Coding and decoding method, equipment and storage medium

Abstract

A coding and decoding method, device and storage medium. The coding method comprises: compressing and coding first information to obtain coded information (S2101); wherein the data structure of the first information comprises a first field or comprises the first field and a second field, the first field is used for indicating metadata corresponding to the audio data, and the second field is an extension field; and sending the encoding information to a decoding device (S2102), where decoding information corresponding to the encoding information is used for an artificial intelligence (AI) task. The method can effectively improve the quantity or types of the expression data, and is better suitable for AI training or application scenes.

Description

Encoding and decoding methods, devices and storage media Technical Field

[0001] This disclosure relates to the field of audio processing technology, and in particular to an encoding / decoding method, device, and storage medium. Background Technology

[0002] With the improvement of computing power and the increase in the amount of available data, artificial intelligence (AI) technology has made rapid progress and has been widely applied in various fields. Among them, AI-based audio technology can be applied to fields such as healthcare, finance, transportation, and education. The training phase of AI models requires massive amounts of labeled audio data.

[0003] Summary of the Invention

[0004] The amount or type of metadata in related technologies is limited, and there is a lack of effective methods to express the metadata of audio files used for AI.

[0005] This disclosure provides an encoding / decoding method, device, and storage medium.

[0006] In a first aspect, embodiments of this disclosure provide an encoding method, executed by an encoding device, the method comprising:

[0007] The first information is compressed and encoded to obtain encoded information; wherein, the data structure of the first information includes a first field or includes a first field and a second field, the first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field;

[0008] The encoded information is sent to the decoding device, wherein the decoding information corresponding to the encoded information is used for artificial intelligence (AI) tasks.

[0009] Secondly, embodiments of this disclosure provide a decoding method, executed by a decoding device, the method comprising:

[0010] Receive encoded information sent by an encoding device; wherein the encoded information is obtained by encoding first information;

[0011] Decoding the encoded information yields decoded information, which is used for artificial intelligence (AI) tasks. The data structure of the decoded information includes a first field or includes a first field and a second field. The first field indicates the metadata corresponding to the audio data, and the second field is an extended field.

[0012] Thirdly, embodiments of this disclosure provide an encoding device, including:

[0013] The processing module is used to compress and encode the first information to obtain encoded information; wherein the data structure of the first information includes a first field or includes a first field and a second field, the first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field;

[0014] The transceiver module is used to send the encoded information to the decoding device, wherein the decoded information corresponding to the encoded information is used for artificial intelligence (AI) tasks.

[0015] Fourthly, embodiments of this disclosure provide a decoding device, including:

[0016] A transceiver module is used to receive encoded information sent by an encoding device; wherein the encoded information is obtained by encoding first information;

[0017] The processing module is used to decode the encoded information to obtain decoded information, which is used for artificial intelligence (AI) tasks. The data structure of the decoded information includes a first field or includes a first field and a second field. The first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field.

[0018] Fifthly, embodiments of this disclosure provide a communication device, including:

[0019] One or more processors;

[0020] The communication device is configured to implement the method described in the first aspect or the second aspect.

[0021] Sixthly, embodiments of this disclosure provide a communication system, including an encoding device and a decoding device, wherein,

[0022] The encoding device is configured to implement the method as described in the first aspect;

[0023] The decoding device is configured to implement the method as described in the second aspect.

[0024] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0025] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0026] Eighthly, embodiments of this disclosure provide a program product, wherein,

[0027] When the program product is executed by a communication device, the communication device performs the method as described in the first aspect or the second aspect.

[0028] The embodiments disclosed herein can effectively increase the quantity or variety of expressive data, making it better suited for AI training or application scenarios. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0030] Figure 1 is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure;

[0031] Figure 2a is an exemplary interactive schematic diagram of a method provided according to an embodiment of the present disclosure;

[0032] Figures 2b to 2d are schematic diagrams of structures provided according to embodiments of the present disclosure;

[0033] Figure 3 is an exemplary flowchart of a method provided according to an embodiment of the present disclosure;

[0034] Figure 4 is an exemplary flowchart of a method provided according to an embodiment of the present disclosure;

[0035] Figure 5a is a schematic diagram of the structure of a device according to an embodiment of the present disclosure;

[0036] Figure 5b is a schematic diagram of the structure of a device according to an embodiment of the present disclosure;

[0037] Figure 6a is a schematic diagram of a communication device according to an embodiment of the present disclosure;

[0038] Figure 6b is a schematic diagram of a communication device according to an embodiment of the present disclosure. Detailed Implementation

[0039] This disclosure provides an encoding / decoding method, device, and storage medium.

[0040] In a first aspect, embodiments of this disclosure provide an encoding method, executed by an encoding device, the method comprising:

[0041] The first information is compressed and encoded to obtain encoded information; wherein, the data structure of the first information includes a first field or includes a first field and a second field, the first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field;

[0042] The encoded information is sent to the decoding device, and the corresponding decoded information is used for artificial intelligence (AI) tasks.

[0043] In the above embodiments, in AI-based audio application scenarios, the same data structure can be used for the information involved in the encoding and decoding process. The first field indicates the metadata, and the second field enhances the scalability of the metadata expression process, thereby effectively increasing the quantity or variety of expressed data and making it more suitable for AI training or application scenarios.

[0044] In conjunction with the embodiments of the first aspect, in some embodiments, the data structure of the first information further includes a third field, which precedes the first and second fields, and the third field is used to indicate that the data type of the metadata is one of the following: integer, string, or floating-point.

[0045] In conjunction with the embodiments of the first aspect, in some embodiments, the first information is compressed and encoded to obtain encoded information, including:

[0046] The second information is compressed and encoded to obtain encoded information. The second information includes multiple first information items and a fourth field preceding the multiple first information items. The fourth field is used to indicate the number of first information items. Each first information item corresponds to a type of metadata used for AI tasks.

[0047] In conjunction with the embodiments of the first aspect, in some embodiments, when the data type of the metadata is integer, the first field includes a first identifier and the basic data corresponding to the metadata, wherein the first identifier is used to indicate whether a second field exists in the first information.

[0048] In conjunction with the embodiments of the first aspect, in some embodiments, when the first identifier is a first value, the first information includes one or more second fields.

[0049] In conjunction with the embodiments of the first aspect, in some embodiments, the second field includes extended data corresponding to the metadata; or, the second field includes a second identifier and extended data, wherein the second identifier is used to indicate whether a new second field exists after the second field.

[0050] In conjunction with the embodiments of the first aspect, in some embodiments, the bit value of the first information is determined based on the bit value corresponding to the basic data, the bit value corresponding to the extended data, and the offset.

[0051] In conjunction with embodiments of the first aspect, in some embodiments, the offset is determined based on the bit length of the underlying data, or the offset includes an offset determined based on the bit length of the underlying data and an offset determined based on the bit length of the extended data.

