A method and system for adjusting wireless network parameters

Abstract

The embodiment of the present specification provides a wireless network parameter adjustment method and system, the method comprises: acquiring a current wireless network parameter of a wireless network in a target place and an environmental feature of the target place; determining a wireless network demand degree in the target place based on the environmental feature; and determining a target adjustment value of the wireless network parameter based on the wireless network demand degree and the current wireless network parameter.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of wireless network, and in particular, to a wireless network parameter adjustment method and system. BACKGROUND

[0002] Wireless network refers to a network that can realize interconnection of various communication devices without wiring. With the development of wireless network technology, wireless network has been deeply applied in people's daily life. When using wireless network in public places, due to the high mobility of the crowd in the place, the connection and use of wireless network are changing constantly, and the current wireless network parameter setting may not meet the wireless network needs of users.

[0003] Therefore, it is desirable to provide a wireless network parameter adjustment method and system, which can adjust wireless network parameters so that the wireless network parameters can better meet the wireless network needs of users. SUMMARY

[0004] One or more embodiments of the present specification provide a wireless network parameter adjustment method. The wireless network parameter adjustment method comprises: obtaining a current wireless network parameter of a wireless network in a target place and an environmental feature of the target place; determining a wireless network demand degree in the target place based on the environmental feature; and determining a target adjustment value of the wireless network parameter based on the wireless network demand degree and the current wireless network parameter.

[0005] One or more embodiments of the present specification provide a wireless network parameter adjustment system. The wireless network parameter adjustment system comprises: an obtaining module configured to obtain a current wireless network parameter of a wireless network in a target place and an environmental feature of the target place; a demand degree determining module configured to determine a wireless network demand degree in the target place based on the environmental feature; and a target adjustment value determining module configured to determine a target adjustment value of the wireless network parameter based on the wireless network demand degree and the current wireless network parameter.

[0006] One or more embodiments of the present specification provide a wireless network parameter adjustment device, comprising a processor configured to execute a wireless network parameter adjustment method.

[0007] One or more embodiments of the present specification provide a computer readable storage medium, which stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes a wireless network parameter adjustment method. BRIEF DESCRIPTION OF DRAWINGS

[0008] The specification will be further described in the manner of example embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers refer to the same structures, wherein:

[0009] Figure 1 is a schematic diagram of an application scenario of a wireless network parameter adjustment system according to some embodiments of the present specification;

[0010] Figure 2 is an exemplary block diagram of a wireless network parameter adjustment system according to some embodiments of the present specification;

[0011] Figure 3 is an exemplary flowchart of a wireless network parameter adjustment method according to some embodiments of the present specification;

[0012] Figure 4 is an exemplary flowchart of determining a wireless network demand degree in a target site according to some embodiments of the present specification;

[0013] Figure 5 is an exemplary schematic diagram of determining at least one target area in a target site according to some embodiments of the present specification;

[0014] Figure 6 is an exemplary flowchart of determining a target adjustment value of a wireless network parameter according to some embodiments of the present specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can be applied to other similar scenarios without creative labor on the basis of these drawings. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in the specification and claims, unless the context clearly indicates otherwise, the words "comprise", "comprising", "consist", "consisting", "include", "including", "contain", "containing", "involving", "involving", "have", "having", "may", "might", "must", "need", "need", "shall", "should", "will", "would", and / or the like are not necessarily limited to a positive state but can include a negative state unless the context clearly indicates otherwise. Generally, the terms "comprise" and "contain" are merely to indicate including, and not to the exclusion of other steps or elements.

[0018] Flowcharts in the specification are used to illustrate operations performed by systems according to embodiments of the specification. It should be understood that the preceding or following operations are not necessarily performed in the order. Instead, the steps can be processed in reverse order or simultaneously. In addition, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0019] Figure 1 is a schematic diagram of an application scenario of a wireless network parameter adjustment system according to some embodiments of the specification. In some embodiments, the application scenario 100 of the wireless network parameter adjustment system can include a target site 110, a processor 120, a storage device 130, a terminal 140, and a network 150.

[0020] The target site 110 refers to a site that needs to adjust the wireless network parameters. The target site can include various, for example, the target site can include business center 110-1, hospital 110-2, restaurant 110-3, etc. In some embodiments, the target site can include various monitoring devices such as camera devices to determine the flow of people and the distribution of people flow, etc. In some embodiments, the target site can also include network devices (such as wireless routing devices, etc.) for providing wireless networks and obtaining wireless network parameters, etc.

[0021] The processor 120 can be used to obtain data and / or information, and analyze and process the obtained data and / or information to execute one or more embodiments described in the specification. For example, the processor 120 can determine the wireless network demand degree in the target site based on the environmental characteristics. For another example, the processor 120 can determine at least one target area in the target site based on the environmental characteristics, etc. In some embodiments, the processor 120 can include one or more processing engines (such as single-chip processing engines or multi-chip processing engines). For example only, the processor 120 can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), etc. or any combination thereof.

[0022] The storage device 130 can be used to store data and / or instructions. For example, the storage device 130 can be used to store environmental characteristics of a target site. The storage device 130 can store data and / or instructions obtained from, for example, the processor 120, the terminal 140, etc. In some embodiments, the storage device 130 can store data and / or instructions used by the processor 120 to perform or use in completing the exemplary methods described in this specification.

[0023] In some embodiments, the storage device 130 can also be integrated in the processor 120 as an integral part of the processor 120.

[0024] The terminal 140 can refer to one or more terminal devices or software used by a user. In some embodiments, the terminal can include a mobile device, a tablet computer, a notebook computer, etc. having a display, or any combination thereof. In some embodiments, the terminal can include a user terminal and an administrator terminal. In some embodiments, a user can connect to and use a wireless network through the user terminal. In some embodiments, a network administrator can view current wireless network parameters through the administrator terminal. In some embodiments, the administrator can also use the wireless network through the administrator terminal to determine the effect of adjusting the wireless network parameters.

