WO2021164333A1 - 一种语音信息交流的管理方法、装置、存储介质和设备 - Google Patents

一种语音信息交流的管理方法、装置、存储介质和设备 Download PDF

Info

Publication number
WO2021164333A1
WO2021164333A1 PCT/CN2020/127810 CN2020127810W WO2021164333A1 WO 2021164333 A1 WO2021164333 A1 WO 2021164333A1 CN 2020127810 W CN2020127810 W CN 2020127810W WO 2021164333 A1 WO2021164333 A1 WO 2021164333A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
user
credit
violation
record data
Prior art date
Application number
PCT/CN2020/127810
Other languages
English (en)
French (fr)
Inventor
陈春勇
Original Assignee
腾讯科技（深圳）有限公司
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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2021164333A1 publication Critical patent/WO2021164333A1/zh
Priority to US17/693,971 priority Critical patent/US20220198468A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/12—Applying verification of the received information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/104—Peer-to-peer [P2P] networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/535—Tracking the activity of the user
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees

Definitions

  • This application relates to the technical field of blockchain, and specifically relates to a management method, device and storage medium for voice information communication.
  • Voice socialization refers to the use of voice as the main means of communication to realize the functions of making friends, information exchange and interaction, and communication sharing. From the perspective of user experience, it is compared with text socialization. Social networking is more lively and interesting; compared with image and video social networking, voice social networking has higher privacy, lower threshold, and is more able to express real emotions.
  • a management method, device, storage medium, and equipment for voice information communication are provided.
  • a management method for voice information exchange, executed by computer equipment including:
  • the credit record data of the user is stored in the blockchain corresponding to the user.
  • it further includes:
  • it further includes:
  • the target credit record data is stored in the blockchain corresponding to the user.
  • a management device for voice information communication including:
  • the obtaining unit is used to obtain the voice information released by the user on the first network platform in the blockchain network;
  • a recognition unit configured to recognize violations of the voice information to obtain a violation recognition result
  • the generating unit is configured to generate the user’s identification information according to the violation identification result, the platform identification information of the first network platform, and the user identification information of the user when the violation identification result meets the preset violation conditions.
  • a broadcasting unit configured to broadcast the user's credit record data to the second network platform in the blockchain network
  • the storage unit is used to store the credit record data of the user in the blockchain corresponding to the user after the blockchain network reaches a consensus on the credit record data of the user,
  • a computer-readable storage medium with a computer program stored thereon.
  • the computer program runs on a computer, the computer executes the voice information communication management method as provided in any embodiment of the present application.
  • a voice information communication device includes a memory and a processor, the memory stores a computer program, and is characterized in that, when the processor executes the computer program, the management of voice information communication as provided in any embodiment of the present application is executed method.
  • a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium; a processor of a first node reads from the computer-readable storage medium And when the computer instructions are executed, the processor is caused to execute the steps of the voice information communication management method.
  • Figure 1a is a schematic diagram of a scene of a voice information exchange management system provided by an embodiment of the present invention
  • Figure 1b is a schematic structural diagram of a blockchain provided by an embodiment of the present invention.
  • Figure 1c is a schematic diagram of a block generation process in a blockchain provided by an embodiment of the present invention.
  • Figure 2a is a schematic flow chart of the first method for managing voice information exchanges according to an embodiment of the present invention
  • FIG. 2b is a schematic diagram of the second flow chart of the voice information exchange management method provided by an embodiment of the present invention.
  • Figure 2c is a schematic diagram of a third process of the voice information exchange management method provided by an embodiment of the present invention.
  • FIG. 3a is a schematic diagram of the first structure of a voice information communication management device provided by an embodiment of the present invention.
  • FIG. 3b is a schematic diagram of a second structure of a management device for voice information exchange according to an embodiment of the present invention.
  • FIG. 3c is a schematic diagram of a third structure of a management device for voice information exchange according to an embodiment of the present invention.
  • Figure 4 is a schematic structural diagram of a voice information exchange device provided by an embodiment of the present invention.
  • Figure 5a is a schematic diagram of a voice live broadcast interface provided by an embodiment of the present invention.
  • Fig. 5b is a schematic diagram of a voice live broadcast interface when a violation is recognized according to an embodiment of the present invention
  • 5c is a schematic diagram of a voice live broadcast interface when it is recognized that the credit score is lower than a preset value according to an embodiment of the present invention
  • Fig. 6 is a schematic diagram of a flow chart of the management of voice information communication provided by an embodiment of the present invention.
  • Fig. 7 is a schematic diagram of a speech recognition process provided by an embodiment of the present invention.
  • Voice information communication The voice information communication in this application uses voice information as the main communication method, and makes friends, information exchanges and interactions, exchanges and sharing through the network platform. Mainly include voice live broadcast, voice call and other forms, and may also include voice message form.
  • Blockchain technology is born out of Bitcoin technology and is the underlying technology of Bitcoin, which is a decentralized distributed ledger database.
  • the blockchain itself is a series of data blocks (i.e. blocks) that are generated using cryptographic algorithms.
  • Each data block contains information for valid confirmation of multiple blockchain network transactions. It is based on this that it is impossible to cheat by tampering with the data on the block, and it can ensure that the data on any block is open and transparent, ensuring the security of the data.
  • a blockchain system containing multiple nodes can be referred to as a blockchain network
  • a chain composed of data stored in the blockchain can be referred to as a block chain.
  • Blockchain networks can be divided into public chains, private chains, and alliance chains. Among them, the consortium chain is between the public chain and the private chain. Several organizations work together to maintain a blockchain network. The use of the blockchain network must be managed with authority, and related information will be protected, such as financial organization.
  • the blockchain network is a distributed database system involving nodes, or, it can also be called a distributed public ledger based on a P2P (peer-to-peer) network. Its characteristics are that it is unchangeable and unforgeable. It is understood as an account book system.
  • Nodes of the blockchain network equipment participating in the construction of the blockchain network, for example, the computer equipment of each content manufacturer participating in the construction of the blockchain network.
  • the computer equipment can be a single computer equipment such as a single server of a certain content manufacturer , It can also be a computer equipment cluster of a certain content manufacturer, such as a server cluster.
  • the nodes of the blockchain network can be the executive body of information processing, and the interaction between nodes can realize transactions and other services.
  • the node stores related blocks.
  • the block may include user credit record data.
  • the server of the network platform may serve as the node of the blockchain network.
  • the embodiments of the present application provide a management method, device, and storage medium for voice information communication.
  • the method for managing voice information exchange may be executed by a computer device, and the computer device may be a voice information communication device that manages voice information exchange, and specifically may be a server or a terminal or other equipment.
  • the terminal may include devices such as a mobile phone, a tablet computer, a notebook computer, a personal computer (PC), and a vehicle-mounted terminal.
  • the server can be a single server, or a server cluster composed of multiple servers.
  • the computer equipment can be integrated in the first node of the blockchain, and the first node can be the first node in the blockchain. Any node.
  • an embodiment of the present application provides a voice information exchange management system, which can implement services such as voice information exchange management.
  • the system may include multiple blockchain nodes and terminals such as mobile phones and computers, where multiple nodes are connected through a network, and nodes and terminals are also connected through a network.
  • the embodiment of the application can obtain the voice information released by the user on the first network platform in the blockchain network; perform violation recognition on the voice information to obtain the violation recognition result; when the violation recognition result meets the preset violation conditions, according to The identification result of the violation, the platform identification information of the first network platform, and the user identification information of the user are used to generate the credit record data of the user; The user's credit record data; when the blockchain network reaches a consensus on the user's credit record data, the user's credit record data is stored in the blockchain corresponding to the user.
  • the user's credit data can be shared with all network platforms in the blockchain. So as to effectively monitor the user's voice information communication behavior on all network platforms.
  • the blockchain network also provides an information query function to query the user's credit record data.
  • the blockchain network node can receive a credit parameter acquisition request sent by the network platform server.
  • the credit parameter acquisition request includes a user ID and is used to request the user’s corresponding credit record data.
  • the blockchain network node can Search for the credit record data corresponding to the user from the blockchain, and then send the credit record data corresponding to the target user to the second network platform server.
  • the architecture of the blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.
  • the underlying platform of the blockchain can include processing modules such as user management, basic services, smart contracts, and operation monitoring.
  • the user management module is responsible for the identity information management of all blockchain participants, including the maintenance of public and private key generation (account management), key management, and maintenance of the correspondence between the user’s real identity and the blockchain address (authority management), etc.
  • authorization supervise and audit certain real-identity transactions, and provide risk control rule configuration (risk control audit); basic service modules are deployed on all blockchain node devices to verify the validity of business requests, After completing the consensus on the valid request, it is recorded on the storage.
  • the basic service For a new business request, the basic service first performs interface adaptation analysis and authentication processing (interface adaptation), and then encrypts the business information through the consensus algorithm (consensus management), After encryption, it is completely and consistently transmitted to the shared ledger (network communication), and recorded and stored; the smart contract module is responsible for contract registration and issuance, contract triggering and contract execution.
  • interface adaptation interface adaptation
  • consensus algorithm consensus algorithm
  • the smart contract module is responsible for contract registration and issuance, contract triggering and contract execution.
  • the operation monitoring module is mainly responsible for the deployment of the product release process , Configuration modification, contract settings, cloud adaptation, and visual output of real-time status during product operation, such as: alarms, monitoring network conditions, monitoring node equipment health status, etc.
  • the platform product service layer provides basic capabilities and implementation frameworks for typical applications. Based on these basic capabilities, developers can superimpose business characteristics to complete the blockchain implementation of business logic.
  • the application service layer provides application services based on the blockchain solution for business participants to use.
  • the blockchain network can be used to manage voice information exchanges:
  • the process of writing credit record data into the blockchain will be described as an example.
  • the process is described from the perspective of a voice information communication management device.
  • the voice information communication management device can be specifically integrated in In the server of the first network platform.
  • the voice information communication in the embodiments of the present application mainly refers to obtaining and playing the voice information sent by the publisher in real time in the form of a data stream, and may include voice live broadcast, voice call, and the like.
  • the voice communication methods such as voice live broadcast and voice call in the embodiments of the present application are communication methods that can publish and receive information in real time.
  • the anchor releases voice information in the voice live broadcast room, and the audience receives the voice messages released by the anchor through the voice live broadcast room.
  • the voice live broadcast room can be understood as a network address interface used to publish and receive voice information
  • the anchor is a user who publishes voice messages during the live broadcast.
  • the host can also conduct voice interaction with other hosts through the method of "linking the microphone". When “linking the microphone", the voice interaction process of the two parties (referring to the host) of the linking microphone can be released in the live broadcast room of both parties at the same time.
  • the host can set up an independent signal collection device on site to import audio and video into the director client of the terminal, upload it to the server of the network platform through the network, and publish it to the network address interface for viewers to watch through the broadcast client.
  • the live broadcast room of the host can be opened to all users on the network platform, and can also be opened to specific users according to the settings of the host.
  • the voice live room is shown in Figure 5a. There will be no video in the voice live room. When the host speaks, there will be sound waves around the host's profile picture.
  • the voice call is not open to users to watch, and multiple users publish voice information to each other.
  • Live broadcasts and voice calls involve streaming media technology.
  • Streaming Media technology refers to compressing a series of media data and then segmenting them in the form of data streams to transmit the media in real time on the network.
  • a technology for streaming data for playback is a technology for streaming data for playback.
  • the user sends voice information to the network platform in the form of a media data stream.
  • the media data stream may be transmitted in units of voice information compressed packets, and the server decodes the acquired media data stream to obtain the voice information.
  • the first network platform can be any network platform that joins the blockchain network
  • the second network platform can also be a network platform other than the first network platform in the blockchain network, which can be expressed as a network platform in the blockchain network.
  • the network platform is a platform for realizing voice information communication through the network.
  • ASR Automatic Speech Recognition, automatic speech recognition technology
  • ASR is used to convert vocabulary content in voice information into computer-readable input, such as keystrokes, binary codes, or character streams.
  • ASR is one of the key technologies of Speech Technology. Enabling computers to be able to listen, see, speak, and feel is the future development direction of human-computer interaction, among which voice has become one of the most promising human-computer interaction methods in the future.
  • the recognition of the voice information by a preset voice recognition algorithm to obtain the text information corresponding to the voice information may specifically include the following steps:
  • the semantic association information between the text words is extracted, and the text words are combined to obtain text information according to the association information.
  • the preprocessing includes emphasis, framing, and windowing.
  • the voice information can be emphasized, and then VAD (silence cut operation technology) is used to frame the voice information.
  • VAD feature cut operation technology
  • the audio feature information may be expressed as an MFCC (Mel-Frequency Cepstral Coefficients, Mel frequency cepstral coefficients) vector