[0052] In conjunction with the embodiments of the first aspect, in some embodiments, the bit length of the first field is an integer number of bits or an integer number of bytes; and / or, the bit length of the second field is an integer number of bits or an integer number of bytes.

[0053] In conjunction with the embodiments of the first aspect, in some embodiments, the first field includes a first part and a second part, wherein the first part is used to indicate the bit length of the second part, the second part is used to indicate metadata, and the second field is contained in the first part.

[0054] In conjunction with the embodiments of the first aspect, in some embodiments, when the data type of the metadata is integer or string, the bit length of the first part is a second value, and the maximum bit length of the second part is determined according to the second value.

[0055] In conjunction with the embodiments of the first aspect, in some embodiments, when the data type of the metadata is floating point, the first part is used to indicate whether the second part corresponds to single-precision floating point data or double-precision floating point data.

[0056] In conjunction with the embodiments of the first aspect, in some embodiments, the encoded information includes at least one of the following:

[0057] The fourth field is used to indicate the quantity of the first piece of information;

[0058] A third field used to indicate the data type of metadata;

[0059] The fifth field used to indicate the encoding method;

[0060] First identifier;

[0061] The second identifier, either the first identifier or the second identifier, is used to indicate whether a second field exists.

[0062] In conjunction with the embodiments of the first aspect, in some embodiments, at least one of the following uses the same data structure as the first information:

[0063] The encoded information;

[0064] The decoded information.

[0065] Secondly, embodiments of this disclosure provide a decoding method, executed by a decoding device, the method comprising:

[0066] Receive encoded information sent by the encoding device; wherein the encoded information is obtained by encoding the first information;

[0067] Decoding information is obtained by decoding encoded information. Decoded information is used for artificial intelligence (AI) tasks. The data structure of the first information includes a first field or includes a first field and a second field. The first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field.

[0068] In conjunction with the embodiments of the second aspect, in some embodiments, the data structure of the first information further includes a third field, which precedes the first and second fields, and the third field is used to indicate that the data type of the metadata is one of the following: integer, string, or floating-point.

[0069] In conjunction with the embodiments of the second aspect, in some embodiments, the encoded information is obtained by compressing and encoding the second information, which includes a plurality of first information and a fourth field preceding the plurality of first information. The fourth field is used to indicate the number of first information, wherein each first information corresponds to a type of metadata for an AI task.

[0070] In conjunction with the embodiments of the second aspect, in some embodiments, when the data type of the metadata is integer, the first field includes a first identifier and the basic data corresponding to the metadata, and the first identifier is used to indicate whether a second field exists in the first information.

[0071] In conjunction with the embodiments of the second aspect, in some embodiments, when the first identifier is a first value, the first information includes one or more second fields.

[0072] In conjunction with the embodiments of the second aspect, in some embodiments, the second field includes extended data corresponding to the metadata; or, the second field includes a second identifier and extended data, wherein the second identifier is used to indicate whether a new second field exists after the second field.

[0073] In conjunction with the embodiments of the second aspect, in some embodiments, the bit value of the first information is determined based on the bit value corresponding to the basic data, the bit value corresponding to the extended data, and the offset.

[0074] In conjunction with embodiments of the second aspect, in some embodiments, the offset is determined based on the bit length of the underlying data, or the offset includes an offset determined based on the bit length of the underlying data and an offset determined based on the bit length of the extended data.

[0075] In conjunction with the embodiments of the second aspect, in some embodiments, the bit length of the first field is an integer number of bits or an integer number of bytes; and / or, the bit length of the second field is an integer number of bits or an integer number of bytes.

[0076] In conjunction with the embodiments of the second aspect, in some embodiments, the first field includes a first part and a second part, wherein the first part is used to indicate the bit length of the second part, the second part is used to indicate metadata, and the second field is contained in the first part.

[0077] In conjunction with the embodiments of the second aspect, in some embodiments, when the data type of the metadata is integer or string, the bit length of the first part is a second value, and the maximum bit length of the second part is determined according to the second value.

[0078] In conjunction with the embodiments of the second aspect, in some embodiments, when the data type of the metadata is floating point, the first part is used to indicate whether the second part corresponds to single-precision floating point data or double-precision floating point data.

[0079] In conjunction with the embodiments of the second aspect, in some embodiments, decoding the encoded information to obtain decoded information includes at least one of the following:

[0080] Decode the fourth field of the encoded information to obtain the quantity of the first information;

[0081] Decode the third field of the encoded information to obtain the data type of the metadata corresponding to the first information;

[0082] Decode the fifth field indicating the method in the encoded information to obtain the encoded method;

[0083] Decode the first or second identifier in the encoded information to determine whether there is a second field after the first field. If there is a second field, decode the first field and the second field respectively to obtain the decoded metadata. If there is no second field, decode the first field to obtain the decoded metadata.

[0084] Thirdly, embodiments of this disclosure provide an encoding device, including:

[0085] The processing module is used to compress and encode the first information to obtain encoded information; wherein the data structure of the first information includes a first field or includes a first field and a second field, the first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field;

[0086] The transceiver module is used to send the encoded information to the decoding device, wherein the decoded information corresponding to the encoded information is used for artificial intelligence (AI) tasks.

[0087] Fourthly, embodiments of this disclosure provide a decoding device, including:

[0088] A transceiver module is used to receive encoded information sent by an encoding device; wherein the encoded information is obtained by encoding first information;

[0089] The processing module is used to decode the encoded information to obtain decoded information, which is used for artificial intelligence (AI) tasks. The data structure of the decoded information includes a first field or includes a first field and a second field. The first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field.

[0090] Fifthly, embodiments of this disclosure provide a communication device, including:

[0091] One or more processors;

[0092] The communication device is configured to implement the method described in the first aspect or the second aspect.

[0093] Sixthly, embodiments of this disclosure provide a communication system, including an encoding device and a decoding device, wherein,

[0094] The encoding device is configured to implement the method as described in the first aspect;

[0095] The decoding device is configured to implement the method as described in the second aspect.

[0096] In a seventh aspect, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0097] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method as described in the first aspect or the second aspect.

[0098] Eighthly, embodiments of this disclosure provide a program product, wherein,

[0099] When the program product is executed by a communication device, the communication device performs the method as described in the first aspect or the second aspect.

[0100] In a ninth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in alternative implementations of the first and second aspects.

[0101] In a tenth aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to optional implementations of the first and second aspects above.

[0102] It is understood that the aforementioned terminals, network devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0103] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0104] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0105] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0106] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0107] In the embodiments disclosed herein, "multiple" refers to two or more.

[0108] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0109] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0110] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0111] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0112] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0113] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0114] In some embodiments, the terms “greater than”, “greater than or equal to”, “not less than”, “more than”, “more than or equal to”, “not less than”, “higher than”, “higher than or equal to”, “not lower than”, and “above” can be used interchangeably, as can the terms “less than”, “less than or equal to”, “not greater than”, “less than”, “less than or equal to”, “not more than”, “lower than”, “lower than or equal to”, “not higher than”, and “below”.

