[go: up one dir, main page]

WO2018210323A1 - Procédé et dispositif permettant la fourniture d'un objet social - Google Patents

Procédé et dispositif permettant la fourniture d'un objet social Download PDF

Info

Publication number
WO2018210323A1
WO2018210323A1 PCT/CN2018/087420 CN2018087420W WO2018210323A1 WO 2018210323 A1 WO2018210323 A1 WO 2018210323A1 CN 2018087420 W CN2018087420 W CN 2018087420W WO 2018210323 A1 WO2018210323 A1 WO 2018210323A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
information
social
social object
objects
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.)
Ceased
Application number
PCT/CN2018/087420
Other languages
English (en)
Chinese (zh)
Inventor
陈大年
刘华平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Zhangmen Science and Technology Co Ltd
Original Assignee
Shanghai Zhangmen Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Zhangmen Science and Technology Co Ltd filed Critical Shanghai Zhangmen Science and Technology Co Ltd
Publication of WO2018210323A1 publication Critical patent/WO2018210323A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Definitions

  • the present application relates to the field of communications, and in particular, to a technology for providing social objects.
  • a method for providing a social object on a network device side includes:
  • a method for providing a social object on a user equipment side includes:
  • a method for providing a social object includes:
  • the user equipment uploads user voice information of the target user to the corresponding network device
  • the network device matches the query in the social object information base based on the user sound information to obtain one or more social objects that match the user sound information;
  • the network device provides at least one of the one or more social objects to the user device;
  • the user device presents at least one of the one or more social objects.
  • a computer readable medium comprising instructions which, when executed, cause a system to perform the operations of the method as described above.
  • a network device for providing a social object includes:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method as described above.
  • a user equipment for providing a social object where the user equipment includes:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method as described above.
  • a system for providing a social object including the network device as described above, and the user device as described above are provided.
  • the user equipment of the present application uploads user voice information of the target user to the corresponding network device, and the network device matches the query in the social object information base based on the user voice information to obtain the voice with the user.
  • One or more social objects that match the information and then providing at least one of the one or more social objects to the user device, the user device presenting at least one of the one or more social objects The social object; thereby facilitating the user to quickly find the social object that matches the user's voice information, and expanding the user's social relationship chain based on the sound feature to enhance the user experience.
  • the application matches the query in the social object information base based on the user voice information and the user related information of the target user to obtain one or more matching with the user voice information and the user related information.
  • the social object can further expand the user experience by expanding the user's social relationship chain based on various features including sound features.
  • the present application provides at least one of the one or more social objects to the user based on the priority information of the social object, thereby facilitating the user to view and saving the user's time.
  • FIG. 1 shows a system topology diagram for providing social objects in accordance with one embodiment of the present application
  • FIG. 2 shows a flow chart of a method for providing a social object in accordance with another embodiment of the present application.
  • the terminal, the device of the service network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media including both permanent and non-persistent, removable and non-removable media, can be stored by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage,
  • FIG. 1 illustrates a system topology diagram for providing social objects, including a user equipment 1 and a network device 2, according to an embodiment of the present application.
  • the network device 2 includes an electronic device capable of automatically performing numerical calculation and information processing according to an instruction set or stored in advance, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), or the like. Programming gate arrays (FPGAs), digital processors (DSPs), embedded devices, and more.
  • the network device 2 includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a plurality of servers; here, the cloud is composed of a large number of computers or network servers based on Cloud Computing. Composition, in which cloud computing is a type of distributed computing, a virtual supercomputer consisting of a group of loosely coupled computers.
  • the network includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless ad hoc network (Ad Hoc network), and the like.
  • the user equipment 1 includes, but is not limited to, any electronic product that can perform human-computer interaction with the user, such as a smart phone, a tablet computer, a notebook computer, etc., and the electronic product can adopt any operating system, such as an android operating system and iOS. Operating system, Windows operating system, etc.
  • FIG. 2 is a flowchart of a method for providing a social object according to another embodiment of the present application, where the method includes step S201, step S202 and step S203 of the network device side, and step S101 and step S102 of the user equipment end. And step S103.
  • step S101 the user equipment 1 uploads the user voice information of the target user to the corresponding network device 2; in step S201, the network device 2 acquires the user voice information of the target user uploaded by the user equipment 1; in step S202, the network device 2 Matching a query in the social object information base based on the user sound information to obtain one or more social objects that match the user sound information; in step S203, the network device 2 will be among the one or more social objects At least one social object is provided to the user equipment 1; in step S102, the user equipment 1 receives one or more social objects provided by the network device 2 that match the user voice information; in step S103, the user equipment 1 presenting at least one of the one or more social objects.
