Wireless network connection methods and systems

Abstract

This specification provides a method and system for connecting to a wireless network. The method includes: upon establishing a pre-connection with a target wireless network, receiving a login page from the target wireless network; extracting page features from the login page; comparing the page features with the features of each sample page in a pre-built sample page feature library to obtain the page confidence score of the login page. The sample page feature library is pre-constructed by extracting features from multiple sample pages. Based on the connection strategy corresponding to the page confidence score, the connection result with the target wireless network is determined. This multi-verification approach ensures data security. The use of detailed and flexible page features for comparison to determine the page confidence score guarantees accuracy and effectiveness of identification, reduces maintenance costs, and improves network connection flexibility and user experience by determining the network connection result based on the connection strategy corresponding to the page confidence score.

Description

Technical Field

[0001] This specification relates to the field of network connectivity technology, and in particular to a method for connecting a wireless network. Background Technology

[0002] With the development of wireless communication technology, wireless networks have been widely used in network data transmission due to their wide distribution, simple configuration, and low cost. However, by forging wireless network identifiers to induce users to establish network connections, data leakage can occur, leading to data security issues.

[0003] Currently, to ensure the security of wireless networks, a security list of access points (APs) is pre-established. This list records relevant information about the access points, such as Service Set Identifier (SSID) and Media Access Control Address (MAC address). When a device establishes a network connection, this information is compared to determine whether the target access point is on the security list, thus determining whether to disconnect the network connection.

[0004] However, due to the large number and frequent changes of wireless network access points, frequent updates and maintenance of the security list are necessary to ensure accuracy and effectiveness of identification. This results in excessive maintenance costs and an inability to establish network connections with secure access points not on the security list, leading to insufficient flexibility in security identification and a poor user experience. Therefore, there is an urgent need for an accurate, effective, highly secure, low-maintenance, and highly flexible wireless network connection method. Summary of the Invention

[0005] In view of this, embodiments of this specification provide a method for connecting a wireless network. One or more embodiments of this specification also relate to a wireless network connection system, a wireless network connection device, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0006] According to a first aspect of the embodiments of this specification, a method for connecting a wireless network is provided, comprising:

[0007] If a pre-connection is established with the target wireless network, the login page of the target wireless network is received;

[0008] Extract the page features of the login page;

[0009] The page features are compared with the features of each sample page in the pre-built sample page feature library to obtain the page confidence of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0010] Based on the connection strategy corresponding to the page confidence level, determine the connection result with the target wireless network.

[0011] According to a second aspect of the embodiments of this specification, a wireless network connection system is provided, the system including a client and a server, comprising:

[0012] The client is used to receive the login page of the target wireless network when a pre-connection is established with the target wireless network, extract the page features of the login page, and send the page features to the server.

[0013] The server receives page features, compares them with the features of each sample page in a pre-built sample page feature library, obtains the page confidence score of the login page, and feeds the page confidence score back to the client. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0014] The client is also used to receive page confidence scores and determine the connection result with the target wireless network based on the connection policy corresponding to the page confidence scores.

[0015] According to a third aspect of the embodiments of this specification, a wireless network connection device is provided, comprising:

[0016] The receiving module is configured to receive the login page of the target wireless network when a pre-connection is established with the target wireless network;

[0017] The extraction module is configured to extract the page features of the login page;

[0018] The comparison module is configured to compare the page features with the features of each sample page in a pre-built sample page feature library to obtain the page confidence of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0019] The determination module is configured to determine the connection result with the target wireless network based on the connection policy corresponding to the page confidence level.

[0020] According to a fourth aspect of the embodiments of this specification, a computing device is provided, comprising:

[0021] Memory and processor;

[0022] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the above-described wireless network connection method.

[0023] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the wireless network connection method described above.

[0024] According to a sixth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the wireless network connection method described above.

[0025] In one or more embodiments of this specification, when a pre-connection is established with a target wireless network, the login page of the target wireless network is received, page features of the login page are extracted, and the page features are compared with the features of each sample page in a pre-built sample page feature library to obtain the page confidence score of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages. Based on the connection strategy corresponding to the page confidence score, the connection result with the target wireless network is determined. This multi-verification approach ensures data security. After establishing a pre-connection, the page features of the login page are extracted and compared with the features of each sample page in the sample page feature library to determine the page confidence score. Utilizing page features—a more detailed and flexible identification information—ensures the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, reducing maintenance costs. The connection result with the target wireless network is determined based on the connection strategy corresponding to the page confidence score, improving network connection flexibility and enhancing user experience. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating a wireless network connection method provided in one embodiment of this specification;

[0027] Figure 2 This is a flowchart illustrating a wireless network connection method provided in one embodiment of this specification;

[0028] Figure 3 This is a front-end schematic diagram of a wireless network connection method provided in one embodiment of this specification;

[0029] Figure 4 This is a front-end schematic diagram of another wireless network connection method provided in one embodiment of this specification;

[0030] Figure 5 This is a flowchart illustrating the processing steps of a connection method applied to a public wireless network, as provided in one embodiment of this specification.

[0031] Figure 6 This is a schematic diagram of the structure of a wireless network connection system provided in one embodiment of this specification;

[0032] Figure 7 This is a schematic diagram of the structure of a wireless network connection device provided in one embodiment of this specification;

[0033] Figure 8 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0034] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0035] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a,” “described,” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0036] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0037] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0038] WiFi: A wireless local area network protocol based on the IEEE 802.11 standard, capable of transmitting high-fidelity data wirelessly, and is a type of wireless network.

[0039] Access Point: Also known as a wireless access point, it is a wireless switch used in wireless networks and is the core of a wireless network. It converts a wired network into a wireless network through wireless network transmitters, including but not limited to wireless routers, wireless gateways, and wireless bridges. To ensure the spatial distribution of the wireless network, a wireless network has multiple access points, each with a corresponding service set identifier and physical address. Each access point establishes a connection with its corresponding network access device to perform data transmission.

[0040] Spoofed WiFi: Spoofed WiFi is a data interception technique that uses fake WiFi networks set up in public places to lure users into connecting to the wireless network, thereby obtaining users' personal information, such as account details and passwords. Spoofed WiFi typically uses highly disguised service set identifiers to trick users into connecting.

