CN113704626B - A Conversational Social Recommendation Method Based on Reconstructed Social Network - Google Patents

Abstract

Translated fromChinese

本发明公开了一种基于重构社交网络的会话社交推荐方法。该方法根据给定用户的当前会话和社交网络，对用户的兴趣以及朋友对用户的社交影响进行建模，来预测用户在下一步最可能感兴趣的物品。主要由四个部分组成：第一部分是基于当前用户，从社交网络中找到当前用户的真实朋友；第二部分是基于当前用户的当前会话和存储的会话集合，找到当前用户的潜在朋友；第三部分是得到当前用户、真实朋友和潜在朋友的兴趣表征；第四部分是结合当前用户的真实朋友和潜在朋友，得到朋友对用户的社交影响；第五部分是结合用户自身兴趣和社交影响，获得用户最终向量表征；最后，根据用户最终向量表征和物品向量表征，推荐物品。

The invention discloses a conversational social recommendation method based on reconstructed social network. The method models the user's interests and the social influence of friends on the user given the user's current session and social network to predict the items that the user is most likely to be interested in in the next step. It mainly consists of four parts: the first part is to find the real friends of the current user from the social network based on the current user; the second part is to find the current user's potential friends based on the current session of the current user and the stored session set; the third part is to find the current user's potential friends; The part is to get the interest representation of the current user, real friends and potential friends; the fourth part is to combine the real friends and potential friends of the current user to get the social influence of friends on the user; the fifth part is to combine the user's own interests and social influence to get The final vector representation of the user; finally, according to the final vector representation of the user and the vector representation of the item, items are recommended.

Description

Conversation social recommendation method based on reconstructed social network

Technical Field

The invention belongs to the technical field of internet services, and particularly relates to a conversation social recommendation method based on a reconstructed social network.

Background

A Session (Session) is an interactive activity of a user over a period of time, and a Session-based recommendation is a recommendation of an item next clicked by the user based on the current Session. The session recommendation divides the historical interaction sequence of the user into a plurality of sessions according to certain logic, models the current session to obtain the current interest of the user, and predicts the next interested article of the user. In the e-commerce platform, a user has a lot of purchasing interests historically, but in the current session, the purchasing interests are single. The current session of the user is modeled, and the current interest of the user can be obtained, so that the current purchase purpose of the user can be captured more accurately. In addition, most online platforms will host social interaction into the infrastructure, allowing users to interact with other users and share their interests. When recommending articles for users, social influence is taken into consideration, and the sparsity of data can be reduced. The method has the starting point that potential friends of the current user are further mined, the social influence of the potential friends and real friends on the current user is considered, and the sparsity of data is further reduced.

At this time, two relationships are involved in the social network: the relationship between the real friend and the current user, and the relationship between the potential friend and the current user. These two relationships are different: the current user and the real friend generally have a lot of interests and hobbies and have common interests, and the extracted current interests of the current user and the real friend are not necessarily close to each other; and the potential friends are obtained by calculating the similarity between the current conversation of the user and the stored conversations of other users, so that the interests of the potential friends are close to the current user. Therefore, the effects of real friends and potential friends on the current user need to be computed separately and in parallel, and then combined to get a unified social impact. And then predicting the next interested item of the user according to the interest of the user.

Disclosure of Invention

The technical problem to be solved by the invention is to model the interests of a user and the social influence of friends on the user to predict the most likely items of interest of the user in the next step, given the current conversation and social network of the user. When modeling social influence, two relationships are involved: the relationship between the real friend and the current user, and the relationship between the potential friend and the current user. These two relationships are different: generally, the current user and the real friend have a lot of interests and hobbies and have common interests, and the current interests of the extracted current user and the extracted real friend are not necessarily close to each other; and the potential friends are obtained by calculating the similarity between the current conversation of the user and the stored conversations of other users, so that the interests of the potential friends are close to the current user. Therefore, the effects of real friends and potential friends on the current user need to be computed separately and in parallel, and then combined to get a unified social impact. And then predicting the next interested item of the user according to the interest of the user.