[0025] The network 150 can include any suitable network that provides for the exchange of information and / or data among the various components of the application scenario 100 of the wireless network parameter adjustment system. Information and / or data can be exchanged between one or more components of the application scenario 100 of the wireless network parameter adjustment system (e.g., the target site 110, the processor 120, the storage device 130, the terminal 140, etc.) through the network 150. In some embodiments, the network 150 can be any one or more of a wired network or a wireless network. In some embodiments, the network 150 can include one or more network access points. For example, the network 150 can include wired or wireless network access points. In some embodiments, the network can be in various topologies or combinations of topologies, such as point-to-point, shared, hub-and-spoke, etc.

[0026] It should be noted that the application scenario 100 of the wireless network parameter adjustment system is provided for illustrative purposes only and is not intended to limit the scope of this specification. Various modifications or changes can be made to the application scenario 100 based on the description of this specification. For example, the application scenario 100 can be implemented on other devices to achieve similar or different functions. However, variations and modifications will not depart from the scope of this specification.

[0027] Figure 2 is an exemplary block diagram of the wireless network parameter adjustment system according to some embodiments of this specification. As shown in FIG. 1, the application scenario 100 of the wireless network parameter adjustment system can include a target site 110, a processor 120, a storage device 130, a terminal 140, and a network 150. Figure 2As shown, the wireless network parameter adjustment system 200 can include an acquisition module 210, a demand degree determination module 220, and a target adjustment value determination module 230.

[0028] The acquisition module 210 can be configured to acquire the current wireless network parameter of the wireless network in the target site and the environmental feature of the target site. In some embodiments, the acquisition module 210 can include a network device such as a wireless routing device configured to acquire the current wireless network parameter of the wireless network in the target site. In some embodiments, the acquisition module 210 can further include a monitoring device such as a camera device configured to acquire the environmental feature of the target site.

[0029] The demand degree determination module 220 can be configured to determine the wireless network demand degree in the target site. In some embodiments, the wireless network demand degree in the target site can be determined based on the environmental feature of the target site.

[0030] In some embodiments, the demand degree determination module 220 can be further configured to: determine at least one target area in the target site based on the environmental feature; determine a secondary wireless network demand degree in each target area based on the at least one target area, the secondary wireless network demand degree including a connection demand degree; and determine the wireless network demand degree in the target site based on the secondary wireless network demand degree in each target area. For details, please refer to Figure 4 .

[0031] In some embodiments, the demand degree determination module 220 can be further configured to: construct a site feature map based on the site structure, the site feature map including nodes and edges, the nodes including at least one area in the site, and the edges including a connection channel existing between the at least one area; determine a crowd flow prediction value of each target area at a future time through a machine learning model based on the site feature map; and determine a target area based on a region with a current crowd flow greater than a preset threshold and / or a region with a crowd flow prediction value greater than a preset threshold. For details, please refer to Figure 5 .

[0032] The target adjustment value determination module 230 can be configured to determine a target adjustment value of the wireless network parameter. In some embodiments, the target adjustment value of the wireless network parameter can be determined based on the wireless network demand degree and the current wireless network parameter.

[0033] In some embodiments, the target adjustment value determination module 230 can be further configured to: generate at least one candidate adjustment value through a preset rule based on the wireless network demand degree; calculate an evaluation value of each candidate adjustment value, and determine the target adjustment value from the at least one candidate adjustment value based on the evaluation value. For details, please refer to Figure 6 .

[0034] It should be noted that the above description of the wireless network parameter adjustment system 200 and its modules is for the convenience of description only, and does not limit the scope of the present specification to the embodiments described. It can be understood that, for those skilled in the art, after understanding the principles of the system, any combination of the modules or connection of the modules to form a subsystem can be made without departing from the principles. In some embodiments, Figure 2 The demand degree determination module and the target adjustment value determination module disclosed in the present specification can be different modules in a system, or can be a module that implements the functions of two or more modules described above. For example, the modules can share a storage module, and each module can have its own storage module. Variations such as these are within the scope of protection of the present specification.

[0035] Figure 3 is an exemplary flowchart of a wireless network parameter adjustment method according to some embodiments of the present specification. As shown in Figure 3 , the flow 300 includes the following steps.

[0036] Step 310, obtaining the current wireless network parameters of the wireless network in the target site and the environmental characteristics of the target site. In some embodiments, step 310 can be performed by the obtaining module 210.

[0037] Wireless network can refer to a network that enables interconnection of various devices without laying lines. In some embodiments, the wireless network can include various types, such as wireless wide area network, wireless local area network, wireless metropolitan area network, etc.

[0038] Wireless network parameters can refer to the transmission parameters of the wireless network transmitted by the wireless routing device, such as transmission power, frequency band, frequency width, channel, channel width, etc. The current wireless network parameters can refer to the wireless network parameters before adjustment, such as the wireless network transmission power, frequency band, frequency width, etc. before adjustment.

[0039] In some embodiments, the obtaining module 210 can obtain the current wireless network parameters of the target site based on the wireless routing device. For example, the obtaining module 210 can obtain the transmission power, frequency band, etc. of the current wireless network through the wireless router, etc.

[0040] Environmental characteristics can refer to relevant characteristics of the target site, such as the traffic characteristics of the target site, the type of site, etc. Among them, the environmental characteristics can include the number of people entering the target site, the number of people leaving the target site, and the original number of people in the target site, etc.; the type of site is related to the service provided by the site, which can include but is not limited to shopping malls, hospitals, and conference centers, etc.

[0041] In some embodiments, the environment feature of the target site can be determined based on the picture, video, and the like information obtained by the camera device through a machine learning model (e.g., a convolutional neural network model, etc.). For example, the processor can identify the picture or the video through a convolutional neural network based on the picture, video, and the like information obtained by the camera device to determine the environment feature such as the number of people entering the target site, the number of people leaving the target site, and the original number of people in the target site, and determine the site type of the target site.