[0041] Access data (cookies): Information data that is temporarily or permanently stored to identify a user.

[0042] IP address (Internet Protocol Address): An Internet Protocol address is a dynamically assigned logical address.

[0043] URL (Uniform Resource Locator) address: A uniform format address that includes the resource type, the host domain name where the resource is stored, and the resource file name.

[0044] TF-IDF (Term Frequency–Inverse Document Frequency) encoding is a commonly used weighted technique for information retrieval and data mining that uses statistical methods to encode the features of textual information.

[0045] Image hashing algorithms: Methods based on hash operations to encode features of image information, including average hashing algorithms and perceptual hashing algorithms.

[0046] Pearson similarity: The cosine of the angle between two vectors obtained by standardizing two encoded features.

[0047] Jaccard similarity: The ratio of the intersection to the union of two encoded features.

[0048] Currently, upon receiving a network access request from a device, a pre-connection is established with the device, and a login page is sent to the device. The user enters verification information on the device and sends it to the server to establish a target connection with the server, thereby enabling network data transmission.

[0049] This specification provides a method for connecting to a wireless network. It also relates to a wireless network connection system, a wireless network connection device, a computing device, a computer-readable storage medium, and a computer program, which will be described in detail in the following embodiments.

[0050] See Figure 1 , Figure 1A flowchart illustrating a wireless network connection method according to an embodiment of this specification is shown, including the following specific steps:

[0051] Step 102: After establishing a pre-connection with the target wireless network, receive the login page of the target wireless network.

[0052] The embodiments in this specification apply to the client or server of a monitoring tool with wireless network monitoring capabilities. The client is configured on a network-connected device with wireless network connectivity, such as a mobile phone, PC (Personal Computer), router, etc.

[0053] The target wireless network is the wireless network that the device selects to connect to, such as WiFi or other wireless local area networks. For example, after a user selects "Enable Wireless Local Area Network (WLAN)" on a mobile phone, several candidate wireless networks are displayed: "WiFi-1", "WiFi-3", and "WiFi-3". After the user selects the target wireless network "WiFi-1", a pre-connection is established with the target wireless network.

[0054] Pre-connection provides a restricted network connection to the target wireless network. After establishing a pre-connection with the target wireless network, the incoming device can only access the front-end content provided by the target wireless network, such as the login page and designated servers. Only after completing authentication can it further access the back-end content provided by the target wireless network.

[0055] The login page is an authentication page provided by the target wireless network. It includes verification information input boxes and login controls. The page information includes static information such as text, images, and elements, as well as behavioral information such as username, account, password, access data (cookies), IP address, URL address, and network fingerprint information.

[0056] Establish a pre-connection with the target wireless network, specifically by establishing a pre-connection with the target access point of the target wireless network.

[0057] To receive the login page of the target wireless network, specifically, receive the login page of the target wireless network sent by the target access point.

[0058] For example, the target wireless network is the WiFi network of an airport, the target access point of the target wireless network is the access point corresponding to Terminal 3 (SSID "Airport Terminal-3"), and the device accessing the network is the user's portable PC, which is configured with a monitoring tool Agent. The portable PC establishes a pre-connection with the target access point (Airport Terminal-3) and receives the WiFi network login page sent by the target access point (Airport Terminal-3).

[0059] Having established a pre-connection with the target wireless network, the login page of the target wireless network is received, laying the foundation for subsequent extraction of page features.

[0060] Step 104: Extract the page features of the login page.

[0061] Step 104 can be implemented on the client side, or it can be implemented by the client sending the received login page to the server side; there is no limitation on this.

[0062] Page features are the encoded features of the page information on the login page. A page feature is an encoded feature, that is, a uniform feature vector or feature sequence, ensuring comparison with other page features later. For example, if the page information is the text "Please enter your account and password to connect," its features can be encoded to obtain the corresponding encoded feature CodeTxtVector.

[0063] The page features of the login page are extracted through the following methods: Feature encoding is performed on the page information to obtain page features. For example, TF-IDF encoding is applied to the text information on the page; image hashing is used to hash the image information on the page; regularized feature extraction algorithms are used to extract strings from the behavioral information on the page; and a pre-trained neural network model is used to encode the page information to obtain the page features of the login page.

[0064] For example, the text information Txt, image information Image, and behavior information String of the login page are feature-encoded to obtain the page feature CodeVector.

[0065] The extracted page features of the login page laid the data foundation for subsequent comparison with the page features of other samples.

[0066] Step 106: Compare the page features with the features of each sample page in the pre-built sample page feature library to obtain the page confidence of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0067] Step 106 can be implemented on the client side, or the client can send the extracted page features to the server side; there is no limitation on this.

[0068] The sample page feature library is a pre-built prior database of page features, storing sample page features from multiple pre-extracted sample pages. The sample page feature library can be stored on the server or distributed from the server to the client; this is not limited here. The validity and accuracy of each sample page feature in the library are ensured by dynamically updating the sample page feature library.

[0069] The sample pages are login pages of sample wireless networks that have passed security checks. Security checks can be performed automatically using security testing tools or manually; this is not limited here. For example, after obtaining the login pages of the internal wireless networks of M organizations and the login pages of the public wireless networks of N public locations, network security engineers can perform security checks on them and then select the login pages of the m organizations' internal wireless networks and the n public locations' public wireless networks as sample pages. It should be noted that sample pages can be positive sample pages (login pages that have passed security checks) or negative sample pages (login pages that have failed security checks).

[0070] Sample page features are the encoded features of page information on a sample page. A sample page feature is a type of encoded feature, i.e., a uniform feature vector or feature sequence, which can be compared with page features. Sample page features can be either positive sample page features (i.e., the sample page features of a positive sample page) or negative sample page features (i.e., the sample page features of a negative sample page).

[0071] Page confidence score is a quantitative value that represents the confidence level of a login page's security.

[0072] The page confidence score of the login page is obtained by comparing the page features with the features of each sample page in a pre-built sample page feature library. Specifically, the page features are compared with the features of each sample page in the pre-built sample page feature library, and the comparison results are used to determine the page confidence score of the login page. For example, if the comparison results are 80% similar, 10% highly similar, and 10% inconsistent, then the page confidence score of the login page is determined to be 80%*1 + 10*0.5 + 10%*0 = 0.85. The comparison result is a quantitative result characterizing the correlation between page features.