[0115] In some embodiments, the apparatus and device may be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. In some cases, they may also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "body", etc.

[0116] In some embodiments, "network" can be interpreted as devices included in the network, such as access network devices, core network devices, etc.

[0117] In some embodiments, "access network device (AN device)" may also be referred to as "radio access network device (RAN device)," "base station (BS)," "radio base station," or "fixed station." In some embodiments, it may also be understood as "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," or "bandwidth part (BWP)."

[0118] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0119] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0120] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0121] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0122] Figure 1 is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0123] As shown in Figure 1, the communication system 100 includes an encoder 101, a decoder 102, and a back-end device 103.

[0124] The encoding device 101 can be used to compress and encode audio data or metadata, and the decoding device 102 is used to decode the compressed and encoded data. The decoded data is used by the backend device 103 for training or application of AI tasks, such as as training data or application data for AI tasks.

[0125] In some embodiments, the encoding device 101, the decoding device 102, and the back-end device 103 may be three independent devices, or two or three of them may use the same device.

[0126] In some embodiments, encoding device 101 may be a terminal or network device, decoding device 102 may be a terminal or network device, and backend device 103 may be a local device or a cloud server.

[0127] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0128] In some embodiments, the network device may include at least one of an access network device and a core network device.

[0129] The access network equipment includes, for example, nodes or devices that connect terminals to the wireless network. The access network equipment may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul equipment, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a wireless fidelity (WiFi) system.

[0130] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0131] In some embodiments, a core network device can be a single device comprising one or more network elements, or it can be multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements can be virtual or physical. The core network includes, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC). Alternatively, a core network device refers to a network element with a specific function, such as an Access Management Function (AMF) or a Service Management Function (SMF).

[0132] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions provided in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in this disclosure are also applicable to similar technical problems.

[0133] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1, or to a part thereof, but are not limited thereto.

[0134] The entities shown in Figure 1 are illustrative. The communication system may include all or some of the entities in Figure 1, or it may include other entities outside of Figure 1. The number and form of each entity are arbitrary. The connection relationship between the entities is illustrative. The entities may not be connected to each other or may be connected in any way. The connection may be direct or indirect, wired or wireless.

[0135] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication processing methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0136] In healthcare, AI can be used for disease diagnosis, drug discovery, and patient care. In finance, it can be used for fraud detection, investment strategies, and customer service. In transportation, it can be used for autonomous vehicles and traffic management. In education, it can be used for personalized learning and task management. AI can also be applied to other sectors such as manufacturing, retail, agriculture, and entertainment.

[0137] Training AI models requires massive amounts of labeled audio data, consuming significant storage space. In an audio program, audio presentations include audio program components, audio elements, audio signals, and audio element metadata. Audio program components include a complete main storyline, music and effects, dialogue, or video description; audio elements are categorized as channel-based, object-based, and scene-based.

[0138] Audio data can be described using corresponding metadata, which can include different categories such as static metadata and object metadata. According to the Moving Picture Experts Group (MPEG) standard, static metadata describes the entire scene and is usually immutable; object metadata is available in the OAM decoder module and is typically time-varying. In related technologies, metadata is decoded using a separate OAM decoder. Referring to the tables below, Table 1-1 illustrates the metadata syntax for one type of object metadata in MPEG-H, and Table 1-2 illustrates the metadata value range for object metadata. As shown in Tables 1-1 and 1-2, object metadata types are limited to location information and gain information.

[0139] Table 1-1

[0140] Table 1-2

[0141] The limited quantity and types of metadata in relevant MPEG-H formats make it impossible to represent the metadata carried by audio files used for AI training. Therefore, it is necessary to propose new metadata representation methods. Furthermore, with the development of AI technology, the types and values ​​of metadata may undergo further changes in the future.

[0142] Figure 2a is an interactive schematic diagram of an encoding / decoding method according to an embodiment of the present disclosure. As shown in Figure 2a, the present disclosure relates to an encoding / decoding method, which includes:

[0143] In step S2101, the encoding device 101 compresses and encodes the first information to obtain encoded information.

[0144] In some embodiments, the first information is one of the input data of the encoding device 101, or encoder.

[0145] In some embodiments, the compression encoding can be lossless compression encoding or lossy compression encoding. For example, the encoding device 101 performs lossless compression or lossy compression on the first information before encoding to obtain encoded information. The encoding device 101 can use one compression encoding method or combine multiple compression encoding methods during the encoding process.

[0146] In some embodiments, the encoded information may have the same or different data structure as the first information.

[0147] For example, the data structure of the encoded information is different from that of the first information. The encoded information is obtained by compressing and encoding the first information. The first information has already been compressed to a certain extent, reducing the number of bits occupied in the bitstream. Therefore, there may not be a problem of insufficient bits, and it is not necessary to use the data structure of the first information to expand the encoded information.

[0148] For example, the data structure of the encoded information is the same as that of the first information. The encoded information may still occupy a lot of bits after compression, requiring the data structure to be expanded; or, for ease of decoding, the data structure of the encoded information can be the same as that of the first information.

[0149] For ease of description, this embodiment is described using the example where the data structure of the encoded information is the same as the data structure of the first information. Same data structure means that it contains the same fields or parts, but the values ​​of those fields or parts are different. For example, the data structure of the first information includes a first field, and the data structure of the encoded information also includes a first field, but the bit values ​​of the two first fields are different.

[0150] In the following embodiments, the relevant implementation of the data structure for the first information can be applied to encoded information or decoded information in the following embodiments.

[0151] In some embodiments, the data structure of the first information includes a first field, or includes a first field and a second field, wherein the first field is used to indicate the metadata corresponding to the audio data, and the second field is an extended field.

[0152] Optionally, metadata can serve as labels for AI training.

[0153] Optionally, metadata or a set of labels can be represented by numerical values, such as representing the domain or purpose of the metadata or label dataset. The domain or purpose could include industry, medical, transportation, or robotics, etc. In this embodiment, metadata can be represented using numerical mapping, taking into account the scalability of a predictable range.

[0154] Optionally, the first field may include metadata or a portion of metadata, or the first field may indicate the domain, purpose, or meaning of the metadata; the second field may extend the representation of the metadata directly or indirectly.

[0155] Optionally, the value of the metadata or the first field after compression encoding can be denoted as val_enc.

[0156] In some embodiments, the data type of the metadata can be integer, string, or float. Depending on the data type of the metadata, the first or second field can have various implementations.

[0157] In the first implementation, the first field includes basic data, and the second field includes extended data. This implementation is applicable to cases where the metadata is of integer type 1.

[0158] Optionally, for the metadata of type 1 integer, the first field includes a first identifier and the underlying data (data_base) corresponding to the metadata. The first identifier is used to indicate whether the second field exists in the first information.

