each unit included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; during the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0191] Figure 13 The following is a schematic structural diagram of the network recommendation device provided in the embodiments of the present application. Please refer to Figure 13 In another aspect of the embodiments of the present application, a network recommendation device is further provided, including: an information acquisition module 1310 and a network switching module 1320;

[0192] The information acquisition module 1310 is configured to acquire the status information of the target device. The status information is used to indicate the network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environmental perception information;

[0193] The network switching module 1320 is configured to switch the target device to the target network, and the target network matches the status information of the target device.

[0194] In one embodiment, the network switching module 1320 is further configured to determine at least one recommended network corresponding to the status information according to the status information of the target device and the personalized knowledge graph data. The personalized knowledge graph data includes: the mapping relationship between the preset status information and the preset recommended network, where each preset status information is the status information obtained when the target device performs a preset operation; and determine the target network from at least one recommended network.

[0195] In one embodiment, the personalized knowledge graph data further includes the score of the preset recommended network corresponding to each group of preset status information; the network switching module 1320 is specifically configured to determine the wireless network with the highest score and the mobile network with the highest score from the preset recommended networks; and determine the target network according to the scores of the wireless network and the mobile network.

[0196] In one embodiment, the network switching module 1320 is specifically configured to, when the current network of the target device is a wireless network, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to the first threshold, determine the wireless network as the target network; when the current network of the target device is a wireless network, if the score of the wireless network is less than the second threshold, and the difference between the score of the mobile network and the score of the wireless network is greater than or equal to the first threshold, determine the mobile network as the target network.

[0197] In one embodiment, the network switching module 1320 is specifically configured to, when the current network of the target device is a mobile network, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to the third threshold, and the score of the wireless network is greater than or equal to the fourth threshold, determine the wireless network as the target network; if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to the fifth threshold, determine the wireless network as the target network, where the fifth threshold is greater than the third threshold.

[0198] In one embodiment, the network switching module 1320 is further configured to, when multiple groups of preset status information correspond to the same preset recommended network, use the score with the smallest value among them as the score of the preset recommended network.

[0199] In one embodiment, in the device, the score of the preset recommended network in the personalized knowledge graph data is determined based on the scores of all network switching behaviors performed by the target device, the scores of the network switching behaviors performed by the target device within a preset time interval, and the scores of the frequency of network switching performed by the target device within a preset time interval.

[0200] In one embodiment, the information acquisition module 1310 is specifically configured to obtain the location of the target device through the positioning module of the target device; when the location of the target device changes, obtain the status information of the target device, and the situations where the location changes include: the target device enters or leaves the fence area.

[0201] In one embodiment, the information acquisition module 1310 is further configured to update the personalized knowledge graph data when the positioning module of the target device is updated.

[0202] In one embodiment, the information acquisition module 1310 is further configured to clear the personalized knowledge graph data if the positioning module of the target device has not been updated for more than a preset time.

[0203] In one embodiment, the network switching module 1320 is further configured to input the status information of the target device into a pre-trained network recommendation model to obtain at least one recommended network, where the network recommendation model is a model obtained by training based on sample status information and sample recommended networks; determine a target network from the at least one recommended network.

[0204] In one embodiment, the network switching module 1320 is further configured to obtain feedback information for the target network switching; adjust the recommendation strategy for the target network according to the feedback information.

[0205] In one embodiment, the network switching module 1320 is specifically configured to stop network recommendation for the target device when the feedback information indicates that the backhaul of the target network is triggered, or when the switch to the target network fails; when the feedback information indicates that the target device cannot perform the target network switching at the current time, generate a switching instruction at every preset time interval, and the switching instruction is used to instruct the target device to switch the current network to the target network.

[0206] In one embodiment, the network switching module 1320 is specifically configured to obtain the network change situation and location change situation of the target device within a preset time when the feedback information indicates that the target device switches the current network to the target network; and generate a recommendation invalidation instruction when the target device meets the recommendation invalidation conditions, where the recommendation invalidation conditions include: no location information of the target device is obtained within the preset time, the location information of the target device is not in the personalized knowledge graph data, the target device does not meet the network fallback conditions, and the target device is in the screen-off state; the recommendation invalidation instruction is used to indicate that the recommendation for the target network has expired.

