WO2019153504A1

WO2019153504A1 - Group creation method and terminal thereof

Info

Publication number: WO2019153504A1
Application number: PCT/CN2018/083287
Authority: WO
Inventors: 陈颖聪
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-02-07
Filing date: 2018-04-17
Publication date: 2019-08-15
Also published as: CN108512670A; CN108512670B

Abstract

The present application is applicable to the technical field of information identification, and provides a group creation method and a terminal thereof. The method comprises: receiving a group creation request initiated by a user; identifying a plurality of first human facial images contained in a group photo image, and extracting a facial feature parameter of each first human facial image; respectively importing the facial feature parameter of any one of the first human facial images and a facial feature parameter of a user corresponding to each social account associated with the user into a matching degree calculation model, and calculating the matching degree between the first human facial image and each social account; selecting the social account with the highest matching degree as a target account corresponding to the first human facial image; and creating a group containing all target accounts. Through the present application, the operating steps of the user are reduced, and the group creation efficiency is improved. Especially on occasions in which group photos can be conveniently taken and the user numbers are large, such as meetings or parties, the aim of creating a group of all users present can also be achieved, and the situation of account omission is avoided.

Description

Method for group creation and terminal thereof

The present application claims the priority of the Chinese Patent Application No. 201101121711.2, entitled "A Method for Creating a Group and Its Terminal", which is incorporated by reference in its entirety. In this application.

Technical field

The present application belongs to the field of information recognition technologies, and in particular, to a method for group creation and a terminal thereof.

Background technique

With the continuous promotion of social applications, users often use social applications to interact with other users, and groups are the most important form of interaction in social applications. How to quickly create a group directly affects the user's experience with the social application.

The existing group creation method requires the user to manually pull the social account in the group, or manually search for the group name through each social account, and find the group to apply for joining. The steps are complicated, resulting in the operation of creating the group. Less efficient. Especially in gatherings or parties, etc., the total number of accounts of Jianqun is large, which further increases the difficulty of operation, and often the situation of account missing is added.

technical problem

In view of this, the embodiment of the present application provides a group creation method and a terminal thereof, so as to solve the existing group creation method, the steps are complicated, and the operation efficiency of creating a group is low.

Technical solution

A method for group creation provided by the application includes:

Receiving a user-initiated group creation request; the group creation request carrying a group image;

Identifying a plurality of first face images included in the combined image, and extracting facial feature parameters of each of the first face images;

Importing a face feature parameter of each of the first face images and a face feature parameter of each user account associated with the user into a matching degree calculation model, and calculating the first face image and each of the The degree of matching between social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F _i is a parameter value of a facial feature parameter of the i-th first facial image; the A _i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant;

Selecting the social account with the highest matching degree as the target account corresponding to the first face image;

Create a group that contains all of the target accounts.

Beneficial effect

In the embodiment of the present application, the user does not need to manually select the target account, and only the uploaded image is uploaded, the social account implicit in the photo image can be automatically determined, and the group is created according to the identified target account, thereby reducing the operation steps of the user and improving The efficiency of the group. Especially in the occasions of convenient photographing and large number of users, such as parties or parties, it is also possible to create a group for all users present, and avoid the addition of account omissions.

DRAWINGS

1 is a flowchart of an implementation of a method for group creation according to a first embodiment of the present application;

2 is a flowchart of a specific implementation of a method for group creation according to a second embodiment of the present application;

3 is a flowchart of a specific implementation of a method for group creation according to a third embodiment of the present application;

4 is a flowchart of a specific implementation of a method for group creation according to a fourth embodiment of the present application;

FIG. 5 is a flowchart of a specific implementation of a method for group creation according to a fourth embodiment of the present application;

FIG. 6 is a structural block diagram of a terminal device according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a terminal device according to another embodiment of the present application.

Embodiments of the invention

In the embodiment of the present application, the execution entity of the process is a group-created terminal, and the terminal device includes a smart phone, a computer device, a tablet computer, a product testing server, and the like. Specifically, the terminal device is a smart phone, and the smart phone is provided with a camera module, and the user can directly collect a photo of the corresponding user of the target account of the required group by using the camera module on the terminal device, and install the image on the smart phone. The application initiates a homing request. FIG. 1 is a flowchart of an implementation of a method for group creation provided by a first embodiment of the present application, which is described in detail as follows:

In S101, a user-initiated group creation request is received; the group creation request carries a group photo.

In this embodiment, the user can communicate with the terminal device provided by the present application through the user terminal, and send a group creation request to the terminal device through the communication connection, after the terminal device receives the group creation request. Then, the related operations of S101 are performed. When the user sends a group creation request, the user may select a photo of the target user including the desired group in the local album, and generate the group creation request according to the photographed image.