[0159] Optionally, referring to Figure 2b, the first field can be a base field or base data section, and the first identifier can be denoted as Flag_base. If the first field is sufficient to represent the metadata, the second field may not be included in the data structure. For example, in this case, the first identifier is used to indicate that the second field is not included after the first field.

[0160] Optionally, when the first identifier is a first value, the first information includes one or more second fields. The first identifier can occupy 1 bit, and the first value can be 0 or 1. For example, when the first identifier is 1, it indicates that the metadata not only includes basic data but also includes one or more second fields after the first field; when the first identifier is 0, it indicates that the metadata is complete and does not include any second fields after the first field.

[0161] Optionally, the first identifier can indicate that there are multiple second fields in the data structure, which can save bits. In this case, the second field can include extended data (data_extend) corresponding to the metadata. The second field can be an extended field or an extended data section.

[0162] Alternatively, referring to Figure 2c, to more accurately express the position of at least one second field in this example, a first flag can be used to indicate whether a second field is set after the first field. The second field can include a second flag and extended data. The second flag, denoted as Flag_extend, indicates whether an extended field exists after the second field, i.e., whether a new second field exists. That is, when multiple extended fields exist, each second field can include a second flag and extended data. The second flag of each second field can be used to indicate whether there is a new second field after it. For example, the second flag occupies 1 bit. If the second flag value is 0, it indicates that the metadata is complete and there is no subsequent extension; if the second flag value is 1, the metadata is incomplete, and there is still extended data after this extended field.

[0163] Optionally, the bit lengths of the base field and the extended field can be set to different values ​​depending on the number of known tags or metadata. For example, when the number of known tags is 30, a 5-bit base field can be selected. Furthermore, the data structure is scalable; when the base field is insufficient, a second field, i.e., the extended field, can be used for expansion.

[0164] In this implementation, referring to Table 2-1, during the representation of metadata or labels, the total value of the first information can be determined based on the bit values ​​of the first field (i.e., the basic field) and the second field (i.e., the extended field), and the indicated domain or meaning (meaning of labels) can be determined; the total length of the first information can be determined based on the bit length of the two fields.

[0165] Table 2-1

[0166] In this embodiment, in conjunction with the description of the foregoing embodiments, the format of either the first or second field can be in the form of "flag|data". The position of the flag in the "flag|data" format can be before or after the data. For example, the first field can be represented as "Flag_base|data_base", and the second field can be represented as "Flag_extend|data_extend". The bit length of "flag|data" is predefined and remains unchanged throughout the encoding and decoding process; it can be an integer byte or an integer number of bits. For example, the bit length of the first field is predefined and can be an integer number of bits or bytes; and / or, the bit length of the first field is predefined, and the bit length of the second field can be an integer number of bits or bytes.

[0167] Optionally, if the second field, i.e. the extended field, exists, the data structure contains a combination of basic data and extended data. The bit value of the first information (represented by data_whole) is determined based on the bit value corresponding to the basic data (represented by data_base), the bit value corresponding to the extended data (represented by data_extend), and the offset.

[0168] For example: When there is only one second field, the offset is determined based on the bit length of the base data. The offset can be denoted as offset(data_base), then: data_whole = data_base + data_extend * offset(data_base) * flag_base;

[0169] In this context, we assume that the bit length of the first identifier, Len(flag_base), is equal to the bit length of the second identifier, len(flag_extend), which is 1; the bit length of the base data, Len(data_base), is equal to the bit length of the extended data, len(data_extend), which is 7; and the offset, Offset(data_base), is 2^len(data_base), which is 128. The bit values ​​of the data structure can be found in Table 2-2.

[0170] Table 2-2

[0171] For example, when there are multiple second fields, the offset includes: an offset determined by the bit length of the base data, denoted as Offset(data_base), and an offset determined by the bit length of the extended data, denoted as Offset(data_extend1). Therefore:

[0172] data_whole=data_base+data_extend1*offset(data_base)*flag_base+data_extend2*offset(data_base)*offset(data_extend1)*flag_base*flag_extend1;

[0173] Here, it is assumed that the bit length of the first identifier Len(flag_base) = the bit length of the second identifier in the first extended field len(flag_extend1) = the bit length of the second identifier in the second extended field len(flag_extend2) = 1;

[0174] The bit length of the base data Len(data_base) = the bit length of the extended data in the first extended field len(data_extend1) = the bit length of the extended data in the second extended field len(data_extend2) = 7;

[0175] Offset(data_base)=2^len(data_base)=128, Offset(data_extend1)=2^len(data_extend1)=128;

[0176] The bit values ​​of the data structure can be found in Table 2-3:

[0177] Table 2-3

[0178] This example can be applied to scenarios where the maximum bit length of metadata is not fixed. In this case, integer metadata uses the integer type1 data format, which can enable the expansion of audio scene classification labels used for AI training.

[0179] In the second implementation, the extended field is set within the first field, dynamically affecting the bit length occupied by the second part. This implementation is applicable to cases where the metadata is of integer type2 or string type.

[0180] In this embodiment, the first field includes a first part and a second part, wherein the first part is used to indicate the bit length of the second part, the second part is used to indicate metadata, and the second field is located in the first part.

[0181] Optionally, the bit length of the second part is determined based on or influenced by the first part. In this embodiment, the second part indicates the data content, while the first part may include an extended field, i.e., be extended in the first part, thereby indirectly affecting the bit length occupied by the second part.

[0182] In the first example, for the metadata of integer type2, the data structure or format of the first information can be denoted as "int_len|int_data", where int_len is the first part, representing the length of int_data in bytes or bits; and int_data is the second part, representing the content or meaning of the integer metadata.

[0183] In this example, if expansion is needed, int_len is expanded. For example, the first part includes the base field and one or more extended fields, with int_len considered as the base field, and the extended fields set after int_len (denoted as subsequent extension or extension).

[0184] In this example, on the encoding device 101 side, the bit length of the first part can be denoted as N bits, then the maximum bit length of the second part can be 2^N, i.e., 2^N bits. N For example, if N = 8 bits, the maximum bit length of the second part is max_len(int_data) = 2^8 = 256 bits. On the decoding device 102 side, the decoding device 102 can first decode N bits to obtain the value M corresponding to the first part; then decode the second part to obtain the data.

[0185] This example is applicable to scenarios where the maximum length of metadata is fixed, and integer metadata can use the data format corresponding to integer type2. For example, for integer metadata of horizontal angles, with an angle range from -180 to 180, 9 bits are sufficient to represent 360 different angle values.

[0186] In the second example, for string-type metadata, the data structure or format of the first piece of information can be denoted as "strlen|string_data", where strlen is the first part, representing the length of string_data in bytes or bits; and string_data is the second part, representing the content or meaning of the string-type metadata.

