Network community matching method and device

Abstract

The present application provides a network community matching method and device, wherein the network community matching method includes: obtaining the image to be matched of the designated user input by the client, and the community portraits of each network community; determining the first similarity between the image to be matched and each community portrait respectively according to the first preset similarity algorithm; in the case where there is a first target similarity among multiple first similarities, determining that the network community corresponding to the first target similarity is the target network community matching the designated user, and the first target similarity is greater than or equal to the first similarity threshold; and feeding back the community entrance of the target network community to the client. The network community search and matching is realized by image matching, which can not only highly concentrate the relevant target users and improve the matching accuracy, but also set a sufficiently high threshold to screen out non-target users, thereby greatly reducing the maintenance pressure of the community administrator.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more particularly to a network community matching method, a network community matching device, a computing device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of computer technology, various online exchanges and sharing emerge in an endless stream, among which sharing in online communities is very popular. At present, the process of establishing online communities and joining new users is completed in a closed loop in the network space. For example, when a new user joins an online community, in addition to the old users of the online community actively sharing the information of the online community with the new user so that the user can join the online community, the new user can find the online community he wants to join by searching for keywords.

[0003] However, there may be multiple ways to express the same thing. Using keyword search to match online communities will cause users to be scattered in multiple similar online communities due to differences in keyword expressions and cannot be concentrated. Due to the polysemy of a word, different online communities may share the same keyword, causing two unrelated user clusters to be in the same online community, causing confusion. In addition, the threshold for searching and matching online communities through keywords is low. In addition to the target users of the online community, non-target users can also be searched. In order to prevent non-target users from entering the online community, the administrator of the online community needs to spend extra costs to establish a new user admission mechanism for screening, which increases the maintenance work of the administrator. Therefore, an effective solution is urgently needed to solve the above problems. Summary of the invention

[0004] In view of this, the embodiment of the present application provides a network community matching method. The present application also relates to a network community matching device, a computing device, and a computer-readable storage medium to solve the technical defects of poor matching effect and high maintenance cost in the prior art.

[0005] According to a first aspect of an embodiment of the present application, a network community matching method is provided, comprising:

[0006] Obtain the image to be matched of the specified user input by the client, as well as the community portraits of each network community;

[0007] Determine, according to a first preset similarity algorithm, a first similarity between the image to be matched and each community portrait;

[0008] In the case that there is a first target similarity among the plurality of first similarities, determining that the network community corresponding to the first target similarity is a target network community matching the designated user, and the first target similarity is greater than or equal to a first similarity threshold;

[0009] Feedback the community entrance of the target network community to the client.

[0010] According to a second aspect of an embodiment of the present application, a network community matching device is provided, including:

[0011] An acquisition module is configured to acquire the to-be-matched image of a designated user input by a client, and community portraits of various network communities;

[0012] A first determination module is configured to determine a first similarity between the to-be-matched image and each community portrait according to a first preset similarity algorithm;

[0013] A second determination module is configured to determine, when there is a first target similarity among the plurality of first similarities, that the network community corresponding to the first target similarity is a target network community matching the designated user, and the first target similarity is greater than or equal to a first similarity threshold;

[0014] The first feedback module is configured to feedback the community entrance of the target network community to the client. According to a third aspect of the embodiment of the present application, a computing device is provided, including a memory, a processor, and computer instructions stored in the memory and executable on the processor, and the processor implements the steps of the network community matching method when executing the computer instructions.

[0015] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, which stores computer instructions. When the computer instructions are executed by a processor, the steps of the network community matching method are implemented.

[0016] The network community matching method provided by the present application obtains the image to be matched of the designated user input by the client, and the community portraits of each network community; determines the first similarity between the image to be matched and each community portrait respectively according to the first preset similarity algorithm; when there is a first target similarity among multiple first similarities, determines that the network community corresponding to the first target similarity is the target network community matched with the designated user, and the first target similarity is greater than or equal to the first similarity threshold; and feeds back the community entrance of the target network community to the client. By receiving the image to be matched, comparing the first similarity with each community portrait and the first similarity threshold, the target network community is determined, and the search and matching of the network community is realized by image matching, which can not only highly concentrate the relevant target users and improve the matching accuracy, but also set a sufficiently high threshold to screen out non-target users, thereby greatly reducing the maintenance pressure of the community administrator. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a network community matching method provided by an embodiment of the present application;

[0018] Figure 2 is a schematic diagram of an image to be matched carrying a marked subject provided by an embodiment of the present application;

[0019] Figure 3A is a processing flow chart of a network community matching method provided in one embodiment of the present application;

[0020] Figure 3B This is a processing flow chart of matching an image to be matched with community portraits provided in one embodiment of the present application;

[0021] Figure 4 It is a processing flow chart of a network community matching method applied in an actual scenario provided by an embodiment of the present application;

[0022] Figure 5 It is a structural diagram of a network community matching device provided by an embodiment of the present application;

[0023] Figure 6 It is a structural block diagram of a computing device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0025] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" used in one or more embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present application refers to any or all possible combinations of one or more associated listed items.

[0026] It should be understood that, although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0027] First, the terms involved in one or more embodiments of the present application are explained.

[0028] An online community is a space where users can freely exchange information and chat online. Online communities can usually be divided into two modes: one is the forum mode, where users exchange information by posting and replying to posts. The other is the group chat mode, where different users take turns to reply to messages in the space for communication.