  • the process of feature extraction may include the following steps: then the audio frame is brought into the Hamming window function, Obtain the short-term analysis window corresponding to each audio frame. For each short-term analysis window, obtain the corresponding frequency spectrum through FFT (Fourier Transform), and then filter the above frequency spectrum through the Mel filter bank to filter out what cannot be heard by humans. Frequency to obtain the Mel spectrum, thereby converting the linear natural spectrum into the Mel spectrum reflecting the characteristics of human hearing. Perform cepstrum analysis on the Mel spectrum (take the logarithm and do the inverse transformation.
  • FFT Fast Fourier Transform
  • the actual inverse transformation is generally realized by the discrete cosine transform. Take the 2nd to 13th coefficients after the discrete cosine as the Mel frequency cepstrum coefficients. ), get the Mel frequency cepstrum coefficient. The 12 Mel frequency cepstral coefficients of each frame are combined to obtain the cepstrum vector of each audio frame.
  • the dynamic change characteristics between frames can also be calculated according to the Mel cepstrum coefficients, and the Mel cepstrum coefficients of each frame are combined to form a cepstrum vector.
  • the cepstrum vectors of all audio frames are the audio feature information of the above-mentioned voice information.
  • phoneme is the smallest phonetic unit divided from the perspective of timbre.
  • the preset dictionary is used to describe the mapping between text words (words) to speech fragments (phones).
  • words text words
  • phones speech fragments
  • the text word stream can be obtained according to the voice feature information stream.
  • a Hidden Markov Model may be used as the acoustic model.
  • Hidden Markov Model needs to be trained before it can be used.
  • a language model can be trained based on a deep neural network, and features can be extracted into the language model to obtain text information corresponding to the voice information.
  • the network platform can preset a collection of violation information.
  • the preset violation information collection is a violation information database generated according to the national audio and video live broadcast laws and regulations.
  • the violation information database can include any one or more of the following: (1) pornography, gambling, drug-related information ; (2) Rumors or other information that disrupts social order and undermines social stability; (3) Contains false, harmful, intimidating, infringing on the privacy of others, slanderous, vulgar, fraudulent or other morally objectionable content; (4) Counterfeiting Fake and shoddy products or product information that is not authorized for sale. (5) Key feature words in the above content.
  • the network platform server can identify the text information in violation of regulations through keyword matching, natural language processing (semantic analysis), etc.
  • the text information includes violation information
  • it is confirmed as a violation and then the text information is counted
  • the information that matches the violation information obtains the violation recognition result; when the number of key feature words including the violation information in the text information is recognized in a live voice broadcast, and reaches the preset credit threshold, it is confirmed as a violation, and then the text information is counted Key feature words for successful matching.
  • the violation identification result includes a conclusion on whether or not the regulation is in violation, and if the conclusion is a violation, then the violation identification result also includes the information obtained by the above statistics.
  • the user's credit record data is data used to indicate the user's credit at the current moment (for example, credit measurement information), and may also include information for changing the user's credit (for example, the result of identification of violations).
  • the generated violation recognition result, the platform identification information of the first network platform, and the user identification information of the user are generated according to the violation identification result.
  • the user's credit record data can specifically include the following steps:
  • the violation record the credit measurement information, and the user identification information, the user's credit record data is generated.
  • the credit measurement information is information used to measure the credit of the user at the current moment, and can be expressed as the user's credit parameter (status value) or the user's credit parameter change amount.
  • the credit measurement information is expressed as a credit parameter (status value)
  • a credit parameter status value
  • the network platform can set the credit parameter to decrease by 2 units when the number of times the gambling keyword is recognized reaches the preset credit threshold.
  • the credit parameter Reduce 4 units.
  • the server of the first network platform After the server of the first network platform obtains the user's credit metric information according to the violation identification result, it may also implement the following steps:
  • the method further includes the following steps:
  • the server when the server recognizes the illegal voice, it generates corresponding prompt information and sends the prompt information to the terminal for display.
  • the server After the server obtains the user's credit measurement information according to the violation identification result, it continues to perform live broadcast permission identification based on the preset credit threshold and the user's measurement parameter information.
  • the user's credit parameters do not meet the preset credit threshold , Stop receiving the voice information uploaded by the user, and send prompt information to the terminal.
  • the blockchain network in order to make the displayed credit warning information more authentic and credible, after the blockchain network reaches a consensus on the user's credit record data, it can be based on the basis of the credit record data. According to the violation record and the credit measurement information, the voice information issuance authority recognition is performed on the user, and the authority recognition result is obtained.
  • the step of generating the credit record data of the user according to the violation record, the credit measurement information, and the user identification information may specifically include the following steps:
  • Including the violation records as part of the credit record data and writing them into the blockchain instead of just writing the credit measurement information into the blockchain can improve the authenticity and security of the credit record data. In addition, it can also be used as evidence when users question the authenticity of credit record data and make credit appeals.
  • the associated information pair is a combination of associated information, which can be specifically expressed in the form of key-value (key-value pair), where the server can generate the key element in the key-value pair according to the user identification information, and according to the user identification information Generate the value element in the key-value pair with the credit record data, and associate the key element with the value element.
  • the user identification information can be used to determine the blockchain corresponding to the credit record data.
  • the registered identity information refers to the information used to verify the identity, such as the ID card, email address, and mobile phone number used when registering an account on the network platform.
  • the first network platform will not share the user’s registered identity information with other network platforms.
  • the first network platform can upload the user’s credit record data to the blockchain and share it with the block.
  • the second network platform in the chain network. In this way, as long as the user's identity information needs to be queried when registering an account or publishing voice information, then after the user is prohibited from live broadcasting on the first network platform or the account is blocked, the user cannot use the same identity information to register an account and publish voice information on other network platforms . So as to more effectively supervise the user's voice live broadcast behavior.
  • the second network platform is a network platform other than the first network platform in the blockchain network.
  • the second network platform needs to perform verification before storing the user's credit record data on the blockchain to ensure that the data has not been tampered with during transmission.
  • the server of the first network platform may perform a hash operation on the credit record data to obtain a hash value, and then encrypt the hash value according to the private key issued by the blockchain network to obtain verification information,
  • the verification information, the user's credit record data, and the public key corresponding to the private key are sent to the second network platform together.
  • the server of the second network platform uses the public key to decrypt the verification information, obtains the hash value calculated by the first network platform, and calculates the hash value of the user's credit record data. If the hash value is consistent, it indicates the user's credit record The data has not been tampered with during transmission.
  • each node in the blockchain network stores one or more identical blockchains.
  • the block chain is composed of multiple blocks. See Figure 1b.
  • the block chain is composed of multiple blocks.
  • the founding block includes a block header and a block body.
  • the block header stores the input information feature value, version number, and time stamp.
  • the next block of the founding block takes the founding block as the parent block, the next block also includes the block header and the block body, and the current block is stored in the block header
  • the blocks of are related to ensure the security of the input information in the block.
  • the server of the second network platform When generating each block in the blockchain, referring to Figure 1c, when the server of the second network platform receives the input information, it verifies the input information according to the verification information. After the verification is completed, the input information is stored in In the local memory pool, and update the hash tree used to record the input information; afterwards, update the update timestamp to the time when the input information is received, try different random numbers, and perform feature value calculations multiple times to make the calculation
  • the characteristic value of can satisfy the following formula:
  • SHA256 is the feature value algorithm used to calculate the feature value
  • version (version number) is the version information of the relevant block protocol in the blockchain
  • prev_hash is the block header feature value of the parent block of the current block
  • merkle_root is the input information
  • Ntime is the update time of the update timestamp
  • nbits is the current difficulty, which is a fixed value within a period of time, and will be determined again after a fixed period of time
  • x is a random number
  • TARGET is the characteristic value threshold, this feature The value threshold can be determined according to nbits.
  • the information can be correspondingly stored, the block header and the block body are generated, and the current block is obtained.
  • the nodes in the blockchain can reach a consensus on the credit record data of the user based on the consensus algorithm.
  • the consensus algorithms adopted by the nodes may be different.
  • nodes can use Practical Byzantine Fault Tolerance (PBFT) consensus algorithm
  • PBFT Practical Byzantine Fault Tolerance
  • Raft consensus algorithm for private chains
  • nodes can use Raft consensus algorithm
  • nodes can use Proof of Work (PoW) Consensus algorithm.
  • PBFT Practical Byzantine Fault Tolerance
  • RoW Proof of Work
  • the blockchain network has a total of 3f+1 nodes, and f is a positive integer.
  • Each node in the network maintains a blockchain for recording user credit measurement data.
  • the PBFT algorithm is actually equivalent to including three
  • the three phases of the protocol are pre-preparation, preparation, and confirmation of nodes. Among them, the pre-preparation and preparation phases are to ensure that all normal nodes execute all valid user requests in the same order.
  • the above 3f+1 nodes can be divided into 1 master node and 3f backup nodes.
  • the server of the first network platform generates a request message according to the credit measurement parameters, and sends the request message to the master node to request to record in the blockchain
  • the credit measurement parameter the master node receives the request message, multicasts the request message to the blockchain network, and then the master node enters the pre-preparation phase, generates a composite message ⁇ m>, and multicasts the composite message on the blockchain network
  • the backup node enters the preparation phase after receiving the composite message and the verification is passed, generates a preparation message, and multicasts the preparation message, and the node stores the above preparation message and preparation message.
  • the node After the node receives the preparation message and the verification succeeds, it stores Prepare the message, when a node is ready Prepared(m,v,n,i), that is, for request m, if node i stores the request message, the pre-prepared message, and 2f+1 prepared messages, it is said that node i is ready m, the node generates a confirmation message and multicasts the confirmation message, and enters the confirmation phase at the same time. After the node receives the confirmation message and passes verification, it stores the confirmation message.
  • a node If a node confirms locally (Committed-local(m, v, n, i)) is established, and all requests with a sequence number less than n are processed, the node executes the operation in request m, and unicasts the result to the first network platform server.
  • the first network platform server receives
  • the PBFT algorithm allows at most f nodes to fail, at least one of the above f+1 nodes is valid, thus ensuring that the above results are valid.
  • Each node can write the user's credit record data in the blockchain by adding new blocks.
  • the blockchain adopts a one-way hash algorithm, and each newly generated block advances strictly in a time linear order.
  • the irreversibility and irreversibility of time leads to any attempt to invade and tamper with the data and information in the blockchain, which can be easily traced.
  • the rejection of other nodes makes the cost of fraud extremely high, which can prevent information from being tampered with.
  • the embodiment of this application can obtain the voice information released by the user on the first network platform in the blockchain network; perform violation recognition on the voice information to obtain the violation recognition result; when the violation recognition result meets the preset In case of a violation condition, generate the credit record data of the user according to the identification result of the violation, the platform identification information of the first network platform, and the user identification information of the user; 2.
  • the network platform broadcasts the credit record data of the user; when the blockchain network reaches a consensus on the credit record data of the user, the credit record data of the user is stored in the blockchain corresponding to the user .
  • the user's credit data can be shared with all network platforms in the blockchain. So as to effectively monitor the user's voice information communication behavior on all network platforms.
  • the process of obtaining credit record data from the blockchain will be described as an example.
  • the process is executed by a management device for voice information exchange, which can be specifically integrated in In the server of the first network platform, the flow of this process is as follows:
  • the user credit acquisition request may be sent to the server of the first network platform based on the user's operation on the terminal interface, which may specifically include the following scenarios:
  • the terminal when the user starts the voice live broadcast on the terminal interface, when the terminal detects the user's click operation on the live broadcast control on the terminal interface, it sends a user credit acquisition request to the server of the first network platform.
  • the terminal when the user checks the user's credit on the terminal interface, when the terminal detects that the user clicks on the credit check control on the terminal interface, it sends a request for obtaining the user's credit to the server of the first network platform.
  • the user's credit record data can be stored in the corresponding blockchain according to the user's user identification information.
  • the credit record data in the blockchain is stored in the form of key-value pairs, which can be hashed according to the user's identification information to obtain the hash value, and the key elements in the block data are hashed to obtain The hash value, if the hash value obtained by the two operations is consistent, then the blockchain is the blockchain corresponding to the user.
  • the credit metric information is expressed as a credit parameter change amount
  • all blocks in the blockchain are obtained, and all the credit metric information of the user is obtained from all the blocks.
  • the current block in the blockchain is obtained, and the user's credit record data is determined from the current block.
  • the current block refers to the newly generated block in the blockchain.
  • the terminal may obtain the user's credit measurement information according to the user's credit record data. If the credit measurement information is expressed as a credit parameter, the terminal may directly obtain the user's credit record data according to the user's credit record data. Credit parameters at the current moment.
  • the credit parameter of the user at the current moment is calculated according to the change amount of all the credit parameters of the user.