[0042] At step 320, the wireless network demand degree in the target site is determined based on the environment feature. In some embodiments, step 320 can be performed by the demand degree determination module 220.

[0043] The wireless network demand degree can refer to the demand degree of the wireless network by the users of the target site. For example, the wireless network demand degree can be that 100 users of the target site need to connect to the wireless network, and the like.

[0044] In some embodiments, the wireless network demand degree can be determined based on the crowd flow. For example, the wireless network demand degree can be determined based on the following formula:

[0045] L = P + P in - P out

[0046] wherein L represents the wireless network demand degree of the target site, P represents the original number of people in the target site, P in represents the number of people entering the target site, and P out represents the number of people leaving the target site.

[0047] In some embodiments, the wireless network demand degree of the target site can also be determined based on the environment feature. Specifically, at least one target area in the target site is determined based on the environment feature; the secondary wireless network demand degree in each target area is determined; and the wireless network demand degree in the target site is determined based on the secondary wireless network demand degree in the at least one target area. The detailed content of determining the wireless network demand degree of the target site based on the environment feature can be referred to in the description of Figure 4 and the related description thereof.

[0048] At step 330, the target adjustment value of the wireless network parameter is determined based on the wireless network demand degree and the current wireless network parameter. In some embodiments, step 330 can be performed by the target adjustment value determination module 230.

[0049] The target adjustment value can refer to the adjustment value of the wireless network parameter when the wireless network is adjusted to meet the demand of most users of the target site. For example, the target adjustment value can include the transmission power adjustment value, the frequency band adjustment value, the frequency width adjustment value, and the like.

[0050] In some embodiments, the demand determining module can determine the target adjustment value of the wireless network parameter based on the wireless network demand, by a first preset condition. The first preset condition can include multiple conditions. For example, the first preset condition can include that the greater the wireless network demand, the greater the adjustment of the wireless network parameter to the transmission parameter. For another example, the first preset condition can include that the target adjustment value of the wireless network parameter is determined based on the sum of the wireless network demands of multiple users.

[0051] In some embodiments, the target adjustment value of the wireless network parameter can also be determined based on multiple candidate adjustment values. Specifically, at least one candidate adjustment value is generated based on the wireless network demand; an evaluation value of each candidate adjustment value is calculated, and the target adjustment value is determined from the at least one candidate adjustment value based on the evaluation value. Details of determining the target adjustment value of the wireless network parameter based on multiple candidate adjustment values can be found in Figure 6 and the related description.

[0052] One or more embodiments of the present specification can obtain the density of the target site terminal, the accurate position and other information through the wireless network positioning, and automatically adjust the wireless network parameter through the machine learning model, so as to realize the optimization of the coverage range, the flow rate and the user network experience of the wireless network.

[0053] Figure 4 is an exemplary flowchart for determining the wireless network demand in the target site according to some embodiments of the present specification. In some embodiments, the flow 400 can be executed by the demand determining module 220. As Figure 4 shown, the flow 400 includes the following steps.

[0054] Step 410, determining at least one target area in the target site based on the environmental features.

[0055] The target area can refer to an area in the target site where the wireless network demand is higher than a certain threshold. For example, the target area of a certain business center can include an area where more than 80 users need to connect to the network, etc.

[0056] In some embodiments, the target area can be determined based on the crowd flow. For example, the demand determining module 220 can determine an area with a crowd flow greater than 100 as a target area, etc.

[0057] In some embodiments, the target area can also be determined based on a venue structure of the target venue. Specifically: a venue feature map of the target venue is constructed based on the venue structure; based on the venue feature map, a crowd flow prediction value of each area at a future time is determined by a machine learning model; an area with a current crowd flow greater than a preset threshold and / or an area with a crowd flow prediction value greater than a preset threshold is determined as the target area. For detailed description of determining the target area based on the venue structure of the target venue, please refer to Figure 5 and the related description.

[0058] In step 420, a secondary wireless network demand degree in each target area is determined, and the secondary wireless network demand degree includes a connection demand degree.

[0059] The secondary network demand degree can refer to a network demand degree of the target area. For example, there are 50 users in a target area who need to connect to a wireless network, etc.

[0060] In some embodiments, the secondary network demand degree can include a connection demand degree.

[0061] The connection demand degree can refer to the number of terminals in the target area that need to connect to a wireless network. For example, when there are 80 terminals in the target area that need to connect to a wireless network, the connection demand degree is 80.

[0062] In some embodiments, the connection demand degree can be determined based on crowd flow, crowd flow distribution, etc.

[0063] The crowd flow can refer to the number of people passing through an area within a period of time (e.g., within 1 hour). For example, when the number of people passing through an area within 1 hour is 100, the crowd flow of the area is 100 people / hour, etc. In some embodiments, the crowd flow can be determined based on data and / or information such as pictures, videos, etc. collected by a camera device, through a person detection algorithm, etc.

[0064] The crowd flow distribution can refer to the number distribution of people of different age groups in an area. For example, the crowd flow distribution of an area can be 20 people aged over 50 years old and 40 people aged less than 50 years old, etc. In some embodiments, the crowd flow distribution can be determined based on data and / or information such as pictures, videos, etc. collected by a camera device, through image recognition technology, etc.

[0065] In some embodiments, the connection demand degree corresponding to different crowd flow and different crowd flow distribution can be different. For example, the greater the crowd flow, the greater the connection demand, etc. For example, the more people aged over 50 years old, the smaller the connection demand, etc. In some embodiments, the connection demand degree can be determined based on the crowd flow, the crowd flow distribution, etc. through a connection demand degree model.

