Semantic evaluation method and apparatus

Abstract

Embodiments of the present application provide a semantic evaluation method and apparatus, used for evaluating the quality of semantic communication. The method comprises: obtaining a first network transmission parameter, the first network transmission parameter being used for indicating the quality of service of a first data stream, and the first data stream being used for transmitting semantic information of a first media file; and on the basis of the first network transmission parameter, determining a semantic evaluation metric of the first media file, the semantic evaluation metric being used for indicating the quality of user experience with respect to the first media file.

Description

A semantic evaluation method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on November 24, 2023, with application number 202311590949.7 and application name “A Semantic Evaluation Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of semantic communication technology, and in particular to a semantic evaluation method and device. Background Art

[0004] For the past few decades, research in the communications field has primarily focused on how to accurately and efficiently transmit symbols from the transmitter to the receiver, a process known as grammatical communication. With the development of wireless communication systems and the accelerated implementation of intelligent and IoT applications, wireless communication capacity is facing unprecedented challenges. Therefore, semantic communication has become a potential key technology for communications. Unlike traditional communication, semantic communication involves the transmitter extracting semantic information from the data being transmitted, which is then transmitted to the receiver for decoding. This reduces the amount of data to be transmitted, thereby reducing the bandwidth required.

[0005] However, how to evaluate the quality of semantic communication still needs further research.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide a semantic evaluation method and apparatus for evaluating the quality of semantic communication.

[0008] In a first aspect, embodiments of the present application provide a semantic evaluation method. The method can be performed by a network device, such as an access network device or a user plane function (UPF) network element within the network device, or by a system-on-chip (SoC) within the network device, capable of implementing the functions of the network device, such as a system-on-chip (SoC) within the access network device or a system-on-chip within a UPF network element. The method includes: obtaining a first network transmission parameter, the first network transmission parameter being used to indicate the quality of service of a first data stream, the first data stream being used to transmit semantic information of a first media file; and determining a semantic evaluation index for the first media file based on the first network transmission parameter, the semantic evaluation index being used to indicate the user experience quality of the first media file.

[0009] In an embodiment of the present application, when sending semantic information of a first media file, the network device can determine a semantic evaluation index based on the service quality of the first data stream used to transmit the semantic information, that is, determine the user's experience quality of the first media file if the semantic information is transmitted based on the current network transmission parameters. If the user experience quality is poor, it indicates that the semantic communication quality is poor; if the user experience quality is good, it indicates that the semantic communication quality is good.

[0010] In one possible implementation, the first network transmission parameter includes one or more of the following: packet delay budget (PDB); packet error rate (PER); transmission time interval between data packets; or jitter. The above parameters are merely examples. In other embodiments, the first network transmission parameter may also include other parameters, such as data flow level.

[0011] In one possible implementation, determining a semantic evaluation index for the first media file based on a first network transmission parameter includes: determining a degree of semantic distortion of the semantic information transmitted via the first network transmission parameter based on a first function; and determining the degree of semantic distortion as the semantic evaluation index. During semantic communication, if the semantic information cannot be correctly transmitted (i.e., the degree of distortion is large), the receiving end may be unable to accurately restore the source file, resulting in a poor user experience. Therefore, using the degree of semantic distortion as the semantic evaluation index can more accurately evaluate the quality of user experience.

[0012] In a possible implementation, the network device may also determine the communication service quality of transmitting the semantic information through the first network transmission parameter based on a second function; and determine the semantic evaluation index based on the communication service quality and the semantic distortion degree. If the first media file is a video, factors affecting the communication service quality may include, for example, video freeze information, video resolution information, video clarity information, etc.; if the first media file is an image, factors affecting the communication service quality may include, for example, image clarity information, etc.; if the first media file is an audio, factors affecting the communication service quality may include, for example, audio freeze information, audio clarity information, etc. That is, the communication service quality will also have a certain impact on the user experience quality. Therefore, the semantic evaluation index determined based on the semantic distortion degree and the communication server quality is more accurate than the semantic evaluation index determined based on the semantic distortion degree, and can more accurately evaluate the user experience quality.

[0013] In a possible embodiment, the network device may also determine the degree of synchronization between adjacent data packets when the semantic information is transmitted through the first network transmission parameters based on a third function; determine the semantic evaluation index based on the degree of synchronization and the degree of semantic distortion, or determine the semantic evaluation index based on the degree of synchronization, the degree of semantic distortion and the quality of the communication server that transmits the semantic information through the first network transmission parameters. The degree of synchronization of the data packet can be the degree of jamming of the first media file, so the semantic evaluation index jointly determined based on the degree of semantic distortion and the degree of synchronization of the data packet is more accurate than the semantic evaluation index determined based on the degree of semantic distortion, and can more accurately evaluate the user experience quality. Jointly determining the semantic evaluation index based on the degree of semantic distortion, the quality of communication service and the degree of synchronization of the data packet can further improve the accuracy of the semantic evaluation index.

[0014] In one possible implementation, the network device may further receive media parameters of the first media file from the application server. The media parameters may include one or more of the following: the size of the first media file; the compression ratio of the first media file; the number of data packets included in the first media file; the size of each data packet included in the first media file; or the amount of semantic information included in the first media file. The media parameters may indicate basic attributes of the first media file. The application server transmits the media parameters of the first media file to the network device, allowing the network device to determine a semantic evaluation metric based on the media parameters and network transmission parameters, thereby improving the accuracy of the semantic evaluation metric.