A conversation social recommendation method based on reconstructed social networks comprises the following steps:

based on the current user, the real friends of the current user are found from the social network. And establishing a social network G according to the data record of the actual friend relationship in the platform, wherein the social network G is an undirected graph. The neighbor nodes of the current user are found from the social network G, which is the current user's set of real friends n (u).

Potential friends of the current user are found based on the current conversation of the current user and the stored set of conversations. The memory matrix M is used to store the most recent sessions that occurred. Current session s ═ { v ═ based on current user₁,v_.,…,v_|s|Finding out the most similar k sessions from the memory matrix M by calculating cosine similarity between the current session and the candidate sessions in the memory matrix M, and ensuring that the similarity is greater than a threshold sim_threAnd then extracting epsilon sessions randomly from the screened k sessions. Finally, the users of the epsilon conversations are determined as the current user's potential friend set B (u), and the extracted conversations represent the interests of the potential friends. The similarity calculation formula is as follows:

wherein s is_jIs any session stored in the memory matrix M.

Is a binary vector representation of a session s, if an item is present in the session, the corresponding position in s is 1, otherwise it is 0. All in oneIn order to solve the problems that,

is a conversation s_jIs represented by a binary vector. l(s) and l(s)_j) Respectively representing sessions s and s_jLength of (d). For all sessions stored in the memory matrix M, the formula sim (s, s)_j) Calculating cosine similarity with the current conversation s, and lowering the similarity to be lower than a threshold sim_threFiltering out the sessions, sequencing the sessions from high to low according to the cosine similarity, finding out the first k sessions, and randomly extracting epsilon sessions from the sessions.

And obtaining interest characteristics of the current user, the real friends and the potential friends. And extracting the interest of the corresponding user from the current conversation of the current user, the latest conversation of the real friend and the screened conversation of the potential friend, and respectively characterizing the conversation by adopting a gate control recurrent neural network (GRU) to obtain interest characterization. Namely, the current conversation of the current user, the latest conversation of the real friend and the screened conversation of the potential friend are respectively used as the input of a gate control recurrent neural network (GRU), and the output of the gate control recurrent neural network (GRU) is respectively used as the interest of the current user, the interest of the real friend and the interest of the potential friend:

z_i＝σ(W_xz·x_i+W_hz·h_i-1)

r_i＝σ(W_xr·x_i+W_hr·h_i-1)

wherein r is_iIs a reset gate, z_iTo update the gates (update gate), these two gating vectors determine which information can be used as the output of the gated loop unit.

Is the current memory content. x is the number of_iIs the node input of the current layer, i.e. the item v_iIs used for vector characterization. W_xz、W_hz、W_xrAnd W_hrRespectively, control the update gate z_iAnd a reset gate r_iThe parameter (c) of (c). W_xhAnd W_hhIs to control the pre-memory content

The parameter (c) of (c). As is the element-level matrix multiplication, σ is the sigmoid function. The output of the last hidden layer of the gated recurrent neural network (GRU) is the session characterization.

And combining the real friends and the potential friends of the current user to obtain the social influence of the friends on the user. The real friends and the potential friends are calculated separately, and the effects of the real friends and the potential friends on the current user are calculated by an attention mechanism, wherein the effect of each friend on the current user is different. The importance of real friends and potential friends is controlled by the prior parameter lambda and needs to be set by the experimenter. Ultimate social impact p_fThe specific calculation method is as follows:

wherein alpha is_uiRepresenting real friends u_iEffect on the current user, α_ujRepresenting potential friends u_jAs a function of the current user's role,

is that the influence of real friends and potential friends on the current user is gathered, p_fIs to

Adding a nonlinear perceptron layer is also the final social influence; h is_u、h_iAnd h_jRespectively a current user and a real friend u_iAnd potential friends u_jIs characterized by the vector of (1), attention value alpha_uiAnd alpha_ujCalculated using a multiplicative attention mechanism and normalized using the softmax function. The prior parameter lambda belongs to [0,1 ]]The weights controlling the true friend role and the potential friend role. W_gIs a transformation matrix parameter and ReLU is a ReLU activation function.

And obtaining the final vector representation of the user by combining the interest of the user and the social influence. The interest of the user is jointly determined by the current conversation behavior and social influence, and the user final vector of the user is characterized by g_uThe two are merged by the full connection layer, such that:

wherein, W_phIs a conversion matrix, p_fIs a social influence, h_uIn order to be the current interest of the current user,

is a vector stitching operation.

And recommending the item according to the final vector representation of the user and the item vector representation. Article v_jVector x of_jMultiplying the representation by the final vector of the user, and then calculating the item v by applying a softmax function_jThe fraction of (c):

wherein, g_uAn interest vector representing the user is generated by the user,

representative article v_jThe possibility of becoming the next interactive item; at the same time according to

The log-likelihood function value of (a), calculating a loss function:

wherein, y_jRepresents v_jThe one-hot code of (a) is,

the function is optimized using a gradient descent method.

The invention has the following beneficial technical effects:

(1) the social recommendation method is different from the traditional social recommendation method in that potential friends of the user are further mined, the social network of the user is expanded, and the sparsity of data is relieved.

(2) The present invention analyzes the differences of two relationships in a social network, which are: the relationship between the real friend and the current user, and the relationship between the potential friend and the current user. And modeling the relationship of the two by adopting an attention mechanism respectively, and finally combining the two to obtain social influence.

Drawings

FIG. 1 is a schematic flow chart of a conversational social recommendation method based on a reconstructed social network according to the present invention;

FIG. 2 is a model framework diagram of a conversational social recommendation method based on a reconstructed social network according to the present invention.

Detailed Description

For further understanding of the present invention, the following describes a conversational social recommendation method based on restructuring social network in detail with reference to specific embodiments, but the present invention is not limited thereto, and those skilled in the art may make insubstantial improvements and modifications under the core guidance of the present invention and still fall within the scope of the present invention.

First, the variables and formulas used need to be given relevant definitions.

Definition 1. V: set of articles, and V ═ V₁，v₂,…，v_|V|And V represents the number of items in the collection of items.

Definition 2. s: current session of current user, session is all interactive item set s ═ v in current time period₁,v₂,…,v_|s|And | s | represents the number of items in the conversation.

Definition 3. S: set of sessions in a system, S ═ S₁，s₂,…,s_|S|And | S | represents the number of sessions in the session set.

Definition 4. G: social networks about users and user relationships.

Definition 5.N (u): the set of friends of the current user in social network G.

Definition 6.B (u): the algorithm mines a set of potential friends of the current user.

Definition 7.

Article v_jIs used for vector characterization.

In conjunction with the above variable definitions, the final problem is defined as: given the current conversation and social network of the current user, a set of potential friends similar to the user behavior is mined, a social influence is obtained by combining the real set of friends and the set of potential friends of the user, and items which are most likely to be interested in the next step of the current user are recommended by combining the interests of the user, wherein the items are a subset of the set V. When modeling social influence, two relationships are involved: the relationship between the real friend and the current user, and the relationship between the potential friend and the current user. The two relationships are different. Generally, the current users and real friends have many interests and have common interests. The extracted real friends and the current interests of the real friends are not necessarily close. And the potential friends are mined by calculating the similarity of the stored recent user session and the current user session, so that the interest of the potential friends is close to the current user. Therefore, the effects of real friends and potential friends on the current user need to be computed separately and in parallel, and then combined to get a unified social impact. And then predicting the next interested item of the user according to the interest of the user.

To this end, the present invention proposes a conversational social recommendation method based on restructuring a social network, as shown in fig. 2, a forward propagation (forward propagation) part of the method is mainly composed of four parts. The first part is to find the real friends of the current user from the social network based on the current user; the second part is to find potential friends of the current user based on the current session of the current user and the stored set of sessions; the third part is to obtain the interest representation of the current user, real friends and potential friends; the fourth part is that real friends and potential friends of the current user are combined to obtain the social influence of the friends on the user; the fifth part is that the final vector representation of the user is obtained by combining the interest of the user and the social influence; and finally, recommending the article according to the final vector representation of the user and the article vector representation.

As shown in fig. 1, according to one embodiment of the present invention, the method comprises the steps of:

and S100, finding out real friends of the current user from the social network based on the current user. And establishing a social network G according to the data record of the actual friend relationship in the platform, wherein the social network G is an undirected graph. The neighbor nodes of the current user are found from the social network G, which is the current user's set of real friends n (u).

S200, based on the current conversation of the current user and the stored conversation set, finding out potential friends of the current user. The memory matrix M is adopted to store the recently-occurring conversation, the algorithm effect and the storage pressure are comprehensively considered in the method, and the number of conversation sequences stored in the memory matrix M is set to 10000. Current session s ═ { v ═ based on current user₁,v₂，…，v_|s|Finding out the most similar k sessions from the memory matrix M by calculating cosine similarity between the current session and the candidate sessions in the memory matrix M, and ensuring that the similarity is greater than a threshold sim_threAnd then extracting epsilon sessions randomly from the screened k sessions. Finally, the users of the epsilon conversations are determined as the current user's potential friend set B (u), and the extracted conversations represent the interests of the potential friends. The similarity calculation formula is as follows:

wherein s is_jIs any session stored in the memory matrix M.

Is a binary vector representation of a session s, if an item is present in the session, the corresponding position in s is 1, otherwise it is 0. In the same way, the method for preparing the composite material,

is a conversation s_jIs represented by a binary vector. l(s) and l(s)_j) Respectively representing sessions s and s_jLength of (d). For all sessions stored in the memory matrix M, the formula sim (s, s)_j) Calculating cosine similarity with the current conversation s, and lowering the similarity to be lower than a threshold sim_threFiltering out the sessions, sequencing the sessions from high to low according to the cosine similarity, finding out the first k sessions, and randomly extracting epsilon sessions from the sessions. sim_threSetting a decimal value can increase the diversity of recommended items, sim_threAnd a large value is set, so that more noises can be filtered. Here, sim_threSet to 0.3, k to 100, and ε to 10.

And S300, obtaining interest representations of the current user, the real friends and the potential friends. And extracting the interest of the corresponding user from the current conversation of the current user, the latest conversation of the real friend and the screened conversation of the potential friend, and respectively characterizing the conversation by adopting a gate control recurrent neural network (GRU) to obtain interest characterization. Namely, the current conversation of the current user, the latest conversation of the real friend and the screened conversation of the potential friend are respectively used as the input of a gate control recurrent neural network (GRU), and the output of the gate control recurrent neural network (GRU) is respectively used as the interest of the current user, the interest of the real friend and the interest of the potential friend:

z_i＝σ(W_xz·x_i+W_hz·h_i-1)

r_i＝σ(W_xr·x_i+W_hr·h_i-1)

wherein r is_iIs a reset gate, z_iTo update the gates (update gate), these two gating vectors determine which information can be used as the output of the gated loop unit.

Is the current memory content. x is the number of_iIs the node input of the current layer, i.e. the item v_iIs used for vector characterization. W_xz、W_hz、W_xrAnd W_hrRespectively, control the update gate z_iAnd a reset gate r_iThe parameter (c) of (c). W_xhAnd W_hhIs to control the pre-memory content

The parameter (c) of (c). As is the element-level matrix multiplication, σ is the sigmoid function. The output of the last hidden layer of the gated recurrent neural network (GRU) is the session characterization.

