CN112131484A - Multi-person session establishing method, device, equipment and storage medium - Google Patents
Multi-person session establishing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112131484A CN112131484A CN201910555161.XA CN201910555161A CN112131484A CN 112131484 A CN112131484 A CN 112131484A CN 201910555161 A CN201910555161 A CN 201910555161A CN 112131484 A CN112131484 A CN 112131484A
- Authority
- CN
- China
- Prior art keywords
- user
- target
- target user
- session
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 239000013598 vector Substances 0.000 claims abstract description 146
- 238000012512 characterization method Methods 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 230000006399 behavior Effects 0.000 claims description 82
- 230000000694 effects Effects 0.000 claims description 12
- 230000002452 interceptive effect Effects 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for establishing a multi-person session, wherein the method comprises the following steps: determining a behavior data sequence of each target user in a preset time, wherein the target users are users in a preset area; inputting the behavior data sequence into a dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model; and clustering the target users according to a preset clustering algorithm and the target vectors to obtain target user sets, and establishing multi-user conversations corresponding to the target user sets. By the technical scheme of the embodiment of the invention, the accuracy of session establishment can be improved.
Description
Technical Field
The embodiment of the invention relates to computer technology, in particular to a method, a device, equipment and a storage medium for establishing a multi-person session.
Background
In the internet era, socialization characteristics of people shopping become more and more obvious, most purchasers have own interest circles, namely groups consisting of users with the same interests and hobbies, and the interest circles often influence purchasing decisions of the purchasers.
In the prior art, statistical preference features of hundreds of dimensions are usually developed manually to characterize users, and interests of each user are analyzed based on characterization results, so that a multi-user session containing users with the same interests can be established for communication.
However, in the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
because each preference feature in the prior art is designed manually based on business experience and abstract features cannot be dug deeper, the representation result cannot accurately reflect the interests and hobbies of users, and the accuracy of session establishment is reduced.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for establishing a multi-person session, so as to improve the accuracy of session establishment.
In a first aspect, an embodiment of the present invention provides a method for establishing a multi-person session, including:
determining a behavior data sequence of each target user in a preset time, wherein the target users are users in a preset area;
inputting the behavior data sequence into a dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model;
clustering all the target users according to a preset clustering algorithm and all the target vectors to obtain all the target user sets, and establishing multi-user conversations corresponding to all the target user sets.
In a second aspect, an embodiment of the present invention further provides a multi-person session establishing apparatus, including:
the behavior data sequence determining module is used for determining a behavior data sequence of each target user within a preset time, wherein the target user is a user located in a preset area;
the target vector determination module is used for inputting the behavior data sequence into a dynamic vector representation model and determining a target vector corresponding to each target user according to the output of the dynamic vector representation model;
and the multi-user session establishing module is used for clustering all the target users according to a preset clustering algorithm and all the target vectors to obtain all the target user sets and establishing multi-user sessions corresponding to all the target user sets.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the steps of the multi-person session establishment method as provided by any embodiment of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the multi-person session establishment method provided in any embodiment of the present invention.
The embodiment of the invention has the following advantages or beneficial effects:
by determining the behavior data sequence of each target user in the preset area within the preset time and inputting each behavior data sequence into the dynamic vector characterization model, the dynamic target vector corresponding to each target user can be obtained according to the output of the dynamic vector characterization model, so that the interest of the user within the preset time can be reflected more accurately by the obtained target vector, all target users in the preset area are clustered based on the target vector, and therefore the target user set with the same interest can be obtained accurately, the corresponding multi-user session is established based on each target user set, and the accuracy of session establishment is improved.