[0015] In one possible embodiment, determining a semantic evaluation index for the first media file based on a first network transmission parameter includes: determining the semantic evaluation index for the first media file based on the first network transmission parameter and the media parameter. Determining the semantic evaluation index based on the media parameter and the network transmission parameter can increase the accuracy of the determined semantic evaluation index. For example, transmitting a video at a certain frame rate based on the current network transmission parameters may result in a better user experience, while transmitting a video at a higher frame rate may result in a poorer user experience.

[0016] In one possible implementation, the network device may further determine a second network transmission parameter based on the semantic evaluation indicator, and transmit the semantic information based on the second network transmission parameter. Utilizing the semantic evaluation indicator to assist network devices in network construction, network planning, or optimization helps improve user experience.

[0017] In a second aspect, an embodiment of the present application provides a communication device, which may be a network device or a module (such as a chip) used in a network device. The device has the function of implementing any implementation method of the first aspect described above. The function may be implemented by hardware or by hardware executing corresponding software implementations. The hardware or software includes one or more modules corresponding to the above functions.

[0018] In a third aspect, embodiments of the present application provide a communication device. The communication device includes a communication interface and a processor, and optionally, a memory. The memory is configured to store a computer program. The processor is coupled to the memory and the communication interface. When the processor reads the computer program or instructions, the communication device executes the method performed by the network device in the first aspect.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store a computer program. When the computer program is run on a computer, the computer executes the method provided in the first aspect above.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, which, when executed on a computer, enables the computer to execute the method described in the first aspect above.

[0021] In a sixth aspect, a chip system is provided, comprising a processor and an interface, wherein the processor is configured to call and execute instructions from the interface so that the chip system implements the method described in the first aspect above.

[0022] For the beneficial effects of the second to sixth aspects mentioned above, refer to the beneficial effects of the first aspect and will not be repeated. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG1 is a schematic diagram of a network architecture used in an embodiment of the present application;

[0024] FIG2A and FIG2B are schematic diagrams of two scenarios applicable to the embodiments of the present application;

[0025] Figures 3, 4, and 5 are flowcharts of several semantic evaluation methods provided in embodiments of the present application;

[0026] FIG6 is a schematic diagram of the structure of a GTP-U message provided in an embodiment of the present application;

[0027] FIG7 is a schematic diagram of adding a field carrying the media parameters and weights to a packet header of the RTP layer according to an embodiment of the present application;

[0028] FIG8 is a schematic diagram of a device provided in an embodiment of the present application;

[0029] FIG9 is a schematic diagram of another device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0031] In the embodiments of the present application, the number of nouns, unless otherwise specified, means "singular noun or plural noun", that is, "one or more". "At least one" means one or more, and "plural" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A or B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. For example, A / B means: A or B. "At least one of the following items" or "one or more of them" and other similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c, or one or more of a, b, or c, means: a, b, c, a and b, a and c, b and c, or a and b and c. Each of a, b, and c can be single or multiple.

[0032] The ordinal numbers "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the size, content, order, timing, priority or importance of multiple objects. In addition, the numbering of the steps in the various embodiments introduced in the embodiments of this application is only to distinguish different steps and is not used to limit the order between the steps. For example, S403 may occur before S401 or S402, or may occur after S401 or S402, or may occur at the same time as S401 or S402.

[0033] Below, some terms or concepts in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0034] (1) Semantic communication refers to the sending end understanding the business needs and environment in advance, understanding, extracting, and transmitting the semantic information of the data to be transmitted. The receiving end then recovers the data to be transmitted based on the received semantic information. Taking video transmission as an example, the sending end first performs selective feature extraction and compression encoding on the original video to obtain relevant semantic information, such as key points, sketches, contours, and color information. The semantic information is then transmitted to the receiving end, which decodes it and reconstructs the video.

[0035] (2) Terminal device: a device with wireless transceiver function, which can be a fixed device, mobile device, handheld device (such as a mobile phone), wearable device, vehicle-mounted device, or a wireless device built into the above devices (such as a communication module, modem, or chip system, etc.). The terminal device is used to connect people, objects, machines, etc., and can be widely used in various scenarios, such as but not limited to the following scenarios: cellular communication, device-to-device communication (D2D), vehicle to everything (V2X), machine-to-machine / machine-type communication (M2M / MTC), Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, drones, robots and other scenarios. The terminal device may sometimes be referred to as user equipment (UE), terminal, access station, UE station, remote station, wireless communication device, or user equipment, etc.

[0036] In the embodiments of the present application, the communication device for implementing the terminal device function may be a terminal device, or may be a device capable of supporting the terminal device to implement the function, such as a chip system, which may be installed in the terminal device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the terminal device as an example in which the device for implementing the terminal device function is a terminal device. In addition, for ease of description, the terminal device in the embodiments of the present application is described by taking a UE as an example.

[0037] (3) Network equipment, such as access network equipment and / or core network equipment. Access network equipment is a network-side equipment with wireless transceiver functions. Access network equipment can be a device in a radio access network (RAN) used to provide wireless communication functions for terminal equipment, and is called a RAN equipment. For example, the access network equipment can be a base station, an evolved Node B in a long term evolution (LTE) system or an advanced long term evolution (LTE-A), which can be referred to as eNB or e-NodeB, a transmission reception point (TRP), a next generation NodeB (gNB) in a fifth generation (5G) mobile communication system, a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a Wi-Fi system, etc. It can also be an access network equipment in an open access network (ORAN) system, etc. The access network device may also be a macro base station, a micro base station (also known as a small station) or an indoor station, or a relay node or a donor node, etc. The access network device may also be a radio network controller (RNC), a node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (for example, a home evolved NodeB, or a home Node B, HNB), a base band unit (BBU) or a remote radio unit (RRU), or a Wi-Fi access point (AP), or a baseband pool (BBU pool) and RRU in a cloud radio access network (CRAN), etc. The embodiments of the present application do not limit the specific technology and specific device form adopted by the access network device.