In this embodiment, the user can directly operate the terminal device, and start the group creation operation by clicking the group initiation button in the terminal device interface. When the user clicks the group initiation button, a group creation request is generated. After detecting the establishment creation request, the terminal device performs the related operation of S101. Of course, the user may choose to use the common group creation mode, or the method for creating a group by using the photographed image provided by the embodiment, where the common group creation mode is to manually select the target account. If the user performs group creation by using the method provided in this embodiment, the terminal device prompts the user to upload a photo of the group for group creation, or starts the camera application and instructs the user to collect the group for the camera function. Create a photo of the group. When the user determines the photographed image by one of the above two methods, the terminal device generates a group creation request according to the photographed image.

Optionally, in this embodiment, after receiving the group creation request, the terminal device may identify the type of the group creation request and determine the group creation mode adopted. Specifically, if the group creation request carries the group image, the related operation of S102 is performed; if the group creation request carries the account identifier, the group is directly created according to the account identifier contained therein.

In this embodiment, the photographed image is specifically a photographed image of the target user of the created group, and the terminal device can identify each target user through the photographed image, and then determine the corresponding social by the target user's face information. Account, the purpose of group creation.

In S102, a plurality of first face images included in the combined image are identified, and facial feature parameters of each of the first face images are extracted.

In this embodiment, after the terminal device extracts the photographed image from the group creation request, the first face image included in the photographed image is determined by the face recognition algorithm, and one for each first face image is created. The temporary database is configured to store the facial feature parameters of the first facial image and the degree of matching with other social accounts, so as to facilitate subsequent determination of the social accounts corresponding to each of the first facial images.

In this embodiment, the facial feature parameters of each first face image may include multiple types. Specifically, the facial feature parameters include, but are not limited to, at least one of the following: a distance between the eyes, and between the organs of the face. Relative distance, face parameter value, chromaticity of facial skin, etc. The relative distance between the organs of the face may be: the distance between the tip of the nose and the mouth, the distance between the left and right ears, the width of the forehead, and the like. The terminal device can acquire as many facial feature parameters as possible according to the captured angle of the captured face image, thereby improving the accuracy of the recognition. However, since each user photographs the photographed image, it is not necessarily photographed in a manner that the front face is unobstructed, and some parameters of the facial feature parameters may not be acquired, for example, only the side face of the user A is photographed in the photograph, in which In this case, the parameters such as the distance between the pupils and the left and right ears cannot be obtained, and the terminal device recognizes the face image that cannot be obtained as described above.

Optionally, in the embodiment, if the received group creation request includes two or more photos of the group, the first face image included in each of the group images is identified, and the plurality of photos are included in the image. The first face images belonging to the same user are merged. After the merging is completed, the facial feature parameters are extracted according to the respective first face images.

In S103, a face feature parameter of each of the first face images and a face feature parameter of each social account associated with the user are respectively imported into a matching degree calculation model, and the first face image is calculated. a degree of matching with each of the social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F _i is a parameter value of a facial feature parameter of the i-th first facial image; the A _i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant.

In this embodiment, after extracting the facial feature data of each first facial image, the terminal device determines the social account corresponding to each first facial image, so the terminal device needs to determine to initiate before determining the social account. What are the social accounts associated with the users requested by the group, and the facial feature parameters of the users corresponding to each social account. Specifically, the manner of determining the social account associated with the user may be: obtaining the buddy list of the user in the social platform, and identifying the social account included in the buddy list as the social account associated with the user. Preferably, in order to improve the accuracy of the group establishment, the terminal device may determine the social account associated with the user based on the second degree relationship, wherein the second degree relationship includes not only the social account in the user friend list but also each social account in the friend list. The social account included in the corresponding buddy list. For example, if the user's buddy list includes the social account A, the social account associated with the user in the second-degree relationship includes not only the social account A but also all the social accounts included in the social account A buddy list, thereby broadening the user association. The range of social accounts, so the base number of the first face image matching also increases, and the accuracy of recognition increases accordingly.

In this embodiment, the facial feature parameters of each social account may be stored in a database of the social network platform, and the database of the social network platform determines the user account according to the avatar uploaded by the social account, the album image, and the identity information of the user. Face feature parameters. The specific process is as follows: the database selects the face image identified from the uploaded avatar and the album image according to the user's identity information, such as gender, age, height, and the like, and selects a face image that meets the above identity information. Then, according to the number of occurrences of the same face image, the face image of the social account is determined, and then the facial feature parameters corresponding thereto are obtained.

In this embodiment, the terminal device calculates the matching degree between the first face image and each social account, and thus sets the facial feature parameter of the first face image to the facial feature parameter of the social account respectively associated with the user. Imported into the matching degree calculation model, it is emphasized that the number of facial feature parameters of the social account is matched according to the number of facial feature parameters of the first facial image.