[0029] In the present application, a network community matching method is provided. The present application also relates to a network community matching device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0030] Figure 1 A flowchart of a network community matching method provided according to an embodiment of the present application is shown, which specifically includes the following steps:

[0031] Step 102: Acquire the to-be-matched image of the designated user input by the client, and the community portraits of each network community.

[0032] Specifically, the image to be matched is any image uploaded by the user to the server through the client, which can be taken by the user using any device with a camera function, drawn using a drawing tool, or downloaded from the Internet; an online community refers to a space where joined users can freely exchange information and chat online; a community portrait refers to an image or text that identifies the communication theme of the online community. For example, if the communication theme of an online community is peony, then the community portrait of the online community can be an image related to peony or a text related to peony.

[0033] In actual applications, the user, that is, the designated user, uploads an arbitrary image to the server through the client. The arbitrary image is the image to be matched. At this time, the server receives the image to be matched of the designated user. At the same time, the server also needs to obtain the community portraits of all online communities. Each online community can have one community portrait or multiple community portraits.

[0034] For example, if a user wants to join a tiger-themed online community, he can upload an image of a tiger to be matched through the online community platform on his mobile phone. At this time, the server receives the user's image to be matched and obtains the community portraits of various online communities.

[0035] It should be noted that the client input is not limited to the image to be matched of the specified user. In addition to the image to be matched, the client input may also include user information, such as the preferences and interests of the specified user, to provide a more accurate matching basis.

[0036] Step 104: Determine the first similarity between the image to be matched and each community portrait according to a first preset similarity algorithm.

[0037] After the to-be-matched image of the designated user and the community portraits of each network community are obtained, further, a first similarity between the to-be-matched image and each community portrait is determined.

[0038] Specifically, the first similarity algorithm may be any similarity algorithm, such as a perceptual hash algorithm, a similarity algorithm for images, a similarity algorithm for texts, and the like.

[0039] In practical applications, the first similarity is calculated by checking a series of features of the image to be matched and the community portrait: when the community portrait is an image, a first preset image similarity algorithm is used to determine the first similarity between the image to be matched and each community portrait; when the community portrait is a text, a preset image recognition algorithm is used to identify the content or object of the image to be matched and convert it into text to be matched, and a first preset text similarity algorithm is used to determine the first similarity between the text to be matched and each community portrait.

[0040] For example, a community portrait is an image, and the first similarity algorithm is a hash algorithm: the community portrait and the image to be matched can be scaled by the hash algorithm to make the community portrait and the image to be matched have the same size, such as scaling the community portrait and the image to be matched to 8*8 and 64 pixels respectively; then the scaled community portrait and the image to be matched are gray-scaled respectively, and further, the pixel means of the gray-scaled community portrait and the image to be matched are calculated and the image fingerprint is determined. The image fingerprint of the community portrait is compared with the image fingerprint of the image to be matched to determine the first similarity between the community portrait and the image to be matched.

[0041] For another example, a community portrait is text, and the first similarity algorithm is a text similarity algorithm: a target detection algorithm (SSD, Single Shot MultiBox Detector) can be used to identify the content or object in the image to be matched. After identification, the content or object in the image to be matched is converted into text for description, and then a text similarity algorithm is used to calculate the first similarity between the text converted from the content or object in the image to be matched and the community portrait.

[0042] Step 106: when there is a first target similarity among the plurality of first similarities, determining that the network community corresponding to the first target similarity is the target network community matching the designated user, and the first target similarity is greater than or equal to a first similarity threshold.

[0043] After determining the first similarities between the to-be-matched image and each community portrait, each first similarity is further compared with a first similarity threshold, thereby determining a first target similarity and a target network community.

[0044] Specifically, the first similarity threshold refers to a threshold set for determining the degree of similarity between the image to be matched and the community portrait, and can be set by a system administrator according to actual conditions.

[0045] In practical applications, after determining the first similarities between the image to be matched and each community portrait, it is necessary to judge the degree of similarity between the image to be matched and the community portrait based on each first relative degree, that is, whether they are similar. This can be achieved by adjusting the threshold for determining the degree of similarity. That is, only when the first similarity between the image to be matched and the community portrait reaches the set first similarity threshold, can it be said that the image to be matched is similar to the community portrait. At this time, the network community corresponding to the community portrait is the target network community that the specified user wants to join.

[0046] As described in Table 1, Table 1 shows five first similarities, where the network community includes community 1, community 2 and community 3. Community 1 has one community portrait: portrait 11, and the first similarity between portrait 11 and the image to be matched is 0.2; Community 2 has two community portraits: portrait 21 and portrait 22, and the first similarity between portrait 21 and the image to be matched is 0.7, and the first similarity between portrait 22 and the image to be matched is 0.8; Community 3 has two community portraits: portrait 31 and portrait 32, and the first similarity between portrait 31 and the image to be matched is 0.1, and the first similarity between portrait 32 and the image to be matched is 0.9. If the first similarity threshold is 0.6, the first similarity between portrait 21 and the image to be matched, the first similarity between portrait 22 and the image to be matched, and the first similarity between portrait 32 and the image to be matched are all greater than 0.6, then community 2 corresponding to portrait 21 and portrait 22, and community 3 corresponding to portrait 32 are the target network communities.