  • user A may use the user's voice information (eg, the target user's voice recording, singing audio, etc.) of the target user through a specific application on the user device 1 (including but not limited to a web application, an application installed on the user device, etc.). ) Network device 2 uploaded to the specific application cloud.
  • the target user may be the user A himself, or may be a relative, friend, colleague, classmate, passerby, etc. of the user A.
  • the network device 2 obtains one or more social objects that match the user voice information of the target user by querying in a social object information repository in which a plurality of user voice information is stored.
  • the user A can immediately upload the user voice information of the target user, and then the network device 2 performs a matching query in the social object information base according to the user voice information; or the network device 2 can also be based on the user.
  • the user voice information uploaded before A is matched in the social object information base.
  • the network device 2 returns the one or more social objects to the user device 1; or the network device 2 matches the one or more social objects with the highest degree according to the matching degree.
  • One or several social objects with a high degree of matching are returned to the user device 1.
  • the user equipment 1 After receiving the one or more social objects that match the user voice information, the user equipment 1 presents to the user A through the specific application (the presented content includes, but is not limited to, the voice, image, height, age, of the social object, The occupation or the like) the one or more social objects; or, according to the degree of matching, presenting to the user A one of the one or more social objects having the highest matching degree or the high matching social objects.
  • the presented content includes, but is not limited to, the voice, image, height, age, of the social object, The occupation or the like
  • the degree of matching presenting to the user A one of the one or more social objects having the highest matching degree or the high matching social objects.
  • the network device 2 acquires user voice information of the target user uploaded by the user equipment 1, and performs pre-processing on the user voice information.
  • the network device 2 is based on the pre-processed user voice information.
  • the query is matched in a social object repository to obtain one or more social objects that match the user's voice information.
  • the network device 2 performs pre-processing such as voice noise reduction, high-pass filtering, framing, and endpoint detection on the user voice information, and then matches the query in the social object information base based on the pre-processed user voice information.
  • pre-processing such as voice noise reduction, high-pass filtering, framing, and endpoint detection
  • the network device 2 extracts a plurality of feature parameters of the user voice information; and obtains a feature vector of the user voice information according to the plurality of feature parameters of the user voice information; based on the user voice information
  • the feature vector matches the query in the social object repository to obtain one or more social objects that match the user's voice information.
  • the characteristic parameters include, but are not limited to, pitch, mel frequency cepstral coefficient (MFCC), dynamic difference parameter, and the like.
  • the voice signal can be divided into two types: unvoiced and voiced according to whether the vocal cord is vibrating.
  • Voiced sounds also known as voiced languages, carry most of the energy in the language, and voiced sounds show significant periodicity in the time domain; while unvoiced sounds are similar to white noise, with no obvious periodicity.
  • voiced sounds When a voiced sound is heard, the airflow passes through the glottis to cause the vocal cord to oscillate and oscillate, generating a quasi-period excitation pulse train.
  • the frequency at which this vocal cord vibrates is called the fundamental frequency, and the corresponding period becomes the pitch period.
  • the relationship between the pitch frequency and the length, thickness, toughness and pronunciation habits of the individual vocal cords reflects to a large extent the characteristics of the individual.
  • MFCC Mel frequency cepstral coefficient
  • this feature does not depend on the nature of the signal, it does not make any assumptions and limitations on the input signal, and uses the research results of the auditory model. Therefore, this parameter has better Lu than the channel-based LPCC.
  • the stickiness is more in line with the auditory characteristics of the human ear, and still has better recognition performance when the signal-to-noise ratio is lowered.
  • MFCC is a cepstrum parameter extracted in the Mel scale frequency domain.
  • the Mel scale describes the nonlinear characteristics of the human ear frequency. Its relationship with frequency can be approximated by the following formula:
  • f is the frequency and the unit is Hz.
  • d t represents the tth first order difference
  • C t represents the tth cepstral coefficient
  • Q represents the order of the cepstral coefficients
  • K represents the time difference of the first derivative, and can be 1 or 2.
  • the pitch (Pitch), the Mel Frequency Cepstrum Coefficient (MFCC), and the dynamic difference parameter of the user voice information are extracted, and each frame of the sound can obtain a feature vector of up to 36 dimensions (including: fundamental frequency, energy, 12-dimensional).
  • a query is matched in the social object information base based on the feature vector of the user sound information to obtain one or more social objects that match the user sound information.
  • the social object information database includes one or more sound feature parameter models corresponding to the social object; the feature vector based on the user sound information matches the query in the social object information database to obtain the user sound information Matching one or more social objects, comprising: using a feature vector of the user voice information as an input of a sound feature parameter model in the social object information database, and obtaining a sound feature parameter model output in the social object information base Matching degree; obtaining one or more social objects that match the user sound information according to the level of matching output by the sound feature parameter model in the social object information database.
  • the input of the sound feature parameter model of each object may be a 36-dimensional feature vector of the user sound information
  • the output may be a degree of matching of the user sound information with the sound feature parameter model.
  • the object database has the sound feature parameter model of the object A, the object B, the object C, the object D, the object E, and the object F, and the feature vectors of the user voice information of the target user are respectively input into the objects A, B, and C.
  • the output matching degree is 75%, 15%, 35%, 80%, 40% 85%, according to the level of matching output of each sound feature parameter model, if three social objects with the highest matching degree are selected, social objects A, D, and F matching the user voice information of the target user can be obtained.
  • the sound feature parameter model of each object may include a speaker model and a counter-actor model, and the feature vectors of the user sound information are respectively input into the speaker model and the counter-actor model of each object, and then passed The DS evidence theory is fused to determine the degree of matching between the user's voice information and the sound feature parameter model.
  • a complete set of incompatible basic propositions is called a recognition framework, representing all possible answers to a question, but only one of them is correct.
  • a subset of this framework is called a proposition.
  • the degree of trust assigned to each proposition is called the basic probability assignment (BPA, also known as the m function), and m(A) is the basic credible number, reflecting the reliability of A.
  • BPA basic probability assignment
  • m(A) is the basic credible number, reflecting the reliability of A.
  • the trust function Bel(A) represents the degree of trust in proposition A.
  • the likelihood function Pl(A) represents the degree of trust in proposition A that is not false, that is, the measure of uncertainty that seems to be possible for A.
  • [Bel( A), Pl(A)] represents the uncertainty interval of A
  • [0, Bel(A)] indicates that proposition A supports the evidence interval
  • [0, Pl(A)] represents the equivalence interval of proposition A
  • [Pl(A) ), 1] represents the rejection evidence interval of Proposition A.
  • m1 and m2 be the basic probability distribution functions derived from two independent evidence sources (sensors)
  • the Dempster combination rule can calculate the new basic probability distribution function reflecting the fusion information generated by the combination of the two evidences.
  • the method further includes: the network device 2 generates a sound feature parameter model of the target user according to the plurality of feature parameters of the user voice information, and deposits the voice feature parameter model of the target user into the social Object information base.
  • the sound feature parameter model of the target user may be trained by machine learning according to multiple feature parameters of the user voice information of the target user. And storing the sound feature parameter model of the target user into the social object information base. If the voice feature parameter model of the target user is already in the object database, the voice feature parameter of the target user may be generated according to multiple feature parameters of the user voice information of the target user that is newly uploaded by the user equipment 1 Modeling and updating a sound feature parameter model of the target user in the object database.
  • the network device 2 determines user personality feature information of the target user based on the user voice information; and matches the query in the social object information database based on the user personality feature information to obtain the user personality.
  • the target feature parameter of the user voice information is extracted, and the user personality feature information of the target user is determined according to the target feature parameter.
  • a pitch (Pitch), a Mel frequency cepstral coefficient (MFCC), and a dynamic difference parameter may be used as the target feature parameter to extract a pitch (Pitch) and a Mel frequency cepstral coefficient (MFCC) of the user's voice information.
  • Dynamic differential parameters each frame of sound can get up to 36-dimensional feature vector (including: fundamental frequency, energy, 12-dimensional MFCC, 12-dimensional first-order differential MFCC, 12-dimensional second-order differential MFCC).
  • the Mel Frequency Cepstrum Coefficient (MFCC) can reflect the characteristics of human voice individualization.
  • the fundamental frequency and energy parameters in the feature parameter matrix can reflect the tone and volume of the speech, thereby determining the user of the target user. Personality characteristics information.
  • the character feature information of the query social object is matched in the social object information base based on the user personality feature information of the target user to obtain one or more social objects that match the user personality feature information of the target user.
  • the network device 2 matches the query in the social object information base based on the user voice information and the user related information of the target user to obtain matching with the user voice information and the user related information.
  • One or more social objects are provided in step S202.
  • mapping the query in the social object information base For example, based on the user voice information, and based on the user-related information of the target user, matching the query in the social object information base to obtain one or more matching the user voice information and the user related information.
  • the user-related information includes at least one of: image information of a desired social object of the target user; image information of the target user; accent information of the target user; interest of the target user information.
  • the user voice information and each of the user related information may be respectively assigned a weight value; based on the user voice information, the image information of the target user's desired social object, the image information of the target user, The accent information of the target user and the hobby information of the target user are respectively matched and queried in the social object information database, and then determined according to the weight information of the user voice information and each user related information.
  • the face matching techniques used include, but are not limited to, geometric matching based on eye coordinates, matching based on SIFT (Scale-invariant feature transform) features, template matching based on statistical features, and the like.
  • SIFT Scale-invariant feature transform
  • the user related information includes image information of the desired social object of the target user; wherein the method further includes: the user equipment 1 uploads image information of the target user's desired social object to the corresponding network device 2; Obtaining image information of the desired social object of the target user uploaded by the user equipment; in step S202, the network device 2 matches the query in the social object information base based on the user voice information and the image information of the desired social object to obtain The user voice information and the image information of the desired social object match one or more social objects; in step S102, the user equipment 1 receives the user voice information and the image provided by the network device 2 One or more social objects that the information matches.
  • the user voice information and the image information of the desired social object may be respectively assigned a weight value; based on the user voice information and the image information of the desired social object, respectively, in the social object information base Matching the query, and determining one or more social objects that match the user sound information and the image information of the desired social object according to the user voice information and the weight value of the image information of the desired social object.
  • the image information of the desired social object and the image information in the social object information base may be matched by the following steps:
  • the haar-like feature can be extracted from the image using the haar classifier + AdaBoost algorithm, and the face detection can be performed using the AdaBoost algorithm.
  • template matching can be used to model face templates such as eyes, nose, mouth and face contours, to detect frontal faces in images, and to calculate the relationship between sub-images and contour templates to detect candidate faces. Area, complete matching with other sub-templates in the candidate area.
  • other existing or future technologies may be employed.
  • the normalized face region image is obtained from the image (the pixels of each image are uniform, uniform size), and this step is mainly to make the faces of the pixels on different faces of the faces correspond to each other. Comparable, this step can be seen as a process of affine changes to an image (linear interpolation or scaling done).
  • the main purpose is to overcome the influence of different illumination on the face and improve the robustness of the algorithm to the illumination conditions.
  • Gaussian difference filtering an illumination normalization method based on Gaussian difference filter
  • other existing or future possible technologies may be employed.
  • the image pixels are segmented such that the surface points of the objects corresponding to each pixel in each segment have similar surface normal vector distributions, thus having a similar gray-scale response to the light source, and then local normalization is performed in each segment to attenuate the illumination effect.
  • the Lambert surface reflection model of the object can be first established, the average surface normal vector distribution matrix of the face shape is estimated by the singular value decomposition method, and the pixel is segmented according to the normal vector direction by the clustering algorithm, and then Local pixel normalization is performed in each segment.
  • Skin color features selected according to different chromaticity spaces of color images, chromaticity spaces such as RGB, SHI, YUV: commonly used skin color models have Gaussian models, histogram models, etc.; gray features: including face contour features, faces Gray distribution characteristics, organ characteristics, template features.
  • Various organs in the face area are important features of the human face.
  • an artificial neural network is used to detect the overall characteristics of the eyes, nose, mouth, and face, respectively.
  • the grayscale of the face region itself can be used as a template feature, usually taking the central region of the face containing only the eyes, nose and mouth as a common facial template feature; other features after transforming the face: such as gabor features And local binary mode (LBP) features, which can fuse multiple features.
  • LBP local binary mode
  • the degree of matching is determined according to the distance between the two image features. The smaller the distance between two image features, the higher the matching degree; the greater the distance between the two image features, the lower the matching degree.
  • the user-related information includes image information of the target user; in step S202, the network device 2 matches the query in the social object information base based on the user voice information and the image information of the target user to obtain The one or more social objects that match the user sound information and the image information of the target user.
  • the user voice information and the image information of the target user may be respectively assigned a weight value; and the matching query is performed in the social object information database based on the user voice information and the image information of the target user respectively. And determining, according to the user voice information and the weight value of the image information of the target user, one or more social objects that match the user voice information and the image information of the target user.
  • the network device 2 acquires user video information of the target user uploaded by the user equipment 1; and extracts user voice information and image information of the target user from the user video information.
  • the user equipment 1 may directly upload audio data, and may also upload video data, wherein the video data includes audio data and image data. If the user equipment 1 uploads the audio data, the network device 2 can directly obtain the user voice information of the target user; if the user equipment 1 uploads the video data, the network device 2 can extract the user voice information of the target user. And image information.
  • the method further includes: determining, by the network device 2, the priority information of the social object; in step S203, the network device 2, based on the priority information of the social object, at least one of the one or more social objects A social object is provided to the user device 1.
  • the priority information of the social object may be determined according to the degree of matching, and the priority information of the social object with higher matching degree is higher than the social object with lower matching degree. Then, based on the priority information of the social object, one of the one or more social objects with the highest priority information or several social objects with higher priority information is provided to the user equipment 1.
  • determining the priority information of the social object comprises: determining priority information of the social object based on object attribute information of the social object.
  • the object attribute information may include: appearance, sound, height, education, wealth, and the like of the social object.
  • the priority information of the social object may be weighted according to the score information of the social object in terms of appearance, sound, height, education, wealth, and the like.
  • each social object may be sorted according to an attribute X (eg, a sound) of the social object, thereby determining priority information of the social object, wherein the attribute X may be set by a user.
  • determining the priority information of the social object includes: adjusting weight information of each component in the object attribute information of the social object based on the attribute information of the target user; and determining object attribute information based on the social object And weight information of each component, and weighting determines priority information of the social object.
  • the self attribute information may include the appearance, sound, height, gender, age, education, and the like of the target user, for example, for most users with higher heights, the social objects may not be paid much attention to. Height, so the weight of the height of the social objects of such users can be appropriately reduced. For another example, for most male users, the appearance of the social object may be more concerned, so the weight of the appearance of the social object of the male user may be appropriately increased.
  • the method further comprises: the user equipment 1 transmitting feedback information about the social object by the user to the network device 2; the network device 2 receiving feedback of the user about the social object sent by the user equipment 1 Information; the network device 2 re-determines the corresponding one or more preferred social objects based on the feedback information; the network device 2 provides at least one of the one or more preferred social objects to the user device 1; the user The device 1 receives one or more preferred social objects returned by the network device 2 based on the feedback information; the user device 1 presents at least one preferred social object of the one or more preferred social objects.
  • the network device 2 matches the query again in the social object information base according to the feedback information, re-determines the corresponding one or more preferred social objects, and provides at least one preferred social object of the one or more preferred social objects to The user device 1 then, the user device 1 presents at least one preferred social object of the one or more preferred social objects.
  • the contact information of the presented social object is in a hidden state; wherein the method further comprises: the user equipment 1 acquiring a contact information request submitted by the user regarding the target social object in the presented social object; when the contact information request The verification information of the target social object is presented by verification.
  • the user equipment 1 After receiving the one or more social objects provided by the network device 2 that match the user voice information, the user equipment 1 does not present the contact information (such as a phone number or an email address) of the social object to the user A. , home address and other information), that is, the contact information of social objects is hidden. If the user A is interested in the target social object of the one or more social objects, the user may submit the contact information request for the target social object to obtain the contact information of the target social object.
  • the contact information such as a phone number or an email address
  • the verification of the contact information request includes, but is not limited to, whether the user A satisfies a predetermined membership level, whether the user A requests payment success with the contact information, and the like.
  • the verification of the contact information request may be completed by the specific application on the user equipment 1; the contact information request may also be sent by the user equipment 1 to the network device 2 of the specific application cloud, by The network device 2 completes verification of the contact information request.
  • the method further comprises: the user equipment 1 sends the contact information request to the network device 2; the network device 2 receives the user's information about the target in the at least one social object sent by the user equipment 1 a contact information request of the social object; the network device 2 verifies the contact information request; when the contact information request is verified, the contact information of the target social object is returned to the user device 1; the user device 1 receives the network The contact information of the target social object returned by the device 2 after the contact information request is verified; the user device 1 presents the contact information of the target social object.
  • the contact information request is sent by the user equipment 1 to the network device 2 of the specific application cloud, and the verification of the contact information request is completed by the network device 2.
  • the network device 2 returns contact information of the target social object to the user device 1.
  • the user equipment 1 receives the contact information of the one or more social objects and each social object provided by the network device 2 that match the user voice information; when the contact information request is verified, the presentation device The contact information stored by the target social object in the user device 1.
  • the user equipment 1 receives the contact information of each social object while receiving the one or more social objects provided by the network device 2 that match the user voice information. However, the contact information of the social object is not presented to the user A. When the contact information request is verified, the contact information of the target social object stored in the user equipment 1 is presented to the user A.
  • a method for providing a social object includes:
  • the user equipment uploads user voice information of the target user to the corresponding network device
  • the network device matches the query in the social object information base based on the user sound information to obtain one or more social objects that match the user sound information;
  • the network device provides at least one of the one or more social objects to the user device;
  • the user device presents at least one of the one or more social objects.
  • a computer readable medium comprising instructions which, when executed, cause a system to perform the operations of the method as described above.
  • a network device for providing a social object includes:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method as described above.
  • a user equipment for providing a social object where the user equipment includes:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method as described above.
  • a system for providing a social object including the network device as described above, and the user device as described above are provided.
  • the user equipment of the present application uploads user voice information of the target user to the corresponding network device, and the network device matches the query in the social object information base based on the user voice information to obtain the voice with the user.
  • One or more social objects that match the information and then providing at least one of the one or more social objects to the user device, the user device presenting at least one of the one or more social objects The social object; thereby facilitating the user to quickly find the social object that matches the user's voice information, and expanding the user's social relationship chain based on the sound feature to enhance the user experience.
  • the application matches the query in the social object information base based on the user voice information and the user related information of the target user to obtain one or more matching with the user voice information and the user related information.
  • the social object can further expand the user's social relationship chain based on various features including sound features, thereby further optimizing the user experience.
  • the present application provides at least one of the one or more social objects to the user based on the priority information of the social object, thereby facilitating the user to view and saving the user's time.
  • the present application can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device.
  • the software program of the present application can be executed by a processor to implement the steps or functions described above.
  • the software programs (including related data structures) of the present application can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like.
  • some of the steps or functions of the present application may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.
  • a portion of the present application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or technical solution in accordance with the present application.
  • the form of computer program instructions in a computer readable medium includes, but is not limited to, source files, executable files, installation package files, etc., accordingly, the manner in which the computer program instructions are executed by the computer includes but not Limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installation. program.
  • the computer readable medium can be any available computer readable storage medium or communication medium that can be accessed by a computer.
  • Communication media includes media that can be transferred from one system to another by communication signals including, for example, computer readable instructions, data structures, program modules or other data.
  • Communication media can include conductive transmission media such as cables and wires (eg, fiber optics, coaxial, etc.) and wireless (unguided transmission) media capable of propagating energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared.
  • Computer readable instructions, data structures, program modules or other data may be embodied, for example, as modulated data signals in a wireless medium, such as a carrier wave or a similar mechanism, such as embodied in a portion of a spread spectrum technique.
  • modulated data signal refers to a signal whose one or more features are altered or set in such a manner as to encode information in the signal. Modulation can be analog, digital or hybrid modulation techniques.
  • the computer readable storage medium may comprise, by way of example and not limitation, vols and non-volatile, implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data.
  • a computer readable storage medium includes, but is not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and nonvolatile memory such as flash memory, various read only memories (ROM, PROM, EPROM) , EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, tapes, CDs, DVDs); or other currently known media or later developed for storage in computer systems Computer readable information/data used.
  • volatile memory such as random access memory (RAM, DRAM, SRAM)
  • nonvolatile memory such as flash memory, various read only memories (ROM, PROM, EPROM) , EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disk

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention a pour objet de proposer un procédé et un dispositif permettant de fournir un objet social. Par comparaison avec l'état de la technique, un équipement utilisateur décrit dans la présente invention télécharge des informations sonores d'utilisateur d'un utilisateur cible dans un dispositif réseau correspondant, le dispositif réseau réalise une interrogation de mise en correspondance dans une base d'informations d'objets sociaux sur la base des informations sonores d'utilisateur afin d'obtenir au moins un objet social mis en correspondance avec les informations sonores d'utilisateur, puis au moins un objet social parmi lesdits objets sociaux sont fournis pour l'équipement utilisateur, et l'équipement utilisateur présente ledit objet social parmi lesdits objets sociaux. Par conséquent, un utilisateur peut trouver commodément et rapidement un objet social mis en correspondance avec des informations sonores d'utilisateur, la chaîne de relations sociales de l'utilisateur peut s'agrandir en fonction de caractéristiques sonores, et l'expérience d'utilisateur est améliorée.
PCT/CN2018/087420 2017-05-19 2018-05-18 Procédé et dispositif permettant la fourniture d'un objet social Ceased WO2018210323A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710359576.0A CN107229691B (zh) 2017-05-19 2017-05-19 一种用于提供社交对象的方法与设备
CN201710359576.0 2017-05-19

Publications (1)

Publication Number Publication Date
WO2018210323A1 true WO2018210323A1 (fr) 2018-11-22

Family

ID=59933274

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/087420 Ceased WO2018210323A1 (fr) 2017-05-19 2018-05-18 Procédé et dispositif permettant la fourniture d'un objet social

Country Status (2)

Country Link
CN (1) CN107229691B (fr)
WO (1) WO2018210323A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111047173A (zh) * 2019-12-05 2020-04-21 国网河南省电力公司 基于改进d-s证据理论的社团可信度评估方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107229691B (zh) * 2017-05-19 2021-11-02 上海掌门科技有限公司 一种用于提供社交对象的方法与设备
CN110111221A (zh) * 2019-04-30 2019-08-09 刘柏佟 一种智能舍友匹配方法及系统
CN111914111A (zh) * 2019-05-08 2020-11-10 阿里巴巴集团控股有限公司 基于声音的面具形象确定方法、装置及计算机存储介质
CN111916096B (zh) * 2019-05-09 2021-04-27 南京农业大学 一种基于树莓派的藏羊牧食行为监测方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105550223A (zh) * 2015-12-04 2016-05-04 小米科技有限责任公司 用户推荐方法及装置
US20160179970A1 (en) * 2012-06-12 2016-06-23 Microsoft Technology Licensing, Llc Disambiguating intents within search engine result pages
CN105893389A (zh) * 2015-01-26 2016-08-24 阿里巴巴集团控股有限公司 一种语音信息搜索方法、装置及服务器
CN107204910A (zh) * 2016-03-20 2017-09-26 徐超 社交软件中利用声音口令查找好友的方法
CN107229691A (zh) * 2017-05-19 2017-10-03 上海掌门科技有限公司 一种用于提供社交对象的方法与设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102486793A (zh) * 2010-12-06 2012-06-06 武汉若鱼网络科技有限公司 一种搜索目标用户的方法和系统
CN105303150B (zh) * 2014-06-26 2019-06-25 腾讯科技（深圳）有限公司 实现图像处理的方法和系统
CN105653614A (zh) * 2015-12-23 2016-06-08 广东欧珀移动通信有限公司 联系信息获取、提供方法及装置
CN106650359A (zh) * 2016-12-30 2017-05-10 中广热点云科技有限公司 一种用于对象信息采集和信息匹配的系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160179970A1 (en) * 2012-06-12 2016-06-23 Microsoft Technology Licensing, Llc Disambiguating intents within search engine result pages
CN105893389A (zh) * 2015-01-26 2016-08-24 阿里巴巴集团控股有限公司 一种语音信息搜索方法、装置及服务器
CN105550223A (zh) * 2015-12-04 2016-05-04 小米科技有限责任公司 用户推荐方法及装置
CN107204910A (zh) * 2016-03-20 2017-09-26 徐超 社交软件中利用声音口令查找好友的方法
CN107229691A (zh) * 2017-05-19 2017-10-03 上海掌门科技有限公司 一种用于提供社交对象的方法与设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111047173A (zh) * 2019-12-05 2020-04-21 国网河南省电力公司 基于改进d-s证据理论的社团可信度评估方法
CN111047173B (zh) * 2019-12-05 2022-09-09 国网河南省电力公司 基于改进d-s证据理论的社团可信度评估方法

Also Published As

Publication number Publication date
CN107229691B (zh) 2021-11-02
CN107229691A (zh) 2017-10-03

Similar Documents

Publication Publication Date Title
US10635893B2 (en) Identity authentication method, terminal device, and computer-readable storage medium
Li et al. Automatic speaker age and gender recognition using acoustic and prosodic level information fusion
WO2021208287A1 (fr) Procédé et appareil de détection d'activité vocale pour reconnaissance d'émotion, dispositif électronique et support de stockage
WO2018210323A1 (fr) Procédé et dispositif permettant la fourniture d'un objet social
RU2720359C1 (ru) Способ и оборудование распознавания эмоций в речи
WO2018176954A1 (fr) Procédé, dispositif et système de fourniture d'objets pour se faire des amis
JP2023551729A (ja) フェイクオーディオの検出のための自己教師あり音声表現
CN107341464A (zh) 一种用于提供交友对象的方法、设备及系统
US20230058259A1 (en) System and Method for Video Authentication
Zhang Voice keyword retrieval method using attention mechanism and multimodal information fusion
Jachimski et al. A comparative study of English viseme recognition methods and algorithms
Tsai et al. Sentiment analysis of pets using deep learning technologies in artificial intelligence of things system
WO2021128847A1 (fr) Procédé et appareil d'interaction de terminal, dispositif informatique et support de stockage
Xiao et al. An introduction to audio and visual research and applications in marketing
Reimao Synthetic speech detection using deep neural networks
CN114299987A (zh) 事件分析模型的训练方法、事件分析方法及其装置
Islam et al. BPN Based Likelihood Ratio Score Fusion for Audio‐Visual Speaker Identification in Response to Noise
Firc Applicability of deepfakes in the field of cyber security
CN114203159A (zh) 语音情感识别方法、终端设备及计算机可读存储介质
Shah et al. Speech recognition using spectrogram-based visual features
CN116631406B (zh) 基于声学特征生成的身份特征提取方法、设备及存储介质
CN120752697A (zh) 用于生成训练生物特征验证系统的合成简档的系统和方法
Fernandez-Lopez et al. Optimizing phoneme-to-viseme mapping for continuous lip-reading in spanish
JP2025504812A (ja) 音響イベント検出システム
Folorunso et al. Laughter signature, a new approach to gender recognition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18801831

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27/02/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18801831

Country of ref document: EP

Kind code of ref document: A1