S400, combining the real friends and the potential friends of the current user to obtain the social influence of the friends on the user. The real friends and the potential friends are calculated separately and the real friendsThe effect of friends and potential friends on the current user is calculated from the attention mechanism, with each friend having a different effect on the current user. The importance of real friends and potential friends is controlled by the prior parameter lambda and needs to be set by the experimenter. Ultimate social impact p_fThe specific calculation method is as follows:

wherein alpha is_uiRepresenting real friends u_iEffect on the current user, α_ujRepresenting potential friends u_jAs a function of the current user's role,

is that the influence of real friends and potential friends on the current user is gathered, p_fIs to

Adding a nonlinear perceptron layer is also the final social influence; h is_u、h_iAnd h_jRespectively a current user and a real friend u_iAnd potential friends u_jIs characterized by the vector of (1), attention value alpha_uiAnd alpha_ujCalculated using a multiplicative attention mechanism and normalized using the softmax function. The prior parameter lambda belongs to [0,1 ]]The weights of the real friend role and the potential friend role are controlled, and lambda is set to be 0.7 in the experiment. W_gIs to convert matrix parametersNumber, ReLU is the ReLU activation function.

And S500, obtaining the final vector representation of the user by combining the interest and social influence of the user. The interest of the user is jointly determined by the current conversation behavior and social influence, and the user final vector of the user is characterized by g_uThe two are merged by the full connection layer, such that:

wherein, W_phIs a conversion matrix, p_fIs a social influence, h_uIn order to be the current interest of the current user,

is a vector stitching operation.

And S600, recommending the article according to the final vector representation of the user and the article vector representation. Article v_jVector x of_jMultiplying the representation by the final vector of the user, and then calculating the item v by applying a softmax function_jThe fraction of (c):

wherein, g_uAn interest vector representing the user is generated by the user,

representative article v_jThe possibility of becoming the next interactive item; at the same time according to

The log-likelihood function value of (a), calculating a loss function:

wherein, y_jRepresents v_jThe one-hot code of (a) is,

the function is optimized using a gradient descent method.

The foregoing description of the embodiments is provided to facilitate understanding and application of the invention by those skilled in the art. It will be readily apparent to those skilled in the art that various modifications to the above-described embodiments may be made, and the generic principles defined herein may be applied to other embodiments without the use of inventive faculty. Therefore, the present invention is not limited to the above embodiments, and those skilled in the art should make improvements and modifications to the present invention based on the disclosure of the present invention within the protection scope of the present invention.

Claims (3)

