CN115794346A - Virtual object interaction method and device, electronic equipment and storage medium - Google Patents

Abstract

The embodiment of the application provides a virtual object interaction method and device, electronic equipment and a storage medium. The virtual object interaction method comprises the following steps: firstly, acquiring target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on a plurality of user information corresponding to the users; then, based on the target weight, carrying out priority sequencing on the plurality of users to obtain a first priority sequencing result; and finally, sequentially interacting with the plurality of users according to the first priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Description

Virtual object interaction method and device, electronic equipment and storage medium

Technical Field

The application belongs to the technical field of computers, and particularly relates to a virtual object interaction method, a virtual object interaction device, an electronic device and a readable storage medium.

Background

In the existing virtual object interaction method, in an interaction scene of multiple persons, after the interaction with a user generally starts, an interaction limiting function is started, and other persons are prevented from being inserted into the interaction process; and the condition that the virtual image without the interaction limiting function is inserted by other users exists in the interaction process of the virtual image with the users.

Disclosure of Invention

In view of the foregoing problems, the present application provides a virtual object interaction method, apparatus, electronic device, and storage medium to improve the foregoing problems.

In a first aspect, an embodiment of the present application provides a virtual object interaction method, which is applied to a virtual object, and the method includes: acquiring target weights corresponding to a plurality of users initiating interactive requests respectively, wherein the target weights are determined based on a plurality of kinds of user information corresponding to the users respectively; based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result; and interacting with the plurality of users in sequence according to the first priority ranking result.

In a second aspect, an embodiment of the present application provides a virtual object interaction apparatus, which runs on a virtual object, and includes: the device comprises a target weight obtaining unit, a first priority sorting unit and an interaction unit. The target weight acquisition unit is used for acquiring target weights corresponding to a plurality of users initiating interactive requests respectively, and the target weights are determined based on a plurality of kinds of user information corresponding to the users respectively; the first priority ranking unit is used for performing priority ranking on the plurality of users based on the target weight to obtain a first priority ranking result; and the interaction unit is used for sequentially interacting with the plurality of users according to the first priority ranking result.

In a third aspect, an embodiment of the present application provides a virtual object interaction electronic device, including one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods described above.

In a fourth aspect, the present application provides a computer-readable storage medium, in which a program code is stored, wherein the program code performs the above-mentioned method when running.

The embodiment of the application provides a virtual object interaction method and device, electronic equipment and a storage medium. The virtual object interaction method comprises the following steps: firstly, acquiring target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on a plurality of user information corresponding to the users; based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result; and interacting with the plurality of users in sequence according to the first priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Drawings

Fig. 1 is a flowchart illustrating a virtual object interaction method according to an embodiment of the present application;

fig. 2 is a flowchart illustrating a virtual object interaction method according to another embodiment of the present application;

fig. 3 is a flowchart illustrating a virtual object interaction method according to yet another embodiment of the present application;

FIG. 4 is a flow chart illustrating a virtual object interaction method according to yet another embodiment of the present application;

fig. 5 is a block diagram illustrating a virtual object interaction system according to yet another embodiment of the present application;

FIG. 6 is a block diagram illustrating an electronic device for executing the virtual object interaction method according to the embodiment of the present application in real time;

fig. 7 illustrates a storage unit for storing or carrying program code for implementing the virtual object interaction method according to the embodiment of the present application in real time.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the accompanying drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, or may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

When the virtual object in the current market is interacted with a plurality of users, interaction limitation can be opened after the virtual object is started by one user, the virtual object is only interacted with the user before the interaction is finished, and other users cannot insert the virtual object; or not open interaction limits resulting in other users being free to insert, resulting in interrupted interaction with the user.

The inventor finds that, in the related virtual object interaction methods, the related virtual object interaction methods are generally processed separately by respectively extracting single modal behavior features, so that the multi-modal interaction information of a user cannot be comprehensively analyzed and interacted in a multi-modal manner in a unified manner, and the efficiency of the interaction process is low.

Therefore, the inventor proposes a virtual object interaction method, a virtual object interaction device, an electronic device and a storage medium in the application. Firstly, acquiring target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on various user information corresponding to the users; then, based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result; and finally, sequentially interacting with the plurality of users according to the first priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Referring to fig. 1, an embodiment of the present application provides a virtual object interaction method, applied to a virtual object, where the method includes:

step S110: the method comprises the steps of obtaining target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on various user information corresponding to the users.