[0066] The connection demand degree model can include a machine learning model for determining the connection demand degree of the target area. In some embodiments, the input of the connection demand degree model can include the crowd flow and the crowd flow distribution, and the output can include the connection demand degree.

[0067] In some embodiments, the connection demand degree model can be trained based on a large number of connection demand degree training samples with connection demand degree labels. Specifically, the connection demand degree training samples with connection demand degree labels are input into the machine learning model, and the parameters of the machine learning model are updated through training, thereby obtaining the trained connection demand degree model.

[0068] In some embodiments, the connection demand degree training samples can include historical crowd flow and historical crowd flow distribution, and the connection demand degree label can include historical connection demand degree.

[0069] In some embodiments, the secondary wireless network demand degree in the target area further includes the traffic demand degree.

[0070] The traffic demand degree can refer to the traffic data required by the terminal connected to the wireless network. In some embodiments, the traffic demand degree can be determined based on the sum of the traffic demand degrees of a plurality of users. At least one of the traffic demand degrees of the plurality of users can be determined based on historical data such as average user traffic usage. For example, the average traffic usage X of a user in the target place in the historical data can be determined as the traffic demand degree of a user.

[0071] In some embodiments, the traffic demand degree of the crowd in the target area can also be determined based on the crowd flow, the crowd flow distribution, and the area characteristics in the target area.

[0072] The area characteristics can refer to the type of the target area. For example, the area characteristics can be a bookstore. For another example, the area characteristics can be a restaurant, etc. In some embodiments, the area characteristics can be obtained in various ways. For example, the area characteristics can be obtained based on a camera device. For another example, the area characteristics can be manually pre-set, etc.

[0073] In some embodiments, the traffic demand degree of the crowd in the target area can be determined based on the crowd flow, the crowd flow distribution, and the area characteristics in the target area through a traffic demand degree model.

[0074] The traffic demand degree model is a machine learning model for determining the traffic demand degree of the target area. In some embodiments, the input of the connection demand degree model can include the crowd flow, the crowd flow distribution, and the area characteristics, and the output can include the traffic demand degree of the crowd in the target area.

[0075] In some embodiments, the traffic demand degree model can be trained based on a large number of traffic demand degree training samples with traffic demand degree labels. Specifically, the traffic demand degree training samples with traffic demand degree labels are input into the machine learning model, the parameters of the machine learning model are updated through training, and the trained traffic demand degree model is obtained.

[0076] In some embodiments, the traffic demand degree training samples can include historical crowd flow, historical crowd flow distribution, and historical regional features, and the traffic demand degree labels can include historical traffic demand degrees of the crowd in the target region.

[0077] In some embodiments of the present specification, the traffic demand degree is determined based on the crowd flow and the crowd flow distribution, which can save wireless network resources while meeting the wireless network needs of different crowds.

[0078] In some embodiments, the traffic demand degree can also be related to the experience degree. For example, the higher the experience degree, the smaller the traffic demand, etc.

[0079] The experience degree can reflect the quality of experience of users connecting to the wireless network. The higher the experience degree of a region, the better the quality of experience of connecting to the wireless network in the region. Since the crowd tends to choose better quality of experience, the crowd also tends to go to the region with a higher experience degree. That is, the transfer probability from a region with a lower experience degree to a region with a higher experience degree is higher; for the case of going from a region with a lower experience degree to multiple regions with higher experience degrees, there are multiple differences in experience degrees between the region with a lower experience degree and the multiple regions with higher experience degrees, and the greater the difference in experience degrees, the higher the transfer probability to the region with a higher experience degree.

[0080] In some embodiments, the experience degree can be determined based on the average response time of the application or webpage. For example, the longer the average response time, the lower the experience degree, etc.

[0081] In some embodiments, the traffic demand degree of each user can also be determined based on the experience degree. For example, the lower the experience degree of a user, the more lack of traffic, and the traffic demand degree of the user can be increased to obtain a better network experience. For another example, the higher the experience degree of a user, the more sufficient traffic, and the traffic demand degree of the user can be appropriately reduced (e.g., reduced by 7%) to reduce the pressure of the wireless network, so that more users can obtain a better network experience.

[0082] In some embodiments, determining the traffic demand degree of a user based on the experience degree can reduce the pressure of the wireless network, balance the network needs of users in different network usage scenarios, and enable more users to obtain a better network experience.

[0083] In some embodiments, the traffic demand degree can also be related to a service quality parameter. The service quality parameter can include a user priority configuration parameter and an application priority configuration parameter, which are one of the parameters of the wireless network.

[0084] The service quality parameter can refer to a related setting parameter for the wireless network to provide high-quality network services for users. For example, the service quality parameter can be to set different forwarding parameters for users, applications, etc. of different priorities.

[0085] The user priority configuration parameter can refer to different priority forwarding parameters configured based on the priority of the user. For example, different wireless network forwarding parameters are configured for users of different priorities, and the higher the priority of the user, the higher the forwarding priority corresponding to the user, that is, the network demand of the user with higher priority is preferentially met. Among them, the priority of the user can be determined based on the number of times and the total length of time that the user accesses the target place, and the user with a larger number of times and a longer total length of time has a higher priority.

[0086] The application priority configuration parameter can refer to different priority forwarding parameters configured based on the priority of the application program. For example, different wireless network forwarding parameters are configured for application programs of different priorities, and the higher the priority of the user, the higher the forwarding priority corresponding to the user, that is, the network demand of the application program with higher priority is preferentially met. Among them, the priority of the application program can be based on different application presets. For example, the priority of a payment application is higher than that of a video application, etc.

[0087] In some embodiments, the traffic demand degree of each user can be determined based on the priority of the service quality parameter. For example, the higher the priority of the service quality parameter, the higher the traffic demand degree of the user.