[0073] Feature extraction is performed on multiple sample pages in the same way as step 104 above, and will not be repeated here.

[0074] For example, the page feature CodeVector is compared with each sample page feature SampleCodeVector_i (i∈[1,m+n]) in the pre-built sample page feature library CodeVectorTable to obtain the comparison result. Based on the comparison result, the page confidence level SafetyDegree of the login page is determined.

[0075] The page features are compared with the features of each sample page in the pre-built sample page feature library to obtain the page confidence score of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages. It utilizes the more detailed and flexible identification information of page features, which ensures the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs.

[0076] In one optional embodiment of this specification, the construction of the sample page feature library includes the following specific steps:

[0077] Get multiple sample pages;

[0078] Extract the page features of each sample page to construct a sample page feature library.

[0079] Multiple sample pages are obtained as follows: Multiple sample pages that have passed security checks are acquired, each labeled with a corresponding tag. For example, sample page 1 is the login page for an organization's internal wireless network; after security checks, sample page 1 is determined to be a positive sample page. Sample page 2 is the login page for an individual's personal wireless network; after security checks, sample page 2 is determined to be a negative sample page. The tags for sample page 1 are: organization, internal wireless network, positive; the tags for sample page 2 are: individual, personal wireless network, negative.

[0080] Extract page features from each sample page to construct a sample page feature library. Specifically, extract the page features of each sample page and construct the sample page feature library based on the tags of each sample page. For example, extract the page features CodeVector1 of sample page 1 and the page features CodeVector2 of sample page 2, store them according to their corresponding tags, and construct the corresponding sample page feature library (Organization – Internal Wireless Network – Positive Sample Page Features: CodeVector1…; Individual – Personal Wireless Network – Negative Sample Page Features: CodeVector2…).

[0081] For example, after obtaining the login pages of the internal wireless networks of M organizations and the login pages of the public wireless networks of N public places, the network security engineer performs security tests on them, filters out the login pages of the internal wireless networks of the m organizations and the login pages of the public wireless networks of the n public places, and obtains m+n sample pages. The page features SampleCodeVector_i (i∈[1,m+n]) of each sample page are extracted, and the sample page feature library CodeVectorTable is constructed according to the label Label_i (i∈[1,m+n]) of each sample page.

[0082] Multiple sample pages were acquired, and the page features of each sample page were extracted to construct a sample page feature library. This provided a priori feature foundation for subsequent comparison with page features to obtain the page confidence of the login page. By utilizing page features as a more detailed and flexible identification information, the accuracy and effectiveness of identification were ensured, while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs.

[0083] In one optional embodiment of this specification, obtaining multiple sample pages includes the following specific steps:

[0084] Retrieve multiple sample pages from the cloud.

[0085] The cloud platform utilizes virtualization and distributed storage technology to retrieve login pages from various wireless networks as sample pages. Different sample pages share data within the cloud, ensuring the sample pages have broader applicability.

[0086] Retrieving multiple sample pages from the cloud can be achieved by actively sending a sample retrieval request, such as a network security engineer sending a sample retrieval request to the cloud via a server. It can also be achieved by retrieving multiple sample pages from the cloud at a preset period, such as retrieving multiple sample pages from the cloud every day. Alternatively, multiple sample pages can be actively distributed to the cloud. The triggering conditions for active distribution can be the detection of an update to the login page of one or more wireless networks, the detection of the configuration of monitoring tools for one or more connected devices, or the detection of a version update of the monitoring tool. These conditions are not limited here.

[0087] For example, the login pages of the internal wireless networks of M organizations and the login pages of the public wireless networks of N public places are retrieved from the cloud three times a day at a preset frequency.

[0088] Retrieving multiple sample pages from the cloud enhances the broad applicability of the recognition, further ensuring its accuracy and effectiveness.

[0089] In one optional embodiment of this specification, the page features include static page features, the sample page features include static sample page features, and step 106 includes the following specific steps:

[0090] Calculate the feature similarity between the static features of a page and the static features of each sample page in a pre-built sample page feature library;

[0091] The page confidence level of the login page is determined based on feature similarity.

[0092] Since the front-end display of wireless network login pages generally follows certain design patterns—for example, including images, a mobile phone number input box, a verification code input box, or a personal information input box in the middle, and a connection control at the bottom—the static features of the login page provide a more detailed and flexible form of identification information compared to the massive amounts of information about access points. This information is used to determine the page's confidence level, further ensuring the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs.

[0093] Page static features are the encoded features of page information displayed on the front end of the login page. The page information displayed on the front end includes at least one of the following: text information, image information, etc. Correspondingly, page static features can be at least one of the following: page text features, page image features, etc.

[0094] The static features of the sample page are the encoded features of the page information displayed on the front-end of the sample page.

[0095] Feature similarity is the similarity of encoded features between static features of a page and static features of a sample page. For example, static features of a page are a feature vector, and static features of a sample page are a feature vector. The cosine similarity between the feature vectors is obtained by directly multiplying the two and dividing by their norms.

[0096] The method for calculating the feature similarity between the static features of a page and the static features of each sample page in a pre-built sample page feature library is as follows: A preset similarity calculation method is used to calculate the feature similarity between the static features of the page and the static features of each sample page in the pre-built sample page feature library. The similarity calculation method includes, but is not limited to, cosine similarity calculation and cross-entropy similarity calculation.

[0097] The confidence score of the login page can be determined based on feature similarity. This can be done by directly determining the feature similarity score as the confidence score of the login page, or by obtaining multiple feature similarities when the static features of the page include multiple features, and then performing a weighted calculation on the multiple feature similarities to obtain the confidence score of the login page. Alternatively, the maximum and minimum feature similarities can be determined by comparing the feature similarities of each feature, and no limitation is imposed here.

[0098] For example, the feature similarity between the page static feature CodeStaticVector and each sample page static feature SampleCodeStaticVector_i (i∈[1,m+n]) in the pre-built sample page feature library is calculated: the static feature similarity of the page with the maximum positive value is 0.6, and the static feature similarity of the page with the maximum negative value is 0.9. Based on 1-0.9=0.1, the page confidence SafetyDegree of the login page is determined to be 0.1.