In the embodiment of the application, the virtual object acquires the target weight corresponding to the user before interacting with the user, and the acquired target weight is related to the user information corresponding to the user. The target weight is a weight value calculated according to user information based on the representation virtual object. The target weight is obtained by a first weight and a second weight, the first weight is used for representing weight values corresponding to the user information, and the second weight is used for representing preset weight values corresponding to the user information determined based on the attribute information of the virtual object.

Step S120: and performing priority ranking on the plurality of users based on the target weight to obtain a first priority ranking result.

In the embodiment of the application, after the target weight of the user is obtained, priority setting is performed from high to low according to the target weight value of the user, the priority of the user with the high target weight value is higher than that of the user with the low target weight value, and the set priorities are sorted, so that a first priority sorting result is obtained. The first priority ranking result is used for representing the numerical value ranking order of the target weight of the user.

Step S130: and interacting with the plurality of users in sequence according to the first priority ranking result.

In the embodiment of the application, after the system obtains the first priority ranking results of the plurality of users, the interaction with the users is performed according to the first priority ranking results, wherein the virtual object is preferentially interacted with the users with high priorities.

The virtual object interaction method comprises the steps of firstly, obtaining target weights corresponding to a plurality of users initiating interaction requests, wherein the target weights are determined based on various user information corresponding to the users; then, based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result; and finally, sequentially interacting with the plurality of users according to the first priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Referring to fig. 2, an embodiment of the present application provides a virtual object interaction method, which is applied to a virtual object, and the method includes:

step S210: and acquiring a plurality of user information corresponding to the plurality of users respectively.

In the embodiment of the application, the system acquires a plurality of pieces of user information corresponding to a plurality of users through a plurality of external sensors. Wherein the plurality of sensors may include a distance sensor, a sound sensor, and an infrared sensor; the plurality of user information includes subjective information and objective information corresponding to the user, the subjective information may include intimacy, intention, gender and age, and the objective information may include distance and time, which are not specifically limited herein.

For example, the virtual object may acquire distances between the plurality of users and the virtual object through an external distance sensor, and acquire the acquired distance information corresponding to the plurality of users.

Step S220: and respectively inputting a plurality of user information corresponding to the plurality of users into a pre-trained weight prediction model, and acquiring target weights corresponding to the plurality of users output by the weight prediction model.

In the embodiment of the application, after the virtual object acquires a plurality of pieces of user information corresponding to a plurality of users through a plurality of external sensors, the acquired plurality of pieces of user information are input into a weight prediction model trained in advance, the weight prediction model calculates the acquired plurality of pieces of user information to obtain corresponding weights, the weights corresponding to the acquired plurality of pieces of information are combined into a weight vector, and the weight prediction model trained in advance outputs target weights corresponding to the plurality of users according to the acquired weight vector.

For example, the virtual object acquires intimacy information, intention information, gender information, age information, distance information and time information of the user through an external sensor, inputs the acquired information into a weight prediction model trained in advance, acquires an intimacy information vector, an intention information vector, a gender information vector, an age information vector, a distance information vector and a time information vector corresponding to the weight prediction model, combines the acquired vectors to acquire a weight vector, and calculates the acquired weight vector to acquire a target weight corresponding to the user through the weight prediction model.

Step S230: and performing priority sequencing on the plurality of users based on the target weight to obtain a first priority sequencing result.

The step S230 may specifically refer to the detailed explanation in the above embodiments, and therefore, is not described in detail in this embodiment.

Step S240: and interacting with the plurality of users in sequence according to the first priority ranking result.

The step S240 may specifically refer to the detailed explanation in the above embodiment, and thus is not described in detail in this embodiment.

The virtual object interaction method comprises the steps of firstly obtaining a plurality of user information corresponding to a plurality of users, then inputting the user information corresponding to the users into a weight prediction model trained in advance, obtaining target weights corresponding to the users output by the weight prediction model, carrying out priority ordering on the users based on the target weights, obtaining a first priority ordering result, and finally interacting with the users in sequence according to the first priority ordering result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Referring to fig. 3, an embodiment of the present application provides a virtual object interaction method, applied to a virtual object, where the method includes:

step S310: and acquiring a plurality of user information corresponding to the plurality of users respectively.