  • the terminal Before the user conducts the live broadcast, the terminal compares the obtained credit parameters with the preset credit threshold. When the credit parameter is greater than the preset credit threshold, the user is allowed to conduct the live broadcast. Specifically, the user is allowed to use the network address interface (live room) to release voice information to other users.
  • the network address interface live room
  • the user is prohibited from live broadcasting. Specifically, users are forbidden to use the network address interface (live room) to post voice messages to other users, and display prompt information on the live room page, for example, it can display "After detection of violations of your account, the broadcast has been suspended until 2020. January 7th.”
  • live room the network address interface
  • the terminal displays the obtained credit parameters on the terminal interface. In addition, it can also display all the user's violation identification results and the corresponding credit measurement information.
  • the embodiment of the present application can share the user's credit data with all network platforms in the blockchain. So as to effectively monitor the user's voice information communication behavior on all network platforms.
  • a management method for voice information communication can also be used to modify the credit record data in the blockchain according to the user's behavior or the credit record data in the blockchain.
  • the specific process can be as follows :
  • the user can send a credit modification request to the first network platform through the user's operation on the terminal interface.
  • the target credit record can be generated according to the review result information.
  • the review standard is preset by the developer. In order to ensure that the data modification can be recognized by each node in the blockchain network, the review standard can be uploaded to the blockchain.
  • the circumstances under which the user terminal can apply for credit modification are as follows:
  • the target information includes current account status information; according to the user identification information and the credit record data to be modified, the user's information is obtained from the blockchain corresponding to the user.
  • Target information can specifically include the following steps:
  • a target block in the blockchain is obtained, and current account status information is obtained from the target block.
  • the current account status information refers to information such as the login location and login time of the user account when the violation is identified.
  • the target information includes voiceprint information
  • the user’s target is obtained from the blockchain corresponding to the user based on the user identification information and the credit record data to be modified Information, which can specifically include the following steps:
  • a target block in the blockchain is obtained, and voiceprint feature information is obtained from the target block.
  • the target information includes user behavior data
  • obtaining the user behavior data of the user according to the user identification information may specifically include the following steps:
  • a target block in the blockchain is obtained, and the user behavior credit record is obtained from the target block.
  • the server When the host is prohibited from live broadcasting, the server recognizes the acquired behavior data of the host (as a viewer), and when it recognizes the behavior of adding points, according to the user identification information of the host, the identification of the first network platform, and the behavior of adding points Corresponding credit increment, the user's behavior record is generated and uploaded to the blockchain.
  • the server may obtain the user's common login location information according to the user identification information;
  • the server may obtain the historical voice information of the user in local storage according to the user identification information;
  • the voiceprint feature information does not match the historical voiceprint feature information, it is determined that the target information satisfies the preset parameter modification condition.
  • the user's credit parameter at the current moment is calculated according to the amount of credit parameter change caused by the user's behavior and the user's credit parameter when live broadcasting is prohibited. If the credit parameter at the current moment is greater than If the credit threshold is preset, it is considered that the target information satisfies the preset parameter modification condition.
  • the user identification information and the credit record data to be modified may be used as key elements, and the target information and the platform identification information of the first network platform may be used as value elements to generate a key-value pair .
  • this embodiment of the application can review the user's credit modification request through preset modification conditions and the credit record data in the blockchain.
  • the block can be modified Data in the chain, thereby restoring the user’s credit.
  • an embodiment of the present application also provides a voice information communication management device.
  • the apparatus for managing voice information communication may include an acquiring unit 401, a recognition unit 402, a generating unit 403, a broadcasting unit 404, and a storage unit 405, as follows:
  • the acquiring unit 401 is configured to acquire the voice information released by the user on the first network platform in the blockchain network.
  • the recognition unit 402 is configured to recognize violations of the voice information to obtain a violation recognition result.
  • the recognition unit 402 may specifically include a voice recognition subunit and a violation recognition subunit, as follows:
  • the voice recognition subunit is used to recognize the voice information to obtain text information corresponding to the voice information;
  • the violation recognition subunit is used to perform content matching on the text information according to a preset violation information set to obtain a matching result; and determine the violation recognition result of the voice information according to the matching result.
  • the voice recognition subunit may be specifically used for:
  • the semantic association information between the text words is extracted, and the text words are combined to obtain text information according to the association information.
  • the generating unit 403 is configured to generate according to the violation recognition result, the platform identification information of the first network platform, and the user identification information of the user when the violation identification result meets the preset violation conditions The credit history data of the user.
  • the generating unit 403 may specifically include a violation record sub-unit, a credit calculation sub-unit, and a generating sub-unit, as follows:
  • the violation record subunit is configured to generate a violation record according to time, platform identification information of the first network platform, and the violation identification result when the violation identification result meets the preset violation condition;
  • a credit calculation subunit configured to obtain credit measurement information of the user according to the violation identification result
  • the generating subunit is configured to generate the credit record data of the user according to the violation record, the credit measurement information, and the user identification information.
  • the generating subunit may be specifically used for:
  • the generating unit 403 may be further configured to obtain the user's registration identity information in the first network platform according to the user identification information; correspondingly, the generating subunit may also be specifically Used to: combine the credit measurement information with the violation record to obtain first combined information; combine the user identification information and the registered identity information to obtain second combined information; according to the first combination The information and the second combined information generate an associated information pair to obtain the credit record data of the user.
  • the generating unit may be further configured to: when the violation identification result meets a preset violation condition, according to the violation identification result, the platform identification information of the first network platform, and the The user identification information and the voiceprint feature information are used to generate credit record data of the user.
  • the generating unit may be further configured to: when the violation identification result meets a preset violation condition, according to the violation identification result, the platform identification information of the first network platform , The user identification information and the current account status information generate credit record data of the user.
  • the broadcasting unit 404 is configured to broadcast the user's credit record data to the second network platform in the blockchain network.
  • the broadcasting unit 404 may also be used for:
  • the verification information is broadcast to the second network platform in the blockchain network.
  • the storage unit 405 is configured to store the credit record data of the user in the blockchain corresponding to the user after the blockchain network reaches a consensus on the credit record data of the user.
  • the apparatus for managing voice information communication may further include a credit obtaining unit 406, configured to receive a user credit obtaining request sent by the terminal, and the user credit obtaining request carries the user identifier;
  • the user identification determines the block chain corresponding to the user; fetches the block in the block chain, and determines the user’s credit record data from the block; returns the user’s information to the terminal Credit history data;
  • the apparatus for managing voice information exchange may further include a credit modification unit 407, configured to obtain a credit modification request from a terminal, the credit modification request carrying the user identification information of the user;
  • the user identification information and the credit record data to be modified obtain the user's target information from the blockchain corresponding to the user; when the target information satisfies the preset parameter modification condition, according to Obtain credit measurement information according to the satisfied parameter modification conditions; generate target credit record data according to the credit measurement information, the user identification information, the target information, and the platform identification information of the first network platform;
  • the second network platform in the blockchain network broadcasts the target credit record data; when the blockchain network reaches a consensus based on the target credit record data, the target credit record data is stored in the corresponding user In the blockchain.
  • each of the above units can be implemented as an independent entity, or can be combined arbitrarily, and implemented as the same or several entities.
  • each of the above units please refer to the previous method embodiments, which will not be repeated here.
  • the embodiment of this application stores the information to be managed related to false information in the blockchain, and the consensus algorithm based on the blockchain can prevent the information to be managed from being tampered with, and ensure the authenticity, credibility and reliability of the information. Security, and at the same time, the blockchain can more directly and widely disseminate the information to be managed based on false information, so as to more effectively control false information.
  • the embodiment of the present application also provides a voice information exchange device, which can be used as a node in the blockchain.
  • the voice information exchange device can be integrated in the first node of the blockchain.
  • a node can be any node in the blockchain.
  • the voice information exchange device may also be a terminal device. As shown in Figure 4, it shows a schematic structural diagram of a computer device involved in an embodiment of the present application, specifically:
  • the voice information exchange device may include one or more processing core processors 501, one or more computer-readable storage media storage 502, power supply 503, input unit 504 and other components.
  • processing core processors 501 one or more computer-readable storage media storage 502, power supply 503, input unit 504 and other components.
  • FIG. 4 does not constitute a limitation on the voice information communication device, and may include more or less components than those shown in the figure, or a combination of certain components, or different components.
  • the processor 501 is the control center of the voice information communication equipment, and uses various interfaces and lines to connect the various parts of the entire voice information communication equipment, by running or executing software programs and/or modules stored in the memory 502, and calling
  • the data in the memory 502 performs various functions and processing data of the voice information communication device, so as to monitor the voice information communication device as a whole.
  • the processor 501 may include one or more processing cores; preferably, the processor 501 may integrate an application processor and a modem processor, where the application processor mainly processes the operating system, user interface, and application programs, etc. ,
  • the modem processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 501.
  • the memory 502 may be used to store software programs and modules.
  • the processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502.
  • the memory 502 may mainly include a storage program area and a storage data area.
  • the storage program area may store an operating system, an application program required by at least one function (such as a sound playback function, an image playback function, etc.), etc.; Data created by the use of computer equipment, etc.
  • the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the memory 502 may further include a memory controller to provide the processor 501 with access to the memory 502.
  • the voice information exchange device also includes a power supply 503 for supplying power to various components.
  • the power supply 503 may be logically connected to the processor 501 through a power management system, so that functions such as charging, discharging, and power management can be managed through the power management system.
  • the power supply 503 may also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.
  • the voice information communication device may also include an input unit 504, which can be used to receive inputted numeric or character information, and generate touch screen, keyboard, mouse, joystick, optical or trackball related to user settings and function control. signal input.
  • input unit 504 can be used to receive inputted numeric or character information, and generate touch screen, keyboard, mouse, joystick, optical or trackball related to user settings and function control. signal input.
  • the voice information exchange device may also include a display unit, etc., which will not be described in detail here.
  • the processor 501 in the computer device will load the executable file corresponding to the process of one or more application programs into the memory 502 according to the following instructions, and the processor 501 will run and store the executable file in the memory 502.
  • the application programs in the memory 502, thereby realizing various functions, are as follows:
  • the user credit acquisition request carries the user ID; according to the user ID, determine the block chain corresponding to the user; fetch the block in the block chain, And determine the credit record data of the user from the block; return the credit record data of the user to the terminal;
  • the credit modification request carrying user identification information of the user
  • the target credit record data is stored in the blockchain corresponding to the user.
  • the embodiment of this application stores the information to be managed related to false information in the blockchain, and the consensus algorithm based on the blockchain can prevent the information to be managed from being tampered with, and ensure the authenticity, credibility and reliability of the information. Security, and at the same time, the blockchain can more directly and widely disseminate the information to be managed based on false information, so as to more effectively control false information.
  • an embodiment of the present application further provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to perform any type of voice information communication management provided by the embodiments of the present application. Steps in the method.
  • the instruction can perform the following steps:
  • the first node is any node in the blockchain to obtain information to be managed based on false information
  • the verification information may be generated according to the information to be managed, the verification information including the information to be managed and the signature information of the first node;
  • the information to be managed is stored in the blockchain, and based on the consensus algorithm of the blockchain, the nodes in the blockchain reach a consensus based on the information to be managed ,
  • the second node is a node other than the first node in the blockchain;
  • the second node is a node other than the first node in the blockchain, and can obtain an information acquisition request sent by a terminal;
  • the computer-readable storage medium may include: read only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks, etc.
  • any voice information communication management method provided in the embodiments of the present application
  • any voice information provided in the embodiments of the present application can be implemented.
  • the beneficial effects that can be achieved by the information exchange management method see the previous embodiment for details, and will not be repeated here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Finance (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Hardware Design (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Telephonic Communication Services (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)