[0099] The similarity between the static features of the login page and the static features of each sample page in the pre-built sample page feature library is calculated. Based on the feature similarity, the page confidence of the login page is determined. This method utilizes the more detailed and flexible identification information of static page features, which further ensures the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs.

[0100] In one optional embodiment of this specification, the page static features include page text features and page image features, and the sample page static features include sample page text features and sample page image features. Calculating the feature similarity between the page static features and each sample page static feature in a pre-built sample page feature library includes the following specific steps:

[0101] Calculate the text feature similarity between the page text features and the text feature similarity between the page text features and the text features of each sample page in the pre-built sample page feature library;

[0102] Calculate the image feature similarity between the page image features and the image feature features of each sample image in the sample page feature library;

[0103] The page confidence score of the login page is determined based on text feature similarity and image feature similarity.

[0104] Page text features are the encoded features of the page text information displayed on the front end of the login page. Page image features are the encoded features of the page image information displayed on the front end of the login page.

[0105] The sample page text features are the encoded features of the page text information displayed on the front end of the sample page. The sample page image features are the encoded features of the page image information displayed on the front end of the sample page.

[0106] Text feature similarity is the similarity of encoded features between page text features and sample page text features. Examples include cosine similarity, Pearson similarity, and Jaccard similarity. Image feature similarity is the similarity of encoded features between page image features and sample page image features, such as cross-entropy similarity.

[0107] The confidence level of the login page is determined based on text feature similarity and image feature similarity. Specifically, the text feature similarity and image feature similarity are weighted and calculated to determine the confidence level of the login page.

[0108] For example, the text feature similarity between the page text feature CodeTxtVector and each sample page text feature SampleCodeTxtVector_i (i∈[1,m+n]) in the pre-built sample page feature library is calculated: the text feature similarity with a certain positive sample text feature is the largest, which is 0.75. The image feature similarity between the page image feature CodeImageVector and each sample page image feature SampleCodeImageVector_i (i∈[1,m+n]) in the pre-built sample page feature library is calculated: the image feature similarity with a certain positive sample image feature is the largest, which is 0.92. The text feature similarity of 0.75 and the image feature similarity of 0.92 are weighted and calculated as 0.75*0.6+0.92*0.4=0.818, and the page confidence degree SafetyDegree of the login page is determined to be 0.818.

[0109] The method calculates the text features of the page and their similarity with the text features of each sample page in a pre-built sample page feature library. It also calculates the image features of the page and their similarity with the image features of each sample page in the sample page feature library. Based on the text feature similarity and image feature similarity, the page confidence of the login page is determined. This method utilizes more detailed and flexible recognition information such as page text features and page image features, which further ensures the accuracy and effectiveness of recognition while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs.

[0110] In one optional embodiment of this specification, the page features further include page behavior features, and the sample page features further include sample page behavior features. Before determining the page confidence of the login page based on feature similarity, the following specific steps are also included:

[0111] The page behavior features are compared with the behavior features of each sample page in the sample page feature library to obtain the behavior comparison results;

[0112] Correspondingly, based on feature similarity, the page confidence of the login page is determined, including the following specific steps:

[0113] Based on feature similarity and behavior comparison results, the page confidence level of the login page is determined.

[0114] Since behavioral information is generally highly correlated with the acquisition of identity information, it is necessary to combine static page features with textual features for identification and judgment to ensure data security. For example, if a secure sample page only requires a verification code, but the login page of a target wireless network requires the user's identity information and password, then there is a high risk, and the target wireless network is insecure.

[0115] Page behavior characteristics are the encoding characteristics of behavior information in the identifier information of the login page, such as the encoding characteristics of behavior information in HTML (Hyper Text Markup Language) and XML (Extensible Markup Language).

[0116] The behavioral characteristics of the sample page are the encoded characteristics of behavioral information in the identifier information of the sample page.

[0117] The behavior comparison result represents the consistency between behavioral features. For example, if the page features include identity information, password, and IP address, and the sample page features include verification code and IP address, then the comparison result is: 1 item matches, 2 items do not match, and 33% matches.

[0118] The confidence level of the login page is determined based on feature similarity and behavior comparison results. This can be done by weighted calculation, or by determining the confidence level of the login page based on feature similarity when the judgment conditions of behavior comparison results are met, or by determining the confidence level of the login page based on behavior comparison results when the feature similarity threshold is met. No restrictions are imposed here.

[0119] For example, the page behavior feature CodeStringVector is compared with the sample page behavior features SampleCodeStringVector_i (i∈[1,m+n]) in the sample page feature library CodeVectorTable. The behavior comparison result is 84% ​​consistent. Under the condition that the behavior comparison result is met (greater than or equal to 80%), the SafetyDegree of the login page is determined to be 0.818 based on the feature similarity of 0.818.

[0120] The page behavior features are compared with the behavior features of each sample page in the sample page feature library to obtain the behavior comparison results. Based on the feature similarity and behavior comparison results, the page confidence of the login page is determined. By utilizing the highly secure identification information of page behavior features, the accuracy and effectiveness of identification are further guaranteed, thus ensuring data security.

[0121] In one optional embodiment of this specification, step 106 includes the following specific steps:

[0122] The page features are sent to the server, which stores a pre-built sample page feature library.

[0123] The server receives the page confidence score of the login page, which is obtained by comparing the page features with the features of each sample page in the sample page feature library.

[0124] Since the computing power and storage capacity of the server are generally greater than those of the network access device where the client is located, the page features can be sent to the server, and the server can compare the page features with the sample page features in the sample page feature library to obtain the page confidence score of the login page, and then receive the page confidence score fed back by the server.

[0125] The page features are sent to the server, which stores a pre-built sample page feature library. The login page confidence score is received from the server. The page confidence score is obtained by comparing the page features with the sample page features in the sample page feature library, which improves the efficiency of recognition and reduces the hardware cost requirements of the client.

[0126] Step 108: Determine the connection result with the target wireless network based on the connection strategy corresponding to the page confidence level.