In the embodiment of the application, the virtual object acquires user information corresponding to a plurality of users through a plurality of external sensors, wherein the user information comprises two parts, namely subjective information comprising intimacy, intention, age and gender; the second is objective information, including distance and time. For example, when each user initiates an interaction request, the identity information and the request record corresponding to the user who interacts are stored in the database, and the greater the number of interactions with the virtual object, the greater the intimacy between the user and the virtual object.

Step S320: and determining a first weight and a second weight corresponding to each of a plurality of user information corresponding to each user.

In the embodiment of the application, the corresponding first weight and the second weight are obtained according to a plurality of user information obtained by the virtual object. The first weight is used for representing the weight value obtained according to the user information when the plurality of pieces of user information are obtained, and the second weight is used for representing which user information in the plurality of pieces of user information has a larger influence degree on interaction between the virtual object and the user.

For example, the first weight corresponding to the information of the plurality of users is calculated as follows, and the distance between the collected virtual object and the plurality of users is D = [ D = [ D ] ₁ ,d ₂ ...d _n ]Wherein n is used to represent the number of users, the distance of each user is weighted by a first weight of

Wherein, W _Di Distance first weight, x, for characterizing the ith user _i Distance information for characterizing an ith user, max (D) for characterizing a maximum distance of distances between the virtual object and the plurality of users; the time of all users initiating the interactive request is T = [ T = [) ₁ ,t ₂ ...t _n ]Then the first weight of time for each user is

Wherein, W _Ti First weight of time, t, for characterizing the ith user _i Time information used for representing the ith user, and max (T) used for representing the longest time in the time of initiating the request by all users; for the intimacy first weight, the system inquires from the database that the number of interactions between the user and the virtual object is I = [ I = [ ] ₁ ,i ₂ ...i _n ]If the user obtains the first weight of the intimacy degree as

If there is no interactive record, the intimacy degree is the first weight W _Ii Is 0, wherein W _Ii First weight, i, for characterizing the intimacy of the ith user _i The affinity of the ith user is characterized, and max (I) is used for characterizing the maximum affinity of the plurality of users and the virtual object; for the first weight of the intention, when the user initiates the interaction, the system identifies the interaction intention of the user, gives a score according to the importance of the intention, and can classify the score according to the obtained score, if the obtained level of the interaction intention of the user is X = [ X ] ₁ ,x ₂ ...x _n ]Then the first weight is intended to be

Wherein, W _Xi First weight, x, for characterizing the intention of the ith user _i An intention level for characterizing an ith user, max (X) being a maximum level for characterizing an interactive intention among a plurality of users; for the gender first weight, the gender first weight W of the female may be set _Gi Set as 1, sex first weight W of male _Gi Set to 0; for the age first weight, the age of the elderly user may be weighted first weight W _Ai Set to 1, first weight W of age of other users _Ai Is set to 0.

Step S330: and determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the user information respectively so as to obtain the target weight corresponding to the user information respectively.

In the embodiment of the application, after the first weight and the second weight corresponding to the plurality of user information are obtained, the target weight of the user is obtained through calculation according to the first weight and the second weight. When a plurality of users exist, the plurality of users correspond to a plurality of target weights.

Illustratively, the distance from the virtual object to the first user is W _D1 Time first weight is W _T1 The first weight of intimacy is W _I1 The intention is that the first weight is W _X1 The first weight of gender is W _G1 Age first weight is W _A1 And the second weight of the simultaneously acquired distance is a _D A second weight of time is a _T The second weight of the intimacy is a _I Intention second weight is a _X A second weight of gender is _G Age second weight is a _A Combining the first weight and the second weight corresponding to the plurality of pieces of acquired user information of the user to obtain the target weight of the user, wherein the calculation formula of the target weight may be Z ₁ ＝a _D *W _D1 +a _T *W _T1 +a _I *W _I1 +a _X *W _X1 +a _G *W _G1+ a _A *W _A1 。

Step S340: and if the multiple users simultaneously initiate the interaction requests, acquiring respective interaction intentions of the multiple users.

In the embodiment of the application, if the time interval of the multiple users initiating the interaction requests is smaller than the preset time interval threshold, it can be determined that the multiple users are simultaneously initiating the interaction requests, so as to obtain the respective interaction intentions of the multiple users. The preset time interval threshold may be a default value of the system, or may be set by the system according to the attribute information of the virtual object, for example, the preset time interval threshold may be set to 1 second by the system. The interactive intention may be a query type request, or a cold talk type request, which is not limited in this embodiment.