Abstract

本申请实施例公开了一种语音信息交流的管理方法、装置、存储介质和设备；本申请实施例可以获取用户在区块链网络中第一网络平台发布的语音信息；对语音信息进行违规识别，得到违规识别结果；当违规识别结果满足预设违规条件时，根据违规识别结果、第一网络平台的平台标识信息、以及用户的用户标识信息，生成用户的信用记录数据；向区块链网络中的第二网络平台广播用户的信用记录数据；当区块链网络针对用户的信用记录数据达成共识后，将用户的信用记录数据存储至用户对应的区块链中。

Description

一种语音信息交流的管理方法、装置、存储介质和设备
本申请要求于2020年02月18日提交中国专利局，申请号为202010100493.1，发明名称为“一种语音信息交流的管理方法、装置和存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及区块链的技术领域，具体涉及一种语音信息交流的管理方法、装置和存储介质。
背景技术
近年来，语音社交成为当下年轻人中流行的社交方式，语音社交是指以声音为主要交流手段，实现交友、信息交流和互动，交流分享等功能，从用户体验看，与文字社交对比，语音社交更加生动有趣；与图片及视频社交对比，语音社交的隐私性更高、门槛更低，且更加能够表达真实情绪。
但是，目前对语音社交的监管主要依赖于网络平台进行的人工审核，效率低，且正确率不高。另外，由于不同网络平台的数据不互通，用户在单个网络平台的违规行为一般不会影响用户在其他网络平台的语音信息交流，因此无法有效地规范用户的语音信息交流行为。
发明内容
根据本申请的各种实施例，提供了一种语音信息交流的管理方法、装置、存储介质和设备。
一种语音信息交流的管理方法，由计算机设备执行，包括：
获取用户在所述第一网络平台发布的语音信息；
对所述语音信息进行违规识别，得到违规识别结果；
当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户 的信用记录数据；
向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；
当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。
在一实施例中，还包括：
接收终端发送的用户信用获取请求，所述用户信用获取请求携带所述用户标识；
根据所述用户标识，确定所述用户对应的区块链；
获取所述区块链中的区块，并从所述区块中确定所述用户的信用记录数据；
向所述终端返回所述用户的信用记录数据。
在一实施例中，还包括：
根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息；
当所述目标信息满足所述预设参数修改条件时，根据满足的参数修改条件，获取信用度量信息；
根据所述信用度量信息、所述用户标识信息、所述目标信息，以及所述第一网络平台的平台标识信息，生成目标信用记录数据；
向所述区块链网络中的第二网络平台广播所述目标信用记录数据；
当所述区块链网络基于所述目标信用记录数据达成共识后，将所述目标信用记录数据存储至所述用户对应的区块链中。
一种语音信息交流的管理装置，包括：
获取单元，用于获取用户在区块链网络中第一网络平台发布的语音信息；
识别单元，用于对所述语音信息进行违规识别，得到违规识别结果；
生成单元，用于当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；
广播单元，用于向所述区块链网络中的第二网络平台广播所述用户的信用 记录数据；
存储单元，用于当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链，
一种计算机可读存储介质，其上存储有计算机程序，当计算机程序在计算机上运行时，使得计算机执行如本申请任一实施例提供的语音信息交流的管理方法。
一种语音信息交流设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时执行如本申请任一实施例提供的语音信息交流的管理方法。
一种计算机程序产品或计算机程序，所述计算机程序产品或计算机程序包括计算机指令，所述计算机指令存储在计算机可读存储介质中；第一节点的处理器从所述计算机可读存储介质读取并执行所述计算机指令时，使得所述处理器执行所述语音信息交流的管理方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1a是本发明实施例提供的语音信息交流的管理系统的场景示意图；
图1b是本发明实施例提供的区块链的结构示意图；
图1c是本发明实施例提供的区块链中区块生成的流程示意图；
图2a是本发明实施例提供的语音信息交流的管理方法的第一种流程示意图；
图2b是本发明实施例提供的语音信息交流的管理方法的第二种流程示意图；
图2c是本发明实施例提供的语音信息交流的管理方法的第三种流程示意图；
图3a是本发明实施例提供的语音信息交流的管理装置的第一种结构示意图；
图3b是本发明实施例提供的语音信息交流的管理装置的第二种结构示意图；
图3c是本发明实施例提供的语音信息交流的管理装置的第三种结构示意图；
图4是本发明实施例提供的语音信息交流设备的结构示意图；
图5a是本发明实施例提供的语音直播界面示意图；
图5b是本发明实施例提供的当识别到违规时，语音直播界面的示意图；
图5c是本发明实施例提供的当识别到信用分低于预设值时，语音直播界面的示意图；
图6是本发明实施例提供的的语音信息交流的管理的流程示意图；
图7是本发明实施例提供的语音识别的流程示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在对本申请实施例进行详细地解释说明之前，先对本申请实施例涉及到的一些名词进行解释说明。
语音信息交流：本申请的语音信息交流是以语音信息为主要交流手段，通过网络平台进行交友、信息交流和互动，交流分享。主要包括语音直播、语音通话等形式，也可以包括语音消息形式。
区块链：区块链技术脱胎于比特币技术，是比特币的底层技术，其是去中心化的分布式账本数据库。区块链本身是一串使用密码学算法相关联产生的数据块(即区块)，每一个数据块中包含了多次区块链网络交易有效确认的信息。 正是基于此，所以无法通过篡改区块上的数据来进行作弊，能够确保任何区块上的数据均是公开透明的，确保了数据的安全性。在以下描述中为了明确区块链系统和区块组成的链，可以将包含多个节点的区块链系统称为区块链网络，将区块链中存储的数据组成的链称为区块链。
区块链网络可以分为公有链、私有链、联盟链。其中，联盟链则介于公有链和私有链之间，由若干组织一起合作维护一个区块链网络，该区块链网络的使用必须是有权限的管理，相关信息会得到保护，典型如金融组织。总结来说，区块链网络是由节点参与的分布式数据库系统，或者，也可称之为一个基于P2P(点对点)网络的分布式公共账本，其特点是不可更改、不可伪造，还可以将其理解为账簿系统。
区块链网络的节点：参与构建区块链网络的设备，比如，参与构建区块链网络的各内容厂商的计算机设备，该计算机设备可以为单台计算机设备如某个内容厂商的单台服务器，也可以为某个内容厂商的计算机设备集群如服务器集群。区块链网络的节点可以为信息处理的执行主体、节点之间交互可以实现交易等业务等。该节点存储有相关区块，比如，该区块可以包括用户的信用记录数据等。在本实施例中，网络平台的服务器可以作为所述区块链网络的节点。
接下来将介绍本申请实施例提供的一种语音信息交流的管理方法、装置和存储介质。
本申请实施例提供一种语音信息交流的管理方法、装置和存储介质。其中，该语音信息交流的管理方法可以由计算机设备执行，该计算机设备可以是对语音信息交流进行管理的语音信息交流设备，具体可以是服务器，也可以是终端等设备。其中，该终端可以包括手机、平板电脑、笔记本电脑、个人计算机(Personal Computer，PC)、车载终端等设备。该服务器可以是单台服务器，也可以是多台服务器组成的服务器集群，当为服务器时，该计算机设备可以集成在区块链的第一节点中，该第一节点可以为区块链中的任意一个节点。
例如，参见图1a，本申请实施例提供了语音信息交流的管理系统，该系统可以实现语音信息交流的管理等业务。该系统可以包括多个区块链的节点和终端如手机、电脑，其中，多个节点之间通过网络连接，节点和终端之间也通过网络连接。
本申请实施例可以获取用户在区块链网络中第一网络平台发布的语音信息；对所述语音信息进行违规识别，得到违规识别结果；当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。通过将用户的信用记录数据存储至区块链，可以将用户的信用数据共享给区块链中的所有网络平台。从而有效地监控用户在所有网络平台的语音信息交流行为。
在实际应用时，区块链网络还提供了信息查询功能，以便查询用户的信用记录数据。具体地，区块链网络节点可以接收网络平台服务器发送的信用参数获取请求，该信用参数获取请求中包括用户标识，用于请求用户对应的信用记录数据，然后区块链网络节点可以根据用户标识从区块链上搜索与用户对应的信用记录数据，接着向第二网络平台服务器发送目标用户对应的信用记录数据。
以下分别进行详细说明。需说明的是，以下实施例的顺序不作为对实施例优选顺序的限定。
一、构建区块链网络：
区块链的架构可以包括区块链底层平台、平台产品服务层以及应用服务层。
区块链底层平台可以包括用户管理、基础服务、智能合约以及运营监控等处理模块。其中，用户管理模块负责所有区块链参与者的身份信息管理，包括维护公私钥生成(账户管理)、密钥管理以及用户真实身份和区块链地址对应关系维护(权限管理)等，并且在授权的情况下，监管和审计某些真实身份的交易情况，提供风险控制的规则配置(风控审计)；基础服务模块部署在所有区块链节点设备上，用来验证业务请求的有效性，并对有效请求完成共识后记录到存储上，对于一个新的业务请求，基础服务先对接口适配解析和鉴权处理(接口适配)，然后通过共识算法将业务信息加密(共识管理)，在加密之后完整一致的传输至共享账本上(网络通信)，并进行记录存储；智能合约模块负责合约的注 册发行以及合约触发和合约执行，开发人员可以通过某种编程语言定义合约逻辑，发布到区块链上(合约注册)，根据合约条款的逻辑，调用密钥或者其它的事件触发执行，完成合约逻辑，同时还提供对合约升级注销的功能；运营监控模块主要负责产品发布过程中的部署、配置的修改、合约设置、云适配以及产品运行中的实时状态的可视化输出，例如：告警、监控网络情况、监控节点设备健康状态等。
平台产品服务层提供典型应用的基本能力和实现框架，开发人员可以基于这些基本能力，叠加业务的特性，完成业务逻辑的区块链实现。应用服务层提供基于区块链方案的应用服务给业务参与方进行使用。
二、在构建区块链网络之后，便可以采用区块链网络进行语音信息交流的管理：
在一实施例中，参考图2a，将以信用记录数据写入区块链的过程为例进行描述，以语音信息交流的管理装置的角度描述该过程，语音信息交流的管理装置具体可以集成在第一网络平台的服务器中。
101、获取用户在区块链网络中第一网络平台发布的语音信息。
其中，本申请实施例中的语音信息交流主要是指以数据流的形式实时获取并播放发布方发送的语音信息，可以包括语音直播、语音通话等形式。
其中，本申请实施例中的语音直播、语音通话等语音交流方法是一种可以实时发布和接收信息的通信方式。其中，语音直播由主播在语音直播间内发布语音信息，观众通过语音直播间接收主播发布的语音消息。其中，语音直播间可以理解为用于发布和接收语音信息的网络地址接口，主播是在直播过程中发布语音消息的用户。主播还可以通过“连麦”的方式，与其他主播进行语音交互，当“连麦”时，连麦的双方(指主播)语音交互过程可以同时在双方的直播间内发布。
在直播过程中，主播可以通过现场架设独立的信号采集设备将音频和视频导入终端中的导播客户端，再通过网络上传至网络平台的服务器，发布至网络地址接口供观众通过播放客户端观看。
主播的直播间可以开放给网络平台中的所有用户，还可以根据主播的设置，开放给特定用户。语音直播间如图5a所示，语音直播间不会有视频画面，当主播说话时，主播头像周围会有音波出现。
其中，语音通话是不开放给用户观看的、由多个用户互相发布语音信息的交流方式。
直播和语音通话涉及到流媒体(Streaming Media)技术，流媒体(Streaming Media)技术是指将一连串的媒体数据压缩后，以数据流的形式在网络中分段传送，实现在网络上实时传输媒体数据流以供播放的一种技术。
用户以媒体数据流的形式向网络平台发送语音信息，在一实施例中，媒体数据流可以以语音信息压缩包为单位进行传输，由服务器对获取到的媒体数据流进行解码得到语音信息。
其中，第一网络平台可以是加入区块链网络的任意网络平台，第二网络平台也可以是区块链网络中除第一网络平台之外的网络平台，可以表现为区块链网络中的任意网络平台。其中，网络平台是通过网络实现语音信息交流的平台。
102、通过预设语音识别算法对所述语音信息进行识别，得到所述语音信息对应的文本信息。
其中，对语音信息进行识别涉及到人工智能的ASR技术。其中，ASR(Automatic Speech Recognition，自动语音识别技术)用于将语音信息中的词汇内容转换为计算机可读的输入，例如按键、二进制编码或者字符流。ASR是语音技术(Speech Technology)的关键技术之一。让计算机能听、能看、能说、能感觉，是未来人机交互的发展方向，其中语音成为未来最被看好的人机交互方式之一。
在一实施例中，参考图7，所述通过预设语音识别算法对所述语音信息进行识别，得到所述语音信息对应的文本信息，具体可以包括如下步骤：
对所述语音信息进行划分，得到所述语音信息对应的音频帧序列；
对所述音频帧序列中的音频帧进行特征提取，得到所述语音信息对应的音频特征信息；
据预设声学模型，获取所述音频特征信息对应的音素；
根据预设语言模型，对所述音素和预设字典进行比较与匹配，得到所述音素对应的文本单词；
提取所述文本单词之间的语义关联信息，根据所述关联信息，将所述文本单词组合得到文本信息。