[0038] In addition, the access network device can also be a module or unit that completes part of the functions of the base station. For example, the access network device can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). Among them, the CU can complete the functions of the radio resource control protocol and the packet data convergence protocol (PDCP) of the base station, and can also complete the function of the service data adaptation protocol (SDAP); the DU can complete the functions of the radio link control layer and the medium access control (MAC) layer of the base station, and can also complete part of the physical layer or all of the physical layer functions. In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU can also be called O-CU, DU can also be called open (open, O)-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CUP-UP, and RU can also be called O-RU.

[0039] Core network equipment is used to implement functions such as mobility management, data processing, session management, policy and billing. The names of the devices that implement core network functions in systems with different access technologies may be different, and the embodiments of this application are not limited to this. Taking the fifth generation (5G) mobile communication system as an example, the core network equipment includes: access and mobility management function (AMF), session management function (SMF), policy control function (PCF) or user plane function (UPF), etc.

[0040] In the embodiments of the present application, the communication device for implementing the network device function may be a network device, or may be a device capable of supporting the network device to implement the function, such as a chip system, which may be installed in the network device. In the technical solutions provided in the embodiments of the present application, the technical solutions provided in the embodiments of the present application are described by taking the network device as an example of the device for implementing the network device function being a network device.

[0041] Please refer to Figure 1, which is a schematic diagram of a 5G network architecture, which is also a network architecture used in the embodiments of the present application. The 5G network architecture shown in Figure 1 may include three parts, namely, a UE part, a data network (DN), and an operator network part. As shown in Figure 1, the UE can access the operator network to obtain services of the external network (such as the data network (DN)) through the operator network, or communicate with other devices through the operator network, such as communicating with other terminal devices.

[0042] Among them, DN can also be called packet data network (PDN), which is a network located outside the operator network. The operator network can access multiple DNs. Application servers corresponding to various services can be deployed in the DN to provide UE with a variety of possible services.

[0043] The operator network may include one or more of the following network elements: network exposure function (NEF) network element, policy control function (PCF) network element, application function (AF) network element, network slice selection function (NSSF) network element, access and mobility management function (AMF) network element, SMF network element, (radio) access network (R)AN) or user plane function (UPF) network element, etc.

[0044] The operator network includes a radio access network and a core network. The UE accesses the core network through the (R)AN. The core network includes user plane network elements and control plane network elements. The user plane network elements of the core network include the UPF, and the control plane network elements of the core network include at least one of the following network elements: the AMF, SMF, NEF, PCF, or AF.

[0045] User plane network elements (e.g., UPF) are primarily responsible for packet forwarding, quality of service (QoS) control, and billing information statistics. Control plane network elements are primarily responsible for business process interaction, issuing packet forwarding policies and QoS control policies to the user plane, etc. In the embodiments of the present application, it is considered that devices such as sensors can access the core network through devices such as UE and (R)AN. Therefore, controllers connected to sensors and other devices in industrial Ethernet can perform industrial data communication on the user plane through UPF.

[0046] The core network control plane can adopt a service-based architecture. That is, the interaction between control plane network elements uses service calls, replacing the point-to-point communication method in the traditional architecture. In a service-based architecture, one control plane network element will open services to other control plane network elements for them to call. In point-to-point communication, the communication interface between control plane network elements will have a specific set of messages that can only be used by the control plane network elements at both ends of the interface during communication.

[0047] The functions of network elements in the core network are described as follows:

[0048] UPF supports all or part of the following functions: interconnecting protocol data unit (PDU) sessions with data networks, packet routing and forwarding (for example, supporting uplink classifier for forwarding traffic to the data network, supporting branching points to support multi-homed PDU sessions), or packet inspection.

[0049] The AMF manages UE access and mobility. It is responsible for maintaining UE status, managing UE reachability, forwarding non-mobility management (MM) and non-access-stratum (NAS) messages, and forwarding session management (SM) N2 messages.

[0050] The SMF, or UE Session Management, allocates and releases resources for UE sessions. These resources include session quality of service (QoS), session paths, and forwarding rules. The SMF is responsible for selecting or reselecting UPFs, allocating Internet Protocol (IP) addresses, and establishing, modifying, and releasing bearers.

[0051] NEF opens network functions to third parties in the form of northbound application programming interfaces (APIs).

[0052] PCF, User Policy Management, is used to generate and manage user, session, and QoS flow processing policies.

[0053] AF (Application Management) provides application layer services to the UE. When providing services to the UE, AF has requirements for QoS (policy) and charging policies, and needs to notify the network. In addition, AF also requires the core network to feedback application-related information.

[0054] The relevant interfaces between network element functions involved in the embodiments of this application include:

[0055] N1: Interface between UE and core network control plane.

[0056] N2: Communication interface between (R)AN and core network control plane.

[0057] N3: Communication interface between (R)AN and UPF, used to transmit user plane data.

[0058] N4: Communication interface between SMF and UPF, used by SMF to configure policies for UPF, etc.

[0059] N5: Communication interface between AF and PCF.

[0060] N6: Communication port between UPF and DN.

[0061] N33: Communication interface between AF and NEF.

[0062] FIG1 is a simplified schematic diagram for ease of understanding only. The network architecture may further include other network devices or other terminal devices, and the core network may further include other network elements, which are not shown in FIG1 .

[0063] The network architecture shown in FIG1 can be applied to a variety of possible scenarios. For example, please refer to FIG2A and FIG2B , which are schematic diagrams of two scenarios applicable to the embodiments of the present application.