Drawings
Fig. 1 is a flowchart of a method for establishing a multi-user session according to an embodiment of the present invention;
fig. 2 is an example of an information transmission system according to an embodiment of the present invention;
fig. 3 is a flowchart of a multi-person session establishment method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a multi-person session establishing apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for establishing a multi-user session according to an embodiment of the present invention, which is applicable to a situation where a user in a preset area is subjected to preference analysis to establish a multi-user session composed of users having the same interests and preferences. The method may be performed by a multi-person session establishing apparatus, which may be implemented in software and/or hardware, integrated in a device, such as a server, that monitors user behavior. The method specifically comprises the following steps:
and S110, determining a behavior data sequence of each target user in a preset time, wherein the target user is a user located in a preset area.
The preset area may be a geographical area preset based on the service scenario and the population distribution. For example, the preset area may refer to a geographical area where one cell or a plurality of adjacent cells are located, so as to improve the trust between users. The target user may refer to an online user located within a preset area. The online user may refer to a user who has generated interactive behavior in the provider online through the network. Interactive behavior may refer to, but is not limited to, browsing items, joining shopping carts, placing orders, searching, and clicking actions, among others. The preset time may be a historical time period preset based on business needs, such as within the last month. The behavior data sequence may refer to a sequence composed of item information in which the target user generates an interactive behavior within a preset time. For example, the behavior data sequence may be a sequence composed of names of articles, which have generated interactive behaviors by the target user within a preset time, in chronological order.
Specifically, each user in the preset area may be screened from all online users as a target user according to the geographical location of each online user. The embodiment can mine the behavior log of each target user in the preset time, determine all articles of which the target user has interactive behavior, and determine the corresponding behavior data sequence based on the article information.
And S120, inputting the behavior data sequence into the dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model.
The dynamic Vector representation model may be a model for dynamically representing Word vectors based on the context of words, which may more accurately reflect semantics, for example, when the context of a Word is different, the dynamic vectors corresponding to the Word are also different, so as to solve a problem that a static Vector representation model in the prior art, such as Word2Vector, TF-IDF (Term Frequency-Inverse Document Frequency), cannot accurately represent semantics. Illustratively, the dynamic vector characterization model may be, but is not limited to, a Bert network model. The Bert network model is pre-trained using two unsupervised prediction tasks, respectively: (1) mask LM task of the shielding language model: the Bert randomly masks some of the input words, only those masked words are predicted, and the final hidden vector corresponding to the masked words is input into the output softmax on the vocabulary to train a deep bi-directional network representation. (2) The next sentence predicts the task: many important NLP (Natural Language Processing) downstream tasks are based on understanding the relationship between two sentences. To train a model for understanding sentence relations, a binary next sentence prediction model is trained in advance, for example, when sentences a and B are selected as pre-training samples, 50% of B is likely to be the next sentence of a, and 50% is likely to be random sentences from the corpus. After the Bert network model is pre-trained, performing Transformer micro-debugging on the Bert network model based on the service corpus, so that a target vector corresponding to each target user can be determined by using the debugged Bert network model.
Specifically, the behavior data sequence corresponding to each target user is input into the dynamic vector characterization model, based on the context of each word in the behavior data sequence, each word vector can be dynamically characterized by using the dynamic vector characterization model, and the word vectors are integrated, and the target vector corresponding to each behavior data sequence is output, so that the target vector corresponding to each target user can be obtained.
S130, clustering the target users according to a preset clustering algorithm and the target vectors to obtain target user sets, and establishing multi-user conversations corresponding to the target user sets.
The preset clustering algorithm may be a method for classifying users, and may be, but not limited to, an LDA (content digital interface, document theme generation model) method and a K-Means (K-Means) clustering method. The set of target users may be made up of target users of the same hobbies. The target user set corresponds to the multi-person conversation one by one. The multi-user session may refer to a session composed of all target users in the target user set, so as to facilitate information sharing and communication among the users.