[0187] In this example, strlen is extended if expansion is required. For instance, the first part includes the base field and one or more extended fields, with strlen treated as the base field, and the extended fields set after strlen (denoted as subsequent extension or extension).

[0188] This example is applicable to metadata of type 1 string, or when the maximum length of metadata is not fixed, for example, the length of an English sentence is uncertain.

[0189] In this example, for metadata of type 2 string, the bit length of the first part is the second value, and the maximum bit length of the second part is determined based on the second value. For example, referring to the description of the previous example, on the encoding device 101 side, the second value is N, and the maximum bit length of the second part is 2. N For example, if N = 8 bits, the maximum bit length of the second part is max_len(int_data) = 2^8 = 256 bits.

[0190] On the decoding device 102 side, the decoding device 102 can first decode N bits to obtain the value M corresponding to the first part; then decode the second part to obtain the data. Assume that the value of strlen is M = 11, and string_data = "industrial".

[0191] When the maximum length of metadata is fixed, string-type metadata can be implemented using the string type2 implementation. For example, the longest word is usually no more than 45 letters, and the longest word "pneultramicroscopicsilicovolcanoconiosis" has 45 letters.

[0192] In the third implementation, the second field, i.e. the extended field, can be omitted, and the bit length of the second part can be adaptively adjusted by the first part. This implementation is applicable to cases where the metadata is of floating-point type.

[0193] In this implementation, for floating-point metadata, the data structure or format of the first information can be denoted as "float_type|float_data", where float_type is the first part, representing the byte or bit length of float_data; and float_data is the second part, representing the content or meaning of the floating-point metadata.

[0194] In this example, the metadata is in floating-point format. The first part indicates whether the second part corresponds to single-precision floating-point data or double-precision floating-point data. Specifically, if the first part indicates single-precision floating-point, the second part requires 4 bytes; if the first part indicates double-precision floating-point, the second part requires 8 bytes, thus indicating the bit length of the second part.

[0195] In this example, the first part can occupy 1 bit, for example, Len(float_type) = 1 bit;

[0196] If the value of this 1 bit is 0, that is, float_type = 0, then the length of the second part len(float_data) = 4 bytes (single-precision floating point);

[0197] If the value of this 1-bit is 1, that is, float_type = 1, then the length of the second part len(float_data) = 8 bytes (double-precision floating point).

[0198] In some embodiments, for multiple metadata or multiple tags, the first information corresponding to each metadata or tag can satisfy the data structure described in the above embodiments.

[0199] Optionally, to improve decoding efficiency, each data structure can also indicate the type of the metadata corresponding to that data structure.

[0200] In one example, the data structure of the first information also includes a third field, which precedes the first and second fields. The third field is used to indicate that the data type of the metadata is one of the following: integer, string, or floating-point.

[0201] Referring to Figure 2d, each piece of first information corresponds to a label in the figure. The figure illustrates three label fields, each of which can be considered a named piece of first information. For example, taking the first information label1 field as an example, its data structure is shown in the figure. The third field can be denoted as data_type, used to indicate the type of metadata in this first information. Combining the first implementation method described above, the first field can be a basic field, and the second field can be an extended field.

[0202] In this example, the value of the third field, data_type, can indicate the type of the first piece of information. For example, if the bit length of the third field, data_type, is Len(data_type) = 3, then:

[0203] When data_type = 0, it indicates that the tag type or the data type in the tag is integer type1;

[0204] When data_type = 1, it indicates that the tag type or the data type in the tag is integer type2;

[0205] When data_type = 2, it indicates that the tag type or the data type in the tag is string type1;

[0206] When data_type = 3, it indicates that the tag type or the data type in the tag is string type2;

[0207] When data_type = 4, it indicates that the tag type or the data type in the tag is floating point;

[0208] data_type = 5-8 can be reserved values.

[0209] In some embodiments, to improve decoding accuracy, this embodiment may also indicate the corresponding quantity in scenarios with multiple metadata or multiple tags.

[0210] For example, this step may include: compressing and encoding the second information to obtain encoded information, the second information including multiple first information and a fourth field preceding the multiple first information, the fourth field being used to indicate the number of first information, wherein each first information corresponds to a type of metadata for an AI task.

[0211] Optionally, referring to Figure 2d, the fourth field can be denoted as Label_num, which indicates the number of tags or metadata, i.e., the number of first pieces of information. The “Label_num” field can be represented by an integer, and its length can be several bits or an integer multiple of 8 bits. In the example of Figure 2d, the number of tags or first pieces of information is 3. The data structure corresponding to each piece of first information can be the same or different, as described above for different types such as integer, floating-point, and string.

[0212] Optionally, in scenarios where expansion is required, the "Label_num" field can also be expanded, such as into a basic field and at least one extended field.

[0213] In step S2102, the encoding device 101 sends the encoding information to the decoding device 102.

[0214] In some embodiments, the decoding device 102 can receive encoded information, wherein the encoded information is obtained based on the first information of the above data structure.

[0215] In some embodiments, the data structure of the encoded information may be the same as the data structure of the first information. Therefore, the data structure of the encoded information here can refer to the description of the first information in step S2101, and will not be repeated here.

[0216] For example, the encoded information includes at least one of the following:

[0217] A fourth field (such as Label_num) is used to indicate the quantity of the first piece of information;

[0218] A third field (such as data_type) used to indicate the data type of the metadata;

[0219] The fifth field used to indicate the encoding method;

[0220] First identifier (Flag_base);

[0221] The second flag (Flag_extend) indicates whether a second field exists. For example, the first flag indicates whether there is a second field after the first field, and the second flag indicates whether there is a new second field after the existing second field.

[0222] The encoded information can be transmitted in the bitstream or in the form of a bitstream.

[0223] Optionally, either the third or fifth field can be selected. For example, the data type can be determined based on the third field, thus enabling the determination of the corresponding encoding method.

[0224] In step S2103, the decoding device 102 decodes the encoded information to obtain the decoded information.

[0225] In some embodiments, the decoded information may be the first information after decoding, which may be the same as the first information before encoding or may produce different degrees of distortion.

[0226] In some embodiments, at least one of the following uses the same data structure as the first information:

[0227] Encoded information;

[0228] Decode the information.

[0229] For example, the data structure of the decoded information is the same as that of the first information. Or, the data structures of the encoded information, the decoded information, and the first information are the same.

[0230] In some embodiments, the decoded information or the decoded first information adopts the same data structure or format as the first information, which will not be repeated here. The data structure of the decoded information can be referred to the description of the foregoing embodiments.

[0231] Optionally, in conjunction with the descriptions of steps S2101 and S2102, the decoding device 102 may include one or more of the following steps during the decoding process of the encoded information:

[0232] Decode the fourth field of the encoded information (such as Label_num) to obtain the number of first information items; thus, it can be determined how many first information items need to be decoded.

[0233] Decoding the third field (such as data_type) of the encoded information yields the data type of the metadata corresponding to the first information; thus, decoding can be performed based on the data type.