Step S350: and classifying the intentions of the users based on the respective interaction intentions of the users to obtain intention classification results, wherein the intention classification results comprise a plurality of intention categories, and each intention category corresponds to at least one user.

In the embodiment of the application, after the interaction intentions corresponding to the multiple users are obtained, the virtual object performs intention classification on the obtained multiple interaction intentions according to Natural Language Processing (NLP), and users who agree with the graph are used as a class of users, so that multiple intention classes can be obtained, wherein each intention class corresponds to at least one user. After a plurality of intention categories are obtained by intention classification, the obtained intention categories are stored in a database. When the virtual object interacts with a plurality of users, the plurality of users in the same intention category are interacted in a unified mode.

As a way, a natural language processing is used for processing speech and character systems used for communication, and generally has applications in five aspects, namely, semantic text similarity analysis, i.e., a process of analyzing similarity between meaning and essence of two sections of text; text classification, which is used for automatically distributing predefined category labels according to the content or theme of a given document; extracting information, namely extracting information of a specified type from the unstructured or semi-structured text, and converting the unstructured text into structured information by means of information merging, redundancy elimination, conflict resolution and the like; fourthly, text mining is used for finding only based on text information; fifthly, machine translation is used for realizing automatic translation from one natural language to another natural language by using a computer.

Step S360: and determining the weight corresponding to each intention category based on the intention classification result and the target weight corresponding to each user.

In the embodiment of the present application, after the virtual object obtains a plurality of intention categories of interaction intentions according to natural language processing, a weight corresponding to each intention category is calculated according to target weights of a plurality of users corresponding to each intention category, where the calculation method may be simple averaging the plurality of target weights, or may be complex compound operation.

Illustratively, there are 5 users with the same intention in any intention category, and the target weight of each user is Z ₁ 、Z ₂ 、Z ₃ 、Z ₄ And Z ₅ Then the weight of the intention category is

Step S370: and performing priority ranking on the users corresponding to the plurality of intention categories based on the weight corresponding to each intention category to obtain a second priority ranking result.

In the embodiment of the application, after the weight corresponding to each intention category is obtained, priority ranking is performed according to the obtained weight value of each intention category, and a second priority ranking result is obtained according to the obtained ranking results of a plurality of intention categories.

As a mode, after the second priority ranking result is obtained, the second priority ranking result is sent to the multiple users initiating the interaction request, and the positions of the multiple users in the second priority ranking result are notified.

Step S380: and interacting with the users corresponding to the plurality of intention categories in sequence according to the second priority ranking result.

In the embodiment of the application, after the second priority ranking result is obtained, the virtual object interacts with the users corresponding to the multiple intention categories according to the second priority ranking result.

Illustratively, the first intention category is first in the second prioritized result, the second intention category is second in the second prioritized result, and the first intention category has a higher priority in the second prioritized result than the second intention category, then the virtual object interacts with priority over the first intention category when interacting, and the interaction is performed with priority over the second intention category after the interaction of the first intention category is completed.

The virtual object interaction method includes the steps of firstly obtaining a plurality of user information corresponding to a plurality of users, then determining a first weight and a second weight corresponding to the user information corresponding to each user, then determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the user information, so as to obtain the target weight corresponding to each user, obtaining an interaction intention of each user if the users initiate an interaction request at the same time, then classifying the users according to the interaction intention of each user, obtaining intention classification results, wherein the intention classification results comprise a plurality of intention categories, each intention category corresponds to at least one user, determining a weight corresponding to each intention category based on the intention classification results and the target weights corresponding to the users, then performing priority ranking on the users corresponding to the intention categories based on the weights corresponding to each intention category, obtaining a second priority ranking result, and finally performing interaction with the users corresponding to the intention categories according to the second priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Referring to fig. 4, an embodiment of the present application provides a virtual object interaction method, applied to a virtual object, where the method includes:

step S401: and acquiring the attribute information of the virtual object.

In the embodiment of the application, when the virtual object is generated, the attribute information of the virtual object is determined according to the function and the attribute of the virtual object, and data corresponding to the attribute information of the virtual object is acquired. The attributes of the virtual object may include entertainment type, service type and work type, and the functions of the virtual object may be an attendant, a shopping guide and a technician, which are not specifically limited herein.

Step S402: and determining a second weight corresponding to each of the plurality of user information corresponding to each user based on the attribute information.

In the embodiment of the application, after the attribute information of the virtual object is acquired, the second weights corresponding to the user information are determined according to the attribute information. The value of the second weight corresponding to the plurality of user information changes according to a change in the attribute information of the virtual object, and for example, if the attribute information of the virtual object is a technician of a working type, the value of the second weight of the distance and time may be set to be larger, and the value of the second weight of the intimacy degree, the intention, the sex, and the age may be set to be smaller.

Step S403: and acquiring a plurality of user information corresponding to the plurality of users respectively.

Step S403 may refer to the detailed explanation in the above embodiment, and therefore, is not described in detail in this embodiment.

Step S404: and determining a first weight and a second weight corresponding to a plurality of user information corresponding to each user.

For the step S404, detailed explanations in the above embodiments may be specifically referred to, and thus are not described in this embodiment.

Step S405: and determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the information of the plurality of users respectively so as to obtain the target weight corresponding to each of the plurality of users.

Step S405 may refer to the detailed explanation in the above embodiments, and therefore is not described in detail in this embodiment.

Step S406: and if the multiple users simultaneously initiate the interaction requests, acquiring respective interaction intentions of the multiple users.

For step S406, the detailed explanation in the above embodiment can be specifically referred to, so that the detailed explanation is not repeated in this embodiment.

Step S407: and performing intention classification on the users based on respective interaction intentions of the users to obtain intention classification results, wherein the intention classification results comprise a plurality of intention categories, and each intention category corresponds to at least one user.

Step S407 may specifically refer to the detailed explanation in the above embodiments, and therefore is not described in detail in this embodiment.

Step S408: and determining the weight corresponding to each intention category based on the intention classification result and the target weight corresponding to each of the plurality of users.

Step S408 may refer to the detailed explanation in the above embodiments, and therefore, is not described in detail in this embodiment.

Step S409: and performing priority ranking on the users corresponding to the plurality of intention categories based on the weight corresponding to each intention category to obtain a second priority ranking result.

Step S409 may specifically refer to the detailed explanation in the above embodiments, and therefore is not described in detail in this embodiment.

Step S410: and if the interaction request initiated by the new user is received in the process of interacting with the multiple users.

In the embodiment of the application, if the time interval of the user initiating the interaction request is greater than the preset time interval threshold, it indicates that the interaction request initiated by the new user is received.

Illustratively, the system sets a preset time interval threshold value to 1 second according to the attribute information of the current virtual object, and if the time interval of the user initiating the interaction request is greater than 1 second, the system determines that the user currently initiating the interaction request is a new user and receives the interaction request initiated by the current new user.

Step S411: and acquiring the target weight of the user who is currently interacting and acquiring the target weight corresponding to the new user.

In the embodiment of the application, after the user who sends the request is judged to be the new user and receives the interaction request of the new user, the system obtains the target weight of the user who is interacting with the virtual object at present, and obtains the target weight of the new user according to the user information of the new user.

As another mode, when interaction requests initiated by a plurality of new users are received, the system obtains interaction intents of the plurality of new users, performs intention classification on the obtained interaction intents to obtain a plurality of intention categories, performs weight calculation on the intention categories corresponding to the obtained new users, and calculates weights of the intention categories interacting with the virtual object at the current time.

Step S412: and if the target weight corresponding to the new user is larger than the target weight of the user currently interacting, interrupting the current interaction and interacting with the new user.

In the embodiment of the application, after the target weight corresponding to the new user and the target weight of the user who is interacting currently are obtained, the target weight of the new user is compared with the target weight of the user who is interacting currently, if the target weight corresponding to the new user is larger than the target weight of the user who is interacting currently, the interaction between the virtual object and the current user is interrupted, the interaction state during interruption is stored, the user who is interrupted in interaction is notified to wait, the interaction request of the new user is responded, the virtual object interacts with the new user, connection is reestablished with the interrupted user until the interaction with the new user is finished, the stored interaction state is read, and interaction with the interrupted user is continued.

As another mode, if the target weight corresponding to the new user is smaller than the target weight of the user currently interacting, the new user continues to interact with the user currently interacting, and the new user is arranged in the first priority ranking result according to the corresponding target weight.

As another mode, if interaction requests initiated by a plurality of new users are received, after weights of intention categories corresponding to the new users are obtained, the weights of the intention categories corresponding to the new users are compared with the weights of the intention categories currently interacting with the virtual object, if the weights of the intention categories corresponding to the new users are greater than the weights of the intention categories currently interacting with the virtual object, the intention categories currently interacting are interrupted, the interaction state during interruption is stored, the user corresponding to the interrupted intention category is notified to wait, the intention categories of the new users with weights less than the weights corresponding to the interrupted intention categories are ranked in a second priority ranking result according to the weights, then the interaction category with the largest weight among the interaction categories corresponding to the new users is preferentially responded, the interaction category with the largest weight is interacted with the interaction category with the largest weight, then the interaction with the intention category with the smallest weight is interacted with, and the interaction with the interrupted category is resumed after the virtual object and the intention category with the largest weight among the new users are all interacted, the interaction state of the stored is read, and the interaction state of the interrupted category is continued.

As another mode, if the weights of the plurality of intention categories corresponding to the new user do not have a weight larger than the weight of the intention category currently interacting with the virtual object, the plurality of intention categories corresponding to the new user are ranked in the second priority ranking result according to the weights, and the interaction with the current interaction category is continued.

Step S413: and acquiring the current interaction interruption times.

In the embodiment of the application, after the target weight corresponding to the new user is greater than the target weight of the user currently interacting and the current interaction is interrupted, the system reads the stored identity information and the request record from the database and obtains the number of times of interrupting the interaction of the new user.

Step S414: and if the times are more than the preset interruption times, entering a standby state.

In the embodiment of the application, the system acquires the number of times of interruption interaction of a new user from the database, if the acquired number of times of interruption interaction is greater than the preset number of times of interruption, the virtual object automatically interrupts the interaction of the current user, sends an information warning to the new user, records the number of violation times of the new user in the database, enters a standby state for the new user, and waits for the new user to initiate an interaction request again. The preset interruption frequency may be a default value of the system, or may be set according to attribute information of the virtual object, for example, the preset interruption frequency may be defaulted to 10 times by the system.

As one mode, if the system queries that the violation number of the user is greater than a preset violation number threshold in the database, the target weight of the user is reduced when the target weight of the user is calculated. Meanwhile, the system can set rule for clearing the number of violations according to the attribute information of the virtual object, for example, the attribute information of the virtual object is an entertainment waiter, and the number of violations of the user can be cleared according to the rule that the number of violations is reduced once per hour. The preset violation number threshold may be a default number of times of the system, or may be set according to attribute information of the virtual object, for example, the preset violation number threshold may be defaulted to 5 times by the system.

Illustratively, if the number of violations of the user is greater than 5, the target weight obtained for the user when calculating the target weight is multiplied by 0.9 ⁵ And simultaneously sending warning information, and clearing the violation times of the user according to a mode of reducing the violation times once every hour.

The application provides a virtual object interaction method, firstly obtaining attribute information of a virtual object, then determining a second weight corresponding to a plurality of user information corresponding to each user based on the attribute information, then obtaining a plurality of user information corresponding to each user, determining a first weight and a second weight corresponding to a plurality of user information corresponding to each user, then determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the plurality of user information, so as to obtain the target weight corresponding to each user, if the plurality of users initiate interaction requests at the same time, obtaining respective interaction intentions of the plurality of users, then performing intention classification on the plurality of users based on the respective interaction intentions of the plurality of users, so as to obtain intention classification results, the intention classification result comprises a plurality of intention categories, each intention category corresponds to at least one user, then based on the intention classification result and the respective corresponding target weights of the users, the weight corresponding to each intention category is determined, the users corresponding to the intention categories are subjected to priority ranking based on the weight corresponding to each intention category, a second priority ranking result is obtained, if an interaction request initiated by a new user is received in the interaction process with the users, the target weight of the user currently interacting is obtained, the target weight corresponding to the new user is obtained, if the target weight corresponding to the new user is greater than the target weight of the user currently interacting, the current interaction is interrupted, the interaction with the new user is carried out, the current interaction interruption frequency is obtained, and if the frequency is greater than the preset interruption frequency, entering a standby state. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

Referring to fig. 5, an embodiment of the present application provides a virtual object interaction apparatus 500, operating on a virtual object, where the apparatus 500 includes:

a target weight obtaining unit 510, configured to obtain target weights corresponding to respective multiple users who initiate the interaction request, where the target weights are determined based on multiple types of user information corresponding to the respective multiple users.