[0088] In some embodiments of the present specification, the traffic demand degree of the user is determined based on the service quality parameter, which can preferentially meet the wireless network demand of the user who needs more traffic, thereby improving the quality of wireless network service while avoiding network congestion caused by throttling of high-priority users and / or applications.

[0089] Step 430, determining the wireless network demand degree in the target place based on the secondary wireless network demand degree in at least one target area.

[0090] In some embodiments, the wireless network demand degree in the target place can be determined based on the secondary wireless network demand degree in at least one target area in a variety of ways. For example, the wireless network demand degree in the target place can be the sum of the secondary wireless network demand degrees in the plurality of target areas. For another example, the wireless network demand degree in the target place can be a weighted sum of the secondary wireless network demand degrees in the plurality of target areas, etc.

[0091] In some embodiments of the present specification, determining the wireless network demand degree of the target region in the target site by the secondary wireless network demand degree of at least one target region can better meet the wireless network needs of different regions and different users, and improve user experience.

[0092] Figure 5 is an exemplary schematic diagram illustrating determination of at least one target region in a target site according to some embodiments of the present specification. In some embodiments, the flow 500 can be executed by the demand degree determination module 220. As shown in Figure 5 , the flow 500 includes the following steps.

[0093] Step 510: constructing a site feature map of the target site based on the site structure.

[0094] In some embodiments, the environmental features can further include the site structure of the target site. The site structure can refer to the spatial layout of the target site. The site structure of the target site can include at least one region in the target site. For example, when the target site is a shopping mall, the site structure thereof can refer to the spatial layout composed of regions such as entertainment area, restaurant, clothing store, etc.

[0095] The site feature map can reflect the regions in the target site and the connection relationship between the regions formed by the connecting channels. In some embodiments, the site feature map can include nodes and edges.

[0096] In some embodiments, the nodes of the site feature map can reflect the regions in the target site. As shown in Figure 5 , the site feature map 511 includes nodes a, b, c, d, e and f, etc. Among them, each node can represent a region in the target site. For example, in a shopping mall, node a represents a clothing store, node b represents a restaurant, etc.

[0097] The regions in the target site can refer to regions divided based on the layout or function of the target site, etc. For example, in a shopping mall, a floor can be divided into a region according to the layout of the shopping mall; a clothing store can be divided into a region, and a restaurant can be divided into a region according to the service types of the shopping mall facilities, etc.

[0098] In some embodiments, the node features can include the passenger flow and the passenger flow distribution of the region corresponding to the node. For example, the node features of node a can include that the passenger flow of the clothing store is 50 people / hour, and the passenger flow distribution is that young people account for 70% and middle-aged and old people account for 30%. In some embodiments, the node features can be obtained based on historical data, manual input, etc. any feasible way.

[0099] In some embodiments, the node features of the node can further include a transition probability vector.

[0100] The transition probability can refer to the probability of a user moving from a node to a neighboring node of the node. The neighboring node refers to a node with a degree of 1 to the node. For example, in the feature map 511, the neighboring nodes of the node b include the node a, the node c, and the node e. The transition probability can be represented by a fraction, a percentage, or other numerical forms. For example, the transition probability of a user moving from the node b to the node a is 20%, the transition probability of a user moving from the node b to the node c is 30%, and the transition probability of a user moving from the node b to the node e is 10%.

[0101] In some embodiments, the transition probability can be determined based on the flow movement in a preset time period. The preset time period can include a recent 10 minutes, a same time of yesterday, or other historical time periods. In some embodiments, the demand degree determination module 220 can determine the transition probability based on the flow movement in the preset time period. For example, a ratio of the number of people moving from a node to a neighboring node of the node in a preset time period to the number of people at the node at the beginning of the preset time period can be taken as the flow movement probability in the preset time period, and the flow movement probability can be taken as the transition probability. For another example, an average of the flow movement probabilities in multiple preset time periods can be taken as the transition probability.

[0102] The transition probability vector can refer to a vector composed of transition probabilities of moving from a node to neighboring nodes of the node. In some embodiments, the transition probability vector can be constructed as Each element in the transition probability vector can represent the probability of moving from the node to a neighboring node of the node. For example, in the previous example, the transition probability vector of the node b is

[0103] Taking the transition probability vector as the node feature of the node can more accurately and comprehensively describe the node feature, and facilitate subsequent prediction of the future traffic and flow distribution based on the node feature.

[0104] In some embodiments, the transition probability is related to the difference between the experience degrees between regions. For more information about the experience degree, please refer to Figure 4 The related content in step 420.

[0105] Based on the relationship between the transition probability and the difference between the experience degrees between regions, the tendency of the crowd to the experience degree can be associated with the transition probability, which is beneficial to scientifically and reasonably determining the transition probability, so that the transition probability is more in line with the actual situation of people connecting to wireless networks.

[0106] In some embodiments, the edges of the venue feature graph can represent the connecting passages between the regions. For example, in the venue feature graph 511, the edge connecting node a and node b can represent the connecting passage between the region corresponding to node a and the region corresponding to node b. For example, if node a represents a clothing store and node b represents a restaurant, the edge connecting node a and node b can represent the passage between the clothing store and the restaurant.

[0107] The connecting passage can refer to the actual passage connecting two regions in the target venue. For example, the passage connecting two regions can include a walking passage, a staircase, an elevator, etc.

[0108] In some embodiments, the edge feature can include the length of the connecting passage. For example, the edge connecting node a and node b can have a feature of 200 meters. In some embodiments, the edge feature can be obtained based on historical data, manual input, etc.

[0109] At step 520, based on the venue feature graph, the machine learning model is used to determine the crowd prediction value of each region at the future time.

[0110] The future time can refer to a time that has not occurred. For example, the future time can be one hour later, the same time tomorrow, etc.

[0111] The crowd prediction value can refer to the predicted crowd at the future time. For example, the crowd one hour later can be 80 people / hour, and the crowd at the same time tomorrow can be 50 people / hour.