Specifically, the present embodiment may calculate the similarity between the target users by using the target vector corresponding to each target user. If the similarity is higher, the probability that the users have the same interests is higher, so that the target users with higher similarity can be clustered together to generate each target user set. Illustratively, the process of clustering the target users by using the LDA method is as follows: and randomly assigning a theme according to the target vector corresponding to each target user, taking the theme as an initial theme, and resampling the theme to which each target user belongs by using a Bayesian statistical Gibbs Sampling formula in the LDA until the Gibbs Sampling formula converges. After convergence, the target users under each theme are users with the same interests, so that the target users under each theme can be combined into a target user set, and each target user set can be obtained more conveniently. After obtaining each target user set, a corresponding multi-user session can be more accurately created for each target user set.
According to the technical scheme of the embodiment, the behavior data sequence of each target user in the preset time in the preset area is determined, and each behavior data sequence is input into the dynamic vector characterization model, so that the dynamic target vector corresponding to each target user can be obtained according to the output of the dynamic vector characterization model, the interest of the user in the preset time can be reflected more accurately by the obtained target vector, all target users in the preset area are clustered based on the target vector, the target user set with the same interest can be obtained accurately, the corresponding multi-user session is established based on each target user set, and the accuracy of session establishment is improved.
On the basis of the above technical solution, S110 may include: determining a behavior log text of each target user within a preset time; mapping each item name in each behavior log text to a corresponding item identifier based on a preset mapping relation; and sequencing the item identifications based on the item sequence in the behavior log text to obtain a behavior data sequence corresponding to each target user.
The behavior log text may refer to a recorded text of the interactive behavior generated within a preset time. The preset mapping relationship may refer to a corresponding relationship between the item name and the item identifier, and may be preset according to a service scenario and a requirement. The item identification may refer to, but is not limited to, at least one of a number, a letter, and a symbol. Illustratively, the item name is: the flower bud silk dress in spring dress, its article sign that corresponds is 1.
Specifically, in this embodiment, the trip can be recognized as each item name in the log text, the item identifier corresponding to each item name is determined based on the preset mapping relationship, the item identifiers are sorted according to the arrangement sequence of the item names in the behavior log text, and the original arrangement sequence of the items is maintained, so that the behavior data sequence composed of the item identifiers can be obtained.
On the basis of the above technical solution, before "determining a behavior log text of each target user within a preset time", the method may further include: determining a user receiving address corresponding to each online user; determining each online user in a preset area as a first user according to each user receiving address; determining the number of interaction behaviors of each first user in a preset time; and determining the first user with the interactive behavior frequency greater than or equal to a preset frequency threshold value as the target user.
The user's shipping address may refer to a shipping address commonly used by the user, and is used for representing the geographic location of the user. The first user may refer to an online user located within a preset area. The preset time threshold may refer to a minimum value of the number of interaction behaviors within a preset time.
Specifically, the embodiment may mine the behavior logs of the online users to determine the user shipping address corresponding to each online user. The reverse geocoding can be carried out on each user receiving address, the longitude and latitude information of each user receiving address is obtained, whether each online user is located in the preset area or not is detected based on the longitude and latitude range corresponding to the preset area, and therefore the first user located in the preset area can be obtained. The embodiment can count the interactive behavior of each first user based on the behavior log of each first user in the preset time to obtain the corresponding interactive behavior times, and determine the first user with the interactive behavior times larger than or equal to the preset time threshold as the target user, so that the target user with higher liveness can be obtained, the situation that the target vector cannot be accurately determined because the data item is 0 due to low liveness is avoided, and the accuracy of establishing the multi-user session is further improved.
On the basis of the above technical solution, when the preset clustering algorithm is a K-Mean clustering algorithm, S130 may include: taking each preset initial centroid vector in each initial user set as a first centroid vector, and taking the initial user set as a current user set, wherein the initial user set is an empty user set; calculating the similarity between each target user and each current user set according to each target vector and each first centroid vector; dividing each target user into a current user set with the maximum similarity; determining a second centroid vector corresponding to each current user set according to the target vector corresponding to each target user in each current user set; if the first centroid vector is different from the corresponding second centroid vector, updating the first centroid vector into the second centroid vector, and returning to execute the operation of calculating the similarity between each target user and each current user set based on the Euclidean distance formula, each target vector and each first centroid vector; and if the first centroid vector is the same as the corresponding second centroid vector, determining each current user set as a target user set.