在一实施例中，预处理包括加重、分帧、加窗，为了避免相邻两帧的变化过大，可以将语音信息进行加重，然后运用VAD(静音切除操作技术)对语音信息进行分帧，把主播上传的语音信息划分为多个小段，每个小段称为一个音频帧，帧与帧之间一般是有交叠的。把首尾端的静音切除，降低对后续步骤造成的干扰。比如，每个音频帧的长度为25毫秒，每两个音频帧之间有15毫秒的重复部分。分帧后，语音就变成了很多小段，根据人耳的生理特性，把每一帧波形进行特征提取，得到一个多维向量。
在一实施例中，音频特征信息可以表现为MFCC(Mel-Frequency Cepstral Coefficients，梅尔频率倒谱系数)向量，进行特征提取的过程可以包括如下步骤：然后将音频帧带入汉明窗函数，得到每个音频帧对应的短时分析窗，对于每个短时分析窗通过FFT(傅里叶变换)得到对应的频谱，然后将上面的频谱通过梅尔滤波器组过滤掉人类听不到的频率，得到梅尔频谱，从而将线形的自然频谱转换为体现人类听觉特性的梅尔频谱。在梅尔频谱上面进行倒谱分析(取对数，做逆变换，实际逆变换一般是通过离散余弦变换来实现，取离散余弦后的第2个到第13个系数作为梅尔频率倒谱系数)，得到梅尔频率倒谱系数。每帧的12个梅尔频率倒谱系数组合得到每帧音频帧的倒谱向量。在一实施例中，还可以根据梅尔倒谱系数计算帧间的动态变化特征，与每帧的梅尔倒谱系数共同组成倒谱向量。所有音频帧的倒谱向量就是上述语音信息的音频特征信息。
其中，音素是从音色的角度划分出来的最小的语音单位。其中，预设字典用于描述文本单词(words)到语音片段(phones)之间的映射。除了字典，还可以通过运用机器学习算法去学习得到一些复杂的函数去完成映射功能。通过训练神经网络模型使学会该映射功能，从而根据语音特征信息流得到文本单词流。
在一实施例中，可以采用隐马尔科夫模型(HMM)作为声学模型。隐马尔科夫模型(HMM)需要经过训练才可以使用。
在另一实施例中，还可以基于深度神经网络训练语言模型，提取特征输入语言模型，得到语音信息对应的文本信息。
103、根据预设违规信息集合对所述文本信息进行违规识别，得到违规识别结果。
其中，网络平台可以预先设置违规信息集合。预设违规信息集合是根据国家音视频直播的法律法规生成的违规信息库，作为一个示例，违规信息库可以包括以下内容中的任意一种或多种：(1)色情、赌博、毒品相关信息；(2)谣言或者其他扰乱社会秩序、破坏社会稳定的信息；(3)含有虚假、有害、胁迫、侵害他人隐私、中伤、低俗、诈骗或其它道德上令人反感的内容；(4)假冒伪劣产品或未经授权销售的产品信息。(5)以上内容中的关键特征词。
网络平台服务器可以通过关键词匹配、自然语言处理(语义分析)等方式对所述文本信息进行违规识别，在一实施例中，当文本信息包括违规信息时，确认为违规，然后统计文本信息中与违规信息匹配的信息，得到违规识别结果；当在一次语音直播中，识别到文本信息中包括违规信息的关键特征词的次数，达到预设信用阈值时，确认为违规，然后统计文本信息中匹配成功的关键特征词。其中，违规识别结果包括是否违规的结论，如果结论为违规，那么违规识别结果还包括上述统计得到的信息。
104、当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据。
其中，用户的信用记录数据是用于表示当前时刻用户的信用的数据(比如信用度量信息)，还可以包括改变用户信用的信息(比如，违规识别结果)。
在一实施例中，所述当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据，具体可以包括如下步骤：
当所述违规识别结果满足预设违规条件时，根据时间、所述第一网络平台 的平台标识信息，以及所述违规识别结果，生成违规记录；
根据所述违规识别结果，获取所述用户的信用度量信息；
根据所述违规记录、所述信用度量信息和所述用户标识信息，生成所述用户的信用记录数据。
其中，信用度量信息是用于度量当前时刻用户信用的信息，可以表现为用户的信用参数(状态值)或者用户的信用参数变化量。
当信用度量信息表现为信用参数(状态值)时，需要预先从区块链中获取用户在当前时刻之前的信用参数，并根据之前的信用参数和违规识别结果对应的信用变化量，来计算用户在当前时刻的信用参数。
其中，不同的违规类型，对信用的改变程度不同，比如，网络平台可以设置当识别到赌博关键词的次数达到预设信用阈值时，信用参数减少2单位，当识别到诈骗信息时，信用参数减少4个单位。
当第一网络平台的服务器在根据所述违规识别结果，获取所述用户的信用度量信息之后，还可以实施如下步骤：
根据所述预设信用阈值和所述信用度量信息，对所述用户进行语音信息发布权限识别，得到权限识别结果；
当所述权限识别结果表现为用户不具备语音信息发布权限时，停止接收所述用户发送的语音信息。
在一实施例中，在所述根据所述违规识别结果，获取所述用户的信用度量信息之后，还包括如下步骤：
根据所述违规记录和所述信用度量信息，生成信用告警消息；
向所述终端返回所述信用告警消息。
参考图5b，当服务器识别到违规语音时，生成相应的提示信息，并将提示信息发送给终端进行显示。
参考图5c，服务器根据所述违规识别结果，获取所述用户的信用度量信息后，继续根据预设信用阈值和用户的度量参数信息进行直播权限识别，当用户信用参数不满足预设信用阈值时，停止接收用户上传的语音信息，并向终端发送提示信息。
参考图6，在另一实施例中，为了使显示的信用告警信息更加真实可信，可以在区块链网络针对所述用户的信用记录数据达成共识后，再根据信用记录数据中的根据所述违规记录和所述信用度量信息，对所述用户进行语音信息发布权限识别，得到权限识别结果。
在一实施例中，所述当根据所述违规记录、所述信用度量信息和所述用户标识信息，生成所述用户的信用记录数据，具体可以包括如下步骤：
将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；
将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
将违规记录也作为信用记录数据的一部分，写入区块链中，而不是只将信用度量信息写入区块链中，能够提高信用记录数据的真实性和安全性。另外，还可以在用户质疑信用记录数据真实性，并进行信用申诉的时候，作为证据。
其中，关联信息对是一种关联信息的组合方式，具体可以表现为key-value(键值对)形式，其中，服务器可根据用户标识信息生成键值对中的键元素，并根据用户标识信息和信用记录数据生成键值对中的值元素，关联该键元素和该值元素。
用户标识信息可以用于确定信用记录数据所对应的区块链。
在一实施例中，在生成信用记录数据时，还可以根据用户的用户标识信息，获取所述用户在所述第一网络平台中的注册身份信息；并将所述信用度量信息与所述违规记录进行组合，得到第一组合信息，然后将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
其中，注册身份信息是指在网络平台注册账号时使用的身份证、邮箱、手机号码等用于验证身份的信息。一般情况下，第一网络平台不会将用户的注册身份信息共享给其他网络平台，当用户出现违规时，第一网络平台可以将用户的信用记录数据上传至区块链，从而共享给区块链网络中第二网络平台。这样只要注册账号或者发布语音信息时，需要查询用户的身份信息，那么用户在第 一网络平台被禁止直播或者查封账号后，用户无法使用相同的身份信息，在其他网络平台注册账号和发布语音信息。从而更有效地监管用户的语音直播行为。
105、向所述区块链网络中的第二网络平台广播所述用户的信用记录数据。
其中，第二网络平台是区块链网络中除第一网络平台之外的网络平台。
在一实施例中，第二网络平台在在将所述用户的信用记录数据存储至区块链之前，还需要进行验证，以确保数据在传输过程中没有被篡改。
在一实施例中，第一网络平台的服务器可以对信用记录数据进行哈希运算，得到哈希值，然后根据区块链网络下发的私钥对哈希值进行加密，得到校验信息，将校验信息、用户的信用记录数据，以及私钥对应的公钥一起发送给第二网络平台。
第二网络平台的服务器使用公钥对校验信息进行解密，得到第一网络平台计算的哈希值，并计算用户的信用记录数据的哈希值，若哈希值一致，说明用户的信用记录数据在传输过程中没有被篡改。
在一实施例中，区块链网络中的每个节点均存储一条或者多条相同的区块链。区块链由多个区块组成，参见图1b，区块链由多个区块组成，创始块中包括区块头和区块主体，区块头中存储有输入信息特征值、版本号、时间戳和难度值，区块主体中存储有输入信息；创始块的下一区块以创始块为父区块，下一区块中同样包括区块头和区块主体，区块头中存储有当前区块的输入信息特征值、父区块的区块头特征值、版本号、时间戳和难度值，并以此类推，使得区块链中每个区块中存储的区块均与父区块中存储的区块存在关联，保证了区块中输入信息的安全性。
在生成区块链中的各个区块时，参见图1c，第二网络平台的服务器在接收到输入信息时，根据校验信息对输入信息进行校验，完成校验后，将输入信息存储至本地内存池中，并更新其用于记录输入信息的哈希树；之后，将更新时间戳更新为接收到输入信息的时间，并尝试不同的随机数，多次进行特征值计算，使得计算得到的特征值可以满足下述公式：
SHA256(SHA256(version+prev_hash+merkle_root+ntime+nbits+x))＜TARGET
其中，SHA256为计算特征值所用的特征值算法；version(版本号)为区块链中相关区块协议的版本信息；prev_hash为当前区块的父区块的区块头特征值；merkle_root为输入信息的特征值；ntime为更新时间戳的更新时间；nbits为当前难度，在一段时间内为定值，并在超出固定时间段后再次进行确定；x为随机数；TARGET为特征值阈值，该特征值阈值可以根据nbits确定得到。
这样，当计算得到满足上述公式的随机数时，便可将信息对应存储，生成区块头和区块主体，得到当前区块。
106、当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。
在一实施例中，可以根据区块链网络的共识算法，可以基于共识算法使区块链中的节点对所述用户的信用记录数据达成共识。具体地，区块链类型不同时，节点采用的共识算法可以是不同的。例如，针对联盟链，节点可以采用实用拜占庭容错(Practical Byzantine Fault Tolerance，PBFT)共识算法，针对私有链，节点可以采用Raft共识算法，针对公有链，节点可以采用工作证明(Proof of Work，PoW)共识算法。
为了便于理解，下面以基于PBFT算法进行一致性验证示例说明。
在该示例中，区块链网络共有3f+1个节点，f为正整数，网络中的每个节点维护有一个用于记录用户信用度量数据的区块链，该PBFT算法实际相当于包括三阶段的协议，三阶段分别是预准备、准备和确认节点，其中，预准备和准备阶段是保证所有正常节点按照相同顺序执行所有有效的用户请求。
上述3f+1个节点可以分为1个主节点和3f个备份节点，第一网络平台的服务器根据信用度量参数生成请求消息，向主节点发送该请求消息，用于请求在区块链中记录该信用度量参数，主节点接收到该请求消息，向区块链网络组播该请求消息，然后主节点进入预准备阶段，产生复合消息<m>，并在区块链网络组播该复合消息，备份节点收到该复合消息且验证通过后进入准备阶段，生成准备消息，并组播该准备消息，同时节点存储上述预准备消息和准备消息，节点在收到准备消息且验证通后，存储准备消息，当某节点准备好Prepared(m,v,n,i)，即对于请求m，若节点i存储了请求消息、预准备消息及2f+1 个准备消息，则称节点i已经准备好m，则该节点生成确认消息并组播该确认消息，同时进入确认阶段，节点在接收到确认消息并验证通过后，存储该确认消息，若某节点本地确认(Committed-local(m,v,n,i))成立，且所有序号小于n的请求都被处理，则该节点执行请求m中的操作，并将结果单播给第一网络平台服务器，当第一网络平台服务器接收到来自不同复制节点的f+1个相同的结果时，由于PBFT算法至多允许f个节点失效，则上述f+1个节点至少有一个是有效的，因而能够确保上述结果是有效的，区块链网络中的各节点可以新增区块的方式在区块链中写入所述用户的信用记录数据。
区块链采取单向哈希算法，每个新产生的区块严格按照时间线形顺序推进，时间的不可逆性、不可撤销导致任何试图入侵篡改区块链内数据信息的行为易被追溯，导致被其他节点的排斥，造假成本极高，从而可以防止信息被篡改。
由上可知，本申请实施例可以可以获取用户在区块链网络中第一网络平台发布的语音信息；对所述语音信息进行违规识别，得到违规识别结果；当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。通过将用户的信用记录数据存储至区块链，可以将用户的信用数据共享给区块链中的所有网络平台。从而有效地监控用户在所有网络平台的语音信息交流行为。
在一实施例中，参考图2b，将以从区块链中获取信用记录数据的过程为例进行描述，该过程由语音信息交流的管理装置来执行，语音信息交流的管理装置具体可以集成在第一网络平台的服务器中，该过程的流程如下：
201、接收终端发送的用户信用获取请求，所述用户信用获取请求携带所述用户标识。
可以基于用户在终端界面上的操作，向第一网络平台的服务器发送用户信用获取请求，具体可以包括如下场景：
比如，当用户在终端界面上开启语音直播时，当终端检测到用户针对终端界面上的直播控件的点击操作时，向第一网络平台的服务器发送用户信用获取请求。
比如，当用户在终端界面上查看用户信用时，当终端检测到用户在终端界面上针对信用查看控件的点击操作时，向第一网络平台的服务器发送用户信用获取请求。
202、根据所述用户标识，确定所述用户对应的区块链。
为了方便区块链的管理，可以根据用户的用户标识信息，将用户的信用记录数据存储至相应的区块链中。
其中，区块链中的信用记录数据以键值对的形式进行存储，可以根据用户的标识信息进行哈希运算，得到哈希值，并对区块数据中的键元素进行哈希运算，得到哈希值，若两次运算得到的哈希值一致，则该区块链为该用户对应的区块链。
203、获取所述区块链中的区块，并从所述区块中确定所述用户的信用记录数据。
在一实施例中，当所述信用度量信息表现为信用参数变化量时，获取所述区块链中的所有区块，并从所述所有区块中获取所述用户的所有信用度量信息。
在另一实施例中，当所述信用度量信息表现为信用参数时，获取所述区块链中的当前区块，并从所述当前区块中确定所述用户的信用记录数据。