[0064] Figure 2A shows a scenario where a UE communicates with an application server through a carrier network. In this scenario, the downlink data transmission path is: application server → UPF network element → access network device → UE; the uplink data transmission path is: UE → access network device → UPF network element → application server.

[0065] As shown in Figure 2B, this is a scenario where a UE communicates with other UEs through an operator network. In this scenario, one UE (UE1 as shown in Figure 2B) is a master domain device, and one UE (UE2 as shown in Figure 2B) is a controlled domain device. The transmission path for UE1 to send data to UE2 is: UE1 → access network device → UPF network element → access network device → UE2. The transmission path for UE2 to send data to UE1 is: UE2 → access network device → UPF network element → access network device → UE1. Taking remote surgery as an example, UE1 includes a helmet and gloves, and UE2 includes a manipulator and a camera. The doctor can remotely observe the on-site situation of the operation through the helmet and issue corresponding instructions through the gloves. After the instructions are transmitted to the operation site through the operator network, they are executed by the on-site manipulator. The camera can collect the execution status and transmit the execution status to the doctor's helmet through the operator network.

[0066] The above applicable scenarios are only examples. The embodiments of the present application can also be applied to other scenarios where semantic communication can be performed, such as WiFi scenarios. The embodiments of the present application do not limit the applicable scenarios.

[0067] When evaluating the quality of semantic communication, subjective evaluation can better describe the quality of user experience, but it has high requirements for the implementation environment and needs to monitor the user's status, etc., which is time-consuming, labor-intensive, and costly. In view of this, an embodiment of the present application provides a semantic evaluation method that can objectively evaluate the quality of user experience. In an embodiment of the present application, when a network device (access network device or UPF network element) sends semantic information of a first media file, it can determine a semantic evaluation index based on the service quality of the first data stream used to transmit the semantic information, that is, determine the user's experience quality of the first media file if the semantic information is transmitted based on the current network transmission parameters. If the user experience quality is poor, it indicates that the semantic communication quality is poor. If the user experience quality is good, it indicates that the semantic communication quality is good.

[0068] The method provided in the embodiments of the present application is described below with reference to the accompanying drawings.

[0069] An embodiment of the present application provides a semantic evaluation method. See Figure 3 for a flowchart of the method. This method can be applied to the network architecture shown in Figure 1. For example, the network device involved in the method is the operator network shown in Figure 1, such as a (R)AN or UPF network element in the operator network, and the terminal device involved in the method is the UE shown in Figure 1. In the embodiment of the present application, all optional steps are represented by dashed lines.

[0070] S301: The network device obtains a first network transmission parameter.

[0071] The first network transmission parameter is a parameter used to indicate the quality of service of a data stream (e.g., a first data stream). The first data stream is used to transmit semantic information of a first media file. The first data stream is, for example, a QoS flow established by a core network device for transmitting the first media file. The first media file can be, for example, a video, an image, voice, or text. The first network transmission parameter may include, for example, one or more of the following: PDB, PER, and parameters such as the transmission time interval or jitter between data packets. It should be understood that the parameters included in the first network transmission parameter are merely examples. In other embodiments, the first network transmission parameter may also include other parameters, such as data stream level.

[0072] The network device may obtain the first network transmission parameter from the SMF network element according to the transmission requirement of the first media file, or the network device may obtain the first network transmission parameter from a QoS profile. For example, if the network device is a UPF network element, the UPF network element obtains the first network transmission parameter from the SMF network element according to the transmission requirement of the first media file; if the network device is a (R)AN, the (R)AN obtains the first network transmission parameter from a QoS profile.

[0073] S302: The network device determines a semantic evaluation index of the first media file based on the first network transmission parameter.

[0074] The semantic evaluation index may be represented by, for example, video semantic multimethod assessment fusion (VSMAF), and the semantic evaluation index may indicate the user experience quality of the first media file.

[0075] Optionally, the network device may determine, based on the first function, a degree of semantic distortion of the semantic information of the first media file if the semantic information of the semantic information is transmitted using the first network transmission parameter, and determine the degree of semantic distortion as the VSMAF.

[0076] The degree of semantic distortion indicates the degree of similarity between the first media file recovered by the receiving end (e.g., a terminal device) based on the semantic information and the first media file sent by the network device (e.g., the source first media file). For example, a high degree of semantic distortion indicates that the first media file recovered by the terminal device is less similar to the source first media file, and the user experience quality of the first media file is poor; a low degree of semantic distortion indicates that the first media file recovered by the terminal device is more similar to the source first media file, and the user experience quality of the first media file is high.

[0077] Alternatively, the network device may further determine, based on the second function, the communication service quality of semantic communication of semantic information of the first media file if the semantic information is transmitted through the first network transmission parameter, and determine the VSMAF based on the semantic distortion degree and the communication service quality.

[0078] Among them, the communication service quality can indicate the display effect of the first media file. For example, if the first media file is a video, the factors affecting the communication service quality may include, for example, video freeze information, video resolution information, video clarity information, etc.; if the first media file is an image, the factors affecting the communication service quality may include, for example, image clarity information, etc.; if the first media file is audio, the factors affecting the communication service quality may include, for example, audio freeze information, audio clarity information, etc. For example, if the communication service quality is low, it means that the first media file restored by the terminal device may be relatively freeze-sensitive, have low clarity, etc., and the user experience quality of the first media file is poor; if the communication service quality is high, it means that the first media file restored by the terminal device may be relatively smooth, have high clarity, and the user experience quality of the first media file is high. Therefore, the VSMAF determined by combining the communication service quality and the degree of semantic distortion is more accurate.