[0234] Decode the fields of the encoded metadata (such as val_enc) in the encoded information to obtain the decoded metadata value; thus, the corresponding decoding method can be used for accurate decoding.

[0235] Decode the fifth field in the encoded information to obtain the encoding method; or, based on the decoding of the third field, obtain the encoding method corresponding to the data type.

[0236] Decoding the first identifier (Flag_base) or the second identifier (Flag_extend) in the encoded information reveals whether a second field exists after the first field. For example, the first identifier can indicate whether there is an extended field after the base field, and the second identifier can indicate whether there is another extended field after a certain extended field. Refer to the description in the foregoing embodiments for accurate decoding of each field.

[0237] When a second field exists, the first and second fields are decoded separately to obtain the decoded metadata. For example, the first field is decoded first to obtain the value of the basic data, and the second field is decoded to obtain the value of the extended data. The two decoded values ​​are then merged to obtain the corresponding value of the decoded metadata. When the second field does not exist, the first field is decoded to obtain the decoded metadata.

[0238] In some embodiments, the decoding device 102 can send the decoding information to the backend device 103, and the backend device 103 can use the decoding metadata for the training or application phase of the AI ​​model.

[0239] This disclosure describes the application of metadata to AI tasks. In other embodiments, the encoding device 101 may also encode audio data or audio files and send them to the decoding device 102. The decoding device 102 then decodes the data and uploads it to the backend device 102 for training or application of AI models.

[0240] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", and "field" can be used interchangeably.

[0241] In some embodiments, “get,” “obtain,” “receive,” “transmit,” “bidirectional transmission,” and “send and / or receive” can be used interchangeably and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining through self-processing, or autonomous implementation, among other meanings.

[0242] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0243] In some embodiments, the terms “radio”, “wireless”, “radio access network (RAN)”, “access network (AN)”, and “RAN-based” can be used interchangeably.

[0244] In some embodiments, terms such as “moment,” “point in time,” “time,” and “time location” can be used interchangeably, as can terms such as “duration,” “segment,” “time window,” “window,” and “time.”

[0245] In some embodiments, the terms "component carrier (CC)," "cell," "frequency carrier," and "carrier frequency" can be used interchangeably.

[0246] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0247] In some embodiments, the determination or judgment can be made by a value represented by 1 bit (0 or 1), or by a true or false value (boolean), or by a comparison of numerical values ​​(e.g., a comparison with a predetermined value), but is not limited thereto.

[0248] In some embodiments, "not expecting to receive" can be interpreted as not receiving on time domain resources and / or frequency domain resources, or as not performing subsequent processing on the data after receiving it; "not expecting to send" can be interpreted as not sending, or as sending but not expecting the receiver to respond to the sent content.

[0249] The method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2103.

[0250] In some embodiments, other alternative implementations may be described before or after the specification corresponding to FIG2a.

[0251] Figure 3 is a flowchart illustrating an encoding method according to an embodiment of this disclosure. As shown in Figure 3, this embodiment of the disclosure relates to an encoding method, which is executed by an encoding device 101, and the method includes:

[0252] Step S3101: Compress and encode the first information to obtain encoded information.

[0253] In some embodiments, the implementation of step S3101 can be found in the implementation of step S2101 in FIG2a, and will not be repeated here.

[0254] Step S3102: Send the encoded information.

[0255] In some embodiments, the implementation of step S3102 can be found in the implementation of step S2102 in FIG2a, and will not be repeated here.

[0256] In some embodiments, other optional implementations may be described before or after the specification corresponding to FIG3.

[0257] Figure 4 is a flowchart illustrating a decoding method according to an embodiment of this disclosure. As shown in Figure 4, this embodiment of the disclosure relates to a decoding method, which is executed by a decoding device 102, and the method includes:

[0258] Step S4101: Receive encoded information.

[0259] In some embodiments, the implementation of step S4101 can be found in the implementation of step S2102 in FIG2a, and will not be repeated here.

[0260] Step S4102: Decode the encoded information to obtain the decoded information.

[0261] In some embodiments, the implementation of step S4102 can be referred to the implementation of step S2103 in FIG2a, and will not be repeated here.

[0262] In some embodiments, other optional implementations may be described before or after the specification corresponding to Figure 4.

[0263] In this embodiment of the disclosure, a novel metadata representation method is provided for the metadata carried in audio files used for AI training, while also considering the scalability of metadata types or numerical ranges. To facilitate understanding of this embodiment, some examples are provided below:

[0264] Example 1:

[0265] The label set is represented by numerical values, such as the domain of the dataset, which can be represented using numerical mappings for industries like industry, healthcare, or transportation. Scalability, typically used for predictable ranges of quantities, is also considered. For integer type 1 data, the following format is used:

[0266] When the basic fields are insufficient, extended fields are used. The relationship between basic fields and extended fields is shown in Figure 2b.

[0267] Depending on the number of known tags, the lengths of the base field and the extended field can be set to different values. For example, when the number of known tags is 30, a 5-bit base field can be selected. See Table 2-1 for tag examples.

[0268] As shown in Figure 2c, the same method can be used to extend the extended fields.

[0269] The format for metadata extensions is "flag|data". In this format, the flag can be placed before or after the data. The bit length of "flag|data" is conventional and remains unchanged throughout the encoding process; it can be an integer byte or a few bits. If the flag value is 0, the data is complete. If the flag value is 1, the data is incomplete, in which case an extended field is added. The bit length of the extended field is also conventional and remains unchanged throughout the encoding process; it can be an integer byte or a few bits. The format for extended fields can also be "flag|data". For example, "flag_base|data_base" can represent the base field, and "flag_extend|data_extend" can represent the extended field.

[0270] When extended fields exist, there is a combination of basic data and extended data, as shown in Table 2-2:

[0271] data_whole=data_base+data_extend*offset(data_base)*flag_base; among them, Len(flag_base)=len(flag_extend)=1, Len(data_base)=len(data_extend)=7, Offset(data_base)=2^len(data_base)=128.

[0272] If there is more than one extended field, for example, two extended fields, refer to Table 2-3:

[0273] data_whole=data_base+data_extend1*offset(data_base)*flag_base+data_extend2*offset(data_base)*offset(data_extend1)*flag_base*flag_extend1; among them, Len(flag_base)=len(flag_extend1) =len(flag_extend2)=1; Len(data_base)=len(data_extend1)=len(data_extend2)=7; Offset(data_base)=2^len(data_base)=128, Offset(data_extend1)=2^len(data_extend1)=128.

[0274] When the maximum length of metadata is not fixed, integer metadata uses the integer type1 data format. For example, audio scene classification labels used for artificial intelligence training will be expanded in the future.

[0275] Example 2:

[0276] For integer type 2 metadata, the format can be "int_len|int_data", where int_len represents the length of int_data in bytes or bits; and int_data represents the content or meaning of the integer metadata.