[0047] Table 1 Five first similarities

[0048]

[0049] It should be noted that all network communities can share the same first similarity threshold, and compare the first similarities between the image to be matched and each community portrait with the same first similarity threshold, so as to determine the first target similarity; each network community can be configured with its own first similarity threshold, such as the first similarity threshold set for network community A is 0.6, and the first similarity threshold set for network community B is 0.7, the first similarity between the image to be matched and the community portrait of network community A is compared with 0.6, and the first similarity between the image to be matched and the community portrait of network community B is compared with 0.7; each community portrait can also correspond to a first similarity threshold, that is, a different first similarity threshold can be set for each community portrait according to needs, such as portrait 11, portrait 21, portrait 22, portrait 31 and portrait 32 in Table 1 each have a first similarity threshold.

[0050] In order to improve the accuracy of network community matching, a first similarity threshold may be set for each community portrait. At this time, the first similarity between the community portrait and the image to be matched may be compared with the first similarity threshold of the community portrait. That is, when a first target similarity exists among the plurality of first similarities, before determining that the network community corresponding to the first target similarity is the target network community matching the designated user, the specific implementation process may be as follows:

[0051] Obtaining a first similarity threshold of a first community portrait, where the first community portrait is a community portrait of any online community;

[0052] Comparing a first similarity corresponding to the first community portrait with a first similarity threshold of the first community portrait;

[0053] If the first similarity corresponding to the first community portrait is greater than the first similarity threshold of the first community portrait, the first similarity corresponding to the first community portrait is determined as the first target similarity.

[0054] In actual applications, after determining the first similarity between the image to be matched and the first community portrait, the first similarity threshold of the first community portrait is obtained, and then the first similarity corresponding to the first community portrait is compared with the first similarity threshold of the first community portrait. If the first similarity is greater than the first similarity threshold, the first similarity threshold is the first target similarity.

[0055] In addition, if the first similarity is less than or equal to the first similarity threshold of the community portrait corresponding to the first similarity, the first similarity is ignored.

[0056] As shown in Table 1, assuming that the first similarity thresholds of portrait 11, portrait 21, portrait 22, portrait 31 and portrait 32 are 0.3, 0.9, 0.8, 0.7 and 0.8 respectively: since 0.2 is less than 0.3, the first similarity corresponding to portrait 11 is ignored; since 0.7 is less than 0.9, the first similarity corresponding to portrait 21 is ignored; since 0.8 is equal to 0.8, the first similarity corresponding to portrait 22 is ignored; since 0.1 is less than 0.7, the first similarity corresponding to portrait 31 is ignored; since 0.9 is greater than 0.9, the first similarity corresponding to portrait 32 is taken as the first target similarity.

[0057] In order to prevent irrelevant users from using unconventional means to obtain images to be matched that are highly similar to community portraits, thereby successfully matching to the corresponding network community, one or more anti-matching images may be set in advance for the network community. As long as the image to be matched uploaded by the user is similar to the anti-matching image, it is determined that the image to be matched uploaded by the user fails to match. That is, when there is a first target similarity among the multiple first similarities, the specific implementation process of determining that the network community corresponding to the first target similarity is the target network community matching the specified user may be as follows:

[0058] When there is a first target similarity among the plurality of first similarities, obtaining at least one anti-matching image of the network community corresponding to the first target similarity, wherein the anti-matching image is a reference image preset for refusing to join the network community;

[0059] Determining, according to a second preset similarity algorithm, a second similarity between the image to be matched and each anti-matching image;

[0060] When there is no second target similarity among the plurality of second similarities, it is determined that the network community corresponding to the first target similarity is the target network community matching the designated user, and the second target similarity is greater than or equal to a second similarity threshold.

[0061] Specifically, the anti-matching image has a one-vote veto system. If the similarity between the image to be matched and any anti-matching image exceeds the second similarity threshold, the match fails. A defense mechanism is set to prevent users from cheating. For example, the images to be matched that have been successfully matched cannot be reused by other users. These images can be used as anti-matching images. The second preset similarity algorithm can be any similarity algorithm, which can be the same as the first preset similarity algorithm or different.

[0062] In practical applications, in order to prevent users from entering the network community abnormally, an anti-matching image can be set for the network community. If the image to be matched successfully matches the community, that is, there is a first target similarity in the first similarity, then the anti-matching process is immediately entered, and the anti-matching image of the network community corresponding to the first target is obtained, and then the second preset similarity algorithm is used to calculate the second similarity between the image to be matched and each anti-matching image, and then each second similarity is compared with the second similarity threshold. If there is no second target similarity greater than the second similarity threshold in the second similarity, it means that the image to be matched fails to match each anti-matching image, that is, the network community corresponding to the image to be matched and the first target similarity is successfully matched, and the network community is determined as the target network community. In this way, it can prevent irrelevant users from using unconventional means to obtain similar images and successfully match them to the corresponding network community, such as collecting images to be matched successfully by other users, uploading them directly without any changes or uploading them after making some minor changes, or using a camera to shoot a similar image to the image to be matched successfully by other users, etc. This kind of way of obtaining similar images is often unacceptable to the network community, and such users are also irrelevant users that the community needs to exclude.

[0063] For example, the image to be matched A1 successfully matches the community portrait A2, that is, the first similarity between the image to be matched A1 and the community portrait A2 is greater than the first target similarity. Then, the anti-matching images of the network community WL to which the community portrait A2 belongs are obtained: anti-matching image B1 and anti-matching image B2. According to the second preset similarity algorithm, the second similarity between the image to be matched A1 and the anti-matching image B1 is 0.5, and the second similarity between the image to be matched A1 and the anti-matching image B2 is 0.3. If the second similarity threshold is 0.8, the network community WL is the target network community.