As one way, the target weight obtaining unit 510 is further configured to obtain a plurality of user information corresponding to each of the plurality of users; determining a first weight and a second weight corresponding to a plurality of user information corresponding to each user; and determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the information of the plurality of users respectively so as to obtain the target weight corresponding to each of the plurality of users.

Optionally, the target weight obtaining unit 510 is further configured to obtain a plurality of user information corresponding to each of the plurality of users; and respectively inputting a plurality of user information corresponding to the plurality of users into a weight prediction model trained in advance, and acquiring target weights corresponding to the plurality of users output by the weight prediction model.

A first prioritization unit 520, configured to prioritize the multiple users based on the target weight to obtain a first prioritization result.

As a manner, the first priority sorting unit 520 is further configured to obtain respective interaction intents of the multiple users if the multiple users initiate interaction requests at the same time; performing intention classification on the multiple users based on respective interaction intentions of the multiple users to obtain intention classification results, wherein the intention classification results comprise multiple intention categories, and each intention category corresponds to at least one user; determining a weight corresponding to each intention category based on the intention classification result and the target weights corresponding to the users respectively; and performing priority ranking on the users corresponding to the plurality of intention categories based on the weight corresponding to each intention category to obtain a second priority ranking result.

Optionally, the first prioritization unit 520 is further configured to obtain attribute information of the virtual object; and determining a second weight corresponding to each of the plurality of user information corresponding to each user based on the attribute information.

An interacting unit 530, configured to sequentially interact with the multiple users according to the first priority ranking result.

As a manner, the interaction unit 530 is further configured to sequentially interact with the users corresponding to the plurality of intention categories according to the second prioritization result.

Optionally, the interaction unit 530 is further configured to receive an interaction request initiated by a new user in the process of interacting with the multiple users; acquiring a target weight of a user who is currently interacting and acquiring a target weight corresponding to the new user; and if the target weight corresponding to the new user is larger than the target weight of the user currently interacting, interrupting the current interaction and interacting with the new user.

Optionally, the interaction unit 530 is further configured to obtain a number of times of interrupting the current interaction; and if the times are more than the preset interruption times, entering a standby state.

It should be noted that the apparatus embodiment and the foregoing method embodiment in this application correspond to each other, and specific principles in the apparatus embodiment may refer to the contents in the foregoing method embodiment, which is not described herein again.

An electronic device provided by the present application will be described with reference to fig. 6.

Referring to fig. 6, based on the virtual object interaction method and apparatus, another electronic device 600 capable of executing the virtual object interaction method is further provided in the embodiment of the present application. The electronic device 600 includes one or more processors 602 (only one shown), memory 604, and a network module 606 coupled to each other. The memory 604 stores programs that can execute the contents of the foregoing embodiments, and the processor 602 can execute the programs stored in the memory 604.

Processor 602 may include one or more processing cores, among other things. The processor 602 interfaces with various components throughout the electronic device 600 using various interfaces and circuitry to perform various functions of the server 600 and process data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 604 and invoking data stored in the memory 604. Alternatively, the processor 602 may be implemented in at least one hardware form of Digital Signal Processing (DSP), field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 602 may integrate one or a combination of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is to be understood that the modem may not be integrated into the processor 602, but may be implemented by a communication chip.

The Memory 604 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). The memory 604 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 604 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The data storage area may also store data created during use by the electronic device 600 (e.g., phone books, audio-visual data, chat log data), and so forth.

The network module 606 is configured to receive and transmit electromagnetic waves, and implement interconversion between the electromagnetic waves and the electrical signals, so as to communicate with a communication network or other devices, for example, an audio playing device. The network module 606 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The network module 606 may communicate with various networks such as the internet, intranets, wireless networks, or with other devices via a wireless network. The wireless network may comprise a cellular telephone network, a wireless local area network, or a metropolitan area network. For example, the network module 606 may perform information interaction with a base station.

Referring to fig. 7, a block diagram of a computer-readable storage medium according to an embodiment of the present application is shown. The computer readable medium 700 has stored therein program code that can be called by a processor to perform the method described in the method embodiments above.