其中，当前区块指的是区块链中最新生成的区块。
204、向所述终端返回所述用户的信用记录数据。
在一实施例中，终端可以根据所述用户的信用记录数据，获取所述用户的信用度量信息，若所述信用度量信息表现为信用参数，则终端直接根据从用户的信用记录数据中获取用户在当前时刻的信用参数。
若所述信用度量参数表现为信用参数变化量，则根据用户的所有信用参数变化量，根据计算所述用户在当前时刻的信用参数。
当用户进行直播之前，终端将获取到的信用参数与预设信用阈值进行比 较，信用参数大于预设信用阈值时，允许用户进行直播。具体地，允许用户使用网络地址接口(直播间)向其他用户发布语音信息。
若信用参数小于或者等于预设信用阈值时，禁止用户进行直播。具体地，禁止用户使用网络地址接口(直播间)向其他用户发布语音信息，并在直播间页面上显示提示信息，比如，可以显示“经检测你的账号存在违规行为，已被停播至2020年1月7日”。
当用户查看信用参数时，终端将获取到的信用参数显示在终端界面上，另外还可以显示用户的所有违规识别结果，以及对应的信用度量信息。
由上可知，本申请实施例通过通过将用户的信用记录数据存储至区块链，可以将用户的信用数据共享给区块链中的所有网络平台。从而有效地监控用户在所有网络平台的语音信息交流行为。
如图2c所示，一种语音信息交流的管理方法，还可以用于根据用户的行为，或者区块链中的信用记录数据，对区块链中的信用记录数据进行修改，具体流程可以如下：
301、获取来自终端的信用修改请求，所述信用修改请求携带所述用户的用户标识信息，以及待修改的信用记录数据以及待修改的信用记录数据。
当用户对查询到的信用记录数据存在质疑时，可以通过用户在终端界面上的操作，向第一网络平台发送信用修改请求，经过第一网络平台审核通过之后，可以根据审核结果生成目标信用记录信息。
其中，审核的标准由开发人员预先设定，为了保障数据修改可以得到区块链网络中各节点的认可，可以将审核的标准上传到区块链中。
在一实施例中，用户端可以申请进行信用修改的情况如下：
(1)当用户账号在异常登录状态下，发布了违规语音；(2)当用户发布违规语音的声纹特征与用户的其他声纹特征不一致时。(3)当用户根据预设信用规则，作出恢复信用的行为时，比如，当主播被禁止进行直播时，主播作为观众，在第一网络平台的评论、弹幕、转发、收藏行为，以及消费行为。
302、根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息。
在一实施例中，所述目标信息包括当前账号状态信息；所述根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息，具体可以包括如下步骤：
根据所述用户标识信息，确定所述用户对应的区块链；
根据所述待修改的信用记录数据，获取所述区块链中的目标区块，并从所述目标区块中获取当前账号状态信息。
其中，当前账号状态信息是指识别到违规时，用户账号的登录位置、登录时间等信息。
在一实施例中，所述目标信息包括声纹信息，所述根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息，具体可以包括如下步骤：
根据所述用户标识信息，确定所述用户对应的区块链；
根据所述待修改的信用记录数据，获取所述区块链中的目标区块，并从所述目标区块中获取声纹特征信息。
在一实施例中，所述目标信息包括用户行为数据，所述根据所述用户标识信息，获取所述用户的用户行为数据，具体可以包括如下步骤：
根据所述用户标识信息，确定所述用户对应的区块链；
根据所述待修改的信用记录数据，获取所述区块链中的目标区块，并从所述目标区块中获取所述用户行为信用记录。
当主播被禁止进行直播后，服务器对获取到的主播(作为观众的)行为数据进行识别，当识别到加分行为时，根据主播的用户标识信息，以及第一网络平台标识，以及加分行为对应的信用增量，生成用户的行为记录上传至区块链中。
303、当所述目标信息满足所述预设参数修改条件时，根据满足的参数修改条件，获取信用度量信息。
在一实施例中，当目标信息为当前账号状态信息时，服务器可以根据所述用户标识信息，获取用户的常用登录位置信息；
当常用登录位置信息与当前账号状态信息中的登录位置不一致时，确定所 述目标信息满足所述预设参数修改条件。
在一实施例中，当目标信息为声纹特征信息时，服务器可以根据所述用户标识信息，获取本地存储中所述用户的历史语音信息；
对所述历史语音信息进行声纹特征提取，得到所述用户的历史声纹特征信息；
将所述历史声纹特征信息与所述声纹特征信息进行对比；
当所述声纹特征信息中存在与所述历史声纹特征信息不匹配时，确定所述目标信息满足所述预设参数修改条件。
在一实施例中，当目标信息为用户行为信用记录时，根据用户行为导致的信用参数变化量与禁止直播时用户的信用参数，计算用户在当前时刻的信用参数，若当前时刻的信用参数大于预设信用阈值，则认为目标信息满足所述预设参数修改条件。
304、根据所述待修改的信用记录数据、所述用户标识信息、所述目标信息，以及所述第一网络平台的平台标识信息，生成目标信用记录数据。
在一实施例中，可以将用户标识信息和所述待修改的信用记录数据，作为键元素，并将所述目标信息和所述第一网络平台的平台标识信息作为值元素，生成键值对。
305、向所述区块链网络中的第二网络平台广播所述目标信用记录数据，并当所述区块链网络基于所述目标信用记录数据达成共识后，将所述目标信用记录数据存储至所述用户对应的区块链中。
其中，广播和达成共识的过程参见上面的实施例，不再赘述。
由上可知，本申请实施例可以通过预设的修改条件和区块链中的信用记录数据，对用户的信用修改请求进行审核，当确定信用修改请求满足预设修改条件时，可以修改区块链中的数据，从而恢复用户的信用。
应该理解的是，虽然图2a、2b、2c的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图2a、2b、2c中的至少一部分步骤可以包括多个步骤或 者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
为了更好地实施以上方法，相应的，本申请实施例还提供一种语音信息交流的管理装置。
例如，如图3a所示，该语音信息交流的管理装置可以包括获取单元401、识别单元402、生成单元403、广播单元404和存储单元405，如下：
(1)获取单元401，用于获取用户在区块链网络中第一网络平台发布的语音信息。
(2)识别单元402，用于对所述语音信息进行违规识别，得到违规识别结果。
在一实施例中，所述识别单元402具体可以包括语音识别子单元和违规识别子单元，如下：
语音识别子单元，用于对所述语音信息进行识别，得到所述语音信息对应的文本信息；
违规识别子单元，用于根据预设违规信息集合，对所述文本信息进行内容匹配，得到匹配结果；并根据所述匹配结果，确定所述语音信息的违规识别结果。
在一实施例中，所述语音识别子单元具体可以用于：
对所述语音信息进行划分，得到所述语音信息对应的音频帧序列；
对所述音频帧序列中的音频帧进行特征提取，得到所述语音信息对应的音频特征信息；
据预设声学模型，获取所述音频特征信息对应的音素；
根据预设语言模型，对所述音素和预设字典进行比较与匹配，得到所述音素对应的文本单词；
提取所述文本单词之间的语义关联信息，根据所述关联信息，将所述文本单词组合得到文本信息。
(3)生成单元403，用于当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据。
在一实施例中，所述生成单元403具体可以包括违规记录子单元、信用计算子单元和生成子单元，如下：
违规记录子单元，用于当所述违规识别结果满足预设违规条件时，根据时间、所述第一网络平台的平台标识信息，以及所述违规识别结果，生成违规记录；
信用计算子单元，用于根据所述违规识别结果，获取所述用户的信用度量信息；
生成子单元，用于根据所述违规记录、所述信用度量信息和所述用户标识信息，生成所述用户的信用记录数据。
在一实施例中，所述生成子单元具体可以用于：
将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；
将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
在一实施例中，所述生成单元403还可以用于根据所述用户标识信息，获取所述用户在所述第一网络平台中的注册身份信息；相应地，所述生成子单元具体还可以用于：将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
在一实施例中，所述生成单元还可以用于：当所述当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、所述用户标识信息以及所述声纹特征信息，生成所述用户的信用记录数据。
在一实施例中，所述所述生成单元还可以用于：当所述当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标 识信息、所述用户标识信息以及所述当前账号状态信息，生成所述用户的信用记录数据。
(4)广播单元404，用于向所述区块链网络中的第二网络平台广播所述用户的信用记录数据。
在一实施例中，所述广播单元404还可以用于：
根据所述用户的信用记录数据，生成校验信息；
在向所述区块链网络中的第二网络平台广播所述用户的信用记录数据的过程中，向所述区块链网络中的第二网络平台广播所述校验信息。
(5)存储单元405，用于当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。
在一实施例中，参考图3b，该语音信息交流的管理装置还可以包括信用获取单元406，用于接收终端发送的用户信用获取请求，所述用户信用获取请求携带所述用户标识；根据所述用户标识，确定所述用户对应的区块链；取所述区块链中的区块，并从所述区块中确定所述用户的信用记录数据；向所述终端返回所述用户的信用记录数据；
在一实施例中，参考图3c，该语音信息交流的管理装置还可以包括信用修改单元407，用于获取来自终端的信用修改请求，所述信用修改请求携带所述用户的用户标识信息；根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息；当所述目标信息满足所述预设参数修改条件时，根据满足的参数修改条件，获取信用度量信息；根据所述信用度量信息、所述用户标识信息、所述目标信息，以及所述第一网络平台的平台标识信息，生成目标信用记录数据；向所述区块链网络中的第二网络平台广播所述目标信用记录数据；当所述区块链网络基于所述目标信用记录数据达成共识后，将所述目标信用记录数据存储至所述用户对应的区块链中。
具体实施时，以上各个单元可以作为独立的实体来实现，也可以进行任意组合，作为同一或若干个实体来实现，以上各个单元的具体实施可参见前面的方法实施例，在此不再赘述。
由上可知，本申请实施例通过将与虚假信息相关的待管理信息存储至区块链，基于区块链的共识算法，可以避免待管理信息被篡改，保障信息的真实性、可信性和安全性，同时区块链可以更直接、更广泛地传播基于虚假信息的待管理信息，从而更有效地治理虚假信息。
此外，本申请实施例还提供一种语音信息交流设备，该语音信息交流设备可作为区块链中的节点，此时该语音信息交流设备可以集成在区块链的第一节点中，该第一节点可以为区块链中的任意一个节点。此外，该语音信息交流设备也可以为终端设备。如图4所示，其示出了本申请实施例所涉及的计算机设备的结构示意图，具体来讲：
本实施例中，该语音信息交流设备可以包括一个或者一个以上处理核心的处理器501、一个或一个以上计算机可读存储介质的存储器502、电源503和输入单元504等部件。本领域技术人员可以理解，图4中示出的语音信息交流设备结构并不构成对语音信息交流设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。其中：
处理器501是该语音信息交流设备的控制中心，利用各种接口和线路连接整个语音信息交流设备的各个部分，通过运行或执行存储在存储器502内的软件程序和/或模块，以及调用存储在存储器502内的数据，执行语音信息交流设备的各种功能和处理数据，从而对语音信息交流设备进行整体监控。可选的，处理器501可包括一个或多个处理核心；优选的，处理器501可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器501中。
存储器502可用于存储软件程序以及模块，处理器501通过运行存储在存储器502的软件程序以及模块，从而执行各种功能应用以及数据处理。存储器502可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等；存储数据区可存储根据计算机设备的使用所创建的数据等。此外，存储器502可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁 盘存储器件、闪存器件、或其他易失性固态存储器件。相应地，存储器502还可以包括存储器控制器，以提供处理器501对存储器502的访问。
该语音信息交流设备还包括给各个部件供电的电源503，优选的，电源503可以通过电源管理系统与处理器501逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。电源503还可以包括一个或一个以上的直流或交流电源、再充电系统、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。
该语音信息交流设备还可包括输入单元504，该输入单元504可用于接收输入的数字或字符信息，以及产生与用户设置以及功能控制有关的触屏、键盘、鼠标、操作杆、光学或者轨迹球信号输入。
尽管未示出，语音信息交流设备还可以包括显示单元等，在此不再赘述。具体在本实施例中，计算机设备中的处理器501会按照如下的指令，将一个或一个以上的应用程序的进程对应的可执行文件加载到存储器502中，并由处理器501来运行存储在存储器502中的应用程序，从而实现各种功能，如下：
获取用户在区块链网络中第一网络平台发布的语音信息；
通过预设语音识别算法对所述语音信息进行识别，得到所述语音信息对应的文本信息；
根据预设违规信息集合对所述文本信息进行违规识别，得到违规识别结果；
当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；
向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；
当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中；
或者，
用于接收终端发送的用户信用获取请求，所述用户信用获取请求携带所述用户标识；根据所述用户标识，确定所述用户对应的区块链；取所述区块链中 的区块，并从所述区块中确定所述用户的信用记录数据；向所述终端返回所述用户的信用记录数据；
或者，
获取来自终端的信用修改请求，所述信用修改请求携带所述用户的用户标识信息；
根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息；
当所述目标信息满足所述预设参数修改条件时，根据满足的参数修改条件，获取信用度量信息；
根据所述信用度量信息、所述用户标识信息、所述目标信息，以及所述第一网络平台的平台标识信息，生成目标信用记录数据；
向所述区块链网络中的第二网络平台广播所述目标信用记录数据；
当所述区块链网络基于所述目标信用记录数据达成共识后，将所述目标信用记录数据存储至所述用户对应的区块链中。
以上各个操作的具体实施可参见前面的实施例，在此不再赘述。
由上可知，本申请实施例通过将与虚假信息相关的待管理信息存储至区块链，基于区块链的共识算法，可以避免待管理信息被篡改，保障信息的真实性、可信性和安全性，同时区块链可以更直接、更广泛地传播基于虚假信息的待管理信息，从而更有效地治理虚假信息。
本领域普通技术人员可以理解，上述实施例的各种方法中的全部或部分步骤可以通过指令来完成，或通过指令控制相关的硬件来完成，该指令可以存储于一计算机可读存储介质中，并由处理器进行加载和执行。
为此，本申请实施例还提供一种计算机可读存储介质，其中存储有多条指令，该指令能够被处理器进行加载，以执行本申请实施例所提供的任一种语音信息交流的管理方法中的步骤。例如，该指令可以执行如下步骤：
应用于第一节点，所述第一节点为区块链中的任意节点，获取基于虚假信息的待管理信息；
可以根据所述待管理信息，生成校验信息，所述校验信息包括所述待管理 信息以及所述第一节点的签名信息；
基于所述校验信息，将所述待管理信息存储至所述区块链中，并基于所述区块链的共识算法，使所述区块链中的节点基于所述待管理信息达成共识，其中，所述第二节点为区块链中除第一节点以外的节点；
或者，
应用于第二节点，所述第二节点为区块链中除所述第一节点以外的节点，可以获取终端发送的信息获取请求；
根据所述信息获取请求所需的信息的属性，从所述区块链中确定目标待管理信息所在的区块链；
基于所述信息获取请求，获取所述区块链中的区块，所述区块包括基于所述虚假信息的待管理信息；
根据所述待管理信息生成推送信息，并向所述终端返回所述推送信息。
以上各个操作的具体实施可参见前面的实施例，在此不再赘述。
其中，该计算机可读存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
由于该计算机可读存储介质中所存储的指令，可以执行本申请实施例所提供的任一种语音信息交流的管理方法中的步骤，因此，可以实现本申请实施例所提供的任一种语音信息交流的管理方法所能实现的有益效果，详见前面的实施例，在此不再赘述。
以上对本申请实施例所提供的一种语音信息交流的管理方法、装置和存储介质进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种语音信息交流的管理方法，由计算机设备执行，其特征在于，包括：
    获取用户在区块链网络中第一网络平台发布的语音信息；
    对所述语音信息进行违规识别，得到违规识别结果；
    当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；
    向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；
    当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链中。
  2. 如权利要求1所述的语音信息交流的管理方法，其特征在于，所述当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据，包括：
    当所述违规识别结果满足预设违规条件时，根据时间、所述第一网络平台的平台标识信息以及所述违规识别结果，生成违规记录；
    根据所述违规识别结果，获取所述用户的信用度量信息；
    根据所述违规记录、所述信用度量信息和所述用户标识信息，生成所述用户的信用记录数据。
  3. 如权利要求2所述的语音信息交流的管理方法，其特征在于，所述当根据所述违规记录、所述信用度量信息和所述用户标识信息，生成所述用户的信用记录数据，包括：
    将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；
    将所述用户标识信息和注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
  4. 如权利要求2所述的语音信息交流的管理方法，其特征在于，所述根据 所述违规记录、所述信用度量参数和所述用户标识信息，生成所述用户的信用记录数据，包括：
    根据所述用户标识信息，获取所述用户在所述第一网络平台中的注册身份信息；
    将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；
    将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；
    根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
  5. 如权利要求1所述的语音信息交流的管理方法，其特征在于，还包括：
    对所述语音信息进行声纹特征识别，得到所述用户的声纹特征信息；
    当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、所述用户标识信息以及所述声纹特征信息，生成所述用户的信用记录数据。
  6. 如权利要求1所述的语音信息交流的管理方法，其特征在于，还包括：
    获取所述用户的当前账号状态信息；
    当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、所述用户标识信息以及所述当前账号状态信息，生成所述用户的信用记录数据。
  7. 如权利要求2所述的语音信息交流的管理方法，其特征在于，在所述根据所述违规识别结果，获取所述用户的信用度量信息之后，还包括：
    根据所述预设信用阈值和所述信用度量信息，对所述用户进行语音信息发布权限识别，得到权限识别结果；
    当所述权限识别结果表现为用户不具备语音信息发布权限时，停止接收所述用户发送的语音信息。
  8. 如权利要求2所述的语音信息交流的管理方法，其特征在于，在所述根据所述违规识别结果，获取所述用户的信用度量信息之后，还包括：
    根据所述违规记录和所述信用度量信息，生成信用告警消息；
    向所述终端返回所述信用告警消息。
  9. 如权利要求1所述的语音信息交流的管理方法，其特征在于，还包括：
    根据所述用户的信用记录数据，生成校验信息；
    在向所述区块链网络中的第二网络平台广播所述用户的信用记录数据的过程中，向所述区块链网络中的第二网络平台广播所述校验信息。
  10. 如权利要求1所述的语音信息交流的管理方法，其特征在于，所述对所述语音信息进行违规识别，得到违规识别结果，包括：
    对所述语音信息进行识别，得到所述语音信息对应的文本信息；
    根据预设违规信息集合，对所述文本信息进行内容匹配，得到匹配结果；
    根据所述匹配结果，确定所述语音信息的违规识别结果。
  11. 如权利要求10所述的语音信息交流的管理方法，其特征在于，所述对所述语音信息进行识别，得到所述语音信息对应的文本信息，包括：
    对所述语音信息进行划分，得到所述语音信息对应的音频帧序列；
    对所述音频帧序列中的音频帧进行特征提取，得到所述语音信息对应的音频特征信息；
    据预设声学模型，获取所述音频特征信息对应的音素；
    根据预设语言模型，对所述音素和预设字典进行比较与匹配，得到所述音素对应的文本单词；
    提取所述文本单词之间的语义关联信息，根据所述关联信息将所述文本单词组合得到文本信息。
  12. 如权利要求1所述的语音信息交流的管理方法，其特征在于，还包括：
    接收终端发送的用户信用获取请求，所述用户信用获取请求携带所述用户标识；
    根据所述用户标识，确定所述用户对应的区块链；
    获取所述区块链中的区块，并从所述区块中确定所述用户的信用记录数据；
    向所述终端返回所述用户的信用记录数据。
  13. 如权利要求1所述的语音信息交流的管理方法，其特征在于，还包括：
    获取来自终端的信用修改请求，所述信用修改请求携带所述用户的用户标 识信息；
    根据所述用户标识信息，以及所述待修改的信用记录数据，从所述用户对应的区块链中获取所述用户的目标信息；
    当所述目标信息满足所述预设参数修改条件时，根据满足的参数修改条件，获取信用度量信息；
    根据所述信用度量信息、所述用户标识信息、所述目标信息，以及所述第一网络平台的平台标识信息，生成目标信用记录数据；
    向所述区块链网络中的第二网络平台广播所述目标信用记录数据；
    当所述区块链网络基于所述目标信用记录数据达成共识后，将所述目标信用记录数据存储至所述用户对应的区块链中。
  14. 一种语音信息交流的管理装置，其特征在于，包括：
    获取单元，用于获取用户在区块链网络中第一网络平台发布的语音信息；
    识别单元，用于对所述语音信息进行违规识别，得到违规识别结果；
    生成单元，用于当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、以及所述用户的用户标识信息，生成所述用户的信用记录数据；
    广播单元，用于向所述区块链网络中的第二网络平台广播所述用户的信用记录数据；
    存储单元，用于当所述区块链网络针对所述用户的信用记录数据达成共识后，将所述用户的信用记录数据存储至所述用户对应的区块链。
  15. 如权利要求14所述的语音信息交流的管理装置，其特征在于，所述生成单元包括：
    违规记录子单元，用于当所述违规识别结果满足预设违规条件时，根据时间、所述第一网络平台的平台标识信息以及所述违规识别结果，生成违规记录；
    信用计算子单元，用于根据所述违规识别结果，获取所述用户的信用度量信息；
    生成子单元，用于根据所述违规记录、所述信用度量信息和所述用户标识 信息，生成所述用户的信用记录数据。
  16. 如权利要求15所述的语音信息交流的管理装置，其特征在于，所述生成子单元，具体用于：
    将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；
    将所述用户标识信息和注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
  17. 如权利要求15所述的语音信息交流的管理装置，其特征在于，所述生成单元，还用于根据所述用户标识信息，获取所述用户在所述第一网络平台中的注册身份信息；
    所述生成子单元，具体用于将所述信用度量信息与所述违规记录进行组合，得到第一组合信息；将所述用户标识信息和所述注册身份信息进行组合，得到第二组合信息；根据所述第一组合信息和所述第二组合信息生成关联信息对，得到所述用户的信用记录数据。
  18. 如权利要求14所述的语音信息交流的管理装置，其特征在于，所述生成单元，还用于对所述语音信息进行声纹特征识别，得到所述用户的声纹特征信息；
    当所述违规识别结果满足预设违规条件时，根据所述违规识别结果、所述第一网络平台的平台标识信息、所述用户标识信息以及所述声纹特征信息，生成所述用户的信用记录数据。
  19. 一种存储介质，其上存储有计算机程序，其特征在于，当计算机程序在计算机上运行时，使得所述计算机执行如权利要求1至13中任一项所述的语音信息交流的管理方法。
  20. 一种语音信息交流设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至13中任一项所述方法的步骤。
PCT/CN2020/127810 2020-02-18 2020-11-10 一种语音信息交流的管理方法、装置、存储介质和设备 WO2021164333A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/693,971 US20220198468A1 (en) 2020-02-18 2022-03-14 Speech information communication management method and apparatus, storage medium, and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010100493.1 2020-02-18
CN202010100493.1A CN111355781B (zh) 2020-02-18 2020-02-18 一种语音信息交流的管理方法、装置和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/693,971 Continuation US20220198468A1 (en) 2020-02-18 2022-03-14 Speech information communication management method and apparatus, storage medium, and device