[0064] It should be noted that the anti-matching images of all network communities can share the same second similarity threshold, and the second similarities between the image to be matched and each anti-matching image are compared with the same second similarity threshold; each network community can be configured with its own second similarity threshold, such as the second similarity threshold set for network community A is 0.8, and the second similarity threshold set for network community B is 0.9, the first similarity between the image to be matched and the anti-matching image of network community A is compared with 0.8, and the second similarity between the image to be matched and the anti-matching image of network community B is compared with 0.9; each anti-matching image can also correspond to a second similarity threshold, that is, a different second similarity threshold can be set for each community portrait according to needs.

[0065] When the image to be matched uploaded by the specified user is successfully matched and located in the corresponding network community, but at the same time is judged to be similar to a certain anti-matching image of the network community, the image to be matched fails to match. The specific implementation process can be as follows:

[0066] When the second target similarity exists among the plurality of second similarities, information indicating that the designated user fails to match with the network community is fed back to the client.

[0067] Continuing with the above example, according to the second preset similarity algorithm, the second similarity between the image to be matched A1 and the anti-matching image B1 is 0.5, and the second similarity between the image to be matched A1 and the anti-matching image B2 is 0.3. If the second similarity threshold is 0.4, the second similarity between the image to be matched A1 and the anti-matching image B1 is 0.5, which is the second target similarity. At this time, the matching of the images to be matched fails, and the information that the matching of the specified user and the network community fails is fed back to the client.

[0068] In addition, some anti-matching algorithms may be used, such as conventional illegal image filtering algorithms, etc. As long as the features of the image to be matched uploaded by the user meet the anti-matching algorithm, the server still determines that the image to be matched uploaded by the user fails to match.

[0069] Preferably, there may be one or more objects in the image to be matched uploaded by the user. If the server does not find a matching network community, the user is prompted to mark a more specific object to be matched in the image to be matched, that is, to mark the subject. There is no restriction on the marking method of the subject, and the subject can be selected by a rectangular frame, painted by a virtual brush, or cut out by a cutout algorithm. If the image to be matched uploaded by the specified user specifies a marked subject that needs to be matched, the server will give priority to matching the marked subject with the portraits of each community, and give priority to returning the matching result of the marked subject.

[0070] In order to screen the target users, the network community may also add regional range information, and filter out users outside the regional range according to the regional range information. That is, when the image to be matched carries the first position and the community portrait carries the regional range information, when there is a first target similarity among the multiple first similarities, the network community corresponding to the first target similarity is determined to be the target network community matching the specified user. The specific implementation process may be:

[0071] In the case where a first target similarity exists among the plurality of first similarities, determining whether the first position is within a range specified by the area range information;

[0072] If so, it is determined that the network community corresponding to the first target similarity is the target network community matching the designated user.

[0073] Specifically, the first position may be a shooting position of the image to be matched, or may be a position where a designated user uploads the image to be matched, which is not limited in the present application.

[0074] In actual applications, when the image to be matched successfully matches one or some community portraits, that is, when there is a first target similarity among multiple first similarities, the area range information carried by the community portrait corresponding to the first target similarity and the first position carried by the image to be matched can be obtained, and then it is determined whether the first position is within the range specified by the area range information. If so, it means that the target community corresponding to the first target similarity is the target network community.

[0075] For example, the first position of the image to be matched is Chengdu, and the regional range information of the community portrait corresponding to the first target similarity is Sichuan Province. Chengdu is located in Sichuan Province, so the network community corresponding to the first target similarity is the target network community.

[0076] The real scenes corresponding to the community portraits bound to some online communities are often not unique in reality. For example, the store sign of a chain store, a tree on the road, etc. These similar scenes are very similar and are spread all over the world. It is basically impossible to distinguish similar scenes in different parts of the world just by using the images to be matched taken by the shooting equipment. However, the administrator who matches to a certain online community hopes that other users of the online community who are matched to the same scene are also users who have taken photos of the same scene there, rather than users who have taken similar scenes in other areas. For example, a user took an image (community portrait) of the "playground in place A" and established a community, but he does not want the user who took the image to be matched of the "playground in place B" to be matched to the online community bound to the playground in place A. For this reason, after the image feature matching is successful, the online community will also add the matching of the first position of the image to be matched according to the needs.

[0077] In addition, if the first position is not within the range specified by the area range information, the network community corresponding to the first target similarity is not the target network community.

[0078] Optionally, the area range information includes second location information and a distance threshold. In this case, the specific implementation process of determining whether the first location is within the range specified by the area range information may be as follows:

[0079] calculating a distance between the first position and the second position;

[0080] It is determined whether the distance is less than the distance threshold.

[0081] Specifically, the distance threshold refers to a threshold set for determining whether the first position of the image to be matched is close to the second position of the community portrait, and can be set by the system administrator according to actual conditions.

[0082] For example, the first position is (30, 40) and the second position is (0, 0), then the distance between the first position and the second position is 50. When the distance threshold is 100, the distance is less than the distance threshold. When the distance threshold is 20, the distance is greater than the distance threshold.

[0083] It should be noted that when the image to be matched is successfully matched with the community portrait, the network community can still add the match of the first position of the image to be matched as needed. Preferably, the first position refers to the geographical location information of the user who was recorded together with the image to be matched when the user used a camera to take a picture of the image to be matched. This position is generally represented by the coordinates of the Global Positioning System (GPS). The network community can also set a range threshold for the second position match, that is, the distance threshold, that is, the distance between the first position and the second position is within the distance threshold range, that is, the match is determined to be successful, that is to say, the network community believes that the scenes shot by all users who have taken the successfully matched images to be matched within that range must be the same scene rather than similar scenes of the same type in different places, then these users are the target users of the network community.