In this embodiment, the parameter format of the facial feature parameter of the first facial image is the same as the parameter format of the facial feature parameter of the social account, so the actual meaning corresponding to the facial feature parameter of the same location is the same. . For example, if the parameter format of the facial feature parameter of the first face image is {pitch distance, eye opening angle, nose tip and mouth distance}, the parameter format of the facial feature parameter of the social account is also the same as the above format, so The first facial feature parameter represents the interpupillary distance so that the difference between the two can be determined. In particular, when a certain parameter value of the first face image is empty, no difference calculation is performed.

In S104, the social account with the highest matching degree is selected as the target account corresponding to the first face image.

In this embodiment, after the terminal device calculates the matching degree between the first face image and each social account, the terminal device selects the social account with the highest matching degree as the target account corresponding to the first face image, due to social interaction. The matching degree between the facial feature parameter of the account and the facial feature parameter of the first facial image is the highest, indicating that the entity user corresponding to the two has the highest probability of belonging to the same person. In this case, the social account is identified as the first A target account corresponding to a face image.

Preferably, after determining the social account with the highest matching degree, the terminal device further compares the matching degree value with a preset effective matching degree threshold. If the highest matching value is still less than the effective matching degree threshold, the indicating A face image cannot be matched to the target account, and the target account identifying the first face image is empty; conversely, if the highest matching value is greater than or equal to the effective matching degree threshold, the target account is identified as valid.

In S105, a group containing all of the target accounts is created.

In this embodiment, after determining the target account corresponding to each first face image, the terminal device creates a group including all target accounts. Specifically, the terminal device acquires the account identifiers of the respective target accounts, and fills in the parameter values of the group members of the group into the parameter values of the group members, thereby establishing an association relationship between the group and the target account, and completing the group creation operation. .

As can be seen from the above, a group creation method provided by the embodiment of the present application determines a first face by receiving a group creation request including a group image and identifying a first face image included in the group image. The social account corresponding to the image, and identifying the social account corresponding to the first face image as the target account, thereby automatically pulling the target account to create the group. Compared with the existing group creation method, the group creation method provided by the present application does not require the user to manually select the target account, and only needs to upload the photographed image, and the social account implied in the photographed image can be automatically determined and obtained according to the identification. The target account creates a group, which reduces the user's operation steps and improves the efficiency of the group. Especially in the occasions of convenient photographing and large number of users, such as parties or parties, it is also possible to create a group for all users present, and avoid the addition of account omissions.

FIG. 2 is a flowchart showing a specific implementation of a method for group creation according to a second embodiment of the present application. As shown in FIG. 2, with reference to the embodiment shown in FIG. 1, the method for group creation provided by this embodiment further includes S201 to S207, which are specifically described as follows:

In S201, a published image of the social account is acquired, and a second face image included in each of the published images is identified.

It should be noted that the step of FIG. 2 may be before S101, that is, the terminal device may determine facial feature parameters of each social account associated with the user before the user initiates the group creation request, for example, the user adds a social account. As a friend, the terminal device determines the facial feature parameter of the social account, and performs related operations of S201 to S207; and before S103, when the matching degree between the first facial image and each social account needs to be calculated, the execution map is executed. 2 operation of the embodiment.

In this embodiment, the terminal device accesses a database of the social account to determine an image that has been published by the social account, and the published image includes an avatar of the social account, an album, and an image sent during the chat.

In S202, a weight value of the second face image included in the posted image is determined according to an album category to which the posted image belongs.

In this embodiment, each of the published images corresponds to one album type, and the album type includes, but is not limited to, an avatar album type, a space album type, a chat record album type, and the like. Different album types correspond to different weight values. Because the facial feature parameters of the physical user corresponding to the social account are determined, it is necessary to locate the face image corresponding to the physical user from the plurality of face images in the published album, and different The album type may have different probability of the face image of the physical user, for example, the probability of the avatar album is larger, and the corresponding weight value is also larger; and the chat record album may have many expression images or network images, so The probability that the face image of the entity user may be included is small, and the corresponding weight value is small, so that the weight value corresponding to the second album image corresponding to the different second face image is determined, and the face of the social account is effectively improved. The accuracy of the characteristic parameters.

In S203, the similarity between each of the second face images is calculated.

In this embodiment, after identifying each published image, the terminal device obtains a plurality of second face images, and calculates a similarity between each second face image, specifically, all second face images. The two and two are compared to determine the similarity between the two. The calculating the similarity may be: determining a facial feature parameter of the second facial image, and determining a similarity between the two based on a difference between the facial feature parameters of the two second facial images.

In S204, the second face images are grouped based on the similarity to obtain a plurality of face groups; wherein the similarity between each of the second face images in each of the face groups Both are greater than the preset similarity threshold.

In this embodiment, after calculating the similarity between the respective second face images, the terminal device performs a grouping operation on the second face image according to the similarity to obtain a plurality of face groups, and the same person face group represents The corresponding physical users are the same, so the similarity between the second face images included in the same personal face group is greater than the preset similarity threshold.