[0112] In some embodiments, the demand determination module 220 can use the machine learning model to determine the crowd prediction value of each region at the future time based on the venue feature graph.

[0113] In some embodiments, the machine learning model can be a graph neural network model.

[0114] The input of the machine learning model can include the feature graph. The output of the machine learning model can include the crowd prediction value of each region at the future time.

[0115] In some embodiments, the demand determining module 220 can train the machine learning model based on the first training samples and the labels. Specifically, the first training samples with labels can be input into the machine learning model, and the parameters of the machine learning model can be updated through training. The first training samples can be the sample feature maps. The first training samples can be derived from historical data of the target site. For example, the first training samples can be derived from a historical feature map constructed based on historical passenger flow, historical passenger flow distribution, and historical transition probability vector of a certain historical moment of a region of the target site. The labels of the first training samples can be sample passenger flow prediction values of the regions. The labels can be derived from historical data of the regions. For example, the labels can be historical passenger flow of the regions at another historical moment after a certain historical moment. The labels can also be determined through manual labeling.

[0116] During the training process, a loss function can be constructed based on the labels and the output of the initial machine learning model, and the parameters of the machine learning model can be iteratively updated based on the loss function through gradient descent or other methods. When the second preset condition is met, the model training is completed, and a trained machine learning model is obtained. The second preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0117] By obtaining the passenger flow prediction values of the regions at the future moment through the machine learning model, the accuracy of determining the passenger flow prediction values of the regions at the future moment can be improved, and the calculation efficiency can be improved, and the error of manual prediction can be reduced.

[0118] At step 530, the regions with current passenger flow greater than a preset threshold and / or the regions with passenger flow prediction values greater than the preset threshold are determined as target regions.

[0119] The preset threshold can refer to a threshold of passenger flow. For example, the preset threshold can include a passenger flow of 80 people / hour. In some embodiments, the preset threshold can be manually preset. In some embodiments, the preset threshold can also be preset by the system. For example, the system can preset the threshold based on historical passenger flow.

[0120] In some embodiments, the demand determining module 220 can determine the target regions through various ways based on the preset threshold. For example, the regions with current passenger flow greater than the preset threshold can be determined as target regions. For another example, the regions with passenger flow prediction values greater than the preset threshold can be determined as target regions. For another example, the target regions can be determined based on the current passenger flow and the passenger flow prediction values. For example, the average of the current passenger flow and the passenger flow prediction values can be calculated, and the regions with average greater than the preset threshold can be determined as target regions.

[0121] Some embodiments of the present specification construct a feature map based on the site structure, determine the crowd prediction value of each area at the future moment based on the site feature map, and then determine the target area, which can improve the accuracy of determining the target area and make the adjustment of the wireless network parameters more targeted.

[0122] Figure 6 is an exemplary flowchart of determining the target adjustment value of the wireless network parameters according to some embodiments of the present specification. In some embodiments, the flow 600 can be executed by the target adjustment value determination module 230. As shown in the flow 600, the flow 600 includes the following steps. Figure 6

[0123] Step 610, generating at least one candidate adjustment value based on the wireless network demand degree.

[0124] The candidate adjustment value refers to a value that can be used to adjust the wireless network parameters. The candidate adjustment value can include a candidate adjustment value of the transmission parameter adjustment value and a candidate adjustment value of the quality of service parameter adjustment value. For example, the candidate adjustment value of the transmission parameter adjustment value can include adjusting the transmission power to 10 mW, adjusting the frequency band to 5 GHz, etc.; the candidate adjustment value of the quality of service parameter adjustment value can include adjusting the user with a longer total connection time to a higher priority, adjusting the traffic generated by the ongoing payment operation to a higher priority, etc.

[0125] In some embodiments, the target adjustment value determination module 230 can generate at least one candidate adjustment value based on the wireless network demand degree through a preset rule. The preset rule can refer to a rule for generating at least one candidate adjustment value. In some embodiments, the preset rule can include that the higher the connection demand degree, the candidate adjustment value of a different transmission parameter adjustment value is generated based on a certain step. Wherein, the higher the connection demand degree, the wider the step can be. In some embodiments, the preset rule can include that the higher the traffic demand degree, the candidate adjustment value of a different quality of service parameter adjustment value is generated based on a certain step. Wherein, the higher the traffic demand degree, the wider the step can be.

[0126] In some embodiments, the number of candidate adjustment values generated can be determined based on the wireless network demand degree, and the higher the wireless network demand degree, the more the number of candidate adjustment values. In some embodiments, the adjustment range of the candidate adjustment value can be determined based on the wireless network demand degree, and the higher the wireless network demand degree, the greater the adjustment range of the candidate adjustment value.

[0127] Step 620, calculating the evaluation value of each candidate adjustment value, and determining the target adjustment value from the at least one candidate adjustment value based on the evaluation value.

[0128] ​The evaluation value can refer to a value used to evaluate whether the candidate adjustment value meets the wireless network demand degree. The evaluation value can be represented by a specific numerical value. For example, the evaluation value is 70, 80, etc. The higher the evaluation value, the better the candidate adjustment value meets the wireless network demand degree.

[0129] In some embodiments, the evaluation value can be determined by weighted calculation based on the estimated number of connected people at the future time and the experience degree of the connected people at the future time.

[0130] The estimated number of connected people at the future time can refer to the number of people connected to the wireless network at the future time estimated by various feasible means.

[0131] In some embodiments, the estimated number of connected people at the future time can be determined based on a connected people prediction model.

[0132] The connected people prediction model can be used to determine the estimated number of connected people at the future time. In some embodiments, the connected people prediction model can be a machine learning model. For example, the connected people prediction model can include any one or combination of various feasible models such as a recurrent neural network model, a deep neural network model, a convolutional neural network model, etc.