[0127] The connection policy is a pre-configured wireless network connection policy. The configuration of the connection policy depends on the actual application requirements for data security on the network access device. For example, if the network access device has a high data security level, wireless networks with lower page confidence levels will directly disconnect the pre-connection; if the network access device has a low data security level, a connection confirmation request will be sent to the front end, allowing the user to choose to disconnect the pre-connection or continue to establish the target connection. Alternatively, if the data security level is high and information related to spoofed wireless networks is identified, it will be intercepted.

[0128] The connection result with the target wireless network refers to the network connection result between the access device and the target wireless network, including: maintaining the pre-connection but not continuing to establish the target connection, disconnecting the pre-connection, and establishing the target connection.

[0129] Based on the connection policy corresponding to the page confidence level, determine the connection result with the target wireless network. Specifically, determine the connection result between the target access point of the target wireless network based on the connection policy corresponding to the page confidence level.

[0130] For example, based on the connection strategy 1 (establish target connection) corresponding to the page confidence level SafetyDegree (0.818), a target connection is established with the access point (Airport Terminal-3) corresponding to Terminal 3, so as to realize network data transmission through the airport's WiFi network.

[0131] Based on the connection strategy corresponding to the page confidence level, the connection result with the target wireless network is determined, which improves the flexibility of network connection and enhances the user experience.

[0132] In one optional embodiment of this specification, step 108 includes the following specific steps:

[0133] When the page confidence level reaches the preset page confidence level threshold, a target connection is established with the target wireless network.

[0134] The preset page confidence level is a pre-defined threshold for judging page confidence, which represents the security of the login page of the wireless network.

[0135] The target connection is an unrestricted network connection provided by the target wireless network. After authenticating by entering verification information on the login page, users can access the back-end content provided by the target wireless network, such as various network servers and encrypted databases.

[0136] If the page confidence level reaches a preset page confidence threshold, a target connection is established with the target wireless network. Specifically, if the page confidence level reaches the preset page confidence threshold, a target connection is established with the target access point of the target wireless network. Furthermore, if the page confidence level reaches the preset page confidence threshold, verification information is sent to the target access point of the target wireless network, and a target connection is established with the target access point.

[0137] For example, when the page confidence level SafetyDegree (0.818) reaches the preset page confidence level threshold (0.8), the verification information (verification code "XXXX") is sent to the access point (Airport Terminal-3) corresponding to Terminal 3 to establish a target connection, so as to realize network data transmission through the airport's WiFi network.

[0138] When the page confidence level reaches the preset page confidence level threshold, a target connection is established with the target wireless network, thus confirming the security of the wireless network and ensuring data security.

[0139] In one optional embodiment of this specification, step 108 includes the following specific steps:

[0140] If the page confidence level does not reach the preset page confidence level threshold, disconnect the pre-connection with the target wireless network.

[0141] The connection strategies corresponding to the embodiments in this specification are applicable to application scenarios with high data security levels on network access devices. By promptly disconnecting pre-connections, data security is ensured.

[0142] If the page confidence level does not reach the preset page confidence level threshold, disconnect the pre-connection with the target wireless network. Specifically, disconnect the pre-connection with the target access point of the target wireless network if the page confidence level does not reach the preset page confidence level threshold.

[0143] For example, if the page confidence level SafetyDegree (0.1) does not reach the preset page confidence level threshold (0.8), the pre-connection between the portable PC and the access point (Airport Terminal-3) corresponding to Terminal 3 is disconnected.

[0144] If the page confidence level does not reach the preset page confidence level threshold, the pre-connection with the target wireless network is disconnected, thus confirming the security of the wireless network and ensuring data security by disconnecting the pre-connection in a timely manner.

[0145] In one optional embodiment of this specification, step 108 includes the following specific steps:

[0146] If the page confidence level does not reach the preset page confidence threshold, a connection confirmation request is sent to the front end;

[0147] Upon receiving a connection confirmation instruction from the front end, establish a target connection with the target wireless network;

[0148] Upon receiving a connection termination command from the front end, disconnect the pre-connection with the target wireless network.

[0149] The connection strategies described in this specification are applicable to application scenarios where the data security level on the network access device is low. By sending a connection confirmation request to the front end, and based on the connection instructions from the front end, the pre-connection can be disconnected or the target connection can be re-established, further improving the flexibility of network connections and enhancing the user experience. For example, a user may want to establish a network connection with their home wireless network. However, since this wireless network may not be in the sample page's feature database, directly disconnecting would prevent the network connection from being established. Therefore, a connection confirmation request can be sent first, allowing the user to confirm the connection on the front end and establish the network connection.

[0150] The front end refers to the front end of the network access device.

[0151] The connection confirmation request is a network connection confirmation request instruction generated by the client. It can be displayed directly on the front end, or it can carry confirmation text information, such as "The wireless network you are connecting to has a risk, do you want to continue connecting?", or it can carry front end display style information, so that the front end generates a confirmation pop-up window based on the confirmation text information and the front end display style information. There is no limitation here.

[0152] The connection confirmation command is a network connection confirmation command fed back by the front end. It can be generated by clicking the confirmation control in the confirmation pop-up window displayed on the front end, or it can be obtained directly by the user from the front end. There is no limitation here.

[0153] The connection termination command is a network connection termination command fed back by the front end. It can be generated by clicking the termination control in the confirmation pop-up window displayed on the front end, or it can be obtained directly by the user from the front end. There is no limitation here.

[0154] The specific methods for establishing a target connection with the target wireless network have been described in detail in the above embodiments and will not be repeated here. The specific methods for disconnecting the pre-connection with the target wireless network have been described in detail in the above embodiments and will not be repeated here.

[0155] For example, if the page confidence level SafetyDegree (0.1) does not reach the preset page confidence level threshold (0.8), a connection confirmation request is sent to the front end of the portable PC for display. If the connection confirmation instruction is received from the front end of the portable PC, verification information (verification code "XXXX") is sent to the access point (AirportTerminal-3) corresponding to Terminal 3 to establish a target connection. If the connection termination instruction is received from the front end of the portable PC, the pre-connection between the portable PC and the access point (Airport Terminal-3) corresponding to Terminal 3 is disconnected.