By dividing the second face group as described above, the images representing the same face can be integrated as the same object for recognition, so that the number of recognized objects is greatly reduced, and a face group includes a plurality of second persons. The face image, thereby improving the accuracy of the recognized face feature parameters.

In S205, a representative coefficient of the face group is calculated according to a weight value of each of the second face images in the face group and a number of included second face images.

In this embodiment, since the weight value of the second face image in the face group is larger, the probability that the face group is the face of the corresponding user of the social account is larger, and the image uploaded by the social account is generally There are many images of my own, so the number of appearances of my face image is also large. It can be seen that through the above two parameters, it is possible to determine whether a face group is a social account corresponding entity user, in this implementation. In the example, it is represented by a representative coefficient.

In this embodiment, the terminal device imports the weight value of each second face image and the number of second face images included in the face group into a representative coefficient calculation model, and calculates a representative coefficient of the face group. The representative coefficient calculation model is specifically:

Where P(x) is the representative coefficient of the face group; Q is the number of the second face image; G _j is the weight value of the jth second face image.

In S206, the face group having the largest value of the representative coefficient is selected as the representative face group of the social account.

In this embodiment, after calculating the representative coefficient corresponding to each face group, the terminal device selects the face group with the largest value of the representative coefficient as the representative face group of the social account. Specifically, if the number of face groups having the largest value of the representative coefficient is two or more, the face group having the largest number of second face images corresponding to the album type having the largest weight value is selected as the social account. The representative face group. For example, if the album type with the largest weight value is the avatar album type, the number of the second face images of the avatar album type included in each face group is counted from the plurality of face groups having the largest representative coefficient, and the avatar album type is selected. The most one face group is the representative face group of the social account.

In S207, a facial feature parameter of the social account corresponding user is determined according to the second facial image in the representative facial group.

In this embodiment, after the terminal device determines the representative face group of the social account, the facial feature parameters in each second face image are extracted according to the second face image included in the representative face group. Then, through the facial feature parameters of the plurality of second face images, the facial feature parameters of the user corresponding to the social account are determined. The manner of determining the facial feature parameters of the user corresponding to the social account from the facial feature parameters of the plurality of second facial images may be: taking the average value and the intermediate value from the plurality of parameter values, and not limited.

In the embodiment of the present application, the published image of the social account is obtained, and the facial feature parameter of the corresponding user of the social account is determined according to the published image, and the facial feature parameter is not manually input by the social account, thereby reducing the operation difficulty of the user. Improve the intelligence of social account information collection.

FIG. 3 is a flowchart of a specific implementation of a method for group creation according to a third embodiment of the present application. As shown in FIG. 3, with reference to the embodiment shown in FIG. 1 and FIG. 2, the method for group creation provided in this embodiment further includes S301 to S303, which are specifically described as follows:

In S301, location information of the user is acquired.

In this embodiment, the terminal device may obtain the location information of the current location of the user in order to determine the social account associated with the user initiated by the group establishment, and the group is required to establish a group for a party such as a party or a party. The users are all in the same geographical location area, and therefore, the social accounts associated with the users can be determined by the geographic location of each user.

In this embodiment, the terminal device may obtain the location information of the user by using the positioning data fed back by the positioning device of the user terminal, and may further query the location of the base station according to the identifier of the base station of the mobile network provided by the user terminal. The location of the base station is identified as the location information of the user.

In S302, the preset effective distance is a radius centered on the location information, and the effective establishment area is determined.

In this embodiment, after determining the location information of the user, the terminal device determines an effective group establishment area according to the location information, and the specific manner of determining the group establishment area is: centering on the location information of the user, preset The effective distance is the radius, and the effective grouping pattern is obtained, and then the area covered by the effective grouping pattern is the effective grouping area. All social accounts in the active Build Area are social accounts associated with the user.

In S303, a social account whose current time is located in the valid group-building area is extracted from the social account library as a social account associated with the user.

In this embodiment, the terminal device queries location information of each social account in the social account library, and selects all social accounts whose current location information is within the coverage of the effective establishment area as the social account associated with the user. Since all the target users who need to establish a group are generally closely gathered in the scene of the party or the queue, that is, the current time is in the venue of the party or the queue, therefore, the current location information of each social account is also in the effective group establishment area. So that you can accurately filter out the social network accounts associated with the user.

In the embodiment of the present application, the social account is filtered by the location information, thereby filtering a large number of invalid social accounts, thereby improving the efficiency and accuracy of the group creation.

FIG. 4 is a flowchart of a specific implementation of a method for group creation according to a fourth embodiment of the present application. As shown in FIG. 4, with reference to the embodiment shown in FIG. 1 and FIG. 2, the method for group creation provided by this embodiment further includes: S401 to S403, which are specifically described as follows:

In S401, the buddy list of the user is obtained.