[0084] Step 108: Feedback the community entrance of the target network community to the client.

[0085] On the basis of determining the target network community, further, the community entrance of the target network is fed back to the designated user of the client.

[0086] Specifically, the community entrance can be the homepage of a certain online community discussion section, the chat window of a certain online community chat room, or an online community related information introduction page. The community related information introduction page can include the number of users in the online community, the topics discussed in the community, the number of articles discussed in the community, etc.

[0087] In actual applications, when the image to be matched of the designated user is matched to the target network community, the server will feed back the community entrance of the target network community to the client, that is, to the designated user of the client, so that the user can join the target network community. In addition, in order to improve the user experience, the community portrait of the target network community can also be returned to the user together with the community entrance, so that the user can select the target network community he wants to join from at least one target network community according to the community portrait.

[0088] In addition, since the image to be matched may contain multiple main contents, and the user may only be interested in one of them, for example, a specified user uploads a personal photo of a celebrity, which may contain many elements, such as scenery, irrelevant people, etc., but the user is often really interested in the face of the celebrity. If the user does not mark the subject of interest, it may lead to the final matching failure or matching to a network community that does not meet the real needs. Therefore, when the image to be matched fails to match all community portraits, the server will prompt the user to mark certain subjects as key matching objects according to his or her interests. The specific implementation process can be as follows:

[0089] When there is no first target similarity among the plurality of first similarities, feeding back a marked subject reminder for the image to be matched to the client;

[0090] Receiving an image to be matched with a marked subject sent by the client, where the marked subject is an object marked in the image to be matched by a user based on a reminder of the marked subject of the image to be matched;

[0091] Determining, according to a third preset similarity algorithm, a third similarity between the marked subject and each community portrait;

[0092] In the case that there is a third target similarity among the plurality of third similarities, determining that the network community corresponding to the third target similarity is the target network community matching the designated user, and the third target similarity is greater than a third similarity threshold;

[0093] Feedback the community entrance of the target network community to the client.

[0094] Specifically, the subject marking reminder refers to a reminder issued by the server to prompt a specified user to mark certain subjects in the to-be-matched image according to his or her own interests; the third preset algorithm may be the same as or different from the first preset algorithm.

[0095] In actual applications, if the image to be matched directly uploaded by the designated user through the client fails to match, that is, the first target similarity does not exist in the first similarity, the server will also feedback a reminder of the marked subject for the image to be matched, and the designated user will be reminded to mark the marked subject in the image to be matched. The marking method can be to use a rectangular box to select, or a virtual brush to paint the approximate area of ​​the subject object on the image to be matched, or to use a cutout algorithm to cut out the subject object, etc. Then the designated user uploads the image to be matched with the marked subject to the server, such as uploading the position information of the marked subject in the image to be matched to the server together with the image to be matched. The server then calculates the third similarity between the marked subject and each community portrait according to the third preset similarity algorithm. If there is a third target similarity greater than the third similarity threshold in the third similarity, the network community corresponding to the third target similarity is the target network community, and the community entrance of the target network community can be fed back to the designated client at this time. In addition, the community portraits of the two target network communities can also be fed back.

[0096] For example, if the image to be matched fails to be matched, the server will provide a reminder of the marked subject of the image to be matched to the designated client. The user marks the marked subject "cat" in the image to be matched and uploads it to the server. Then the server determines the third similarity between the marked subject "cat" and the portraits of each community based on the third preset similarity algorithm. Assuming that the third similarities are 0.1, 0.3, 0.8 and 0.9 respectively, if the third similarity threshold is 0.7, the network communities corresponding to 0.8 and 0.9 are determined as the target network communities, and the community entrances of these two network communities are fed back.

[0097] like Figure 2 As shown, Figure 2 A schematic diagram of an image to be matched with a marked subject provided by an embodiment of the present application is shown: a landscape image is the image to be matched, wherein the night sky marked with a box is the marked subject.

[0098] In one or more optional embodiments, when the first target similarity does not exist among the plurality of the first similarities, information that the designated user fails to match the network community is fed back to the client. That is, the image to be matched fails to match, and the server feeds back matching failure information such as "no match to the network community" to the designated client, that is, the client.

[0099] After the server feeds back the matching failure information, it can also feed back to the designated user whether to create a new network community, so that the designated user can build a new network community. That is, after feeding back to the client that the matching failure between the designated user and the network community is failed, it also includes:

[0100] Feedback to the client whether to create a new network community;

[0101] After receiving the confirmation information sent by the client, a new network community is created for the designated user according to the image to be matched.

[0102] Specifically, whether to create a new network community information refers to information used to prompt the user whether to create a new network community.

[0103] In actual applications, if the image uploaded by the specified user does not match any online community and the server returns a match failure message, the server will further feedback to the specified user whether to establish a new online community and wait for the specified user to make further processing. When the user returns a confirmation message such as "confirm to create a new community", the server will create a new online community for the user and set the image to be matched as the user portrait of the new online community.