[0133] The input of the connected people prediction model can include the wireless network signal strength of each target area at the current time, the wireless network signal strength of each target area adjusted based on the candidate adjustment value, the current number of connected people, the crowd flow and crowd distribution of each target area at the current time, the crowd flow and crowd distribution of each target area at the future time, etc. Among them, the wireless network signal strength of each target area at the current time can be determined in advance by software speed measurement, etc., the crowd flow and crowd distribution of each target area at the current time can be determined based on terminal quantity, image recognition, etc., and the crowd flow and crowd distribution of each target area at the future time can be determined based on a machine learning model. The output of the connected people prediction model can include the estimated number of connected people at the future time in the target place, or the estimated number of connected people at the future time in each target area.

[0134] In some embodiments, the target adjustment value determination module 230 can train the connected person number prediction model based on the second training sample and the label. The second training sample can include, for example, the wireless network signal strength of each target area at a certain historical time (t1), the wireless network signal strength of each target area after being adjusted based on the candidate adjustment value, the connected person number at t1, the people flow and people flow distribution of each target area at t1, the people flow and people flow distribution of each target area at another historical time (t2) after the certain historical time (t1), etc. The label of the second training sample can be the connected person number of each target area at t2, or the connected person number in the target place at t2. The second training sample and the label can be derived from historical data. Specifically, the second training sample can be derived from historical wireless network signal data, historical connected person number, historical people flow data, historical people flow distribution data, etc. at t1. The label can be derived from historical connected person number at t2.

[0135] During the training of the model, the target adjustment value determination module 230 can train the connected person number prediction model through various feasible training methods. For example, the training of the connected person number prediction model can refer to Figure 5 the training of a machine learning model.

[0136] By predicting the connected person number at the estimated future time through the connected person number prediction model, the determination of the connected person number at the future time can be more accurate, and the calculation efficiency can be improved, and the error of manual prediction can be reduced.

[0137] In some embodiments, the connected person number at the estimated future time can also be determined based on historical data. For example, the connected person number at the same time of the history (e.g., the same time of yesterday, the same time of a week ago), the average of the connected person numbers at multiple historical same times, etc. can be used as the connected person number at the estimated future time.

[0138] The connected person at the estimated future time refers to the person who has connected to the wireless network at the future time.

[0139] In some embodiments, the experience goodness of the connected person at the estimated future time can be determined based on an experience goodness prediction model.

[0140] The experience goodness prediction model is used to determine the experience goodness of the connected person at the estimated future time. In some embodiments, the experience goodness prediction model can be any feasible machine learning model.

[0141] The input of the experience goodness prediction model includes the number of connected people at the predicted future time, the wireless network parameters adjusted based on the candidate adjustment value, and the application usage features of the connected people. The application usage features of the connected people can refer to the terminal usage features of the connected people. For example, the application usage features of the connected people can include that among the 10 connected people, 8 people are browsing web pages, 1 person is watching a video, and 1 person is not using a mobile phone. The application features of the connected people can be obtained based on image recognition and various feasible manners. In some embodiments, the number of connected people at the predicted future time can be the number of connected people at the predicted future time in the target place, or the total number of connected people at the predicted future time in each target area; the application usage features of the connected people can be the application usage features of the connected people in the target place, or the application usage features of the connected people in each target area. The output of the experience goodness prediction model can include the experience goodness of the connected people at the predicted future time in the target place, or the experience goodness of the connected people at the predicted future time in each target area.

[0142] In some embodiments, the target adjustment value determination module 230 can train the experience goodness prediction model based on the third training sample and the label. The third training sample can include the number of connected people at a certain historical time (t3), the wireless network parameters adjusted based on the candidate adjustment value, and the application usage features of the connected people. The label of the third training sample can be the experience goodness of the connected people in the target place at time t3, or the experience goodness of the connected people in each target area at time t3. The third training sample and the label can be derived from historical data. Specifically, the third training sample can be derived from the historical number of connected people at time t3, the historical wireless network parameters, and the historical application usage features of the connected people. The label can be derived from the historical experience goodness of the connected people at time t3.

[0143] During the training of the model, the target adjustment value determination module 230 can train the experience goodness prediction model through various feasible training manners. For example, the training of the experience goodness prediction model can refer to Figure 5 the training of the machine learning model.

[0144] By predicting the experience goodness of the connected people at the predicted future time through the experience goodness prediction model, the determination of the experience goodness of the connected people at the predicted future time can be more accurate, and the calculation efficiency can be improved, and the error of manual prediction can be reduced.

[0145] In some embodiments, the estimated experience degree of the connected people at the future time can also be obtained based on historical data. For example, the experience degree of the connected people at the same time in the past (e.g., the same time yesterday, the same time a week ago), or the average of the experience degrees of the connected people at multiple historical same times can be used as the estimated experience degree of the connected people at the future time.

[0146] In some embodiments, the evaluation value can be determined based on weighted calculation. For example, the weighted formula can be D = K1*M + K2*N, where D represents the evaluation value, M represents the estimated number of connections at the future time, N represents the estimated experience degree of the connected people at the future time, K1 represents the weight of the estimated number of connections at the future time, and K2 represents the weight of the estimated experience degree of the connected people at the future time. For example, if the estimated number of connections at the future time is 20, the corresponding weight is 0.4, the estimated experience degree of the connected people at the future time is 80, and the corresponding weight is 0.6, then the evaluation value can be calculated to be 56.

[0147] Based on the estimated number of connections at the future time and the estimated experience degree of the connected people at the future time, the evaluation value is obtained by weighted calculation, which can make the calculation of the evaluation value more accurate, and thus a better adjustment value that meets the wireless network demand degree can be selected.

[0148] In some embodiments, the weights in the weighted calculation of the evaluation value are related to the transfer probability of the people in the target area staying in place.