In this embodiment, since the group creation request is initiated, it is generally created based on the social account in the user's buddy list, and the social account that is not in the buddy list of the user is generally unable to pull it. Take it to the group. Therefore, the terminal device may perform further screening according to the social account included in the user's buddy list, and extract the social account related to the group creation.

In this embodiment, the terminal device reads the account of the user's account in the social network platform, determines the buddy list corresponding to the user account, and the account identifiers of all the social accounts included in the buddy list, and then performs the related operations of S102. .

In S402, a valid friend account in the buddy list is determined based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction.

In this embodiment, after determining the social account included in the buddy list of the user, the terminal device acquires an interaction between the account of the user and each social account in the buddy list, where the interaction includes the number of interactions and The interaction time of the last interaction. For example, when a user needs to initiate a party or a party, the user needs to contact each social account in advance to determine the location and time of the party. In the recent period of time, the user must contact the social account that needs to be established. Corresponding interaction records are generated in the social networking platform. Therefore, the terminal device can filter out a valid friend account according to the interaction between the user account and other social accounts.

In this embodiment, the specific manner of determining the valid friend account in the buddy list may be: the interaction number is greater than the preset number threshold, and the date of the last interaction time needs to be within the valid date range from the current date, and the above two conditions are met. The social account is the user's valid friend account.

In S403, the valid buddy account is used as a social account associated with the user.

In this embodiment, all the social accounts that meet the preset conditions are used as valid buddy accounts of the user, and other social accounts that meet the preset conditions are regarded as invalid buddy accounts, and the relevant buddy accounts are selected from the effective buddy accounts. A social account, so a valid buddy account is used as the social account associated with the user.

In the embodiment of the present application, by filtering the social accounts in the buddy list, selecting valid buddy accounts related to the faculty, thereby reducing the number of social accounts that need to be matched, and filtering most of the invalid social accounts. Improves the efficiency and accuracy of group creation.

FIG. 5 is a flowchart of a specific implementation of a method for group creation according to a fifth embodiment of the present application. As shown in FIG. 5, with reference to the embodiment shown in FIG. 1, the method for group creation provided by this embodiment further includes S501 to S503, which are specifically described as follows:

In S501, the address book information of the user is obtained; the address book information includes a plurality of contact information; the contact information includes a contact phone and a contact avatar.

In this embodiment, the user's address book can be stored in the local memory. If the terminal device provided by the embodiment is the terminal used by the user, the terminal device can directly obtain the address book information of the user by reading the local memory. If the terminal device is not the terminal used by the user, an address book information acquisition request may be sent to the user terminal, and the address book information returned by the user terminal according to the request may be accepted. If the user's address book information is stored in the cloud database, the terminal device can be connected to the cloud server to download the user's address book information.

In this embodiment, the contact information includes a plurality of contact information, and the contact phone and the contact avatar of the contact are recorded in each contact information. The contact avatar may be manually uploaded by the user, or may be extracted from the published image of the social account associated with the contact phone. The manner of the extraction may be referred to the embodiment described in FIG. 2, and details are not described herein again.

In S502, a social account that is bound to the contact phone is used as a social account associated with the user.

In this embodiment, since each social account is bound with a contact phone, the social network platform records the correspondence between the social account and the contact phone. Therefore, the terminal device can query the social network platform bound to the contact phone from the social network platform according to the contact phone obtained in S501, and identify the social account as a social account associated with the user. If a contact phone does not have a social account bound, the social account corresponding to the contact phone is empty. If a contact phone corresponds to two or more social accounts, the plurality of social accounts that are bound to the contact phone are identified as social accounts associated with the user.

In S503, a facial feature parameter of the social account corresponding user is determined according to the contact avatar.

In this embodiment, after the social account bound to the phone is determined, the contact avatar that belongs to the same contact information as the contact phone may be used as the facial feature parameter of the user corresponding to the social account. Since the contact avatar is generally a face image of the contact entity user during the setting process, the facial feature parameter of the corresponding user of the social account may be directly determined according to the contact avatar.

In the embodiment of the present application, the social account associated with the user is determined by acquiring the address book information of the user, and the facial feature parameters of the user corresponding to the associated social account are improved, thereby improving the accuracy of the recognition.

It should be understood that the size of the sequence of the steps in the above embodiments does not mean that the order of execution is performed. The order of execution of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.

FIG. 6 is a structural block diagram of a group-created terminal according to an embodiment of the present application. Each unit included in the group created by the group is used to execute each step in the embodiment corresponding to FIG. 1. For details, please refer to the related description in the embodiment corresponding to FIG. 1 and FIG. For the convenience of explanation, only the parts related to the present embodiment are shown.