[0104] In addition, the server will regard the first user who creates a new online community as the administrator of the online community, but other users can also be appointed as community administrators according to actual conditions. Considering that the scenes in reality will continue to change, the community administrator can replace, add, and delete the community portraits of the online community according to needs; some scenes may be large in scale, and only using images taken from a certain angle as the only community portrait may miss many users who shoot the same scene from other angles. Based on this, more different community portraits can be added to bind to the online community, and other users who match any of the community portraits can find the online community to ensure that relevant users are not missed. The community administrator can also add brief community introduction information and name the community, but this information cannot be used to search and match the community. The only way to join the community is through similar image matching. After the new online community is established, the server will return the community entrance of the new online community to the specified user and update the relevant data in the online community server module.

[0105] See also Figure 3A , Figure 3AThe flowchart of a network community matching method provided by an embodiment of the present application is shown: the client first uploads the image to be matched to the server, and then the server receives the image to be matched, matches the image to be matched with the portraits of each community, and performs layout management according to the matching results. If the user directly creates a new community, the layout management can be directly entered according to the received image to be matched. After the layout management, the network community database is updated. Figure 3B , Figure 3B A processing flow chart of matching an image to be matched with community portraits provided by an embodiment of the present application is shown: when matching an image to be matched with community portraits, the image to be matched is first received, and then a matching judgment between the image to be matched and the community portrait is entered, that is, determining whether a first target similarity exists in the first similarity; then a matching judgment between the image to be matched and the anti-matching image is entered, that is, determining whether a second target similarity exists in the second similarity; and finally a matching judgment between the first position and the regional position information is entered, that is, determining whether the first position is located in the area pointed to by the regional position information.

[0106] The network community matching method provided by the present application obtains the image to be matched of the designated user input by the client, and the community portraits of each network community; determines the first similarity between the image to be matched and each community portrait respectively according to the first preset similarity algorithm; when there is a first target similarity among multiple first similarities, determines that the network community corresponding to the first target similarity is the target network community matched with the designated user, and the first target similarity is greater than or equal to the first similarity threshold; and feeds back the community entrance of the target network community to the client. By receiving the image to be matched, comparing the first similarity with each community portrait and the first similarity threshold, the target network community is determined, and the search and matching of the network community is realized by image matching, which can not only highly concentrate the relevant target users and improve the matching accuracy, but also set a sufficiently high threshold to screen out non-target users, thereby greatly reducing the maintenance pressure of the community administrator.

[0107] The following combination Figure 4 , taking the application of the network community matching method provided by this application in a practical scenario as an example, the network community matching method is further explained. Figure 4 A processing flow chart of a network community matching method applied in an actual scenario provided by an embodiment of the present application is shown, which specifically includes the following steps:

[0108] Step 402: Acquire the to-be-matched image of the designated user input by the client, and the community portraits of each network community.

[0109] Each online community includes at least one community portrait.

[0110] Step 404: Determine the first similarity between the image to be matched and each community portrait according to the first preset similarity algorithm.

[0111] Step 406: When the first target similarity does not exist among the plurality of first similarities, information indicating that the matching between the designated user and the network community fails is fed back to the client.

[0112] The first target similarity is greater than or equal to a first similarity threshold.

[0113] Afterwards, information on whether to create a new network community is fed back to the client; after receiving confirmation information sent by the client, a new network community is created for the designated user according to the image to be matched.

[0114] Optionally, when there is no first target similarity among multiple first similarities, a marked subject reminder for the image to be matched is fed back to the client; the image to be matched with the marked subject sent by the client is received, and the marked subject is an object marked by the user in the image to be matched based on the marked subject reminder of the image to be matched; according to a third preset similarity algorithm, a third similarity between the marked subject and each community portrait is determined; when there is a third target similarity among multiple third similarities, the network community corresponding to the third target similarity is determined to be the target network community matched with the specified user, and the third target similarity is greater than a third similarity threshold; and the community entrance of the target network community is fed back to the client.

[0115] Step 408: when there is a first target similarity among the plurality of first similarities, obtaining at least one anti-matching image of the network community corresponding to the first target similarity.

[0116] The anti-matching image is a reference image preset for refusing to join the network community, and the first target similarity is greater than or equal to the first similarity threshold.

[0117] Step 410: Determine the second similarity between the to-be-matched image and each anti-matching image according to a second preset similarity algorithm.

[0118] Step 412: when there is no second target similarity among the plurality of second similarities, information indicating that the matching between the designated user and the network community fails is fed back to the client.

[0119] The second target similarity is a second similarity that is greater than or equal to a second similarity threshold.

[0120] Afterwards, feedback is given on whether to create a new network community information; after receiving the confirmation information, a new network community is created for the designated user according to the image to be matched.

[0121] Step 414: When there is no second target similarity among the plurality of second similarities, determine whether the first position is within the range specified by the area range information.

[0122] Among them, the image to be matched carries a first position, and the community portrait carries area range information; the second target similarity is a second similarity greater than or equal to a second similarity threshold.

[0123] Optionally, the area range information includes the second location information and a distance threshold;

[0124] Determining whether the first location is within a range specified by the area range information includes:

[0125] calculating a distance between a first position and a second position;

[0126] Determine if the distance is less than the distance threshold.

[0127] Step 416: If not, feedback to the client that the matching between the designated user and the network community fails.

[0128] Afterwards, feedback is given on whether to create a new network community information; after receiving the confirmation information, a new network community is created for the designated user according to the image to be matched.

[0129] Step 418: If yes, determine that the network community corresponding to the first target similarity is the target network community matching the designated user.