The initial user set is a preset empty user set, and the number K of the initial user set may be preset. Each initial user set corresponds to a different preset initial centroid vector. The preset initial centroid vector may refer to a center vector of the initial user set, which may be set in advance based on traffic data. The current set of users may refer to each set of users when clustered, such as when clustered for the first time, the current set of users refers to the respective initial set of users. The first centroid vector may refer to a centroid vector of each current user set when clustering, such as when clustering for the first time, the first centroid vector refers to a respective preset initial centroid vector.
Specifically, the present embodiment may calculate, based on a euclidean distance formula, a euclidean distance between a target vector corresponding to each target user and a first centroid vector of each current user set, and the euclidean distance may reflect a magnitude of a similarity, where the greater the euclidean distance, the smaller the similarity. The target users may be classified into the current user set with the greatest similarity to the target users, that is, the current user set with the smallest euclidean distance, so that all the target users may be classified into the corresponding current user sets to update the current user sets. After secondary clustering is completed, the target vectors corresponding to each target user in the current user set can be averaged, the obtained average target vector is used as a second centroid vector of the current user set, so that the second centroid vector corresponding to each current user set can be determined, and whether clustering of the target users is completed or not is determined by comparing whether the first centroid vector and the second centroid vector corresponding to the same current user set are the same or not. If the first centroid vector is different from the corresponding second centroid vector, it indicates that the centroid of the current user set changes, and at this time, each first centroid vector may be updated to be the corresponding second centroid vector, and next clustering is performed based on each updated first centroid vector. If each first centroid vector is the same as the corresponding second centroid vector, it indicates that the centroid of the current user set does not change after secondary clustering, that is, clustering is finished, and at this time, the current user set can be directly used as a target user set, so that each target user set can be determined more conveniently based on a K-Mean clustering algorithm.
On the basis of the above technical solution, after S130, the method further includes: determining a first session to which each target user belongs according to the target users contained in each session; and sending the information of the first session to a user terminal corresponding to the corresponding target user so as to display the information of the first session on a display interface of the user terminal.
The information of the first session may refer to, but is not limited to, a session number, a session name, and session profile information. The user terminal may refer to a terminal device used by a target user, such as a smart phone.
Specifically, after each session is created, a corresponding session number may be assigned to each session, and a corresponding session name, session profile information, and the like may be set based on information of a target user included in the session. Fig. 2 shows an example of an information transmission system. The server in fig. 2 may refer to a device for establishing a multi-person session. The network in fig. 2 may refer to the medium that provides the communication links, and may include various connection types such as wired, wireless, or optical fiber cables. The server may interact with each user terminal device over a network. As shown in fig. 2, the server may send the information of the first session to the user terminal corresponding to each target user, so that the display interface of each user terminal displays the information of the corresponding first session, and the user may be reminded to join in the corresponding session for communication. Illustratively, the user terminal may display a poster of information that "your proprietary session found you" so that users with the same hobbies can be added to the same session, thereby sharing shopping experience, recommending items, spelling each other, etc. in the session. It should be noted that, since the target users in this embodiment are all users in the preset area, the trust level between the users can be increased during communication in the session, and thus the recommendation effect and the purchase rate of the articles are improved.
Example two
Fig. 3 is a flowchart of a multi-user session establishing method according to a second embodiment of the present invention, where on the basis of the foregoing embodiment, after establishing a multi-user session corresponding to each target user set, the present embodiment further includes determining a session manager of each session, so as to better perform session management. Wherein explanations of the same or corresponding terms as those of the above-described embodiments are omitted.
Referring to fig. 3, the method for establishing a multi-person session provided in this embodiment specifically includes the following steps:
s210, determining a behavior data sequence of each target user in a preset time, wherein the target users are users located in a preset area.