Referring to FIG. 6, the terminal device includes:

a group creation request receiving unit 61, configured to receive a group creation request initiated by a user; the group creation request carries a group image;

The facial feature parameter extracting unit 62 is configured to identify a plurality of first facial images included in the combined image, and extract facial feature parameters of each of the first facial images;

The matching degree calculation unit 63 is configured to import the facial feature parameters of the corresponding facial features of the first facial image and the facial feature parameters of the corresponding social accounts associated with the user into the matching degree calculation model, and calculate the a degree of matching between a face image and each of the social accounts; the matching degree calculation model is specifically:

The target account selecting unit 64 is configured to select the social account with the highest matching degree as the target account corresponding to the first face image;

The group creating unit 65 is configured to create a group including all the target accounts.

Optionally, the terminal device further includes:

a published image obtaining unit, configured to acquire a published image of the social account, and identify a second face image included in each of the published images;

a weight value determining unit, configured to determine, according to an album category to which the posted image belongs, a weight value of the second face image included in the posted image;

a similarity calculation unit, configured to calculate a similarity between each of the second facial images;

a face image grouping unit, configured to group the second face images based on the similarity to obtain a plurality of face groups; wherein each of the second face images in each of the face groups The similarity between the two is greater than the preset similarity threshold;

a representative coefficient calculation unit, configured to calculate a representative coefficient of the face group according to a weight value of each of the second face images in the face group and a number of included second face images;

a representative face group determining unit, configured to select a face group having the largest value of the representative coefficient as a representative face group of the social account;

The social account feature parameter obtaining unit is configured to determine a facial feature parameter of the social account corresponding user according to the second facial image in the representative facial group.

Optionally, the terminal device further includes:

a location information obtaining unit, configured to acquire location information of the user;

An effective group establishment determining unit is configured to determine, according to the location information, a preset effective distance is a radius, and determine an effective grouping area;

The first associated account determining unit is configured to extract, from the social account library, a social account whose current time is located in the valid grouping area as a social account associated with the user.

Optionally, the terminal device further includes:

a buddy list obtaining unit, configured to acquire a buddy list of the user;

a valid friend account obtaining unit, configured to determine a valid friend account in the friend list based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction;

And a second associated account determining unit, configured to use the valid friend account as a social account associated with the user.

Optionally, the terminal device further includes:

The address book information obtaining unit is configured to obtain the address book information of the user; the address book information includes a plurality of contact information; the contact information includes a contact phone and a contact avatar;

a third associated account determining unit, configured to use a social account that is bound to the contact phone as a social account associated with the user;

And a contact avatar extraction unit, configured to determine, according to the contact avatar, a facial feature parameter of the user corresponding to the social account.

Therefore, the terminal device provided by the embodiment of the present application can also automatically select the social account implicit in the photo image and create a group according to the identified target account by simply uploading the photo of the target without uploading the target account. Reduce the user's operating procedures and improve the efficiency of the group. Especially in the occasions of convenient photographing and large number of users, such as parties or parties, it is also possible to create a group for all users present, and avoid the addition of account omissions.

FIG. 7 is a schematic diagram of a terminal device according to another embodiment of the present application. As shown in FIG. 7, the terminal device 7 of this embodiment includes a processor 70, a memory 71, and computer readable instructions 72 stored in the memory 71 and executable on the processor 70, such as group creation. program of. The steps in the method embodiment of implementing the various group creation described above when the processor 70 executes the computer readable instructions 72, such as S101 to S105 shown in FIG. Alternatively, the processor 70, when executing the computer readable instructions 72, implements the functions of the various units in the various apparatus embodiments described above, such as the functions of modules 61 through 65 shown in FIG.

Illustratively, the computer readable instructions 72 may be partitioned into one or more units, the one or more units being stored in the memory 71 and executed by the processor 70 to complete the application. . The one or more units may be a series of computer readable instruction instructions segments capable of performing a particular function for describing the execution of the computer readable instructions 72 in the terminal device 7. For example, the computer readable instructions 72 may be segmented into a group creation request receiving unit, a facial feature parameter extraction unit, a matching degree calculation unit, a target account selection unit, and a group creation unit, each unit having a specific function as described above.

The terminal device 7 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device may include, but is not limited to, a processor 70 and a memory 71. It will be understood by those skilled in the art that FIG. 7 is only an example of the terminal device 7, and does not constitute a limitation of the terminal device 7, and may include more or less components than those illustrated, or combine some components or different components. For example, the terminal device may further include an input/output device, a network access device, a bus, and the like.

The processor 70 may be a central processing unit (CPU), or may be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like.

The memory 71 may be an internal storage unit of the terminal device 7, such as a hard disk or a memory of the terminal device 7. The memory 71 may also be an external storage device of the terminal device 7, for example, a plug-in hard disk provided on the terminal device 7, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc. Further, the memory 71 may also include both an internal storage unit of the terminal device 7 and an external storage device. The memory 71 is configured to store the computer readable instructions and other programs and data required by the terminal device. The memory 71 can also be used to temporarily store data that has been output or is about to be output.