[0149] If the transfer probability of the people staying in place is large, it indicates that the mobility of the people in the place is small, i.e., the number of connections in the target area changes little, and the estimated number of connections at the future time has little effect on the evaluation value. At this time, the weight value of the estimated experience degree of the connected people at the future time can be increased, and the weight of the estimated number of connections at the future time can be correspondingly reduced.

[0150] Considering the effect of the transfer probability of the people in the target area staying in place on the evaluation value, and then adjusting the weights in the weighted calculation, the evaluation value obtained by calculation can be more in line with the actual situation.

[0151] In some embodiments, the target adjustment value determination module 230 can determine the target adjustment value from the at least one candidate adjustment value based on the evaluation value. For example, the candidate adjustment value with the highest evaluation value can be determined as the target adjustment value. For another example, the candidate adjustment values can be sorted from large to small according to the evaluation values, and the candidate adjustment values with high rankings (e.g., the top three, the top 10%) can be provided to the user, and the user can select a candidate adjustment value from them as the target adjustment value.

[0152] According to some embodiments of the present specification, the at least one candidate adjustment value is generated based on the wireless network demand degree, and the target adjustment value is determined based on the evaluation value of each candidate adjustment value, so that the determination of the target adjustment value is more accurate, and the wireless network demand degree can be better satisfied.

[0153] The foregoing merely illustrates the principles of the application. It will thus be appreciated that those skilled in the art will be able to devise various arrangements which, although not explicitly described or shown herein, embody the principles of the application and are thus within its spirit and scope. For example, although the above-described system components can be implemented by hardware devices, they can also be implemented by software solutions, such as installing the described system on an existing server or mobile device.

[0154] In addition, the present specification uses specific terms to describe the embodiments of the present specification. As "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic in relation to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that "an embodiment" or "one embodiment" or "an alternative embodiment" mentioned in different places in the present specification does not necessarily mean the same embodiment. In addition, some features, structures, or characteristics in one or more embodiments of the present specification can be properly combined.

[0155] In addition, unless the claim explicitly states otherwise, the order of the processing elements and sequences, the use of numerical terms, or the use of other names in the present specification does not limit the order of the processes and methods of the present specification. Although some currently considered useful embodiments of the invention are discussed in the above disclosure through various examples, it should be understood that such details are only for the purpose of illustration, and the additional claims are not limited to the disclosed embodiments, but rather, the claims are intended to cover all modifications and equivalent combinations within the spirit and scope of the embodiments of the present specification. For example, although the above-described system components can be implemented by hardware devices, they can also be implemented by software solutions, such as installing the described system on an existing server or mobile device.

[0156] Similarly, it should be noted that, in order to simplify the expression of the present specification and to help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present specification, various features are sometimes combined into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the present specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiments disclosed above.

[0157] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0158] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0159] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for adjusting wireless network parameters, characterized in that, include: Obtain the current wireless network parameters of the wireless network in the target location and the environmental characteristics of the target location. The wireless network parameters refer to the transmission parameters of the wireless router device transmitting the wireless network. Based on the location structure in the environmental features, a location feature map of the target location is constructed. The location feature map includes nodes and edges. The nodes reflect the regions in the target location, and the edges reflect the connection channels between the regions. The features of the nodes include a transition probability vector, which is a vector composed of the transition probability of a user moving from a certain node to its neighboring nodes. The transition probability is also related to the difference in experience quality between regions. Based on the location feature map, a machine learning model is used to determine the predicted pedestrian flow for each area at future times; The areas where the current pedestrian flow is greater than a preset threshold and / or the areas where the predicted pedestrian flow is greater than the preset threshold are identified as target areas; Determine the secondary wireless network requirement level for each of the target areas; Based on the secondary wireless network demand within the target area, determine the wireless network demand within the target location; Based on the wireless network demand and the current wireless network parameters, the target adjustment value of the wireless network parameters is determined.

2. The wireless network parameter adjustment method as described in claim 1, characterized in that, The secondary wireless network demand also includes traffic demand, and the traffic demand in each target area is determined based on the population flow, population distribution, and regional characteristics within the target area.

3. The wireless network parameter adjustment method as described in claim 1, characterized in that, The step of determining the target adjustment value of the wireless network parameters based on the wireless network demand includes: At least one candidate adjustment value is generated based on the wireless network demand. Calculate an evaluation value for each of the candidate adjustment values, and determine a target adjustment value from the at least one candidate adjustment value based on the evaluation value.

4. The wireless network parameter adjustment method as described in claim 3, characterized in that, The evaluation value is determined by a weighted calculation based on the estimated number of connected users at future times and the estimated experience quality of already connected users at future times.

5. A wireless network parameter adjustment system, characterized in that, include: The acquisition module is used to acquire the current wireless network parameters of the wireless network in the target location and the environmental characteristics of the target location; The demand determination module is used for: Based on the location structure in the environmental features, a location feature map of the target location is constructed. The location feature map includes nodes and edges. The nodes reflect the regions in the target location, and the edges reflect the connection channels between the regions. The features of the nodes include a transition probability vector, which is a vector composed of the transition probability of a user moving from a certain node to its neighboring nodes. The transition probability is also related to the difference in experience quality between regions. Based on the location feature map, a machine learning model is used to determine the predicted pedestrian flow for each area at future times; The areas where the current pedestrian flow is greater than a preset threshold and / or the areas where the predicted pedestrian flow is greater than the preset threshold are identified as target areas; Determine the secondary wireless network requirement level for each of the target areas; Based on the secondary wireless network demand within the target area, determine the wireless network demand within the target location; The target adjustment value determination module is used to determine the target adjustment value of the wireless network parameters based on the wireless network demand and the current wireless network parameters.

6. A wireless network parameter adjustment device, comprising a processor, the processor being configured to execute the wireless network parameter adjustment method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the wireless network parameter adjustment method as described in any one of claims 1 to 4.

Images