[0079] Alternatively, the network device may also determine, based on a third function, the degree of synchronization between adjacent data packets if the semantic information of the first media file is transmitted through the first network transmission parameters, and determine the VSMAF based on the degree of semantic distortion and the degree of synchronization; alternatively, the network device may also determine the VSMAF based on the degree of semantic distortion, communication service quality, and degree of synchronization.

[0080] The degree of synchronization between adjacent data packets can indicate the network transmission rate. For example, a low degree of synchronization between adjacent data packets indicates a low network transmission rate, a long transmission time for semantic information, and a poor user experience quality for the first media file. A high degree of synchronization between adjacent data packets indicates a high network transmission rate, a short transmission time for semantic information, and a high user experience quality for the first media file. Therefore, the VSMAF accuracy is higher when it is determined by combining the degree of semantic distortion between data packets with the degree of synchronization and / or communication service quality.

[0081] Optionally, when the network device determines the VSMAF based on the degree of semantic distortion and the quality of communication service, the value corresponding to the degree of semantic distortion (for example, the first value) and the value corresponding to the quality of communication service (for example, the second value) may be weighted summed to obtain the VSMAF. When the network device determines the VSMAF based on the degree of semantic distortion and the degree of synchronization, the first value and the value corresponding to the degree of synchronization (for example, the third value) may be weighted summed to obtain the VSMAF. When the network device determines the VSMAF based on the degree of semantic distortion, the quality of communication service, and the degree of synchronization, the first value, the second value, and the third value may be weighted summed to obtain the VSMAF.

[0082] For example, a network device determines VSMAF based on semantic distortion, communication service quality, and synchronization. VSMAF can be obtained as follows:

[0083] VSMAF=W_1×H_1(x)+W_2×H_2(x)+W_3×H_3(Δt) Formula 1

[0084] Wherein, x is the first network parameter, i.e., x = PDB, PER, jitter, ...; H_1 is the first function used to determine the degree of semantic distortion, H_2 is the second function used to determine the quality of communication service, H_3 is the third function used to determine the degree of synchronization between adjacent data packets (or adjacent feature streams), H_3 is, for example, a synchronization difference function, Δt is the transmission time interval between adjacent data packets (or adjacent feature streams), that is, the transmission time interval between data packets in the aforementioned first network transmission parameter, such as the duration that data packet 2 is later than data packet 1, and data packet 1 and data packet 2 are adjacently transmitted data packets. Wherein, H_1, H_2, and H_3 can be predefined by the protocol or reported by the terminal device; W_1, W_2, and W_3 are weights corresponding to the first function, the second function, and the third function, respectively. W_1, W_2, and W_3 can be predefined by the protocol, reported by the terminal device, or indicated by the application server. The application server indication may be an indication sent to the network device after the application server calculates W_1, W_2, and W_3 based on application layer parameters (e.g., the media parameters described below). Alternatively, the protocol may predefine a function table, where each row of the table includes a set of weight values, namely, W_1, W_2, and W_3. The application server may indicate to the network device which row in the table to use as a set of weight values ​​for determining the VSMAF. In the following embodiments, unless otherwise specified, the weights sent by the application server to the network device are used as an example.

[0085] Alternatively, the network device may obtain the VSMAF based on a preconfigured table, or may determine the VSMAF in other ways. The embodiment of the present application does not limit the method for determining the VSMAF.

[0086] Optionally, in order to improve the accuracy of the network device in determining VSMAF, before executing S302, the application server may also send media parameters of the first media file to the network device, and the media parameters may include one or more of the following: the size of the first media file, the compression rate of the first media file, the number of data packets included in the first media file, the size of each data packet included in the first media file, or the amount of semantic information included in the first media file. For example, if the first media file is a video, the media parameters may include frame rate, frame number, frame size, compression rate, number of data packets, data packet size, amount of semantic information, etc. If the first media file is an image (or voice, text), the media parameters may include the size of the image (or voice, text), compression rate, number of data packets, data packet size, and amount of semantic information. Unless otherwise specified, the following embodiments take the first media file as a video as an example. It should be understood that the parameters included in the media parameters are only examples. In other embodiments, the media parameters may also include other parameters, such as parameters such as semantic similarity.

[0087] Semantic information, such as video semantic information, refers to information describing the shapes of objects, spatial relationships between objects, and events surrounding objects. This information can also be referred to as semantic features, feature streams, or features. Semantic information content refers to the amount of information contained in a video, specifically the richness of meaning the video can convey. This information content depends not only on the length and size of the video, but also on the richness of the information it contains and the meaning it can convey.

[0088] After receiving the media parameters from the application server, the network device can determine the VSMAF based on the media parameters and the first network transmission parameters. The method used by the network device to determine the VSMAF based on the media parameters and the first network transmission parameters can refer to the method used by the aforementioned network device to determine the VSMAF based on the first network transmission parameters, for example, through function calculation, table matching, etc. When the network device uses the function calculation method to determine the VSMAF, the variables of the function also include the media parameters. Taking the example of the network device determining the VSMAF based on the degree of semantic distortion, communication service quality, and synchronization degree, the VSMAF can be obtained as follows:

[0089] VSMAF=W_1×H_1(x,y)+W_2×H_2(x,y)+W_3×H_3(Δt) Formula 2

[0090] For the descriptions of W_1, W_2, W_3, H_1, H_2, H_3 and x, refer to the descriptions of the corresponding parameters in Formula 1, and y is the aforementioned media parameter.