And S220, inputting the behavior data sequence into the dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model.
S230, clustering each target user according to a preset clustering algorithm and each target vector to obtain each target user set, and establishing a multi-user session corresponding to each target user set.
S240, determining the activity corresponding to each target user according to the behavior data corresponding to each target user.
The behavior data may refer to interaction behavior data generated in the target user online power supplier, such as data of shopping behavior. Liveness may refer to the degree of interaction in a user powering a merchant online.
Specifically, the interaction behavior times in the behavior data of each target user may be counted to determine the total interaction times of each target user, and the total interaction times may be directly used as the activity corresponding to the target user.
And S250, in each session, taking the target user with the highest activity as a manager to be determined in the session, and sending a session management request message to a terminal of the user to be determined of the manager to be determined.
Wherein, the session manager may refer to a user for managing the session, so as to organize the user to perform group purchase, item distribution, and the like. The session management solicitation message may be a message for soliciting whether to approve to become a session manager.
Specifically, the present embodiment may use the target user with the highest liveness in the session as the administrator of the pending session, and solicit the agreement of the administrator of the pending session by sending the session management request message.
And S260, taking the manager of the to-be-determined conversation as the manager of the corresponding conversation after receiving the conversation management agreement message sent by the user terminal to be determined.
Specifically, if the pending session manager agrees to become the session manager, that is, after receiving the session management agreement message, the pending session manager may be used as the session manager of the session. The conversation management personnel can collect the purchase demand of the offline user in the conversation, generate and match better and more accurate articles, directly deliver the articles to the conversation management personnel, and distribute the articles by the conversation management personnel, so that a pre-selling mode can be adopted, the storage and operation cost is effectively reduced, and the labor cost is saved. It should be noted that, if receiving the session management rejection message sent by the user terminal to be determined, the session management request message may be sent to the target user with the second highest activity level based on the sequence of the activity levels from large to small; a target user who agrees to become a session manager outside the session may also be added to the session, becoming the session manager for the session.
According to the technical scheme of the embodiment, the target user with the highest activity level in each session and agreeing to become the session manager is used as the session manager of the session, so that the session can be managed and distributed by the session manager, and the article popularization effect and the purchase rate are improved.
On the basis of the above scheme, after establishing the multi-user session corresponding to each target user set, the method may further include: when detecting that a newly added first target user exists in a preset area, acquiring a first behavior data sequence of the first target user; inputting the first behavior data sequence into a dynamic vector characterization model, and determining a first target vector corresponding to a first target user according to the output of the dynamic vector characterization model; and inputting the first target vector into a pre-trained preset network model, and determining the session to which the first target user belongs according to the output of the preset network model.
The preset network model may refer to, but is not limited to, a decision tree model, a random forest model, a neural network model, and the like. Specifically, before using the preset network model, the embodiment may use the target vector corresponding to each target user and the session to which the target vector belongs as training samples, and train the preset network model until the training error is smaller than the preset error, which indicates that the training of the preset network model is finished. When a new first target user is detected to appear in the preset area, a first target vector corresponding to the first target user can be determined by using the dynamic vector representation model, the first target vector is used as the input of the preset network model, and the session to which the first target user belongs is determined according to the output of the preset network model, so that the first target user can be added to the corresponding session, and the real-time addition and updating of the user in the session are realized.
The following is an embodiment of the multi-person session establishing apparatus provided in the embodiments of the present invention, which belongs to the same inventive concept as the multi-person session establishing methods in the embodiments described above, and reference may be made to the embodiments of the multi-person session establishing method for details that are not described in detail in the embodiments of the multi-person session establishing apparatus.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a multi-user session establishing apparatus according to a third embodiment of the present invention, which is applicable to a situation where preference analysis is performed on users in a preset area to establish a multi-user session composed of users having the same interests, and the apparatus specifically includes: a behavior data sequence determination module 310, a target vector determination module 320, and a multi-person session establishment module 330.