Publications (1)

Publication Number Publication Date
WO2021164333A1 true WO2021164333A1 (zh) 2021-08-26

Family

ID=71194006

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/127810 WO2021164333A1 (zh) 2020-02-18 2020-11-10 一种语音信息交流的管理方法、装置、存储介质和设备

Country Status (3)

Country Link
US (1) US20220198468A1 (zh)
CN (1) CN111355781B (zh)
WO (1) WO2021164333A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114786038A (zh) * 2022-03-29 2022-07-22 慧之安信息技术股份有限公司 基于深度学习的低俗直播行为监测方法

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111355781B (zh) * 2020-02-18 2021-06-08 腾讯科技（深圳）有限公司 一种语音信息交流的管理方法、装置和存储介质
CN112183079A (zh) * 2020-09-07 2021-01-05 绿瘦健康产业集团有限公司 一种语音监测方法、装置、介质及终端设备
CN112839043B (zh) * 2021-01-12 2022-02-11 南京汇智互娱网络科技有限公司 一种基于区块链技术的上网服务场所信用管理系统
CN113032658A (zh) * 2021-02-25 2021-06-25 未鲲(上海)科技服务有限公司 违规词检测方法、装置、设备及计算机可读存储介质
CN113299293A (zh) * 2021-05-25 2021-08-24 阿波罗智联(北京)科技有限公司 语音识别结果处理方法和装置、电子设备、计算机介质
CN113891104A (zh) * 2021-09-24 2022-01-04 北京沃东天骏信息技术有限公司 一种直播处理方法、直播平台、存储介质及电子设备
CN115499678B (zh) * 2022-09-20 2024-04-09 广州虎牙科技有限公司 视频直播方法、装置及直播服务器
CN116072123B (zh) * 2023-03-06 2023-06-23 南昌航天广信科技有限责任公司 广播信息播放方法、装置、可读存储介质及电子设备
CN116127173B (zh) * 2023-04-10 2023-08-08 上海蜜度信息技术有限公司 基于区块链的网络媒体监管方法及系统、存储介质及平台
CN116805078A (zh) * 2023-06-14 2023-09-26 深圳市易联锋达科技有限公司 一种基于大数据的物流信息平台数据智能管理系统及方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011014878A1 (en) * 2009-07-31 2011-02-03 Anakam, Inc. System and method for strong remote identity proofing
CN110365996A (zh) * 2019-07-25 2019-10-22 深圳市元征科技股份有限公司 直播管理方法、直播管理平台、电子设备及存储介质
CN110602248A (zh) * 2019-09-27 2019-12-20 腾讯科技（深圳）有限公司 异常行为信息的识别方法、系统、装置、设备及介质
CN111355781A (zh) * 2020-02-18 2020-06-30 腾讯科技（深圳）有限公司 一种语音信息交流的管理方法、装置和存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111727450B (zh) * 2018-01-19 2024-01-02 维萨国际服务协会 经由区块链网络进行的事件通信和验证
US10791353B2 (en) * 2018-02-13 2020-09-29 Ernest Huang Systems and methods for content management of live or streaming broadcasts and video publishing systems
CN110457918B (zh) * 2019-01-09 2022-09-09 腾讯科技（深圳）有限公司 滤除区块链数据中非法内容的方法、装置、节点和介质
CN109768983B (zh) * 2019-01-24 2021-07-27 易保互联医疗信息科技（北京）有限公司 基于区块链的多维动态身份识别方法、装置及系统
CN110674222B (zh) * 2019-10-08 2021-08-13 腾讯科技（深圳）有限公司 一种数据共享方法、装置、设备及介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011014878A1 (en) * 2009-07-31 2011-02-03 Anakam, Inc. System and method for strong remote identity proofing
CN110365996A (zh) * 2019-07-25 2019-10-22 深圳市元征科技股份有限公司 直播管理方法、直播管理平台、电子设备及存储介质
CN110602248A (zh) * 2019-09-27 2019-12-20 腾讯科技（深圳）有限公司 异常行为信息的识别方法、系统、装置、设备及介质
CN111355781A (zh) * 2020-02-18 2020-06-30 腾讯科技（深圳）有限公司 一种语音信息交流的管理方法、装置和存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114786038A (zh) * 2022-03-29 2022-07-22 慧之安信息技术股份有限公司 基于深度学习的低俗直播行为监测方法

Also Published As

Publication number Publication date
CN111355781B (zh) 2021-06-08
CN111355781A (zh) 2020-06-30
US20220198468A1 (en) 2022-06-23

Similar Documents

Publication Publication Date Title
WO2021164333A1 (zh) 一种语音信息交流的管理方法、装置、存储介质和设备
CN110991391B (zh) 一种基于区块链网络的信息处理方法及装置
CN111488433B (zh) 一种适用于银行的提升现场体验感的人工智能交互系统
CN111739521B (zh) 电子设备唤醒方法、装置、电子设备及存储介质
Delgado et al. ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan
US10158633B2 (en) Using the ability to speak as a human interactive proof
JP6502512B2 (ja) 動的パスワード音声に基づいた自己学習機能を有する身分認証システム及び方法
EP4114012A1 (en) Method and apparatus for processing multimedia information, and electronic device and storage medium
US11831779B2 (en) Decentralized trust using blockchain for tracking and validation of voice communications
US20200296098A1 (en) Voiceprint security with messaging services
US11526906B2 (en) System and method for secure content streaming, governance, fraud prevention, and the embedding artificial intelligence into content
WO2017166651A1 (zh) 语音识别模型训练方法、说话人类型识别方法及装置
CN111858892A (zh) 基于知识图谱的语音交互方法、装置、设备及介质
CN112037800A (zh) 声纹核身模型训练方法、装置、介质及电子设备
Dixit et al. Review of audio deepfake detection techniques: Issues and prospects
CN109726536A (zh) 鉴权方法、电子设备和计算机可读程序介质
Zhang et al. Volere: Leakage resilient user authentication based on personal voice challenges
Li et al. Design and research of multimedia information publishing system based on speech recognition technology
US20230169272A1 (en) Communication framework for automated content generation and adaptive delivery
Firc Applicability of Deepfakes in the Field of Cyber Security
US11436309B2 (en) Dynamic knowledge-based voice authentication
Lim et al. Overo: Sharing Private Audio Recordings
WO2024174714A1 (zh) 真实性验证方法和装置
CN117244254A (zh) 游戏数据校验方法、装置、设备、存储介质和程序产品
CN116975823A (zh) 数据处理方法、装置、计算机设备、存储介质及产品

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: 20919649

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20919649

Country of ref document: EP

Kind code of ref document: A1