The computer-readable storage medium 700 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer-readable storage medium 700 includes a non-volatile computer-readable storage medium. The computer readable storage medium 700 has storage space for program code 710 to perform any of the method steps of the method described above. The program code can be read from and written to one or more computer program products. The program code 710 may be compressed, for example, in a suitable form.

The embodiment of the application provides a virtual object interaction method and device, electronic equipment and a storage medium. The virtual object interaction method comprises the following steps: firstly, acquiring target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on various user information corresponding to the users; based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result; and interacting with the plurality of users in sequence according to the first priority ranking result. By the method, the target weights corresponding to the multiple users are obtained through the multiple user information, the virtual object performs priority sequencing on the users according to the weights of the multiple users, and interaction is performed according to the priority sequences of the multiple users, so that the efficiency of an interaction process is improved.

While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (10)

1. A virtual object interaction method, applied to a virtual object, the method comprising:

acquiring target weights corresponding to a plurality of users initiating interactive requests, wherein the target weights are determined based on various user information corresponding to the users;

based on the target weight, carrying out priority ranking on the plurality of users to obtain a first priority ranking result;

and interacting with the plurality of users in sequence according to the first priority ranking result.

2. The method of claim 1, wherein prioritizing the plurality of users based on the target weights results in a first prioritization result, comprising:

if the multiple users simultaneously initiate interaction requests, acquiring respective interaction intentions of the multiple users;

performing intention classification on the multiple users based on respective interaction intentions of the multiple users to obtain intention classification results, wherein the intention classification results comprise multiple intention categories, and each intention category corresponds to at least one user;

determining a weight corresponding to each intention category based on the intention classification result and a target weight corresponding to each of the plurality of users;

performing priority ranking on the users corresponding to the plurality of intention categories based on the weight corresponding to each intention category to obtain a second priority ranking result;

the sequentially interacting with the plurality of users according to the first priority ranking result comprises:

and interacting with the users corresponding to the plurality of intention categories in sequence according to the second priority ranking result.

3. The method of claim 1, wherein obtaining the target weight corresponding to each of the plurality of users initiating the interactive request comprises:

acquiring a plurality of user information corresponding to the plurality of users respectively;

determining a first weight and a second weight corresponding to a plurality of user information corresponding to each user;

and determining a target weight corresponding to each user based on the first weight and the second weight corresponding to the information of the plurality of users respectively so as to obtain the target weight corresponding to each of the plurality of users.

4. The method of claim 3, wherein determining the first weight and the second weight corresponding to each of the plurality of user information corresponding to each user further comprises:

acquiring attribute information of the virtual object;

and determining a second weight corresponding to each of the plurality of user information corresponding to each user based on the attribute information.

5. The method of claim 1, wherein obtaining the target weight corresponding to each of the plurality of users initiating the interactive request comprises:

acquiring a plurality of user information corresponding to the plurality of users respectively;

and respectively inputting a plurality of user information corresponding to the plurality of users into a weight prediction model trained in advance, and acquiring target weights corresponding to the plurality of users output by the weight prediction model.

6. The method of claim 1, wherein the sequentially interacting with the plurality of users according to the first prioritization result further comprises:

if the interaction request initiated by a new user is received in the process of interacting with the plurality of users;

acquiring a target weight of a user who is currently interacting and acquiring a target weight corresponding to the new user;

and if the target weight corresponding to the new user is larger than the target weight of the user currently interacting, interrupting the current interaction and interacting with the new user.

7. The method of claim 6, further comprising:

acquiring the current interaction interruption times;

and if the times are more than the preset interruption times, entering a standby state.

8. A virtual object interaction apparatus, operable with a virtual object, the apparatus comprising:

the target weight acquisition unit is used for acquiring target weights corresponding to a plurality of users initiating interactive requests respectively, and the target weights are determined based on a plurality of kinds of user information corresponding to the users respectively;

the first priority ranking unit is used for performing priority ranking on the plurality of users based on the target weight to obtain a first priority ranking result;

and the interaction unit is used for sequentially interacting with the plurality of users according to the first priority ranking result.

9. An electronic device comprising one or more processors and memory, one or more programs stored in the memory and configured to be executed by the one or more processors to perform the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program code comprising instructions for performing the method according to any of claims 1-7.

Images