[0156] If the page confidence level does not reach the preset page confidence level threshold, a connection confirmation request is sent to the front end. Upon receiving the connection confirmation instruction from the front end, a target connection is established with the target wireless network. Upon receiving the connection termination instruction from the front end, the pre-connection with the target wireless network is disconnected, further improving the flexibility of network connection and enhancing the user experience.

[0157] In one optional embodiment of this specification, step 108 includes the following specific steps:

[0158] If the page confidence level does not reach the preset page confidence level threshold, a preset reverse interception strategy is executed against the target wireless network.

[0159] Reverse interception strategies are data interception strategies used to further obtain the identity information of a target wireless network. These include reverse attack strategies and honeypot strategies. For example, honeypot data can be used to prevent the target wireless network from obtaining its identity information. Then, analytical tools can be used to analyze the behavioral data of the target wireless network to determine its identity.

[0160] If the page confidence level does not reach the preset page confidence level threshold, a preset reverse interception strategy is executed against the target wireless network to further ensure data security.

[0161] In the embodiments of this specification, when a pre-connection is established with a target wireless network, the login page of the target wireless network is received, page features of the login page are extracted, and the page features are compared with the features of each sample page in a pre-built sample page feature library to obtain the page confidence score of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages. Based on the connection strategy corresponding to the page confidence score, the connection result with the target wireless network is determined. This multi-verification approach ensures data security. After establishing a pre-connection, the page features of the login page are extracted and compared with the features of each sample page in the sample page feature library to determine the page confidence score. Utilizing page features—a more detailed and flexible identification information—ensures the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, reducing maintenance costs. The connection result with the target wireless network is determined based on the connection strategy corresponding to the page confidence score, improving the flexibility of network connection and enhancing the user experience.

[0162] Figure 2 A flowchart illustrating a wireless network connection method according to an embodiment of this specification is shown, such as... Figure 2 As shown, the client is equipped with a monitoring tool to monitor the security of the wireless network connected to the client. There is a data link between the server and the client of the monitoring tool.

[0163] The server retrieves sample pages from the cloud at a preset frequency and updates the sample page feature library. When the client establishes a pre-connection with the target wireless network, the target wireless network returns a login page to the client. The client extracts the page features of the login page and sends these features to the server. The server compares the page features with the features of each sample page in the pre-built sample page feature library to obtain the page confidence score of the login page, and then feeds the page confidence score back to the client. The client determines the connection result with the target wireless network based on the connection strategy corresponding to the page confidence score.

[0164] Figure 3This specification illustrates a front-end schematic diagram of a wireless network connection method according to an embodiment of the present specification, as shown below. Figure 3 As shown:

[0165] After establishing a pre-connection with the target wireless network, the login page of the target wireless network is received and displayed on the front end. The login page includes a mobile phone number input box, a verification code input box, a verification code receiving control, and an internet connection control. The user first enters their mobile phone number "1XXXXXXXXX" in the mobile phone number input box, clicks the verification code receiving control, and receives the verification code sent by the target wireless network provider to the mobile terminal corresponding to the user's mobile phone number. After the user enters the verification code "XXXX" on the front end, they click the internet connection control to establish a target connection with the target wireless network.

[0166] Figure 4 This specification illustrates a front-end schematic diagram of another wireless network connection method provided in one embodiment, as shown below. Figure 4 As shown:

[0167] Through the above Figure 1 In steps 102 to 106 of the embodiment, after obtaining the page confidence level of the login page, if the page confidence level does not reach the preset page confidence level threshold, a connection confirmation request is sent to the front end. Based on the connection confirmation request, a connection confirmation pop-up window is generated on the front end. The connection confirmation pop-up window contains the confirmation text message "The wireless network you are connecting to has a risk, do you want to continue connecting?", and also includes a confirmation control ("Yes") and a termination control ("No"). If the user clicks the confirmation control, the front end provides a connection confirmation instruction, establishing a target connection with the target wireless network; if the user clicks the termination control, the front end provides a connection confirmation instruction, disconnecting the pre-connection with the target wireless network.

[0168] The following is in conjunction with the appendix Figure 5 Taking the wireless network connection method provided in this specification as an example of its application in a public wireless network, the connection method of the wireless network will be further explained. Among other things, Figure 5 This specification illustrates a flowchart of a connection method for a public wireless network according to an embodiment of the present invention, including the following specific steps:

[0169] Step 502: Establish a pre-connection with the public wireless network.

[0170] The embodiments in this specification apply to the client side of a monitoring tool installed on a portable telephone.

[0171] Step 504: Receive the login page for the public wireless network.

[0172] Step 506: Extract the page text features, page image features, and page behavior features of the login page.

[0173] Step 508: Calculate the text feature similarity between the page text features and the text feature similarity between the page text features and the text features of each sample page in the pre-built sample page feature library.

[0174] The sample page feature library is constructed by pre-extracting text features, image features, and behavioral features from multiple sample pages.

[0175] Step 510: Calculate the image feature similarity between the page image features and the image feature similarity between them and the image features of each sample image in the sample page feature library.

[0176] Step 512: Compare the page behavior features with the behavior features of each sample page in the sample page feature library to obtain the behavior comparison results.

[0177] Step 514: Determine the page confidence level of the login page based on the text feature similarity, image feature similarity, and behavior comparison results.

[0178] Step 516: When the page confidence level reaches the preset page confidence level threshold, establish a target connection with the public wireless network.

[0179] Step 518: If the page confidence level does not reach the preset page confidence level threshold, send a connection confirmation request to the front end.

[0180] Step 520: Upon receiving a connection confirmation instruction from the front end, establish a target connection with the public wireless network.

[0181] Step 522: Upon receiving a connection termination instruction from the front end, disconnect the pre-connection to the public wireless network.

[0182] In the embodiments of this specification, data security is ensured through multiple verification methods. After establishing a pre-connection, the page features of the login page are extracted and compared with the page features of each sample page in the sample page feature library to determine the page confidence level of the login page. By utilizing page features, a more detailed and flexible identification information, the accuracy and effectiveness of identification are ensured, while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs. Based on the connection strategy corresponding to the page confidence level, the connection result with the public wireless network is determined, improving the flexibility of network connection and enhancing the user experience.