[0277] You can extend int_len. For example, int_len can include a base field and an extended field similar to those in Example 1.

[0278] On the encoding device 101 side, if the bit length of int_len can be denoted as N bits, then the maximum bit length of int_data can be 2^N, i.e., 2^N. N On the decoding device 102 side, the decoding device 102 can first decode N bits to obtain the value M corresponding to int_len; then decode M bits to obtain the data.

[0279] For example, if N = 8 bits, then max_len(int_data) = 2^8 = 256 bits.

[0280] When the maximum length of metadata is fixed, integer metadata uses the integer type2 data format. For example, the horizontal angle range of integers is from -180 to 180, and 9 bits are sufficient to represent 360 different values.

[0281] Example 3:

[0282] For string type1 data, the format is "strlen|string_data", where strlen represents the length of string_data in bytes or bits, and string_data represents the string content.

[0283] You can extend strlen. For example, strlen can include a base field and an extended field, similar to Example 1.

[0284] When the maximum length of metadata is not fixed, string-type metadata uses the string type1 data format. For example, the length of an English sentence is indeterminate.

[0285] Example 4:

[0286] For string type2 data, the format is "strlen|string_data", where strlen represents the length of string_data in bytes or bits, and string_data represents the string content.

[0287] At the encoder end, strlen has a length of N bits. N indicates that the maximum length of string_data is 2^N.

[0288] At the decoder end, the decoder first parses N bits to obtain the value M of strlen. Then, the decoder parses M bytes to obtain the entire string_data.

[0289] For example, N = 8 bits, max_len(string_data) = 2^8 = 256 bits. Assume strlen = M = 11, and string_data = "industrial".

[0290] When the maximum length of metadata is fixed, string-type metadata can be implemented using the string type2 implementation. For example, the longest word is usually no more than 45 letters, and the longest word "pneultramicroscopicsilicovolcanoconiosis" has 45 letters.

[0291] Example 5:

[0292] For floating-point data, single-point floating-point numbers are represented by 4 bytes, and double-point floating-point numbers are represented by 8 bytes. The format of a floating-point type is "float_type|float_data".

[0293] Len(float_type) = 1 bit;

[0294] If float_type = 0, then len(float_data) = 4 bytes (single-precision floating-point);

[0295] If float_type = 1, then len(float_data) = 8 bytes (double-precision floating point).

[0296] Example 6:

[0297] This example illustrates the case of multiple labels. As shown in Figure 2d, each label can follow the data structure of Example 1.

[0298] In this example, a new "Label_num" field has been added to indicate the number of labels. The "Label_num" field is of integer data type, and its length can be several bits or a multiple of 8 bits. The "Label_num" field can also be expanded into a basic field and extended field 1, extended field 2, etc.

[0299] The label field includes data_type, a basic field, and several extended fields.

[0300] Assuming the bit length of data_type, Len(data_type) = 3, then:

[0301] When data_type = 0, it indicates that the tag type or the data type in the tag is integer type1;

[0302] When data_type = 1, it indicates that the tag type or the data type in the tag is integer type2;

[0303] When data_type = 2, it indicates that the tag type or the data type in the tag is string type1;

[0304] When data_type = 3, it indicates that the tag type or the data type in the tag is string type2;

[0305] When data_type = 4, it indicates that the tag type or the data type in the tag is floating point;

[0306] data_type = 5-8 can be reserved values.

[0307] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0308] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0309] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0310] Figure 5a is a schematic diagram of the structure of the encoding device proposed in an embodiment of this disclosure. As shown in Figure 5a, the encoding device 5100 may include at least one of a processing module 5101 and a transceiver module 5102. In some embodiments, the processing module 5101 is used to compress and encode first information to obtain encoded information; wherein the data structure of the first information includes a first field or includes a first field and a second field, the first field being used to indicate metadata corresponding to the audio data, and the second field being an extended field. The transceiver module 5102 is used to send the encoded information to a decoding device, wherein the decoding information corresponding to the encoded information is used for artificial intelligence (AI) tasks.

[0311] Figure 5b is a schematic diagram of the structure of the decoding device proposed in an embodiment of this disclosure. As shown in Figure 5b, the decoding device 5200 may include at least one of a transceiver module 5201 and a processing module 5202. In some embodiments, the transceiver module 5201 is used to receive encoded information sent by an encoding device; wherein the encoded information is obtained by encoding first information; the processing module 5202 is used to decode the encoded information to obtain decoded information, the decoded information being used for artificial intelligence (AI) tasks, wherein the data structure of the decoded information includes a first field or includes a first field and a second field, the first field being used to indicate metadata corresponding to the audio data, and the second field being an extended field.

[0312] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0313] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with a processor.

[0314] Figure 6a is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0315] As shown in Figure 6a, the communication device 6100 includes one or more processors 6101. The processor 6101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 can be used to execute any of the above methods. Optionally, one or more processors 6101 can be used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0316] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above method, and the processor 6101 performs at least one of the other steps. In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0317] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data. Optionally, all or part of the memories 6103 may be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuits 6104 are connected to the memories 6103 and can be used to receive data from the memories 6103 or other devices, and to send data to the memories 6103 or other devices. For example, the interface circuits 6104 can read data stored in the memories 6103 and send that data to the processor 6101.

[0318] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6a. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0319] Figure 6b is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6b, but it is not limited thereto.

[0320] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0321] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data. Optionally, all or part of the memories 6203 may be located outside chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data from memory 6203 or other devices, and interface circuit 6202 can be used to send data to memory 6203 or other devices. For example, interface circuit 6202 can read data stored in memory 6203 and send the data to processor 6201.

[0322] In some embodiments, the interface circuit 6202 performs at least one of the communication steps, such as sending and / or receiving, in the above-described method. For example, the interface circuit 6202 performing the communication steps, such as sending and / or receiving, in the above-described method means that the interface circuit 6202 performs data interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of the other steps.

[0323] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0324] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0325] This disclosure also provides a program product that, when executed by the communication device 6100, causes the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0326] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0327] In AI-based audio applications, it can effectively increase the quantity or variety of expressive data, making it better suited for AI training or application scenarios.

Claims

1. An encoding method, performed by an encoding device, comprising: compressively encoding first information to obtain encoded information, wherein a data structure of the first information comprises a first field or comprises the first field and a second field, the first field being used to indicate metadata corresponding to audio data, and the second field being an extension field; sending the encoded information to a decoding device, wherein decoded information corresponding to the encoded information is used for an artificial intelligence (AI) task.

2. The method of claim 1, wherein, The data structure of the first information further comprises a third field, the third field being before the first field and the second field, and the third field being used to indicate that a data type of the metadata is one of the following: an integer type, a string type, and a floating point type.