Translated fromChinese

1.一种基于重构社交网络的会话社交推荐方法，其特征在于：1. A conversational social recommendation method based on reconstructing a social network, characterized in that:基于当前用户，从社交网络中找到当前用户的真实朋友；根据平台中实际好友关系的数据记录，建立社交网络G，社交网络G是无向图；从社交网络G中找到当前用户的邻居节点，就是当前用户的真实朋友集合N(u)；Based on the current user, find the real friends of the current user from the social network; build a social network G according to the data records of the actual friend relationship in the platform, and the social network G is an undirected graph; find the neighbor nodes of the current user from the social network G, is the real friend set N(u) of the current user;基于当前用户的当前会话和存储的会话集合，找到当前用户的潜在朋友；采用记忆矩阵M存储最近发生的会话；基于当前用户的当前会话s＝{v₁,v₂,…,v_|s|}，通过计算当前会话和记忆矩阵M中的候选会话之间的cosine相似度，从记忆矩阵M中找出最相似的k个会话，且保证相似度大于阈值sim_thre，再从筛选出的k个会话中随机抽取ε个会话；最后确定这ε个会话的用户为当前用户的潜在朋友集合B(u)，且抽取出的会话代表了潜在朋友的兴趣；Based on the current session of the current user and the set of stored sessions, find the potential friends of the current user; use the memory matrix M to store the most recent sessions; based on the current session of the current user s={v₁ ,v₂ ,...,v_|s| }, by calculating the cosine similarity between the current session and the candidate sessions in the memory matrix M, find the most similar k sessions from the memory matrix M, and ensure that the similarity is greater than the threshold sim_thre , and then select the k Randomly select ε sessions from the ε sessions; finally determine that the users of these ε sessions are the current user's potential friend set B(u), and the extracted sessions represent the interests of potential friends;得到当前用户、真实朋友和潜在朋友的兴趣表征；从当前用户的当前会话、真实朋友的最近会话以及筛选出的潜在朋友的会话中抽取出对应用户的兴趣，采用门控制循环神经网络GRU分别对会话进行表征，得到兴趣表征；也就是将当前用户的当前会话、真实朋友的最近会话以及筛选出的潜在朋友的会话分别作为门控制循环神经网络GRU的输入，分别得到门控制循环神经网络GRU的输出作为当前用户的兴趣、真实朋友的兴趣以及潜在朋友的兴趣；最后，得到当前用户、任一真实朋友u_i和任一潜在朋友u_j的兴趣表征分别为h_u、h_i和h_j；Obtain the interest representations of the current user, real friends and potential friends; extract the interests of the corresponding users from the current session of the current user, the recent sessions of real friends and the sessions of the screened potential friends, and use the gated recurrent neural network GRU to respectively The session is characterized to obtain the interest representation; that is, the current session of the current user, the recent session of the real friend, and the session of the screened potential friend are used as the input of the gated recurrent neural network GRU, respectively, and the gated recurrent neural network GRU is obtained. The output is the interest of the current user, the interest of the real friend and the interest of the potential friend; finally, the interest representations of the current user, any real friend_ui and any potential friend_uj are obtained as hu,_hi and_hj respectively;结合当前用户的真实朋友和潜在朋友，得到朋友对用户的社交影响；将真实朋友和潜在朋友分开计算，且真实朋友和潜在朋友对当前用户的作用由注意力机制计算得到，每个朋友对当前用户的作用不同；而真实朋友和潜在朋友的重要度由先验参数λ控制，需要由实验者设置；最终社交影响p_f具体的计算方式如下：Combine the current user's real friends and potential friends to get the social influence of friends on the user; real friends and potential friends are calculated separately, and the effect of real friends and potential friends on the current user is calculated by the attention mechanism, and each friend has an impact on the current user. The roles of users are different; the importance of real friends and potential friends is controlled by a priori parameter λ, which needs to be set by the experimenter; the final calculation method of social influence p_f is as follows:

其中，α_ui表示真实朋友u_i对当前用户的作用，α_uj表示潜在朋友u_j对当前用户的作用，

是聚集了真实朋友和潜在朋友对当前用户的影响，p_f是对

加一层非线性的感知器层，也是最终社交影响；h_u、h_i和h_j分别是当前用户、真实朋友u_i和潜在朋友u_j的兴趣表征，注意力值α_ui和α_uj采用乘法注意力机制计算得到，并使用softmax函数进行了归一化；先验参数λ∈[0,1]控制真实朋友作用和潜在朋友作用的权重；W_g 是转换矩阵参数，ReLU是ReLU激活函数；Among them, α_ui represents the effect of the real friend u_i on the current user, α_uj represents the effect of the potential friend u_j on the current user,

is the influence of real friends and potential friends on the current user, p_f is the

Adding a non-linear perceptron layer is also the final social influence;_hu , hi and h_j are the interest representations of the current user, real friend_ui and potential friend u_{jrespectively} , and the attention values α_ui and α_uj adopt The multiplicative attention mechanism is calculated and normalized using the softmax function; the prior parameter λ∈[0,1] controls the weight of the true friend role and the potential friend role; W_g is the transformation matrix parameter, and ReLU is the ReLU activation function ;结合用户自身兴趣和社交影响，获得用户最终向量表征；用户的兴趣由他当前会话行为和社交影响共同决定，用户的最终向量表征g_u就由全连接层合并两者得到，令：Combining the user's own interests and social influence, the final vector representation of the user is obtained; the user's interest is jointly determined by his current session behavior and social influence, and the final vector representation of the user_gu is obtained by combining the two at the fully connected layer, let:

其中，W_ph是转换矩阵，p_f是社交影响，h_u为当前用户的兴趣表征，

为向量拼接操作；where W_ph is the transformation matrix, p_f is the social influence,_hu is the current user’s interest representation,

is a vector splicing operation;根据用户最终向量表征和物品向量表征，推荐物品；将物品v_j的向量x_j乘以用户最终向量表征，再应用softmax函数计算出物品v_j的分数：According to the final vector representation of the user and the vector representation of the item, recommend items; multiply the vector x_j of the item v_j by the final vector representation of the user, and then apply the softmax function to calculate the score of the item v_j :

其中，g_u代表用户的最终向量表征，

代表物品v_j成为下一个交互物品的可能性；同时根据

的对数似然函数值，计算损失函数：where_gu represents the final vector representation of the user,

represents the possibility of item v_j becoming the next interactive item; meanwhile, according to

The log-likelihood function value of , calculates the loss function:

其中，y_j代表v_j的one-hot编码，

函数用梯度下降法来最优化。Among them, y_j represents the one-hot encoding of v_j ,

The function is optimized using gradient descent.2.根据权利要求1所述的一种基于重构社交网络的会话社交推荐方法，其特征在于：所述会话之间的cosine相似度计算公式如下：2. a kind of conversational social recommendation method based on reconstructed social network according to claim 1, is characterized in that: the cosine similarity calculation formula between described conversations is as follows:

其中，s_j是记忆矩阵M中存储的任一会话；

是会话s的二进制向量表示，如果一个物品出现在会话中，那么s中对应位置为1，否则为0；同理，

是会话s_j的二进制向量表示；l(s)和l(s_j)分别代表了会话s和s_j的长度；对于记忆矩阵M中存储的所有会话，用公式sim(s,s_j)计算出和当前会话s的cosine相似度，把相似度低于阈值sim_thre的会话过滤掉，再按照cosine相似度由高到低排序，找出前k个会话，并从中随机抽取出ε个会话。where s_j is any session stored in the memory matrix M;

is the binary vector representation of session s. If an item appears in the session, the corresponding position in s is 1, otherwise it is 0; similarly,

is the binary vector representation of session s_j ; l(s) and l(s_j ) represent the lengths of sessions s and s_j respectively; for all sessions stored in memory matrix M, use the formula sim(s,s_j ) to calculate Get the cosine similarity with the current session s, filter out the sessions whose similarity is lower than the threshold sim_thre , and then sort them according to the cosine similarity from high to low, find the top k sessions, and randomly extract ε sessions from them.3.根据权利要求1所述的一种基于重构社交网络的会话社交推荐方法，其特征在于：所述门控制循环神经网络GRU为：3. a kind of conversational social recommendation method based on reconstructed social network according to claim 1, is characterized in that: described gate control recurrent neural network GRU is:z_i＝σ(W_xz·x_i+W_hz·h_i-1)z_i =σ(W_xz ·x_i +W_hz ·h_i-1 )r_i＝σ(W_xr·x_i+W_hr·h_i-1)r_i =σ(W_xr ·x_i +W_hr ·h_i-1 )

其中，r_i是重置门，z_i为更新门，这两个门控向量决定了哪些信息能作为门控循环单元的输出；

是当前记忆内容；x_i是当前层的节点输入，也就是物品v_i的向量表征；W_xz、W_hz、W_xr和W_hr分别是控制更新门z_i和重置门r_i的参数；W_xh和W_hh是控制前记忆内容

的参数；⊙是元素级别的矩阵相乘，σ是sigmoid函数；门控制循环神经网络GRU的最后一个隐藏层的输出就是会话表征。Among them,_ri is the reset gate,_zi is the update gate, these two gate control vectors determine which information can be used as the output of the gated loop unit;

is the current memory content;_xi is the node input of the current layer, that is, the vector representation of the item vi; W_xz , W_hz , W_xr and W_hr are the parameters that control the update gate_zi and the reset gate_{rirespectively} ; W_xh and W_hh are the pre-control memory contents

⊙ is the element-level matrix multiplication, σ is the sigmoid function; the output of the last hidden layer of the gated recurrent neural network GRU is the session representation.

Images