A User Anti-Location Method and System Based on Content Generation and Delivery

Abstract

This invention provides a user anti-location method and system based on content generation and delivery, relating to the field of network security technology. The method crawls and cleans dynamically published datasets by users and assesses the risk of user location information leakage. Based on different dynamic delivery strategies corresponding to the assessment results, it generates and dynamically delivers interference data to disrupt user location information. This invention solves the technical problem in existing technologies where advanced location methods are difficult to effectively resist, leading to user information leakage. It effectively combats user location inference techniques based on generated text and more advanced location methods, thereby providing users with more comprehensive location privacy protection.

Description

Technical Field

[0001] This invention relates to the field of network security technology, and in particular to a user anti-location method and system based on content generation and delivery. Background Technology

[0002] With the rapid development of internet technology and the widespread adoption of smart devices, cyberspace has become an indispensable second space in people's lives. Especially driven by mobile internet technology, social media platforms have sprung up like mushrooms after rain, greatly facilitating people's communication and information access.

[0003] In these social media platforms, user geolocation information is a valuable data resource. However, the leakage of user geolocation information also poses a serious threat to user privacy.

[0004] Currently, user location inference technology based on social media has achieved certain research results. These technologies infer a user's frequent location by analyzing publicly available social media data, such as blog content and social relationships. Although social media platforms have taken certain measures to protect user privacy, it is difficult to effectively prevent such inference methods. Therefore, conducting research on user anti-location based on social media has extremely important application value and practical significance for protecting user location privacy, preventing illegal use, and improving the online user experience. In terms of existing technologies, anti-location techniques mainly focus on two aspects: anti-content location and anti-social relationship location. Existing anti-location strategies mainly include adding random noise or spoofing user identities to modify the social network structure. However, these methods are inadequate against some advanced location techniques. Some advanced location methods delve into location-related words in user blog posts and even combine them with images posted by users for comprehensive judgment. Therefore, simply modifying the social network structure is insufficient to effectively counter such location methods. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a user anti-location method and system based on content generation and delivery to solve the technical problem in the prior art where it is difficult to effectively resist advanced location methods, leading to the leakage of user information. The method includes:

[0006] By crawling and cleaning multiple user dynamic data, a user dataset is constructed, which includes each user's user ID, historical posts, and posting locations.

[0007] The risk of location information leakage for each user in the user dataset is assessed and classified into different levels to obtain the classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies.

[0008] The user dataset is input into a neural network model, and the output is a disturbance dataset. The disturbance dataset includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities.

[0009] According to the dynamic delivery strategy corresponding to each user in the division results, the predicted dynamic data in the interference dataset are dynamically delivered respectively.

[0010] Furthermore, based on the location information of each user's dynamic data in the user dataset, the location result, and the consistency between the location information and the location result, the risk of location information leakage for each user in the user dataset is assessed and classified, and the classification result is obtained.

[0011] Furthermore, the classification results include high-risk level, dangerous level, general level, and safe level.

[0012] Furthermore, according to the dynamic delivery strategy corresponding to each user in the partitioning results, the predicted dynamic data in the interference dataset are dynamically delivered respectively, which also includes:

[0013] If the classification result is high-risk, the following operations are performed on users classified to this level: modify the user's IP proxy to the first preset location, and deliver the user's predicted dynamic data at the first preset location until the user's location result is the first preset location;

[0014] If the classification result is a danger level, the following operations are performed on the user classified to this level: modify the user's IP proxy to the second preset location, and send the user's predicted dynamic data at the second preset location until the user's location result is the second preset location. The sent predicted dynamic data does not contain geographical information and the number of times it is sent is greater than the number of times the user actually sends dynamic data.

[0015] If the classification result is a general level, the following operation is performed on users classified to this level: send the user's predicted dynamic data at a third preset location until the user's location result is the third preset location.

[0016] Furthermore, the risk of leakage of location information of each user in the user dataset is assessed based on the PaQL content location algorithm.

[0017] Furthermore, when dynamically delivering the predicted dynamic data in the interference dataset, the preset location for dynamically delivering the predicted dynamic data to each user is determined based on the user's anti-location requirements.

[0018] Furthermore, after dynamically delivering the predicted dynamic data in the interference dataset, the anti-localization effect is detected on the results of the dynamic delivery.