3. The method of claim 2, wherein, The compressively encoding the first information to obtain the encoded information comprises: compressively encoding second information to obtain the encoded information, the second information comprising a plurality of the first information and a fourth field before the plurality of the first information, the fourth field being used to indicate a number of the first information, wherein each of the first information corresponds to metadata used for the AI task.

4. The method of any one of claims 1 to 3, wherein in a case where the data type of the metadata is the integer type, the first field comprises a first identifier and base data corresponding to the metadata, the first identifier being used to indicate whether the second field exists in the first information.

5. The method of claim 4, wherein in a case where the first identifier is a first value, the first information comprises one or more of the second field.

6. The method of claim 4, wherein the second field comprises extension data corresponding to the metadata, or the second field comprises a second identifier and the extension data, the second identifier being used to indicate whether a new second field exists after the second field.

7. The method of claim 6, wherein a bit value of the first information is determined according to a bit value corresponding to the base data, a bit value corresponding to the extension data, and an offset.

8. The method of claim 7, wherein the offset is determined according to a bit length of the base data, or the offset comprises an offset determined according to the bit length of the base data and an offset determined according to a bit length of the extension data.

9. The method of any one of claims 4 to 8, wherein a bit length of the first field is an integer number of bits or an integer number of bytes, and / or a bit length of the second field is an integer number of bits or an integer number of bytes.

10. The method of any one of claims 1 to 3, wherein the first field comprises a first part and a second part, wherein the first part is used to indicate a bit length of the second part, the second part is used to indicate the metadata, and the second field is included in the first part.

11. The method of claim 10, wherein in a case where the data type of the metadata is the integer type or the string type, a bit length of the first part is a second value, and a maximum bit length of the second part is determined according to the second value. ​ 12. The method of claim 10, wherein, in a case where the data type of the metadata is a floating point type, the first part is used to indicate whether the second part corresponds to single-precision floating point data or double-precision floating point data.

13. The method of any one of claims 1 to 12, wherein, the encoding information comprises at least one of: a fourth field used to indicate a quantity of the first information; a third field used to indicate the data type of the metadata; a fifth field used to indicate an encoding method; a first identifier; a second identifier, the first identifier or the second identifier being used to indicate whether the second field exists.

14. The method of any one of claims 1 to 12, wherein, at least one of the following adopts a same data structure as the first information: the encoding information; the decoding information.

15. A decoding method performed by a decoding device, the method comprising: receiving encoding information sent by an encoding device, wherein the encoding information is obtained by encoding first information; decoding the encoding information to obtain decoding information, the decoding information being used for an artificial intelligence (AI) task, wherein a data structure of the first information comprises a first field or comprises the first field and a second field, the first field being used to indicate metadata corresponding to audio data, and the second field being an extension field.

16. The method of claim 15, wherein, the data structure of the first information further comprises a third field, the third field being before the first field and the second field, and the third field being used to indicate that the data type of the metadata is one of: an integer type, a string type, and a floating point type.

17. The method of claim 16, wherein, the encoding information is obtained by compressively encoding second information, the second information comprising a plurality of the first information and a fourth field before the plurality of the first information, the fourth field being used to indicate a quantity of the first information, wherein each of the first information corresponds to one kind of metadata used for an AI task.

18. The method of any one of claims 15 to 17, wherein, in a case where the data type of the metadata is an integer type, the first field comprises a first identifier and base data corresponding to the metadata, the first identifier being used to indicate whether the second field exists in the first information.

19. The method of claim 18, wherein, when the first identifier is a first value, the first information comprises one or more of the second field.

20. The method of claim 18, wherein, the second field comprises extension data corresponding to the metadata; or the second field comprises a second identifier and the extension data, wherein the second identifier is used to indicate whether a new second field exists after the second field.

21. The method of claim 20, wherein, a bit value of the first information is determined according to a bit value corresponding to the base data, a bit value corresponding to the extension data, and an offset.

22. The method of claim 21, wherein, the offset is determined according to a bit length of the base data, or the offset comprises an offset determined according to the bit length of the base data and an offset determined according to a bit length of the extension data.

23. The method of any one of claims 15 to 22, wherein, A bit length of the first field is an integer number of bits or an integer number of bytes; and / or, a bit length of the second field is an integer number of bits or an integer number of bytes.

24. The method of any of claims 15 to 17, wherein, The first field comprises a first part and a second part, wherein the first part is used to indicate a bit length of the second part, and the second part is used to indicate the metadata, and the second field is contained in the first part.

25. The method of claim 24, wherein, In a case that a data type of the metadata is an integer type or a string type, a bit length of the first part is a second value, and a maximum bit length of the data part is determined according to the second value.

26. The method of claim 24, wherein, In a case that the data type of the metadata is a floating point type, the first part is used to indicate whether the second part corresponds to single-precision floating point data or double-precision floating point data.

27. The method of any one of claims 14 to 26, wherein, The decoding of the encoded information obtains decoded information, including at least one of: Decoding a fourth field of the encoded information obtains a number of the first information; Decoding a third field of the encoded information obtains a data type of metadata corresponding to the first information; Decoding a fifth field of the encoded information obtains an encoding method; Decoding a first identifier or a second identifier of the encoded information obtains whether the second field exists after the first field, and when the second field exists, the first field and the second field are respectively decoded to obtain decoded metadata, and when the second field does not exist, the first field is decoded to obtain decoded metadata.

28. The method of any one of claims 15 to 27, wherein, At least one of the following adopts the same data structure as the first information: The encoded information; The decoded information.

29. An encoding device, comprising: a processing module configured to compress and encode first information to obtain encoded information, wherein a data structure of the first information comprises a first field or comprises the first field and a second field, the first field is used to indicate metadata corresponding to audio data, and the second field is an extension field; a transceiver configured to send the encoded information to a decoding device, wherein decoded information corresponding to the encoded information is used for an artificial intelligence (AI) task.

30. A decoding device, comprising: a transceiver configured to receive encoded information sent by an encoding device, wherein the encoded information is obtained by encoding first information; a processing module configured to decode the encoded information to obtain decoded information, wherein a data structure of the decoded information comprises a first field or comprises the first field and a second field, the first field is used to indicate metadata corresponding to audio data, and the second field is an extension field, and the decoded information is used for an artificial intelligence (AI) task.

31. A communication device, comprising: one or more processors; wherein the communication device is configured to implement the method of any of claims 1 to 14, or claims 15 to 28.

32. A communication system comprising an encoding device and a decoding device, wherein the encoding device is configured to implement the method of any of claims 1 to 14; and the decoding device is configured to implement the method of any of claims 15 to 28. The decoding device is configured to implement a method according to any one of claims 15 to 28.

33. A storage medium having stored thereon instructions, wherein, the instructions, when executed on a communication device, cause the communication device to perform a method according to any one of claims 1 to 14, or claims 15 to 28.

34. A program product, wherein, the program product, when executed by a communication device, causes the communication device to perform a method according to any one of claims 1 to 13, or claims 15 to 28.

Images