The above-mentioned embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing embodiments. The technical solutions described in the examples are modified or equivalently replaced with some of the technical features; and the modifications or substitutions do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in Within the scope of protection of this application.

Claims

A method for group creation, comprising:

Receiving a user-initiated group creation request; the group creation request carrying a group image;

Identifying a plurality of first face images included in the combined image, and extracting facial feature parameters of each of the first face images;

Importing a face feature parameter of each of the first face images and a face feature parameter of each user account associated with the user into a matching degree calculation model, and calculating the first face image and each of the The degree of matching between social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F i is a parameter value of a facial feature parameter of the i-th first facial image; the A i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant;

Selecting the social account with the highest matching degree as the target account corresponding to the first face image;

Create a group that contains all of the target accounts.
The method according to claim 1, wherein the method for group creation further comprises:

Obtaining a published image of the social account, and identifying a second face image included in each of the published images;

Determining, according to an album category to which the posted image belongs, a weight value of the second face image included in the posted image;

Calculating a similarity between each of the second face images;

And grouping the second face images according to the similarity to obtain a plurality of face groups; wherein, the similarity between each of the second face images in each of the face groups is greater than a preset Similarity threshold

Calculating a representative coefficient of the face group according to a weight value of each of the second face images in the face group and a number of included second face images;

Selecting a face group having the largest value of the representative coefficient as a representative face group of the social account;

Determining, according to the second face image in the representative face group, a facial feature parameter of the social account corresponding user.
The method according to claim 1 or 2, wherein the method for group creation further comprises:

Obtaining location information of the user;

Centering on the location information, the preset effective distance is a radius, and determining an effective grouping area;

A social account whose current time is located in the valid establishment area is extracted from the social account library as a social account associated with the user.
The method according to claim 1 or 2, wherein the method for group creation further comprises:

Obtaining a list of friends of the user;

Determining a valid friend account in the buddy list based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction;

The valid buddy account is used as a social account associated with the user.
The method according to claim 1, wherein the method for group creation further comprises:

Obtaining address book information of the user; the address book information includes multiple contact information; the contact information includes a contact phone and a contact avatar;

The social account that is bound to the contact phone is used as a social account associated with the user;

Determining, according to the contact avatar, a facial feature parameter of the social account corresponding user.
A terminal device, comprising:

a group creation request receiving unit, configured to receive a group creation request initiated by a user; the group creation request carries a group image;

a facial feature parameter extracting unit, configured to identify a plurality of first facial images included in the combined image, and extract facial feature parameters of each of the first facial images;

a matching degree calculation unit, configured to import a face feature parameter of each of the first face images and a face feature parameter of each social account associated with the user into a matching degree calculation model, and calculate the first a degree of matching between the face image and each of the social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F i is a parameter value of a facial feature parameter of the i-th first facial image; the A i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant;

a target account selecting unit, configured to select the social account with the highest matching degree as a target account corresponding to the first face image;

A group creation unit for creating a group containing all of the target accounts.
The terminal device according to claim 6, wherein the terminal device further comprises:

a published image obtaining unit, configured to acquire a published image of the social account, and identify a second face image included in each of the published images;

a weight value determining unit, configured to determine, according to an album category to which the posted image belongs, a weight value of the second face image included in the posted image;

a similarity calculation unit, configured to calculate a similarity between each of the second facial images;

a face image grouping unit, configured to group the second face images based on the similarity to obtain a plurality of face groups; wherein each of the second face images in each of the face groups The similarity between the two is greater than the preset similarity threshold;

a representative coefficient calculation unit, configured to calculate a representative coefficient of the face group according to a weight value of each of the second face images in the face group and a number of included second face images;

a representative face group determining unit, configured to select a face group having the largest value of the representative coefficient as a representative face group of the social account;

The social account feature parameter obtaining unit is configured to determine a facial feature parameter of the social account corresponding user according to the second facial image in the representative facial group.
The terminal device according to claim 6 or 7, wherein the terminal device further comprises:

a location information obtaining unit, configured to acquire location information of the user;

An effective group establishment determining unit is configured to determine, according to the location information, a preset effective distance is a radius, and determine an effective grouping area;

The first associated account determining unit is configured to extract, from the social account library, a social account whose current time is located in the valid grouping area as a social account associated with the user.
The terminal device according to claim 6 or 7, wherein the terminal device further comprises:

a buddy list obtaining unit, configured to acquire a buddy list of the user;

a valid friend account obtaining unit, configured to determine a valid friend account in the friend list based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction;

And a second associated account determining unit, configured to use the valid friend account as a social account associated with the user.
The terminal device according to claim 6, wherein the terminal device further comprises:

The address book information obtaining unit is configured to obtain the address book information of the user; the address book information includes a plurality of contact information; the contact information includes a contact phone and a contact avatar;

a third associated account determining unit, configured to use a social account that is bound to the contact phone as a social account associated with the user;

And a contact avatar extraction unit, configured to determine, according to the contact avatar, a facial feature parameter of the user corresponding to the social account.
A terminal device, comprising: a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing the computer readable The following steps are implemented when the instruction is executed:

Receiving a user-initiated group creation request; the group creation request carrying a group image;

Identifying a plurality of first face images included in the combined image, and extracting facial feature parameters of each of the first face images;

Importing a face feature parameter of each of the first face images and a face feature parameter of each user account associated with the user into a matching degree calculation model, and calculating the first face image and each of the The degree of matching between social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F i is a parameter value of a facial feature parameter of the i-th first facial image; the A i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant;

Selecting the social account with the highest matching degree as the target account corresponding to the first face image;

Create a group that contains all of the target accounts.
The terminal device according to claim 11, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining a published image of the social account, and identifying a second face image included in each of the published images;

Determining, according to an album category to which the posted image belongs, a weight value of the second face image included in the posted image;

Calculating a similarity between each of the second face images;

And grouping the second face images according to the similarity to obtain a plurality of face groups; wherein, the similarity between each of the second face images in each of the face groups is greater than a preset Similarity threshold

Calculating a representative coefficient of the face group according to a weight value of each of the second face images in the face group and a number of included second face images;

Selecting a face group having the largest value of the representative coefficient as a representative face group of the social account;

Determining, according to the second face image in the representative face group, a facial feature parameter of the social account corresponding user.
The terminal device according to claim 11 or 12, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining location information of the user;

Centering on the location information, the preset effective distance is a radius, and determining an effective grouping area;

A social account whose current time is located in the valid establishment area is extracted from the social account library as a social account associated with the user.
The terminal device according to claim 11 or 12, wherein the processor executes the computer readable instructions to implement the following steps:

Obtaining a list of friends of the user;

Determining a valid friend account in the buddy list based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction;

The valid buddy account is used as a social account associated with the user.
The terminal device according to claim 11, wherein said processor further implements the following steps when said computer readable instructions are executed:

Obtaining address book information of the user; the address book information includes multiple contact information; the contact information includes a contact phone and a contact avatar;

The social account that is bound to the contact phone is used as a social account associated with the user;

Determining, according to the contact avatar, a facial feature parameter of the social account corresponding user.
A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the following steps:

Receiving a user-initiated group creation request; the group creation request carrying a group image;

Identifying a plurality of first face images included in the combined image, and extracting facial feature parameters of each of the first face images;

Importing a face feature parameter of each of the first face images and a face feature parameter of each user account associated with the user into a matching degree calculation model, and calculating the first face image and each of the The degree of matching between social accounts; the matching degree calculation model is specifically:

The S is a degree of matching between the first face image and the social account; the n is the number of facial feature parameters included in the first face image; the F i is a parameter value of a facial feature parameter of the i-th first facial image; the A i is a parameter value of a facial feature parameter of the user corresponding to the i-th social account; the e is a natural constant;

Selecting the social account with the highest matching degree as the target account corresponding to the first face image;

Create a group that contains all of the target accounts.
The computer readable storage medium of claim 16, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining a published image of the social account, and identifying a second face image included in each of the published images;

Determining, according to an album category to which the posted image belongs, a weight value of the second face image included in the posted image;

Calculating a similarity between each of the second face images;

And grouping the second face images according to the similarity to obtain a plurality of face groups; wherein, the similarity between each of the second face images in each of the face groups is greater than a preset Similarity threshold

Calculating a representative coefficient of the face group according to a weight value of each of the second face images in the face group and a number of included second face images;

Selecting a face group having the largest value of the representative coefficient as a representative face group of the social account;

Determining, according to the second face image in the representative face group, a facial feature parameter of the social account corresponding user.
The computer readable storage medium according to claim 16 or 17, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining location information of the user;

Centering on the location information, the preset effective distance is a radius, and determining an effective grouping area;

A social account whose current time is located in the valid establishment area is extracted from the social account library as a social account associated with the user.
The computer readable storage medium according to claim 16 or 17, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining a list of friends of the user;

Determining a valid friend account in the buddy list based on the number of interactions between the social account in the buddy list and the user's account and the interaction time of the last interaction;

The valid buddy account is used as a social account associated with the user.
The computer readable storage medium of claim 16, wherein the processor further implements the following steps when the computer readable instructions are executed:

Obtaining address book information of the user; the address book information includes multiple contact information; the contact information includes a contact phone and a contact avatar;

The social account that is bound to the contact phone is used as a social account associated with the user;

Determining, according to the contact avatar, a facial feature parameter of the social account corresponding user.