[0130] Step 420: Feedback the community entrance of the target network community to the client.

[0131] The network community matching method provided by the present application obtains the image to be matched of the designated user input by the client, and the community portraits of each network community; determines the first similarity between the image to be matched and each community portrait respectively according to the first preset similarity algorithm; when there is a first target similarity among multiple first similarities, determines that the network community corresponding to the first target similarity is the target network community matched with the designated user, and the first target similarity is greater than or equal to the first similarity threshold; and feeds back the community entrance of the target network community to the client. By receiving the image to be matched, comparing the first similarity with each community portrait and the first similarity threshold, the target network community is determined, and the search and matching of the network community is realized by image matching, which can not only highly concentrate the relevant target users and improve the matching accuracy, but also set a sufficiently high threshold to screen out non-target users, thereby greatly reducing the maintenance pressure of the community administrator.

[0132] Corresponding to the above method embodiment, the present application also provides a network community matching device embodiment, Figure 5 FIG. 1 shows a schematic diagram of the structure of a network community matching device provided by an embodiment of the present application. Figure 5 As shown, the device comprises:

[0133] The acquisition module 502 is configured to acquire the to-be-matched image of the designated user input by the client, and the community portraits of each network community;

[0134] A first determination module 504 is configured to determine a first similarity between the to-be-matched image and each community portrait according to a first preset similarity algorithm;

[0135] A second determination module 506 is configured to determine that the network community corresponding to the first target similarity is a target network community matching the designated user when there is a first target similarity among the plurality of first similarities, and the first target similarity is greater than or equal to a first similarity threshold;

[0136] The first feedback module 508 is configured to feedback the community entrance of the target network community to the client.

[0137] Optionally, the device also includes a comparison module, configured to obtain a first similarity threshold of a first community portrait, where the first community portrait is a community portrait of any online community; compare the first similarity corresponding to the first community portrait with the first similarity threshold of the first community portrait; if the first similarity corresponding to the first community portrait is greater than the first similarity threshold of the first community portrait, determine the first similarity corresponding to the first community portrait as the first target similarity.

[0138] Optionally, the second determination module 506 is further configured to, when there is a first target similarity among multiple first similarities, obtain at least one anti-matching image of the network community corresponding to the first target similarity, the anti-matching image being a reference image pre-set for refusing to join the network community; determine, according to a second preset similarity algorithm, a second similarity between the image to be matched and each anti-matching image; and, when there is no second target similarity among multiple second similarities, determine that the network community corresponding to the first target similarity is the target network community matched with the designated user, and the second target similarity is greater than or equal to a second similarity threshold.

[0139] Optionally, the device further comprises a second feedback module configured to feedback information that the matching between the designated user and the network community fails to the client when the second target similarity exists among the plurality of second similarities.

[0140] Optionally, the image to be matched carries a first location, and the community portrait carries area range information;

[0141] The second determination module 506 is further configured to determine whether the first location is within the range specified by the area range information when there is a first target similarity among the plurality of first similarities; if so, determine that the network community corresponding to the first target similarity is a target network community matching the designated user.

[0142] Optionally, the area range information includes second location information and a distance threshold;

[0143] The second determination module 506 is further configured to calculate the distance between the first position and the second position; and determine whether the distance is less than the distance threshold.

[0144] Optionally, the device also includes a third feedback module, which is configured to, when there is no first target similarity among multiple first similarities, provide feedback to the client of a marked subject reminder for the image to be matched; receive the image to be matched with a marked subject sent by the client, the marked subject being an object marked in the image to be matched by the user based on the marked subject reminder of the image to be matched; determine, according to a third preset similarity algorithm, a third similarity between the marked subject and each community portrait; when there is a third target similarity among multiple third similarities, determine that the network community corresponding to the third target similarity is the target network community matching the specified user, and the third target similarity is greater than a third similarity threshold; and provide feedback to the client of the community entrance of the target network community.

[0145] Optionally, the apparatus further comprises a fourth feedback module configured to feedback information that the matching between the designated user and the network community fails to the client when there is no first target similarity among the plurality of first similarities.

[0146] Optionally, the device further comprises a creation module configured to feed back information on whether to create a new network community to the client; after receiving confirmation information sent by the client, create a new network community for the designated user according to the image to be matched.

[0147] The network community matching device provided by the present application obtains the image to be matched of the designated user input by the client, and the community portraits of each network community; determines the first similarity between the image to be matched and each community portrait respectively according to the first preset similarity algorithm; when there is a first target similarity among multiple first similarities, determines that the network community corresponding to the first target similarity is the target network community matched with the designated user, and the first target similarity is greater than or equal to the first similarity threshold; and feeds back the community entrance of the target network community to the client. By receiving the image to be matched, comparing the first similarity with each community portrait and the first similarity threshold, the target network community is determined, and the search and matching of the network community is realized by image matching, which can not only highly concentrate the relevant target users and improve the matching accuracy, but also set a sufficiently high threshold to screen out non-target users, thereby greatly reducing the maintenance pressure of the community administrator.

[0148] The above is a schematic scheme of a network community matching device of this embodiment. It should be noted that the technical scheme of the network community matching device and the technical scheme of the network community matching method described above are of the same concept, and the details not described in detail in the technical scheme of the network community matching device can be found in the description of the technical scheme of the network community matching method described above.

[0149] Figure 6 The block diagram of a computing device 600 according to an embodiment of the present application is shown. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and the database 650 is used to store data.