[0019] A second aspect of this invention also provides a user anti-location system based on content generation and delivery, to solve the technical problem in the prior art where advanced location methods are difficult to effectively resist, leading to the leakage of user information. The system includes:

[0020] The user dataset construction module is used to construct a user dataset by crawling and cleaning multiple user dynamic data. The user dataset includes each user's user ID, historical posts, and posting locations.

[0021] The risk level classification module is used to assess and classify the risk of location information leakage of each user in the user dataset, and obtain the classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies.

[0022] The interference information output module is used to input the user dataset into the neural network model and output the interference dataset, which includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities.

[0023] The interference dynamic delivery module is used to dynamically deliver the predicted dynamic data in the interference dataset according to the dynamic delivery strategy corresponding to each user in the partitioning result.

[0024] A third aspect of the present invention also provides a computer-readable storage medium storing a computer program that performs any of the above-described user anti-location methods based on content generation and delivery.

[0025] A fourth aspect of the present invention also provides a computer-readable storage medium storing a computer program of any of the above-described user anti-location methods based on content generation and delivery.

[0026] Compared with the prior art, the beneficial effects that can be achieved by the above-mentioned at least one technical solution adopted in the embodiments of this specification include at least the following: the present invention generates dynamics that confuse user location information in different geographical locations, and formulates reasonable delivery strategies by analyzing the risk of user information leakage, thereby achieving the purpose of protecting user location information. The present invention can effectively counter user location inference technology based on generated text and more advanced positioning methods, and achieve the technical purpose of providing users with more comprehensive location privacy protection. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the user anti-location method based on content generation and delivery provided in an embodiment of the present invention;

[0029] Figure 2 This is a schematic diagram of the user location leakage risk level assessment process provided in an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram illustrating content delivery strategies for different risk levels provided in embodiments of the present invention;

[0031] Figure 4 This is a schematic diagram illustrating the distribution of user risk levels under the protection of the current location requirement provided in an embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram illustrating the anti-location effect under the requirement of protecting the current location, as provided in an embodiment of the present invention.

[0033] Figure 6 This is a schematic diagram illustrating the distribution of user risk levels under the protection of long-term location requirements, provided in an embodiment of the present invention.

[0034] Figure 7 This is a schematic diagram illustrating the anti-positioning effect under the long-term positioning requirement provided by an embodiment of the present invention;

[0035] Figure 8 This is a schematic diagram of the overall structure of the user anti-location system based on content generation and delivery provided in an embodiment of the present invention;

[0036] Figure 9 This is a schematic diagram of the computer device structure provided in an embodiment of the present invention;

[0037] The attached diagram is labeled as follows: 800, System; 801, User Dataset Construction Module; 802, Risk Level Classification Module; 803, Interference Information Output Module; 804, Interference Dynamic Delivery Module; 901, Memory; 902, Processor. Detailed Implementation

[0038] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0039] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] This invention generates dynamics that obfuscate user location information in different geographical locations and formulates reasonable delivery strategies by analyzing the risk of user information leakage, thereby achieving the goal of protecting user location information. This invention can effectively counter user location inference techniques based on generated text and more advanced positioning methods, and achieve the technical goal of providing users with more comprehensive location privacy protection.

[0041] according to Figure 1 As shown, the user anti-location method based on content generation and delivery in this embodiment specifically includes the following steps:

[0042] Step S100: By crawling and cleaning multiple user dynamic data, a user dataset is constructed. The user dataset includes each user's user ID, historical posts, and posting locations.

[0043] Specifically, in step S100, a dynamic user dataset containing user IDs, historical blog posts, and posting location information is constructed through data crawling and cleaning, providing basic data for this method.

[0044] Step S200: Assess and classify the risk of location information leakage for each user in the user dataset to obtain the classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies.

[0045] Preferably, in step S200, the risk of leakage of location information of each user in the user dataset is assessed based on the PaQL content location algorithm.

[0046] Furthermore, based on the location information of each user's dynamic data in the user dataset, the location result, and the consistency between the location information and the location result, the risk of leakage of each user's location information in the user dataset is assessed and classified into levels to obtain the classification result, which includes high-risk level, dangerous level, general level, and safe level.

[0047] Specifically, the PaQL content location algorithm is reproduced, and the risk of user location information leakage is assessed based on the PaQL content location algorithm and the user dataset in step S100, such as... Figure 2 As shown, users are divided into four risk levels based on whether they can be successfully located, whether the location information is available, and whether the two are consistent: high-risk level (level 1), dangerous level (level 2), normal level (level 3), and safe level (level 4).

[0048] Step S300: Input the user dataset into the neural network model and output the interference dataset. The interference dataset includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities.

[0049] Specifically, by studying the positioning mechanism of existing text-based location inference algorithms and the posting habits of users on social media platforms such as Weibo, a large artificial intelligence model is used to generate predictive dynamic data for each user in multiple cities to interfere with positioning, according to the requirements of effectiveness and simulation. A matching image is configured for each dynamic to interfere with text-based location inference technology.

[0050] Step S400: According to the dynamic delivery strategy corresponding to each user in the division result, dynamically deliver the predicted dynamic data in the interference dataset.

[0051] Furthermore, such as Figure 3 As shown, step S400 further includes:

[0052] Step S401: If the classification result is a high-risk level, perform the following operations on the user classified to this level: modify the user's IP proxy to the first preset location, and deliver the predicted dynamic data of the user in the first preset location until the user's location result is the first preset location;

[0053] Step S402: If the classification result is a danger level, perform the following operations on the user classified to this level: modify the user's IP proxy to the second preset location, and send the user's predicted dynamic data at the second preset location until the user's location result is the second preset location. The sent predicted dynamic data does not contain geographical information and the number of times it is sent is greater than the number of times the user actually sends dynamic data.

[0054] Step S403: If the classification result is a general level, perform the following operation on the user classified to this level: send the user's predicted dynamic data at the third preset location until the user's location result is the third preset location.

[0055] Furthermore, when dynamically delivering the predicted dynamic data in the interference dataset, the preset location for dynamically delivering the predicted dynamic data to each user is determined based on the user's anti-location requirements.

[0056] Specifically, users' anti-location requirements include protecting their current location and protecting their long-term location. Based on the dynamic delivery strategy corresponding to the user's location information leakage risk level in the classification results described in steps S401-S403, the predicted dynamic data for each user is dynamically delivered using the interference dataset generated in step S300, and the anti-location effect is detected on the delivered results.

[0057] Example 1

[0058] Step 1: Construct a user blog post dataset:

[0059] Dynamic data was crawled and cleaned from user data on social media platforms to construct a user dataset containing user ID, historical posts, and posting locations. This dataset provides basic data for research on anti-location techniques. In this first embodiment, Weibo is used as an example, and the statistical user data is shown in Table 1 below.

[0060] Table 1: User Data Statistics

[0061]

[0062]

[0063] Step 2: Construct a user blog post dataset:

[0064] The PaQL content location algorithm is reproduced. Based on the requirement to protect the user's recent location, the user is located using the five most recent blog posts from the user dataset obtained in step 1. The location is then compared with the posting location information in the user's blog posts. Figure 2 The process shown divides users in the user dataset into four risk levels. The risk level distribution of users under the requirement of protecting their current location is as follows: Figure 4 As shown.

[0065] Step 3: Generating location-disrupting blog posts:

[0066] By studying the positioning mechanism of existing text-based location inference algorithms and the posting habits of users on social media platforms such as Weibo, this study uses a large-scale artificial intelligence model to generate interference data for blog posts related to provincial capital cities, based on the requirements of effectiveness and simulation. Matching images were then assigned to each interference post to disrupt text-based location inference technology. Specifically, 400 interference posts were generated for each of 30 provincial capital cities, and images were paired with them.

[0067] Step 4: Content delivery strategy formulation:

[0068] Based on the user risk level classification results in step 2, according to Figure 3 Different dynamic delivery strategies are adopted for different users. Location-interference blog posts generated in step 3 are used for dynamic delivery, and the anti-location effectiveness is tested on the delivery results. The final anti-location effectiveness test results are as follows: Figure 5 As shown.

[0069] Example 2

[0070] Step 1: Construct a user blog post dataset:

[0071] We crawled and cleaned user blog post data from domestic microblogging platforms, and constructed a user dataset containing user IDs, historical blog posts, and posting location information. This dataset provides basic data for research on anti-location techniques, and the results are the same as in Example 1.

[0072] Step 2, Risk Assessment of User Location Information Leakage:

[0073] The PaQL content location algorithm is reproduced. Based on the need to protect the user's long-term location, all blog post data in the user dataset obtained in step 1 of this embodiment is used to locate the user. The location results are then compared with the posting location information in the user's blog post data. Figure 2 The process categorizes users into four risk levels, and the risk level distribution for users with long-term location protection needs is as follows: Figure 6 As shown.

[0074] Step 3: Generating location-disrupting blog posts:

[0075] By studying the positioning mechanism of existing text-based location inference algorithms and the posting habits of users on social media platforms such as Weibo, a large artificial intelligence model was used to generate interference data related to provincial capitals according to the requirements of effectiveness and simulation. Matching images were dynamically configured for the predicted interference to interfere with text-based location inference technology. The results are the same as in Example 1.

[0076] Step 4: Content delivery strategy formulation:

[0077] Based on the result of determining the user's risk level in step 2, according to... Figure 3 Different content delivery strategies are adopted for different users. The interference data generated in step 3 is used for dynamic delivery, and the anti-location effect is tested on the delivery results. The final detected anti-location effect is as follows: Figure 7 As shown.

[0078] In summary, the present invention achieves the following technical effects through the above embodiments:

[0079] This invention generates dynamics that obfuscate user location information in different geographical locations and formulates reasonable delivery strategies by analyzing the risk of user information leakage, thereby achieving the goal of protecting user location information. This invention can effectively counter user location inference techniques based on generated text and more advanced positioning methods, and achieve the technical goal of providing users with more comprehensive location privacy protection.

[0080] Based on the same inventive concept, this invention also provides user anti-location based on content generation and delivery, as described in the following embodiments. Since the principle of solving the problem of user anti-location based on content generation and delivery is similar to that of the user anti-location method based on content generation and delivery, the implementation of the user anti-location system based on content generation and delivery can refer to the implementation of the user anti-location method based on content generation and delivery; repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0081] Figure 8 This is a structural block diagram of a user anti-location system 800 based on content generation and delivery according to an embodiment of the present invention, such as... Figure 8 As shown, it includes:

[0082] The user dataset construction module 801 is used to construct a user dataset by crawling and cleaning multiple user dynamic data. The user dataset includes each user's user ID, historical posts, and posting locations.

[0083] The risk level classification module 802 is used to assess the risk of location information leakage of each user in the user dataset and classify it into levels to obtain classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies.

[0084] The interference information output module 803 is used to input the user dataset into the neural network model and output the interference dataset. The interference dataset includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities.

[0085] The interference dynamic delivery module 804 is used to dynamically deliver the predicted dynamic data in the interference dataset according to the dynamic delivery strategy corresponding to each user in the division result.

[0086] Furthermore, the risk level classification module 802 is also used to: assess the risk of leakage of location information of each user in the user dataset based on the PaQL content location algorithm.

[0087] Furthermore, the risk level classification module 802 is also used to: assess and classify the risk of leakage of location information of each user in the user dataset based on the release location information, location result, and consistency between the release location information and the location result of each user's dynamic data in the user dataset, and obtain the classification result, which includes high-risk level, dangerous level, general level and safe level.

[0088] Furthermore, the interference dynamic delivery module 804 is also used for:

[0089] If the classification result is high-risk, the following operations are performed on users classified to this level: modify the user's IP proxy to the first preset location, and deliver the user's predicted dynamic data at the first preset location until the user's location result is the first preset location;

[0090] If the classification result is a danger level, the following operations are performed on the user classified to this level: modify the user's IP proxy to the second preset location, and send the user's predicted dynamic data at the second preset location until the user's location result is the second preset location. The sent predicted dynamic data does not contain geographical information and the number of times it is sent is greater than the number of times the user actually sends dynamic data.

[0091] If the classification result is a general level, the following operation is performed on users classified to this level: send the user's predicted dynamic data at the third preset location until the user's location result is the third preset location.

[0092] Furthermore, the interference dynamic delivery module 804 is also used to: determine the preset location for dynamic delivery of the predicted dynamic data for each user according to the user's anti-location requirements; and after dynamically delivering the predicted dynamic data in the interference dataset, perform anti-location effect detection on the results after dynamic delivery.

[0093] Obviously, those skilled in the art should understand that the modules or steps of the above-described embodiments of the present invention can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of the present invention are not limited to any particular hardware and software combination.

[0094] In this embodiment, a computer device is provided, such as... Figure 9 As shown, it includes a memory 901, a processor 902, and a computer program stored in the memory 901 and executable on the processor 902. When the processor 902 executes the computer program, it implements any of the above-mentioned user anti-location methods based on content generation and delivery.

[0095] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0096] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that executes any of the above-described user anti-location methods based on content generation and delivery.

[0097] Specifically, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device. As defined in this application, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0098] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A user anti-location method based on content generation and delivery, characterized in that, The method includes: By crawling and cleaning multiple user dynamic data, a user dataset is constructed, which includes each user's user ID, historical posts, and posting locations. The risk of location information leakage for each user in the user dataset is assessed and classified into different levels to obtain the classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies. The user dataset is input into a neural network model, and the output is a disturbance dataset. The disturbance dataset includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities. According to the dynamic delivery strategy corresponding to each user in the division result, the predicted dynamic data in the interference dataset are dynamically delivered, including: if the division result is a high-risk level, the following operations are performed on the user classified to this level: modify the user's IP proxy to a first preset location, and deliver the predicted dynamic data of the user at the first preset location until the user's location result is the first preset location; If the classification result is a danger level, the following operations are performed on the user classified to this level: modify the user's IP proxy to the second preset location, and send the user's predicted dynamic data at the second preset location until the user's location result is the second preset location. The sent predicted dynamic data does not contain geographical information and the number of times it is sent is greater than the number of times the user actually sends dynamic data. If the classification result is a general level, the following operation is performed on users classified to this level: send the user's predicted dynamic data at a third preset location until the user's location result is the third preset location.

2. The user anti-location method based on content generation and delivery according to claim 1, characterized in that, The risk of location information leakage for each user in the user dataset is assessed and classified into different levels, and the classification results are obtained, including: Based on the location information, location results, and consistency between the location information and the location results of each user's dynamic data in the user dataset, the risk of location information leakage for each user in the user dataset is assessed and classified into levels, and the classification results are obtained.

3. The user anti-location method based on content generation and delivery according to claim 2, characterized in that, The classification results include high-risk level, dangerous level, general level, and safe level.

4. The user anti-location method based on content generation and delivery according to claim 1, characterized in that, The risk of location information leakage for each user in the user dataset is assessed based on the PaQL content location algorithm.

5. The user anti-location method based on content generation and delivery according to claim 1, characterized in that, The step of dynamically delivering the predicted dynamic data in the interference dataset includes: Based on the user's anti-location requirements, the preset location for the dynamic delivery of the predicted dynamic data for each user is determined.

6. The user anti-location method based on content generation and delivery according to claim 5, characterized in that, Also includes: After dynamically delivering the predicted dynamic data in the interference dataset, the anti-localization effect is detected on the results of the dynamic delivery.

7. A user anti-location system based on content generation and delivery, characterized in that, include: The user dataset construction module is used to construct a user dataset by crawling and cleaning multiple user dynamic data. The user dataset includes each user's user ID, historical posts, and posting locations. The risk level classification module is used to assess and classify the risk of location information leakage of each user in the user dataset, and obtain the classification results. Different information leakage risk levels in the classification results correspond to different dynamic delivery strategies. The interference information output module is used to input the user dataset into the neural network model and output the interference dataset, which includes the predicted dynamic data of each user, wherein the predicted dynamic data of each user includes dynamic data of multiple cities. The interference dynamic delivery module is used to dynamically deliver the predicted dynamic data in the interference dataset according to the dynamic delivery strategy corresponding to each user in the division result, including: if the division result is a high-risk level, the following operations are performed on the user classified to this level: modify the user's IP proxy to a first preset location, and deliver the predicted dynamic data of the user at the first preset location until the user's location result is the first preset location; If the classification result is a danger level, the following operations are performed on the user classified to this level: modify the user's IP proxy to the second preset location, and send the user's predicted dynamic data at the second preset location until the user's location result is the second preset location. The sent predicted dynamic data does not contain geographical information and the number of times it is sent is greater than the number of times the user actually sends dynamic data. If the classification result is a general level, the following operation is performed on users classified to this level: send the user's predicted dynamic data at a third preset location until the user's location result is the third preset location.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a user anti-location method based on content generation and delivery as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs a user anti-location method based on content generation and delivery as described in any one of claims 1 to 6.

Images