The behavior data sequence determining module 310 is configured to determine a behavior data sequence of each target user within a preset time, where the target user is a user located in a preset area; the target vector determination module 320 is configured to input the behavior data sequence into the dynamic vector characterization model, and determine a target vector corresponding to each target user according to the output of the dynamic vector characterization model; the multi-user session establishing module 330 is configured to cluster the target users according to a preset clustering algorithm and the target vectors to obtain target user sets, and establish a multi-user session corresponding to each target user set.
Optionally, the behavior data sequence determining module 310 is specifically configured to:
determining a behavior log text of each target user within a preset time; mapping each item name in each behavior log text to a corresponding item identifier based on a preset mapping relation; and sequencing the item identifications based on the item sequence in the behavior log text to obtain a behavior data sequence corresponding to each target user.
Optionally, the apparatus further comprises: a target user determination module to: before determining the behavior log text of each target user in the preset time, determining a user receiving address corresponding to each online user; determining each online user in a preset area as a first user according to each user receiving address; determining the number of interaction behaviors of each first user in a preset time; and determining the first user with the interactive behavior frequency greater than or equal to a preset frequency threshold value as the target user.
Optionally, the dynamic vector characterization model is a Bert network model.
Optionally, the preset clustering algorithm is: a K-Mean clustering algorithm; accordingly, the target multi-person session establishing module 330 is specifically configured to:
taking each preset initial centroid vector in each initial user set as a first centroid vector, and taking the initial user set as a current user set, wherein the initial user set is an empty user set; calculating the similarity between each target user and each current user set according to each target vector and each first centroid vector; dividing each target user into a current user set with the maximum similarity; determining a second centroid vector corresponding to each current user set according to the target vector corresponding to each target user in each current user set; if the first centroid vector is different from the corresponding second centroid vector, updating the first centroid vector into the second centroid vector, and returning to execute the operation of calculating the similarity between each target user and each current user set based on the Euclidean distance formula, each target vector and each first centroid vector; and if the first centroid vector is the same as the corresponding second centroid vector, determining each current user set as a target user set.
Optionally, the apparatus further comprises:
the first session determining module is used for determining a first session to which each target user belongs according to the target users contained in each session after the multi-user session corresponding to each target user set is established;
and the information sending module of the first session is used for sending the information of the first session to the user terminal corresponding to the corresponding target user so as to display the information of the first session on the display interface of the user terminal.
Optionally, the apparatus further comprises:
the activity determining module is used for determining the activity corresponding to each target user according to the behavior data corresponding to each target user after the multi-user session corresponding to each target user set is established;
the session management request message sending module is used for taking the target user with the highest liveness as a pending session manager in each session and sending a session management request message to a pending user terminal of the pending session manager;
and the session manager determining module is used for taking the manager of the to-be-determined session as the session manager of the corresponding session after receiving the session management agreement message sent by the user terminal to be determined.
The multi-person session establishing device provided by the embodiment of the invention can execute the multi-person session establishing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the multi-person session establishing method.
Example four
Fig. 5 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention. Fig. 5 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 5 is only an example and should not bring any limitations to the functionality and scope of use of the embodiments of the present invention.
As shown in FIG. 5, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement the steps of a multi-person session establishment method provided by the embodiment of the present invention, the method including:
determining a behavior data sequence of each target user in a preset time, wherein the target users are users in a preset area;
inputting the behavior data sequence into a dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model;
clustering each target user according to a preset clustering algorithm and each target vector to obtain each target user set, and establishing a multi-user session corresponding to each target user set.
Of course, those skilled in the art can understand that the processor may also implement the technical solution of the multi-person session establishment method provided in any embodiment of the present invention.