[0150] The computing device 600 also includes an access device 640 that enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0151] In one embodiment of the present application, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0152] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or PC. The computing device 600 may also be a mobile or stationary server.

[0153] When the processor 620 executes the computer instructions, the steps of the network community matching method are implemented.

[0154] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above network community matching method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above network community matching method.

[0155] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the network community matching method as described above.

[0156] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above network community matching method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above network community matching method.

[0157] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0158] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0159] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0160] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0161] The preferred embodiments of the present application disclosed above are only used to help explain the present application. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the present application. The present application selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can understand and use the present application well. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A network community matching method, characterized in that: include: Obtain the image to be matched of the specified user input by the client, as well as the community portraits of each network community; Determine, according to a first preset similarity algorithm, a first similarity between the image to be matched and each community portrait; In the case that there is a first target similarity among the plurality of first similarities, determining that the network community corresponding to the first target similarity is a target network community matching the designated user, and the first target similarity is greater than or equal to a first similarity threshold; Feedback the community entrance of the target network community to the client; Wherein, when there is a first target similarity among the plurality of first similarities, determining the network community corresponding to the first target similarity as the target network community matching the designated user includes: When there is a first target similarity among the plurality of first similarities, obtaining at least one anti-matching image of the network community corresponding to the first target similarity, wherein the anti-matching image is a reference image preset for refusing to join the network community; Determining, according to a second preset similarity algorithm, a second similarity between the image to be matched and each anti-matching image; When there is no second target similarity among the plurality of second similarities, it is determined that the network community corresponding to the first target similarity is the target network community matching the designated user, and the second target similarity is greater than or equal to a second similarity threshold.

2. The method according to claim 1, characterized in that Before determining that the network community corresponding to the first target similarity is the target network community matching the designated user when there is a first target similarity among the plurality of the first similarities, the method further includes: Obtaining a first similarity threshold of a first community portrait, where the first community portrait is a community portrait of any online community; Comparing a first similarity corresponding to the first community portrait with a first similarity threshold of the first community portrait; If the first similarity corresponding to the first community portrait is greater than the first similarity threshold of the first community portrait, the first similarity corresponding to the first community portrait is determined as the first target similarity.

3. The method according to claim 1, characterized in that Also includes: When the second target similarity exists among the plurality of second similarities, information indicating that the designated user fails to match with the network community is fed back to the client.

4. The method according to any one of claims 1 to 3, characterized in that: The image to be matched carries a first location, and the community portrait carries area range information; In the case that there is a first target similarity among the plurality of first similarities, determining the network community corresponding to the first target similarity as a target network community matching the designated user includes: In the case where a first target similarity exists among the plurality of first similarities, determining whether the first position is within a range specified by the area range information; If so, it is determined that the network community corresponding to the first target similarity is the target network community matching the designated user.

5. The method according to claim 4, characterized in that The area range information includes second location information and a distance threshold; and determining whether the first location is within a range specified by the area range information includes: calculating a distance between the first position and the second position; It is determined whether the distance is less than the distance threshold.

6. The method according to claim 1, characterized in that Also includes: When there is no first target similarity among the plurality of first similarities, feeding back a marked subject reminder for the image to be matched to the client; Receiving an image to be matched with a marked subject sent by the client, where the marked subject is an object marked in the image to be matched by a user based on a reminder of a marked subject of the image to be matched; Determining, according to a third preset similarity algorithm, a third similarity between the marked subject and each community portrait; In the case that there is a third target similarity among the plurality of third similarities, determining that the network community corresponding to the third target similarity is the target network community matching the designated user, and the third target similarity is greater than a third similarity threshold; Feedback the community entrance of the target network community to the client.

7. The method according to claim 1, characterized in that Also includes: In the case that the first target similarity does not exist among the plurality of the first similarities, information indicating that the designated user fails to match with the network community is fed back to the client.

8. The method according to claim 3 or 7, characterized in that: After feeding back to the client the information that the designated user fails to match with the network community, the method further includes: Feedback to the client whether to create a new network community; After receiving the confirmation information sent by the client, a new network community is created for the designated user according to the image to be matched.

9. A network community matching device, characterized in that: include: An acquisition module is configured to acquire the to-be-matched image of a designated user input by a client, and community portraits of various network communities; A first determination module is configured to determine a first similarity between the to-be-matched image and each community portrait according to a first preset similarity algorithm; A second determination module is configured to determine, when there is a first target similarity among the plurality of first similarities, that the network community corresponding to the first target similarity is a target network community matching the designated user, and the first target similarity is greater than or equal to a first similarity threshold; A first feedback module is configured to feedback the community entrance of the target network community to the client; Wherein, when there is a first target similarity among the plurality of first similarities, determining the network community corresponding to the first target similarity as the target network community matching the designated user includes: When there is a first target similarity among the plurality of first similarities, obtaining at least one anti-matching image of the network community corresponding to the first target similarity, wherein the anti-matching image is a reference image preset for refusing to join the network community; Determining, according to a second preset similarity algorithm, a second similarity between the image to be matched and each anti-matching image; When there is no second target similarity among the plurality of second similarities, it is determined that the network community corresponding to the first target similarity is the target network community matching the designated user, and the second target similarity is greater than or equal to a second similarity threshold.

10. A computing device comprising a memory, a processor, and computer instructions stored in the memory and executable on the processor, characterized in that: When the processor executes the computer instructions, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instruction is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

12. A computer program product comprising computer instructions, characterized in that: When the computer instruction is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images