[0091] Optionally, the network device may further input semantic-related parameters among the above media parameters into the first function, and input communication service quality-related parameters into the second function. For example, please refer to Formula 3:

[0092] VSMAF=W_1×H_1(x,y_1)+W_2×H_2(x,y_2)+W_3×H_3(Δt) Formula 3

[0093] y_1 is a semantically relevant parameter among the media parameters, and y_2 is a communication service quality-related parameter among the media parameters. For example, y_1 may include the number of data packets included in the first media file, the size of the data packets included in the first media file, and the amount of semantic information included in the first media file. y_2 may include, for example, the size of the first media file and the compression ratio of the first media file. For example, if the first media file is a video, y_1 may include, for example, the number of data packets, the size of the data packets, and the amount of semantic information included in the video, while y_2 may include, for example, the video's frame rate, frame number, frame size, and compression ratio.

[0094] S303: The network device determines a second network transmission parameter based on the semantic evaluation indicator.

[0095] If the VSMAF meets the conditions (for example, the value of the VSMAF is greater than the threshold), it indicates that the terminal device can recover the first media file with a better user experience based on the received data packet, wherein the semantic communication is mainly based on the feature stream for communication, so in the following embodiments, the feature stream and the data packet can be used interchangeably. Taking the first media file as a video as an example, if the value of the VSMAF is greater than the threshold, it indicates that the terminal device can recover a relatively smooth and high-definition video, and the network device can determine the first network transmission parameter as the second network transmission parameter. If the value of the VSMAF is less than or equal to the threshold, it indicates that the terminal device may not be able to provide the first media file with a better user experience based on the received feature stream, that is, the first media file recovered by the terminal device may be relatively stuck and have a lower definition, and the network device can determine the second network transmission parameter based on the value of the VSMAF. For example, the network device can adjust the modulation and coding scheme (MCS) of the semantic information based on the value of the VSMAF, or the network device can select a QoS flow with better service quality from multiple QoS flows established for the terminal device to transmit the semantic information of the first media file. For example, the network device can obtain the network transmission parameters corresponding to each QoS flow in the multiple QoS flows, and use Formula 1, Formula 2, or Formula 3 to determine the VSMAF of each QoS flow based on the network transmission parameters corresponding to each QoS flow, and select the QoS flow whose VSMAF value is greater than the threshold and is idle as the QoS flow for transmitting the semantic information of the first media file.

[0096] S304: The network device sends the semantic information of the first media file to the terminal device based on the second network transmission parameter. Correspondingly, the terminal device receives the semantic information from the network device.

[0097] Taking the data stream corresponding to the second network transmission parameter as the second data stream as an example, the network device can send the semantic information of the first media file to the terminal device through the second data stream.

[0098] In the above technical solution, before sending the semantic information of the first media file to the terminal device, the network device can determine the semantic evaluation index of the first media file based on Formula 1, Formula 2 or Formula 3, and select appropriate network transmission parameters based on the value of the semantic evaluation index to transmit the semantic information, thereby greatly improving the user experience.

[0099] Two embodiments are introduced below with reference to FIG. 4 and FIG. 5 . These two embodiments are two examples of the semantic evaluation method introduced in the embodiment shown in FIG. 3 .

[0100] Please refer to Figure 4, which is a flowchart of an example of a semantic evaluation method provided in the embodiment shown in Figure 3. In this example, the semantic evaluation method shown in Figure 3 is implemented by a RAN. In the embodiment of this application, all optional steps are represented by dotted lines.

[0101] S401: The application server sends media parameters and / or weights of a first media file to the core network. Correspondingly, the core network receives the media parameters and / or weights from the application server.

[0102] As described in S301, the network device can determine the VSMAF based on the network transmission parameters, or can also determine the VSMAF based on the network transmission parameters and media parameters; and the network device can determine the VSMAF based on a function or a table, and even if the network device determines the VSMAF based on a function, the weight used to determine the VSMAF can be predetermined by the protocol or indicated by the application server, so S401 is an optional step.

[0103] Taking the example of an application server sending media parameters and weights to the core network, the application server can send these media parameters and weights to the UPF network element in the core network via the N6 interface. Alternatively, the application server can send media parameters to the UPF network element in the core network via the N6 interface; and send weights to the PCF network element in the core network via the N5 interface, or send weights to the NEF network element in the core network via the N33 interface. For a description of the media parameters, refer to the description of media parameters in S302 and will not be repeated here.

[0104] S402: The core network sends the media parameters and / or the weights to the RAN. Correspondingly, the RAN receives the media parameters and / or weights from the core network.

[0105] In an embodiment of the present application, the media parameters and / or weights received by the core network from the application server may all be sent to the RAN, or may be selectively sent to the RAN. For example, the core network may send only part or all of the media parameters, or only the weights, or part or all of the weights and media parameters. The embodiment of the present application is not limited to this. In the embodiment of the present application, the core network sending all media parameters and weights to the RAN is taken as an example.

[0106] Optionally, if the application server in S401 sends the media parameters and weights to the UPF network element via the N6 interface, then after receiving the media parameters and weights, the UPF network element may carry the media parameters and weights in a general packet radio system tunneling protocol user (GTP-U) message and send it to the RAN via the N3 interface. For example, please refer to Figure 6, which is a schematic diagram of the structure of a GTP-U message. As shown in Figure 6, the GTP-U message includes the following fields: version (version), protocol type (PT), extension header flag (E), sequence number (S), number marking (PN), message type (message type), network layer protocol data unit (N-PDU), number (number), and extension header (extension header). It should be understood that Figure 6 is only a simplified diagram for ease of understanding. The GTP-U message may also include other fields, not all of which are shown in Figure 6.

[0107] Optionally, the field carrying the media parameters and weights can be added to the Real-time Transport Protocol (RTP) layer, or to the User Datagram Protocol (UDP) layer, or a new protocol layer or field can be added between the RTP and UDP layers to carry the media parameters and weights, or the field carrying the media parameters can be added to the Internet Protocol Version 6 (IPV6) layer. For example, please refer to FIG7 , which is a schematic diagram of adding the field carrying the media parameters and weights to the RTP layer header.

[0108] If the application server in S401 sends the media parameters to the UPF network element through the N6 interface, and sends the weight to the PCF network element through the N5 interface, or sends the weight to the NEF network element through the N33 interface, then after receiving the weight, the PCF network element or the NEF network element can transmit the weight to the SMF network element, and the SMF transmits the weight to the AMF network element, and then the AMF network element transmits the weight to the RAN through the N2 interface.

[0109] Since S401 is an optional step, S402 is also an optional step.

[0110] S403: The RAN obtains a first network transmission parameter.

[0111] The RAN may obtain the first network transmission parameter from the QoS profile. For a related description of the first network transmission parameter, reference may be made to the related description of the first network transmission parameter in S301 , which will not be repeated here.

[0112] S404: The RAN determines a semantic evaluation index of the first media file based on the first network transmission parameter.

[0113] If the aforementioned S401 and S402 are not executed, that is, the weight is predefined by the protocol, the RAN can, for example, use Formula 1 in S302 to determine the VSMAF based on the first network transmission parameter and the weight; if the aforementioned S401 and S402 are executed, the RAN can, for example, use Formula 2 or Formula 3 in S302 to determine the VSMAF based on the first network transmission parameter, the weight, and the media parameter.

[0114] Please refer to Figure 5, which is a flowchart of another example of the semantic evaluation method provided in the embodiment shown in Figure 3. In this example, the semantic evaluation method shown in Figure 3 is implemented by a UPF network element. In the embodiment of this application, all optional steps are represented by dashed lines.

[0115] S501: The application server sends media parameters and / or weights of a first media file to the core network. Correspondingly, the core network receives the media parameters and / or weights from the application server.

[0116] The relevant description of S501 can refer to the relevant description of S401, which will not be repeated here.

[0117] Optionally, if the application server sends the weight to the PCF network element or NEF network element, the PCF network element or NEF network element may send the weight to the SMF network element after receiving the weight, and then the SMF network element may send the weight to the UPF network element through the N4 interface.

[0118] S502: The UPF network element in the core network obtains the first network transmission parameter.

[0119] The UPF network element can obtain the first network transmission parameter from the SMF network element based on the transmission requirements of the first media file. The relevant description of the first network transmission parameter can refer to the relevant description of the first network transmission parameter in S301, which is not repeated here.

[0120] S503: The UPF network element in the core network determines a semantic evaluation index of the first media file based on the first network transmission parameter.

[0121] If the aforementioned S501 is not executed, that is, the weight is predefined by the protocol, the UPF network element can, for example, use Formula 1 in S302 to determine the VSMAF based on the first network transmission parameter and the weight; if the aforementioned S501 is executed, the UPF network element can, for example, use Formula 2 or Formula 3 in S302 to determine the VSMAF based on the first network transmission parameter, media parameter and weight.

[0122] For the description of the technical features involved in the examples shown in FIG. 4 and FIG. 5 , reference may be made to the relevant description of S301 to S304 , which will not be repeated here.

[0123] FIG8 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application. The communication device 800 may be a network device or a circuit system of the network device as described in any of the embodiments shown in FIG3 to FIG5 , and is used to implement the method corresponding to the network device in the above method embodiment. For example, one circuit system is a chip system.

[0124] The communication device 800 includes at least one processor 801. Processor 801 can be used for internal processing of the device to implement certain control processing functions. Optionally, processor 801 includes instructions. Optionally, processor 801 can store data. Optionally, different processors can be independent devices, located in different physical locations, or on different integrated circuits. Optionally, different processors can be integrated into one or more processors, for example, on one or more integrated circuits.

[0125] Optionally, the communication device 800 includes one or more memories 803 for storing instructions. Optionally, data may also be stored in the memories 803. The processor and memory may be provided separately or integrated together.

[0126] Optionally, the communication device 800 includes a communication line 802 and at least one communication interface 804. Since the memory 803, the communication line 802 and the communication interface 804 are all optional, they are indicated by dotted lines in FIG8 .

[0127] Optionally, the communication device 800 may further include a transceiver and / or an antenna. The transceiver may be used to send information to or receive information from other devices. The transceiver may be referred to as a transceiver, a transceiver circuit, an input / output interface, etc., and is used to implement the transceiver function of the communication device 800 through the antenna. Optionally, the transceiver includes a transmitter and a receiver. For example, the transmitter may be used to generate a radio frequency signal from a baseband signal, and the receiver may be used to convert the radio frequency signal into a baseband signal.

[0128] The processor 801 may include a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0129] The communication link 802 may include a pathway for transmitting information between the aforementioned components.

[0130] The communication interface 804 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0131] The memory 803 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 803 may exist independently and be connected to the processor 801 via the communication line 802. Alternatively, the memory 803 may be integrated with the processor 801.

[0132] Memory 803 is used to store computer-executable instructions for executing the solution of the present application, and is controlled by processor 801. Processor 801 is used to execute the computer-executable instructions stored in memory 803, thereby implementing the steps performed by the network device described in any of the embodiments shown in Figures 3 to 5.

[0133] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0134] In a specific implementation, as an embodiment, the processor 801 may include one or more CPUs, such as CPU0 and CPU1 in FIG8 .

[0135] In a specific implementation, as an embodiment, the communication device 800 may include multiple processors, such as the processor 801 and the processor 805 in FIG8 . Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0136] When the device shown in FIG8 is a chip, such as a chip of a network device, the chip includes a processor 801 (and may also include a processor 805), a communication circuit 802, and a communication interface 804. Optionally, the chip may include a memory 803. Specifically, the communication interface 804 may be an input interface, a pin, or a circuit. The memory 803 may be a register, a cache, or the like. The processor 801 and the processor 805 may be a general-purpose CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the semantic evaluation method of any of the above-described embodiments.

[0137] In the embodiment of the present application, the functional modules of the device can be divided according to the above-mentioned method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, in the case of dividing each functional module according to each function, Figure 9 shows a schematic diagram of a device. The device 900 can be the network device involved in the above-mentioned various method embodiments, or a chip in the network device. The device 900 includes a sending unit 901, a processing unit 902 and a receiving unit 903.

[0138] It should be understood that the device 900 can be used to implement the steps performed by the network device in the semantic evaluation method of the embodiment of the present application. The relevant features can refer to any of the embodiments shown in any of the figures in Figures 3 to 5 above, and will not be repeated here.

[0139] Optionally, the functions / implementation processes of the sending unit 901, the receiving unit 903, and the processing unit 902 in FIG9 can be implemented by the processor 801 in FIG8 calling computer-executable instructions stored in the memory 803. Alternatively, the functions / implementation processes of the processing unit 902 in FIG9 can be implemented by the processor 801 in FIG8 calling computer-executable instructions stored in the memory 803, and the functions / implementation processes of the sending unit 901 and the receiving unit 903 in FIG9 can be implemented by the communication interface 804 in FIG8.

[0140] Optionally, when the device 900 is a chip or a circuit, the functions / implementation processes of the sending unit 901 and the receiving unit 903 can also be implemented through pins or circuits.

[0141] The present application also provides a computer-readable storage medium, which stores a computer program or instruction. When the computer program or instruction is executed, the method performed by the network device in the above-mentioned method embodiment is implemented. In this way, the functions described in the above embodiments can be implemented in the form of software functional units and sold or used as independent products. Based on this understanding, the technical solution of the present application can be essentially or in other words, the part that contributes or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0142] The present application also provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute the method executed by the network device in any of the aforementioned method embodiments.

[0143] An embodiment of the present application further provides a processing device, including a processor and an interface; the processor is used to execute the method executed by the network device involved in any of the above method embodiments.

[0144] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0145] The various illustrative logic units and circuits described in the embodiments of the present application can be implemented or operated by a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.

[0146] The steps of the methods or algorithms described in the embodiments of the present application can be directly embedded in hardware, software units executed by a processor, or a combination of the two. The software units can be stored in RAM, flash memory, ROM, erasable programmable read-only memory (EPROM), EEPROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Alternatively, the storage medium can also be integrated into the processor. The processor and storage medium can be provided in an ASIC, which can be provided in a network device. Alternatively, the processor and storage medium can also be provided in different components in the network device.

[0147] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0148] The contents of the various embodiments of this application can refer to each other. If there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0149] It is understood that in the embodiments of the present application, the network device may perform some or all of the steps in the embodiments of the present application. These steps or operations are merely examples. In the embodiments of the present application, other operations or variations of various operations may also be performed. In addition, the various steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

Claims

1. A semantic evaluation method, characterized in that: The method comprises: Acquire a first network transmission parameter, where the first network transmission parameter is used to indicate a quality of service of a first data stream, where the first data stream is used to transmit semantic information of a first media file; Determine a semantic evaluation index of the first media file based on the first network transmission parameter, where the semantic evaluation index is used to indicate a user experience quality of the first media file.

2. The method according to claim 1, characterized in that The first network transmission parameter includes one or more of the following: Packet delay budget PDB; Packet Error Ratio PER; The transmission time interval between packets; or, Jitter.

3. The method according to claim 1 or 2, characterized in that Determining a semantic evaluation index of the first media file based on the first network transmission parameter includes: determining, based on a first function, a degree of semantic distortion of transmitting the semantic information through the first network transmission parameter; The semantic distortion degree is determined as the semantic evaluation index.

4. The method according to claim 3, characterized in that The method further comprises: determining, based on a second function, a quality of communication service for transmitting the semantic information via the first network transmission parameter; The semantic evaluation index is determined based on the communication service quality and the semantic distortion degree.

5. The method according to claim 3 or 4, characterized in that The method further comprises: determining, based on a third function, a degree of synchronization between adjacent data packets when transmitting the semantic information through the first network transmission parameter; The semantic evaluation index is determined based on the synchronization degree and the semantic distortion degree, or the semantic evaluation index is determined based on the synchronization degree, the semantic distortion degree and the quality of the communication server transmitting the semantic information through the first network transmission parameter.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Receive media parameters of the first media file from the application server, where the media parameters include one or more of the following: the size of the first media file; a compression rate of the first media file; the number of data packets included in the first media file; The size of each data packet included in the first media file; or The amount of semantic information included in the first media file.

7. The method according to claim 6, characterized in that Determining a semantic evaluation index of the first media file based on the first network transmission parameter includes: A semantic evaluation index of the first media file is determined based on the first network transmission parameter and the media parameter.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: A second network transmission parameter is determined based on the semantic evaluation index, and the semantic information is sent based on the second network transmission parameter.

9. A communication device, characterized in that: The method comprises a unit for executing each step of the method according to any one of claims 1 to 8.

10. A communication device, characterized in that: The method comprises a processor and a memory, wherein the memory is coupled to the processor, and the processor is used to call computer instructions in the memory to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The method comprises a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that When the method is executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 8.

13. A chip system, characterized in that: include: A processor, configured to call and run a computer program from a memory, so that the method according to any one of claims 1 to 8 is implemented.

Images