EXAMPLE five
This fifth embodiment provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of a multi-person session establishment method provided in any embodiment of the present invention, where the method includes:
determining a behavior data sequence of each target user in a preset time, wherein the target users are users in a preset area;
inputting the behavior data sequence into a dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model;
clustering each target user according to a preset clustering algorithm and each target vector to obtain each target user set, and establishing a multi-user session corresponding to each target user set.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A multi-person session establishment method, comprising:
determining a behavior data sequence of each target user in a preset time, wherein the target users are users in a preset area;
inputting the behavior data sequence into a dynamic vector characterization model, and determining a target vector corresponding to each target user according to the output of the dynamic vector characterization model;
clustering all the target users according to a preset clustering algorithm and all the target vectors to obtain all the target user sets, and establishing multi-user conversations corresponding to all the target user sets.
2. The method of claim 1, wherein determining a behavior data sequence of each target user within a preset time comprises:
determining a behavior log text of each target user within a preset time;
mapping each item name in each behavior log text into a corresponding item identifier based on a preset mapping relation;
and sequencing the item identifications based on the item sequence in the behavior log text to obtain a behavior data sequence corresponding to each target user.
3. The method of claim 2, further comprising, prior to determining the behavior log text of each target user within a preset time:
determining a user receiving address corresponding to each online user;
determining each online user in a preset area as a first user according to each user receiving address;
determining the number of interaction behaviors of each first user in a preset time;
and determining the first user with the interactive behavior frequency greater than or equal to a preset frequency threshold value as a target user.
4. The method of claim 1, wherein the dynamic vector characterization model is a Bert network model.
5. The method according to claim 1, wherein the predetermined clustering algorithm is: a K-Mean clustering algorithm;
correspondingly, clustering each target user according to a preset clustering algorithm and each target vector to obtain each target user set, including:
taking each preset initial centroid vector in each initial user set as a first centroid vector, and taking the initial user set as a current user set, wherein the initial user set is an empty user set;
calculating the similarity between each target user and each current user set according to each target vector and each first centroid vector;
dividing each target user into a current user set with the maximum similarity;
determining a second centroid vector corresponding to each current user set according to the target vector corresponding to each target user in each current user set;
if the first centroid vector is different from the corresponding second centroid vector, updating the first centroid vector to be the second centroid vector, and returning to execute the operation of calculating the similarity between each target user and each current user set based on the Euclidean distance formula, each target vector and each first centroid vector;
and if the first centroid vector is the same as the corresponding second centroid vector, determining each current user set as a target user set.
6. The method of claim 1, further comprising, after establishing the multi-person session for each of the target user sets:
determining a first session to which each target user belongs according to the target users contained in each session;
and sending the information of the first session to a user terminal corresponding to a corresponding target user so as to display the information of the first session on a display interface of the user terminal.
7. The method according to any one of claims 1-6, further comprising, after establishing the multi-person session corresponding to each of the target user sets:
determining the activity corresponding to each target user according to the behavior data corresponding to each target user;
in each conversation, the target user with the highest activity degree is used as a manager of the conversation to be determined, and a conversation management request message is sent to a terminal of the user to be determined of the manager of the conversation to be determined;
and when receiving a session management agreement message sent by the user terminal to be determined, taking the session manager to be determined as a session manager of a corresponding session.
8. A multi-person session establishment apparatus, comprising:
the behavior data sequence determining module is used for determining a behavior data sequence of each target user within a preset time, wherein the target user is a user located in a preset area;
the target vector determination module is used for inputting the behavior data sequence into a dynamic vector representation model and determining a target vector corresponding to each target user according to the output of the dynamic vector representation model;
and the multi-user session establishing module is used for clustering all the target users according to a preset clustering algorithm and all the target vectors to obtain all the target user sets and establishing multi-user sessions corresponding to all the target user sets.