[0207] The description of the above device embodiments is similar to that of the above method embodiments, and has similar beneficial effects to the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0208] It should be noted that in the embodiments of the present application Figure 13 The division of the modules of the network recommendation device shown is schematic, and is only a logical function division. In actual implementation, there may be other division methods. In addition, each functional unit in the various embodiments of the present application may be integrated in a processing unit, or may exist physically alone, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software functional unit. It may also be implemented in the form of a combination of software and hardware.

[0209] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the related technology, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disc that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0210] Figure 14 For the structural schematic diagram of the computer device provided in the embodiments of the present application, please refer to Figure 14 In the embodiments of the present application, a computer device is provided. The computer device may be the above target device or other electronic devices communicatively connected to the target device, and its internal structure diagram may be as Figure 14As shown in the figure. The computer device includes a processor 1420, a memory, and a network interface 1440 connected through a system bus 1410. Among them, the processor 1420 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium 1431 and an internal memory 1432. The non-volatile storage medium 1431 stores an operating system, a computer program, and a database. The internal memory 1432 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium 1431. The database of the computer device is used to store data. The network interface 1440 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor 1420, the above method is implemented.

[0211] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method provided in the above embodiment are implemented.

[0212] An embodiment of the present application provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the steps in the method provided in the above method embodiment.

[0213] Those skilled in the art can understand that Figure 14 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0214] In one embodiment, the network recommendation device provided by the present application can be implemented in the form of a computer program, and the computer program can run on a computer device such as Figure 14 shown in the figure. Each program module constituting the above device can be stored in the memory of the computer device. The computer program constituted by each program module causes the processor to execute the steps in the methods of various embodiments of the present application described in this specification.

[0215] It should be pointed out here that: the descriptions of the above storage medium and device embodiments are similar to the descriptions of the above method embodiments, and have beneficial effects similar to those of the method embodiments. For the technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0216] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the appearances of "in one embodiment" or "in an embodiment" or "in some embodiments" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the magnitude of the serial numbers of the above processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments. The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated herein.

[0217] As used herein, the term "and / or" is merely a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, object A and / or object B can represent: the situation where object A exists alone, the situation where object A and object B exist simultaneously, and the situation where object B exists alone.

[0218] It should be noted that, as used herein, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0219] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The above-described embodiments are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of the devices or modules can be electrical, mechanical or other forms.

[0220] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network elements; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0221] In addition, in each embodiment of this application, all the functional modules may be integrated in one processing unit, or each module may be a separate unit alone, or two or more modules may be integrated in one unit; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of a combination of hardware and software functional units.

[0222] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), magnetic disks, or optical disks and other various media that can store program codes.

[0223] Alternatively, if the above integrated unit of this application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that makes contributions to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of this application. And the foregoing storage medium includes: removable storage devices, ROM, magnetic disks, or optical disks and other various media that can store program codes.

[0224] The methods disclosed in the several method embodiments provided by this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0225] The features disclosed in the several product embodiments provided by this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0226] The features disclosed in the several method or device embodiments provided by this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0227] As described above, it is only the implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the said claims.

Claims

1. A network recommendation method, characterized in that: include: Acquire status information of a target device, where the status information is used to indicate a network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environment perception information; The target device is switched to a target network, where the target network matches the status information of the target device.

2. The method according to claim 1, characterized in that: Before switching the target device to the recommended network, the method further includes: Determine at least one recommendation network corresponding to the state information according to the state information of the target device and the personalized knowledge graph data, wherein the personalized knowledge graph data includes: a mapping relationship between preset state information and preset recommendation networks, wherein each preset state information is state information obtained when the target device performs a preset operation; The target network is determined from the at least one recommended network.

3. The method according to claim 2, characterized in that The personalized knowledge graph data also includes the score of the preset recommendation network corresponding to each set of preset status information; The determining, according to the state information of the target device and the personalized knowledge graph data, at least one recommendation network corresponding to the state information includes: Determine the wireless network with the highest score and the mobile network with the highest score from the preset recommended networks; The determining the target network from the at least one recommended network includes: The target network is determined according to the score of the wireless network and the score of the mobile network.

4. The method according to claim 3, characterized in that: The determining the target network according to the score of the wireless network and the score of the mobile network includes: In a case where the current network of the target device is a wireless network, if a difference between a score of the wireless network and a score of the mobile network is greater than or equal to a first threshold, determining that the wireless network is the target network; In the case that the current network of the target device is a wireless network, if the score of the wireless network is less than a second threshold, and the difference between the score of the mobile network and the score of the wireless network is greater than or equal to a first threshold, the mobile network is determined to be the target network.

5. The method according to claim 3, characterized in that: The determining the target network according to the score of the wireless network and the score of the mobile network includes: In the case where the current network of the target device is a mobile network, if the difference between the score of the wireless network and the score of the mobile network is greater than or equal to a third threshold, and the score of the wireless network is greater than or equal to a fourth threshold, determining that the wireless network is the target network; If the difference between the score of the wireless network and the score of the mobile network is greater than or equal to a fifth threshold, the wireless network is determined to be the target network, wherein the fifth threshold is greater than the third threshold.

6. The method according to claim 3, characterized in that Before determining the wireless network with the highest score and the mobile network with the highest score from the preset recommended networks, the method further includes: In the case where multiple sets of preset status information correspond to the same preset recommended network, the score with the smallest score among them is used as the score of the preset recommended network.

7. The method according to claim 3 or 6, characterized in that: The score of the preset recommended network in the personalized knowledge graph data is determined based on the scores of all network switching behaviors performed by the target device, the score of the network switching behaviors performed by the target device within a preset time interval, and the score of the frequency of network switching performed by the target device within a preset time interval.

8. The method according to claim 2, characterized in that: The step of obtaining the status information of the target device includes: Acquiring the location of the target device through a positioning module of the target device; When the position of the target device changes, the state information of the target device is acquired, and the position change includes: the target device enters or leaves a fence area.

9. The method according to claim 8, characterized in that The method further comprises: When the positioning module of the target device is updated, the personalized knowledge graph data is updated.

10. The method according to claim 8, characterized in that The method further comprises: If the positioning module of the target device is not updated within a preset time, the personalized knowledge graph data is cleared.

11. The method according to claim 1, characterized in that: Before switching the target device to the recommended network, the method further includes: Inputting the state information of the target device into a pre-trained network recommendation model to obtain at least one recommendation network, wherein the network recommendation model is a model obtained after training based on the sample state information and the sample recommendation network; The target network is determined from the at least one recommended network.

12. The method according to any one of claims 1 to 2 or 11, characterized in that: After switching the target device to the target network, the method further includes: Obtaining feedback information for the target network switching; The recommendation strategy for the target network is adjusted according to the feedback information.

13. The method according to claim 12, characterized in that The adjusting the recommendation strategy for the target network according to the feedback information includes: When the feedback information indicates that a switchback to the target network is triggered, or when the switch to the target network fails, stopping network recommendation for the target device; When the feedback information indicates that the target device cannot perform target network switching at the current time, a switching instruction is generated at a preset time interval, and the switching instruction is used to instruct the target device to switch the current network to the target network.

14. The method according to claim 12, characterized in that The adjusting the recommendation strategy for the target network according to the feedback information includes: When the feedback information indicates that the target device switches the current network to the target network, obtaining the network change status and the location change status of the target device within a preset time; When the target device meets the recommendation expiration condition, a recommendation expiration instruction is generated, and the recommendation expiration condition includes: the location information of the target device is not obtained within a preset time, the location information of the target device is not in the personalized knowledge graph data, the target device does not meet the network switching condition, and the target device is in a screen-off state; the recommendation expiration instruction is used to indicate that the recommendation for the target network has expired.

15. A network recommendation device, characterized in that: include: Information acquisition module and network switching module; The information acquisition module is used to acquire status information of the target device, where the status information is used to indicate the network usage preference of the target device, and the status information includes at least one of the following: network information, application information, and environment perception information; The network switching module is used to switch the target device to a target network, and the target network matches the status information of the target device.

16. A computer device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 14 are implemented.

17. 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 14 is implemented.

Images