[0183] It should be noted that the information and data, such as login pages and sample pages, involved in the above method embodiments are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0184] Corresponding to the above method embodiments, this specification also provides embodiments of wireless network connection systems. Figure 6 A schematic diagram of a wireless network connection system according to one embodiment of this specification is shown. Figure 6 As shown, the system includes client 602 and server 604, specifically:

[0185] Client 602 is used to receive the login page of the target wireless network when a pre-connection is established with the target wireless network, extract the page features of the login page, and send the page features to server 604.

[0186] The server 604 is used to receive page features, compare the page features with the features of each sample page in the pre-built sample page feature library, obtain the page confidence of the login page, and feed back the page confidence to the client 602. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0187] Client 602 is also used to receive page confidence and determine the connection result with the target wireless network based on the connection policy corresponding to the page confidence.

[0188] In the embodiments of this specification, the wireless network connection system includes a client and a server. The client, upon establishing a pre-connection with the target wireless network, receives the login page of the target wireless network, extracts the page features of the login page, and sends the page features to the server. The server receives the page features, compares them with the features of each sample page in a pre-built sample page feature library, obtains the page confidence score of the login page, and feeds back the page confidence score to the client. The sample page feature library is pre-constructed by extracting features from multiple sample pages. The client also receives the page confidence score and determines the connection result with the target wireless network based on the connection strategy corresponding to the page confidence score. Data security is ensured through multiple verification methods. After establishing a pre-connection, the page features of the login page are extracted and compared with the features of each sample page in the sample page feature library to determine the page confidence level of the login page. By utilizing page features, a more detailed and flexible identification information, the accuracy and effectiveness of identification are guaranteed, while avoiding frequent updates and maintenance of the security list, thus reducing maintenance costs. Based on the connection strategy corresponding to the page confidence level, the connection result with the target wireless network is determined, improving the flexibility of network connection and enhancing the user experience.

[0189] The above is an illustrative scheme of a wireless network connection system according to this embodiment. It should be noted that the technical solution of this wireless network connection system and the technical solution of the aforementioned wireless network connection method belong to the same concept. Details not described in detail in the technical solution of the wireless network connection system can be found in the description of the technical solution of the aforementioned wireless network connection method.

[0190] Corresponding to the above method embodiments, this specification also provides embodiments of wireless network connection devices. Figure 7 A schematic diagram of a wireless network connection device according to one embodiment of this specification is shown. Figure 7 As shown, the device includes:

[0191] The receiving module 702 is configured to receive the login page of the target wireless network when a pre-connection is established with the target wireless network;

[0192] Extraction module 704 is configured to extract the page features of the login page;

[0193] The comparison module 706 is configured to compare the page features with the features of each sample page in a pre-built sample page feature library to obtain the page confidence of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages.

[0194] The determination module 708 is configured to determine the connection result with the target wireless network based on the connection policy corresponding to the page confidence level.

[0195] Optionally, page features include static page features, and sample page features include static sample page features;

[0196] Correspondingly, the comparison module 706 is further configured as follows:

[0197] Calculate the feature similarity between the static features of the login page and the static features of each sample page in the pre-built sample page feature library; determine the page confidence score of the login page based on the feature similarity.

[0198] Optionally, the static features of the page include page text features and page image features, and the static features of the sample page include sample page text features and sample page image features;

[0199] Correspondingly, the comparison module 706 is further configured as follows:

[0200] Calculate the text features of the page and their similarity to the text features of each sample page in the pre-built sample page feature library; calculate the image features of the page and their similarity to the image features of each sample page in the sample page feature library; determine the page confidence of the login page based on the text feature similarity and the image feature similarity.

[0201] Optionally, page features may also include page behavior features, and sample page features may also include sample page behavior features;

[0202] Correspondingly, the device also includes:

[0203] The behavior comparison module is configured to compare the page behavior features with the behavior features of each sample page in the sample page feature library to obtain the behavior comparison results.

[0204] Correspondingly, the comparison module 706 is further configured as follows:

[0205] Based on feature similarity and behavior comparison results, the page confidence level of the login page is determined.

[0206] Optionally, the comparison module 706 is further configured as follows:

[0207] The page features are sent to the server, which stores a pre-built sample page feature library; the page confidence score of the login page is received from the server, which is obtained by the server comparing the page features with the sample page features in the sample page feature library.

[0208] Optionally, the determination module 708 is further configured as follows:

[0209] When the page confidence level reaches the preset page confidence level threshold, a target connection is established with the target wireless network.

[0210] Optionally, the determination module 708 is further configured as follows:

[0211] If the page confidence level does not reach the preset page confidence level threshold, disconnect the pre-connection with the target wireless network.

[0212] Optionally, the determination module 708 is further configured as follows:

[0213] If the page confidence level does not reach the preset page confidence level threshold, a connection confirmation request is sent to the front end; if a connection confirmation instruction is received from the front end, a target connection is established with the target wireless network; if a connection termination instruction is received from the front end, the pre-connection with the target wireless network is disconnected.

[0214] Optionally, the determination module 708 is further configured as follows:

[0215] If the page confidence level does not reach the preset page confidence level threshold, a preset reverse interception strategy is executed against the target wireless network.

[0216] Optionally, the device further includes:

[0217] The module is configured to acquire multiple sample pages; extract the page features of each sample page; and construct a sample page feature library.

[0218] Optionally, the building module is further configured as follows:

[0219] Retrieve multiple sample pages from the cloud.

[0220] In the embodiments of this specification, when a pre-connection is established with a target wireless network, the login page of the target wireless network is received, page features of the login page are extracted, and the page features are compared with the features of each sample page in a pre-built sample page feature library to obtain the page confidence score of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages. Based on the connection strategy corresponding to the page confidence score, the connection result with the target wireless network is determined. This multi-verification approach ensures data security. After establishing a pre-connection, the page features of the login page are extracted and compared with the features of each sample page in the sample page feature library to determine the page confidence score. Utilizing page features—a more detailed and flexible identification information—ensures the accuracy and effectiveness of identification while avoiding frequent updates and maintenance of the security list, reducing maintenance costs. The connection result with the target wireless network is determined based on the connection strategy corresponding to the page confidence score, improving the flexibility of network connection and enhancing the user experience.

[0221] The above is a schematic scheme of a wireless network connection device according to this embodiment. It should be noted that the technical solution of this wireless network connection device and the technical solution of the wireless network connection method described above belong to the same concept. For details not described in detail in the technical solution of the wireless network connection device, please refer to the description of the technical solution of the wireless network connection method described above.

[0222] Figure 8 This specification illustrates a structural block diagram of a computing device according to one embodiment. The components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0223] The computing device 800 also includes an access device 840, which enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include PSTN (Public Switched Telephone Network), LAN (Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), or combinations of communication networks such as the Internet. The access device 840 may include one or more of any type of wired or wireless network interface (e.g., NIC (Network Interface Controller)), such as an IEEE 802.12 WLAN (Wireless Local Area Networks) wireless interface, Wi-MAX (World Interoperability for Microwave Access) interface, Ethernet interface, USB (Universal Serial Bus) interface, cellular network interface, Bluetooth interface, NFC (Near Field Communication) interface, and so on.

[0224] In one embodiment of this specification, the above-described components of the computing device 800 and Figure 8 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 8 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0225] The computing device 800 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs (Personal Computers). The computing device 800 can also be a mobile or stationary server.

[0226] The processor 820 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-described wireless network connection method.

[0227] The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the wireless network connection method described above belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the wireless network connection method described above.

[0228] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the wireless network connection method described above.

[0229] The above is an illustrative embodiment of a computer-readable storage medium. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the wireless network connection method described above. Details not described in detail in the technical solution of the storage medium can be found in the description of the technical solution of the wireless network connection method described above.

[0230] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described wireless network connection method.

[0231] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the above-described wireless network connection method belong to the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-described wireless network connection method.

[0232] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0233] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0234] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0235] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0236] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A method for connecting a wireless network, comprising: If a pre-connection is established with the target wireless network, the login page of the target wireless network is received, wherein the pre-connection is a restricted network connection provided by the target wireless network; Extract the page features of the login page; The page features are compared with the features of each sample page in the pre-built sample page feature library to obtain the page confidence of the login page. The sample page feature library is constructed in advance by extracting features from multiple sample pages. The sample page feature library supports dynamic updates. The page features include page behavior features. Based on the connection policy corresponding to the page confidence level, the connection result with the target wireless network is determined, wherein the connection result includes: maintaining the pre-connection but not continuing to establish the target connection, or disconnecting the pre-connection or establishing the target connection.

2. The method according to claim 1, wherein the page features include static page features, and the sample page features include static sample page features; The step of comparing the page features with the sample page features in a pre-built sample page feature library to obtain the page confidence score of the login page includes: Calculate the feature similarity between the static features of the page and the static features of each sample page in the pre-built sample page feature library; Based on the feature similarity, the page confidence level of the login page is determined.

3. The method according to claim 2, wherein the page static features include page text features and page image features, and the sample page static features include sample page text features and sample page image features; The calculation of the feature similarity between the static features of the page and the static features of each sample page in the pre-built sample page feature library includes: Calculate the text feature similarity between the page text features and the text features of each sample page in the pre-built sample page feature library; Calculate the image feature similarity between the page image features and the image features of each sample image in the sample page feature library; The page confidence level of the login page is determined based on the text feature similarity and the image feature similarity.

4. The method according to claim 2 or 3, wherein the page features further include page behavior features, and the sample page features further include sample page behavior features; Before determining the page confidence score of the login page based on the feature similarity, the method further includes: The page behavior features are compared with the behavior features of each sample page in the sample page feature library to obtain the behavior comparison results; Determining the page confidence score of the login page based on the feature similarity includes: Based on the feature similarity and the behavior comparison results, the page confidence level of the login page is determined.

5. The method according to claim 1, wherein comparing the page features with each sample page feature in a pre-built sample page feature library to obtain the page confidence score of the login page includes: The page features are sent to the server, wherein the server stores a pre-built sample page feature library; The server receives the page confidence score of the login page, wherein the page confidence score is obtained by the server comparing the page features with the sample page features in the sample page feature library.

6. The method according to claim 1, wherein determining the connection result with the target wireless network based on the connection policy corresponding to the page confidence level includes: When the page confidence level reaches a preset page confidence level threshold, a target connection is established with the target wireless network.

7. The method according to claim 1, wherein determining the connection result with the target wireless network based on the connection policy corresponding to the page confidence level includes: If the page confidence level does not reach the preset page confidence level threshold, the pre-connection with the target wireless network is disconnected.

8. The method according to claim 1, wherein determining the connection result with the target wireless network based on the connection policy corresponding to the page confidence level includes: If the page confidence level does not reach the preset page confidence threshold, a connection confirmation request is sent to the front end; Upon receiving the connection confirmation instruction from the front end, a target connection is established with the target wireless network; Upon receiving the connection termination instruction from the front end, the pre-connection with the target wireless network is disconnected.

9. The method according to claim 1, wherein determining the connection result with the target wireless network based on the connection policy corresponding to the page confidence level includes: If the page confidence level does not reach the preset page confidence level threshold, a preset reverse interception strategy is executed against the target wireless network.

10. The method according to claim 1, wherein the construction of the sample page feature library comprises the following steps: Get multiple sample pages; Extract the page features of each sample page to construct a sample page feature library.

11. The method according to claim 10, wherein obtaining multiple sample pages includes: Retrieve multiple sample pages from the cloud.

12. A wireless network connection system, the system comprising a client and a server, including: The client is configured to receive the login page of the target wireless network when a pre-connection is established with the target wireless network, extract the page features of the login page, and send the page features to the server, wherein the pre-connection is a restricted network connection provided by the target wireless network. The server is configured to receive the page features, compare the page features with each sample page feature in a pre-built sample page feature library to obtain the page confidence score of the login page, and feed back the page confidence score to the client. The sample page feature library is pre-built by extracting features from multiple sample pages and supports dynamic updates. The page features include page behavior features, and the sample page features include sample page behavior features. The client is further configured to receive the page confidence score and determine the connection result with the target wireless network according to the connection policy corresponding to the page confidence score. The connection result includes: maintaining the pre-connection but not continuing to establish the target connection, or disconnecting the pre-connection or establishing the target connection.

13. A computing device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the wireless network connection method according to any one of claims 1 to 11.

14. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the wireless network connection method according to any one of claims 1 to 11.

Images