9. An apparatus, characterized in that the apparatus comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the multi-person session establishment method steps of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the multi-person session establishment method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910555161.XA CN112131484A (en) | 2019-06-25 | 2019-06-25 | Multi-person session establishing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910555161.XA CN112131484A (en) | 2019-06-25 | 2019-06-25 | Multi-person session establishing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112131484A true CN112131484A (en) | 2020-12-25 |
Family
ID=73849441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910555161.XA Pending CN112131484A (en) | 2019-06-25 | 2019-06-25 | Multi-person session establishing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112131484A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469785A (en) * | 2021-06-29 | 2021-10-01 | 深圳市点购电子商务控股股份有限公司 | Method and device for establishing multi-person session and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649517A (en) * | 2016-10-17 | 2017-05-10 | 北京京东尚科信息技术有限公司 | Data mining method, device and system |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107818334A (en) * | 2017-09-29 | 2018-03-20 | 北京邮电大学 | A kind of mobile Internet user access pattern characterizes and clustering method |
| CN108632311A (en) * | 2017-03-20 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN109685128A (en) * | 2018-12-18 | 2019-04-26 | 电子科技大学 | A kind of MB-kmeans++ clustering method and the user conversation clustering method based on it |
-
2019
- 2019-06-25 CN CN201910555161.XA patent/CN112131484A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649517A (en) * | 2016-10-17 | 2017-05-10 | 北京京东尚科信息技术有限公司 | Data mining method, device and system |
| CN108632311A (en) * | 2017-03-20 | 2018-10-09 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
| CN107247786A (en) * | 2017-06-15 | 2017-10-13 | 北京小度信息科技有限公司 | Method, device and server for determining similar users |
| CN107818334A (en) * | 2017-09-29 | 2018-03-20 | 北京邮电大学 | A kind of mobile Internet user access pattern characterizes and clustering method |
| CN109685128A (en) * | 2018-12-18 | 2019-04-26 | 电子科技大学 | A kind of MB-kmeans++ clustering method and the user conversation clustering method based on it |
Non-Patent Citations (1)
| Title |
|---|
| 宋斌;王玲;张宏;赵建;: "基于Web日志的匿名网络用户聚类研究", 南京理工大学学报(自然科学版), no. 05, 30 October 2006 (2006-10-30) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469785A (en) * | 2021-06-29 | 2021-10-01 | 深圳市点购电子商务控股股份有限公司 | Method and device for establishing multi-person session and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| US20210304075A1 (en) | Batching techniques for handling unbalanced training data for a chatbot | |
| CN111552880B (en) | Knowledge graph-based data processing method and device, medium and electronic equipment | |
| CN110869969A (en) | Virtual assistant for generating personalized responses within a communication session | |
| CN109976997B (en) | Test method and device | |
| US20210150398A1 (en) | Conversational interchange optimization | |
| CN110020162B (en) | User identification method and device | |
| US11544721B2 (en) | Supporting automation of customer service | |
| US11095601B1 (en) | Connection tier structure defining for control of multi-tier propagation of social network content | |
| US20220253647A1 (en) | Automatic machine learning model evaluation | |
| US20200167613A1 (en) | Image analysis enhanced related item decision | |
| CN112163081A (en) | Label determination method, device, medium and electronic equipment | |
| CN111639162A (en) | Information interaction method and device, electronic equipment and storage medium | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN111310065A (en) | Social contact recommendation method and device, server and storage medium | |
| CN113392920B (en) | Method, apparatus, device, medium, and program product for generating cheating prediction model | |
| CN114119123A (en) | Information pushing method and device | |
| CN112836128A (en) | Information recommendation method, device, equipment and storage medium | |
| CN112131484A (en) | Multi-person session establishing method, device, equipment and storage medium | |
| CN111435381A (en) | Request distribution method and device | |
| CN116806339A (en) | Virtual dialog system performance assessment and enrichment | |
| CN111897910A (en) | Information pushing method and device | |
| CN113742564A (en) | Target resource pushing method and device | |
| CN111782776A (en) | Method and device for realizing intention identification through slot filling | |
| CN112328871A (en) | Reply generation method, device, equipment and storage medium based on RPA module |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |