Uplink multiple access method and device, electronic equipment and storage medium

By dividing and integrating semantic information between the user end and the base station end, the transmission strategy of multi-user semantic communication is optimized, the problem of inefficient multi-user transmission in semantic communication is solved, and the efficient utilization of resources is achieved.

CN118945604APending Publication Date: 2024-11-12BEIJING UNIV OF POSTS & TELECOMM
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310538345.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-12
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In semantic communication scenarios, when multiple users transmit information to the base station at the same time, a large number of duplicate semantic information leads to waste of transmission resources and inefficient efficiency, and the existing systems are not compatible with multiple access technology.

Method used

The user side encodes the information to be uploaded into common information and personal information through a semantic coding model, and uploads it separately. The base station side receives and integrates it to decode it. The transmission is optimized through the division of information entropy and variance judgment. The user side allocates and caches according to resource allocation and cache. Status report adjusts the transmission policy.

Benefits of technology

It saves time and bandwidth for transmitting common information, avoids waste of communication resources, and improves communication efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945604A_ABST
    Figure CN118945604A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of communication, in particular to the technical field of semantic communication, and particularly relates to an uplink multiple access method and device, electronic equipment and a storage medium. According to the specific implementation scheme, a user side encodes first service information to be uploaded through a semantic encoding model to obtain first semantic information; the user side divides the first semantic information into common information and personalized information; the user side uploads the common information and the personalized information to the base station side; any user side with the common information uploads the common information to the base station side, and each user side with the personalized information uploads the corresponding personalized information to the base station side; after the base station end receives the common information and the personality information, the common information and the personality information are integrated to obtain second semantic information; and the base station end decodes the second semantic information through the semantic decoding model to obtain the second service information. And the common information is only transmitted once by multiple users, so that the transmission time and bandwidth for transmitting the common information are saved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, specifically to the field of semantic communication technology, and especially to an uplink multiple access method, device, electronic device and storage medium. Background Art

[0002] With the increase in wireless terminal devices, the data rate in wireless communications is approaching the Shannon capacity limit, and spectrum resources are insufficient to support a large number of connected smart devices in the fifth generation of communications. Semantic communication has emerged as one of the enabling technologies for intelligent communications. Thanks to the advancement of artificial intelligence technology, semantic communication based on end-to-end technology and deep learning has become a research focus. Semantic communication extracts the semantic information of transmitted information through artificial intelligence models, focusing on interpreting the semantic information of the sender and the meaning behind the transmitted symbols with the help of a background knowledge base.

[0003] In the semantic communication scenario, during the uplink transmission of information by a single user, the user side extracts the semantic information corresponding to the transmitted information through the artificial intelligence model, and the semantic information is encoded and transmitted to the base station through the channel. After decoding, the base station interprets the transmitted semantic information through the semantic knowledge base. The current semantic communication system is not compatible with multiple access technology. When multiple users transmit information to the base station at the same time, a large amount of duplicate semantic information may be uploaded to the base station, resulting in a waste of transmission resources and affecting transmission efficiency. Summary of the invention

[0004] The present disclosure provides an uplink multiple access method, device, electronic device, storage medium, and computer program product.

[0005] According to one aspect of the present disclosure, an uplink multiple access method is provided, which is applied to a scenario in which multiple user terminals simultaneously upload first service information to the same base station terminal, including:

[0006] The user end encodes the first service information to be uploaded by using a semantic coding model to obtain first semantic information;

[0007] The user terminal divides the first semantic information into common information and individual information;

[0008] The user terminal uploads the common information and the individual information to the base station: any one of the user terminals having the common information uploads the common information to the base station, and each of the user terminals having the individual information uploads the corresponding individual information to the base station;

[0009] After receiving the common information and the individual information, the base station integrates the common information and the individual information to obtain second semantic information;

[0010] The base station decodes the second semantic information through a semantic decoding model to obtain second service information.

[0011] Optionally, the user terminal dividing the first semantic information into common information and individual information includes:

[0012] Calculating mutual information between the first semantic information corresponding to a plurality of the user terminals;

[0013] Determining whether the information entropy of the mutual information is lower than a first threshold;

[0014] In response to the information entropy of the mutual information being lower than the first threshold, determining that the mutual information is the common information;

[0015] In response to the information entropy of the mutual information being not lower than the first threshold, determining the mutual information as the personal information.

[0016] Optionally, after the user terminal divides the first semantic information into common information and individual information, the method further includes:

[0017] The user end calculates the variance of the common information between the multiple user ends, and determines whether the multiple common information have the same or opposite signal directions according to the variance.

[0018] Optionally, before the user terminal uploads the common information and the individual information to the base station terminal, the method further includes:

[0019] The user terminal sends a scheduling request to the base station terminal;

[0020] The base station allocates uplink resources to the user terminal according to the scheduling request;

[0021] The user terminal determines whether the uplink resource allocated by the base station terminal meets the data upload requirement;

[0022] In response to the uplink resource satisfying the data upload requirement, the user terminal uploading the common information and the individual information to the base station terminal;

[0023] In response to the uplink resource not meeting the data upload requirement, the user terminal sends a buffer status report to the base station terminal; wherein the buffer status report is used to apply for the uplink resource from the base station terminal.

[0024] Optionally, the user terminal sending a buffer status report to the base station terminal includes:

[0025] The user end determines whether the uplink resource allows sending the buffer status report to the base station end;

[0026] In response to the uplink resource being allowed to send the buffer status report to the base station, the user terminal sends the buffer status report to the base station;

[0027] After the user terminal sends the buffer status report to the base station terminal, the user terminal continues to determine whether the uplink resource allocated by the base station terminal can upload the common information and the individual information:

[0028] If yes, uploading the common information and the individual information to the base station;

[0029] If not, returning to the step of determining whether the uplink resource allows sending the buffer status report to the base station;

[0030] In response to the uplink resource not allowing the buffer status report to be sent to the base station, the user terminal continues to determine whether the uplink resource is allowed to send the scheduling request to the base station:

[0031] If yes, sending the scheduling request to the base station until the uplink resources are sufficient to send the buffer status report;

[0032] If not, a contention random access process is initiated to apply for the uplink resource from the base station until the uplink resource is sufficient to send the buffer status report.

[0033] Optionally, the cache status report includes the following information: knowledge base information corresponding to the first semantic information, semantic coding model information, and buffer size information.

[0034] Optionally, the step of integrating the common information and the individual information to obtain the second semantic information includes:

[0035] The base station integrates the common information and the individual information according to the knowledge base information and the semantic coding model information provided by the user terminal to obtain the second semantic information.

[0036] Optionally, before the user terminal divides the first semantic information into common information and individual information, the method further includes:

[0037] The base station determines whether the first semantic information to be uploaded by the plurality of user terminals belongs to the same semantic knowledge base;

[0038] In response to the first semantic information to be uploaded by the multiple user terminals belonging to the same semantic knowledge base, simultaneously sending a transmission permission request to the multiple user terminals;

[0039] The user terminal divides the first semantic information into common information and individual information according to the transmission permission request.

[0040] According to another aspect of the present disclosure, an uplink multiple access device is provided, which is applied to a scenario where multiple user terminals upload first service information to the same base station terminal at the same time, and is characterized by comprising:

[0041] A semantic coding module, disposed at the user terminal, configured to encode the first service information to be uploaded through a semantic coding model to obtain first semantic information;

[0042] An information division module, provided at the user terminal, configured to divide the first semantic information into common information and individual information;

[0043] A first transmission module is provided at the user terminal and is configured to upload the common information and the individual information to the base station: any one of the user terminals having the common information uploads the common information to the base station, and each of the user terminals having the individual information uploads the corresponding individual information to the base station;

[0044] An information integration module, disposed at the base station, configured to receive the common information and the individual information, and then integrate the common information and the individual information to obtain second semantic information;

[0045] The semantic decoding module is arranged at the base station end, and is configured to decode the second semantic information through a semantic decoding model to obtain second service information.

[0046] Optionally, the information division module includes:

[0047] A first calculation unit is configured to calculate mutual information between the first semantic information corresponding to a plurality of the user terminals;

[0048] A judging unit, configured to judge whether the information entropy of the mutual information is lower than a first threshold;

[0049] In response to the information entropy of the mutual information being lower than the first threshold, determining that the mutual information is the common information;

[0050] In response to the information entropy of the mutual information being not lower than the first threshold, determining the mutual information as the personal information.

[0051] Optionally, the information division module further includes:

[0052] The second calculation unit is configured to divide the first semantic information into common information and individual information, calculate the variance of the common information between multiple user terminals, and determine whether the multiple common information have the same or opposite signal directions based on the variance.

[0053] Optionally, before the user terminal uploads the common information and the individual information to the base station terminal, the method further includes:

[0054] A request module, provided at the user terminal, configured to send a scheduling request to the base station terminal;

[0055] An allocation module, arranged at the base station end, configured to allocate uplink resources to the user end according to the scheduling request;

[0056] A first judgment module, provided at the user terminal, is configured to judge whether the uplink resource allocated by the base station terminal meets the data upload requirement;

[0057] The first transmission module uploads the common information and the individual information to the base station in response to the uplink resource satisfying the data upload requirement;

[0058] In response to the uplink resources not meeting the data upload requirement, the first transmission module sends a buffer status report to the base station; wherein the buffer status report is used to apply for the uplink resources from the base station.

[0059] Optionally, the first transmission module sending a buffer status report to the base station includes:

[0060] The first judgment module judges whether the uplink resource allows sending the buffer status report to the base station;

[0061] In response to the uplink resource allowing the buffer status report to be sent to the base station, the first transmission module sends the buffer status report to the base station;

[0062] After the first transmission module sends the buffer status report to the base station, the first transmission module continues to determine whether the uplink resource allocated by the base station can upload the common information and the individual information:

[0063] If yes, uploading the common information and the individual information to the base station;

[0064] If not, returning to the step of determining whether the uplink resource allows sending the buffer status report to the base station;

[0065] In response to the uplink resource not allowing the buffer status report to be sent to the base station, the first transmission module continues to determine whether the uplink resource is allowed to send the scheduling request to the base station:

[0066] If yes, sending the scheduling request to the base station until the uplink resources are sufficient to send the buffer status report;

[0067] If not, a contention random access process is initiated to apply for the uplink resource from the base station until the uplink resource is sufficient to send the buffer status report.

[0068] Optionally, the cache status report includes the following information: knowledge base information corresponding to the first semantic information, semantic coding model information, and buffer size information.

[0069] Optionally, the information integration module integrates the common information and the individual information to obtain the second semantic information, including:

[0070] The common information and the individual information are integrated according to the knowledge base information and the semantic coding model information provided by the user terminal to obtain the second semantic information.

[0071] Optionally, also include:

[0072] A second judgment module is provided at the base station end and is configured to judge whether the first semantic information to be uploaded by multiple user terminals belongs to the same semantic knowledge base before the information division module divides the first semantic information into common information and individual information;

[0073] A second transmission module, arranged at the base station, is configured to send a transmission permission request to the multiple user terminals at the same time in response to the first semantic information to be uploaded by the multiple user terminals belonging to the same semantic knowledge base;

[0074] The information division module divides the first semantic information into common information and individual information according to the transmission permission request.

[0075] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0076] at least one processor; and

[0077] a memory communicatively connected to the at least one processor; wherein,

[0078] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any method in any of the above technical solutions.

[0079] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described in the above technical solutions.

[0080] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements any one of the methods described in the above technical solutions when executed by a processor.

[0081] The present disclosure provides an uplink multiple access method, device, electronic device, storage medium, and computer program product, which divide the semantic information that multiple users need to transmit into common information and individual information. For the common information, multiple users only transmit it once, which saves the transmission time and bandwidth of the common information, avoids the waste of communication resources, and improves the communication efficiency.

[0082] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0084] Figure 1 is a schematic diagram of the steps of the uplink multiple access method in an embodiment of the present disclosure;

[0085] Figure 2 is an application scenario diagram of the uplink multiple access method in the embodiment of the present disclosure;

[0086] Figure 3 is a schematic diagram of information carried by a cache status report in an embodiment of the present disclosure;

[0087] Figure 4 is a flow chart of a user terminal applying for uplink scheduling in an embodiment of the present disclosure;

[0088] Figure 5 is a flow chart of two-user model multiple access uplink transmission in an embodiment of the present disclosure;

[0089] Figure 6 is a principle block diagram of an uplink multiple access device in an embodiment of the present disclosure;

[0090] Figure 7 It is a block diagram of an electronic device used to implement the uplink multiple access method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0091] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0092] Multi-access: multiple access. When multiple users are connected to a common transmission medium to communicate with each other, it is necessary to distinguish the users in a certain domain. Common domains of distinction include time domain, which distinguishes users by time; frequency domain, which distinguishes users by using frequency; and space domain, which distinguishes users by using space.

[0093] Time-frequency resources: When data is transmitted between the transmitter and receiver in a multiple access manner, the multiple devices participating in the transmission are divided into their own transmission intervals according to time division, frequency division, etc. When a device is assigned to a specific time domain interval and / or frequency domain interval, the time domain interval and / or frequency domain interval becomes the time-frequency resource available to the device. This means that the device performs multiple access transmission on the time-frequency resource.

[0094] Business information: information involved in information business services. Depending on the type of information, it can be subdivided into text business information, image business information, voice business information, video business information, point cloud business information, etc. It can also be subdivided into structured information and unstructured information. It can also be all possible types of business information transmitted by communication.

[0095] Semantic coding: semantic information contained in business information. According to different semantic types, it can be subdivided into text semantic coding, image semantic coding, audio semantic coding, video semantic coding, point cloud semantic coding, etc. The possible categories of semantic coding are related to the possible categories of business information, and can be all possible types of semantic coding for communication transmission. The generation of semantic coding is also related to the semantic coding model, which can adopt all possible models of artificial intelligence, deep learning, pattern recognition and other disciplines.

[0096] Semantic multiple access: After converting the service information to be transmitted into semantic codes, the semantic codes are split into a common part and an individual part, and the common part and the individual part corresponding to each semantic code are transmitted to perform multiple access transmission.

[0097] Common information: after multiple business information is converted into multiple semantic codes, the common parts obtained by superimposing multiple semantic codes on the semantic domain.

[0098] Personalized information: After the business information is converted into semantic code, the semantic code can be divided into a common part and a personalized part. The semantic code obtained by converting the business information is different from the personalized part of the common part in the semantic domain.

[0099] Transmitter and receiver: There is a channel connection between the transmitter and the receiver, the transmitter (transmitter) has an encoder, and the receiver (receiver) has a decoder. The present disclosure is based on semantic coding and semantic decoding, so the transmitter of the present disclosure has a semantic encoder; the receiver of the present disclosure has a semantic decoder. The transmitter and receiver of the present disclosure work at the semantic layer, and the bottom layer is still the Shannon physical layer.

[0100] Artificial intelligence model: includes artificial intelligence semantic coding model and artificial intelligence semantic decoding model. The artificial intelligence semantic coding model is used to encode the service information of the future self-source into semantic information. The semantic information is transmitted on the channel. The artificial intelligence semantic decoder is used to decode the semantic information transmitted on the channel into service information. According to the different semantic types, it can be divided into text artificial intelligence model, audio artificial intelligence model, image artificial intelligence model, video artificial intelligence model, point cloud artificial intelligence model, one-dimensional waveform model, radar data model, etc. The category of artificial intelligence model is related to the category of semantic coding and the category of service information, and can be a model of all possible types of communication transmission.

[0101] The present disclosure provides an uplink multiple access method, which is applied to a scenario where multiple user terminals upload first service information to the same base station terminal at the same time, such as Figure 1 As shown, including:

[0102] Step S101: The user end encodes the first service information to be uploaded by using a semantic coding model to obtain first semantic information;

[0103] Step S102, the user terminal divides the first semantic information into common information and individual information;

[0104] Step S103, the user terminal uploads common information and individual information to the base station: any user terminal with common information uploads the common information to the base station, and each user terminal with individual information uploads corresponding individual information to the base station;

[0105] Step S104, after receiving the common information and the individual information, the base station integrates the common information and the individual information to obtain second semantic information;

[0106] Step S105: the base station decodes the second semantic information through a semantic decoding model to obtain second service information.

[0107] Specifically, the semantic coding model and the semantic decoding model in this embodiment can both be artificial intelligence models obtained based on neural network training. It should be noted that the second business information obtained after the base station uses the semantic decoding model to restore the semantic coding is highly similar to the first business information transmitted by the user end. For example, the first business information is a cat image. After the semantic features of the cat image are extracted and compressed using the semantic coding model, the first semantic information is obtained; after being divided into common information and individual information in step S102, it is transmitted to the base station through the channel; the base station then uses the semantic decoding model to integrate the common information and individual information to obtain the second semantic information, and reconstructs the image based on the second semantic information to obtain the cat image (i.e., the second business information). This cat image restored by the semantic decoding model will have some differences in image quality compared to the original cat image, but the two are consistent in content, and the visual experience for the user is almost the same. However, compared with directly transmitting the original business information, the transmission of the compressed semantic information extracted by the semantic coding model can significantly reduce the amount of communication transmission data and greatly improve the transmission efficiency. For example, the original size of 3M pictures is compressed into semantic information of about 30K.

[0108] In step S102, the user terminal divides the first semantic information into common information and individual information, and the common information refers to the common part of the information to be uploaded by multiple user terminals. Any user terminal with common information can upload the common information to the base station, and then each user terminal can upload its own individual information. In this way, it is not necessary for each user terminal to upload the common information once, and the common information is only transmitted once among multiple users.

[0109] Exemplarily, taking the two-user model multiple access uplink transmission process as an example, taking UE1 (first user end) and UE2 (first user end) both transmitting the Google Open Image dataset (first business information) with a picture size of 512*512*3 as an example, the first semantic information is extracted respectively through the artificial intelligence model, and the first semantic information corresponding to each picture is obtained, which is 4096 bits. By calculating that UE1 and UE2 have 50% common information, that is, 1024 bits, and the other 50% of each is individual information. At the next moment, UE1 sends common information to the base station gNB. After receiving the information, gNB sends a confirmation signal to UE1, indicating that it sends individual information. UE1 receives the confirmation signal and continues to send individual information to gNB. After receiving the individual information, gNB sends a confirmation signal to UE1, indicating that the reception is complete, and sends a confirmation signal to UE2, indicating that it sends individual information. UE2 receives the confirmation signal and sends individual information to gNB. After receiving the information, gNB sends a confirmation signal to UE2, indicating that the reception is complete.

[0110] After all common information and personal information are received, the base station integrates the personal part and common part of UE1 for decoding based on the knowledge base information and the coding model information provided by UE1, and recovers the semantic information (i.e., the second semantic information) to be transmitted by UE1 from the semantic information, thereby completing the user uplink transmission process. It can be seen here that if the semantic model multiple access method is not used, 4096 bits of information need to be transmitted. Through the semantic model multiple access method, two users only need to transmit a common information of 1024 bits and the personal information of the two users, a total of 2048 bits, saving 1024 bits, saving the transmission time and bandwidth of the common information, avoiding the waste of communication resources, and improving communication efficiency.

[0111] As an optional implementation, in step S102, the user terminal divides the first semantic information into common information and individual information including:

[0112] Calculating mutual information between first semantic information corresponding to multiple user terminals;

[0113] Determine whether the information entropy of the mutual information is lower than a first threshold;

[0114] In response to the information entropy of the mutual information being lower than a first threshold, determining that the mutual information is common information;

[0115] In response to the information entropy of the mutual information being not lower than a first threshold, the mutual information is determined to be personal information.

[0116] Specifically, mutual information refers to the useful information in the difference between the information to be uploaded by different user terminals. For example, the semantic information to be uploaded by UE1 and UE2 is x and y respectively, and mutual information is the useful information that is different between x and y. Common information and individual information can be distinguished by information entropy. If the information entropy is small, it is determined to be common information, and if the information entropy is large, it is determined to be individual information. Information entropy refers to the probability of occurrence of a certain type of information (the probability of occurrence of a discrete random event). The higher the probability of an event, the lower the information entropy it carries. For example, the information "the sun rises from the east" is a certain event, so it does not carry any useful information. From the perspective of information theory, this sentence does not eliminate any uncertainty.

[0117] Exemplarily, UE1 and UE2 group the first semantic information to be transmitted, and calculate the information entropy of the mutual information between each group of uplink users through the mutual information network. If the information entropy corresponding to the mutual information is lower than the first threshold, that is, the amount of useful information in the difference part is low, then it is identified as common information of multiple users, that is, the group of data expresses the same semantics, and this part of information only needs to be transmitted once between the two users. Any user terminal of UE1 and UE2 can send the common information to the base station. In this way, UE1 and UE2 do not need to send it once each, which saves the transmission time and bandwidth for transmitting the common information and improves communication efficiency.

[0118] As an optional implementation manner, after the user terminal divides the first semantic information into common information and individual information, the method further includes:

[0119] The user end calculates the variance of the common information among the multiple user ends, and determines, according to the variance, whether the multiple common information have the same or opposite signal directions.

[0120] Specifically, the common information between multiple user terminals is the group of data that expresses the same semantics. The variance of this part of the common information is calculated. If the variance is small, it is considered to be the same-sign common information (the signal direction is the same), and if the variance is large, it is the different-sign common information (the signal direction is opposite). When the user terminal uploads the common information to the base station, it can indicate through instructions whether it is the same-sign common information or the different-sign common information.

[0121] As an optional implementation, in step S103, before the user end uploads the common information and the individual information to the base station end, the method further includes:

[0122] The user end sends a scheduling request (SR) to the base station end;

[0123] The base station allocates uplink resources to the user terminal according to the scheduling request SR;

[0124] The user terminal determines whether the uplink resources allocated by the base station terminal meet the data upload requirements;

[0125] In response to the uplink resources satisfying the data upload requirement, the user terminal uploads the common information and the individual information to the base station terminal;

[0126] In response to the uplink resource not meeting the data upload requirement, the user terminal sends a buffer status report (Buffer Status, BSR) to the base station; wherein the buffer status report is used to apply for uplink resources from the base station.

[0127] like Figure 2As shown in the figure, in the semantic communication scenario, a base station (gNB) can accommodate multiple user terminals (UE). When the UE does not transmit data, the gNB will not allocate transmission resources to the UE to avoid wasting resources. When UE1 needs to transmit, it needs to extract the corresponding semantic information from the transmission content, that is, the source on the terminal side using an artificial intelligence model, and send a scheduling request SR to the gNB side, indicating that UE1 applies to the base station for scheduling uplink resources. The SR information does not include the required resource information. SR information is generally transmitted through PUCCH (Physical Uplink Control Channel). After receiving it, the base station gNB sends a confirmation instruction to UE1 to allocate resources for UE1. When UE1 uploads data on the PUSCH channel, it stops sending SR information. UE1 determines whether the resources allocated by the gNB meet the data transmission requirements. If they meet, they are sent directly to the base station. If not, BSR information is sent. The BSR information is a cache status report used to apply for uplink scheduling resources and notify the gNB of the required resources. The information carried by the BSR is as follows: Figure 3 As shown, it includes the knowledge base information corresponding to the semantic information (which knowledge base the semantic information belongs to), the semantic encoding model information and the buffer size information.

[0128] Furthermore, after receiving the BSR information sent by UE1, the gNB waits for a period of time, and searches for users UE2, UE3...UEn from the same signal source as UE1 among other user terminals that have sent BSR information. If no uplink user from the same signal source as UE1 is found, the transmission data amount requested in the BSR request information is allocated to UE1, and a transmission permission instruction is sent to UE1 on PDCCH (Physical Downlink Control Channel). After receiving the instruction, UE1 starts to transmit on PUSCH (Physical Uplink Shared Channel); if uplink users UE2, UE3...UEn from the same signal source as UE1 are found, the base station gNB allocates resources to UE1 and UE2, UE3...UEn and other users from the same signal source base as UE1 according to their transmission data amount, and sends a transmission permission instruction to UE1 and UE2, UE3...UEn users through PDCCH.

[0129] As an optional implementation, Figure 4 As shown, the user terminal sends a buffer status report (BSR) to the base station terminal, including:

[0130] Step S401, the user terminal applies for uplink resources from the base station;

[0131] Step S402, the user end determines whether uplink resources allow sending a buffer status report to the base station end;

[0132] Step S403, in response to the uplink resource being allowed to send a buffer status report to the base station, the user terminal sends a buffer status report to the base station;

[0133] Step S404: After the user terminal sends the buffer status report to the base station, it continues to determine whether the uplink resources allocated by the base station can upload the common information and the individual information:

[0134] If yes, go to step S405 to upload common information and individual information to the base station;

[0135] If not, return to step S402 to determine whether uplink resources allow sending a buffer status report to the base station;

[0136] Step S406: In response to the uplink resource not allowing the buffer status report to be sent to the base station, the user terminal continues to determine whether the uplink resource is allowed to send a scheduling request to the base station:

[0137] If yes, go to step S407, send a scheduling request to the base station, and after obtaining sufficient resources to send a BSR, go to step S404;

[0138] If not, go to step S408, initiate a competitive random access process, apply for uplink resources from the base station, and after the base station allocates enough uplink resources to send BSR, go to step S404 to continue to determine whether the uplink resources allocated by the base station can send semantic information (common information and individual information). Among them, competitive random access means that the access resources are randomly obtained by the UE itself, rather than allocated by the base station.

[0139] For example, if UE1 has enough uplink resources on the PUSCH channel to send BSR, it can directly send request information to gNB through the PUSCH channel without sending SR to request the base station to allocate resources in the PUSCH channel. If UE1 does not have enough resources on the PUSCH channel to send BSR, it needs to send SR to request the base station to allocate resources until sufficient resources are obtained to send BSR. If it is determined in step S406 that the uplink resources are not sufficient to send SR, competitive random access can be initiated as a backup to ensure that the user end can obtain sufficient resources to send BSR, thereby ensuring the stability of data uploaded by the user end.

[0140] As an optional implementation, Figure 5As shown, when the UE sends SR information to the gNB, it can be sent through the PUCCH channel; when the UE sends BSR information to the gNB, it can be sent through the PUSCH channel; when the UE sends common information or individual information to the gNB, it can also be sent through the PUSCH channel; when the gNB sends a confirmation instruction to the UE, it is sent through the PDCCH channel.

[0141] As an optional implementation, the second semantic information obtained by integrating the common information and the individual information includes:

[0142] The base station integrates the common information and the individual information according to the knowledge base information and the semantic coding model information provided by the user terminal to obtain the second semantic information.

[0143] Exemplarily, UE1 sends BSR information to gNB, and the BSR information includes the resources required for its data transmission, the knowledge base information to which the data to be transmitted by UE1 belongs, and the semantic coding model information used by UE1, wherein the knowledge base information indicates to which knowledge base the semantic information to be sent by UE1 to the base station belongs, and the semantic coding model information includes the parameters of the semantic coding model used by UE1 to extract the first semantic information. The base station can integrate the common information and individual information transmitted separately to ensure the integrity and accuracy of the semantic information integration.

[0144] As an optional implementation manner, before the user terminal divides the first semantic information into common information and individual information, the method further includes:

[0145] The base station determines whether the first semantic information to be uploaded by multiple user terminals belongs to the same semantic knowledge base;

[0146] In response to the first semantic information to be uploaded by the multiple users belonging to the same semantic knowledge base, simultaneously sending a transmission permission request to the multiple users;

[0147] The user end divides the first semantic information into common information and individual information according to the transmission permission request.

[0148] For example, after receiving the BSR information from UE1, the gNB receives the BSR information from UE2. By comparison, if the data to be transmitted by the two users belongs to the same semantic knowledge base, a transmission permission request is sent to UE1 and UE2 at the same time. If the semantic information uploaded by the two user terminals does not belong to the same semantic knowledge base, it means that the semantics expressed by the two are not the same or similar, and it is impossible to distinguish between common information and individual information.

[0149] The present disclosure also provides an uplink multiple access device, which is applied to a scenario where multiple user terminals upload first service information to the same base station terminal at the same time, such as Figure 6 As shown, including:

[0150] The semantic coding module 601 is provided at the user end and is configured to encode the first service information to be uploaded by using a semantic coding model to obtain first semantic information;

[0151] The information division module 602 is provided at the user end and is configured to divide the first semantic information into common information and individual information;

[0152] The first transmission module 603 is provided at the user end and is configured to upload common information and individual information to the base station end: any user end with common information uploads the common information to the base station end, and each user end with individual information uploads the corresponding individual information to the base station end;

[0153] The information integration module 604 is provided at the base station end and is configured to receive the common information and the individual information and integrate the common information and the individual information to obtain the second semantic information;

[0154] The semantic decoding module 605 is provided at the base station end, and is configured to decode the second semantic information through a semantic decoding model to obtain the second service information.

[0155] Specifically, the semantic coding model and the semantic decoding model in this embodiment can both be artificial intelligence models obtained based on neural network training. It should be noted that the second business information obtained after the base station uses the semantic decoding model to restore the semantic coding is highly similar to the first business information transmitted by the user end. For example, the first business information is a cat image. After the semantic features of the cat image are extracted and compressed using the semantic coding model, the first semantic information is obtained; after being divided into common information and individual information by the information division module 602, it is transmitted to the base station through the channel; the base station then uses the semantic decoding model to integrate the common information and individual information to obtain the second semantic information, and reconstructs the image based on the second semantic information to obtain the cat image (i.e., the second business information). This cat image restored by the semantic decoding model will have some differences in image quality compared to the original cat image, but the two are consistent in content, and the visual experience for the user is almost the same. However, compared with directly transmitting the original business information, the transmission of the compressed semantic information extracted by the semantic coding model can significantly reduce the amount of communication transmission data, greatly improving the transmission efficiency, for example, the original size of 3M picture is compressed into semantic information of about 30K size.

[0156] In this embodiment, the first semantic information is divided into common information and individual information by the information division module 602. The common information refers to the common part of the information to be uploaded by multiple user terminals. Any user terminal with common information can upload the common information to the base station, and then each user terminal can upload its own individual information. In this way, it is not necessary for each user terminal to upload the common information once, and the common information is only transmitted once among multiple users.

[0157] Exemplarily, taking the two-user model multiple access uplink transmission process as an example, taking UE1 (first user end) and UE2 (first user end) both transmitting the Google Open Image dataset (first business information) with a picture size of 512*512*3 as an example, the first semantic information is extracted respectively through the artificial intelligence model, and the first semantic information corresponding to each picture is obtained, which is 4096 bits. By calculating that UE1 and UE2 have 50% common information, that is, 1024 bits, and the other 50% of each is individual information. At the next moment, UE1 sends common information to the base station gNB. After receiving the information, gNB sends a confirmation signal to UE1, indicating that it sends individual information. UE1 receives the confirmation signal and continues to send individual information to gNB. After receiving the individual information, gNB sends a confirmation signal to UE1, indicating that the reception is complete, and sends a confirmation signal to UE2, indicating that it sends individual information. UE2 receives the confirmation signal and sends individual information to gNB. After receiving the information, gNB sends a confirmation signal to UE2, indicating that the reception is complete.

[0158] After all common information and personal information are received, the base station integrates the personal part and common part of UE1 for decoding based on the knowledge base information and the coding model information provided by UE1, and recovers the semantic information (i.e., the second semantic information) to be transmitted by UE1 from the semantic information, thereby completing the user uplink transmission process. It can be seen here that if the semantic model multiple access method is not used, 4096 bits of information need to be transmitted. Through the semantic model multiple access method, two users only need to transmit a common information of 1024 bits and the personal information of the two users, a total of 2048 bits, saving 1024 bits, saving the transmission time and bandwidth of the common information, avoiding the waste of communication resources, and improving communication efficiency.

[0159] As an optional implementation, the information division module 602 includes:

[0160] A first calculation unit is configured to calculate mutual information between first semantic information corresponding to multiple user terminals;

[0161] A judging unit, configured to judge whether the information entropy of the mutual information is lower than a first threshold;

[0162] In response to the information entropy of the mutual information being lower than a first threshold, determining that the mutual information is common information;

[0163] In response to the information entropy of the mutual information being not lower than a first threshold, the mutual information is determined to be personal information.

[0164] Specifically, mutual information refers to the useful information in the difference between the information to be uploaded by different user terminals. For example, the semantic information to be uploaded by UE1 and UE2 is x and y respectively, and mutual information is the useful information that is different between x and y. Common information and individual information can be distinguished by information entropy. If the information entropy is small, it is determined to be common information, and if the information entropy is large, it is determined to be individual information. Information entropy refers to the probability of occurrence of a certain type of information (the probability of occurrence of a discrete random event). The higher the probability of an event, the lower the information entropy it carries. For example, the information "the sun rises from the east" is a certain event, so it does not carry any useful information. From the perspective of information theory, this sentence does not eliminate any uncertainty.

[0165] Exemplarily, UE1 and UE2 group the first semantic information to be transmitted, and calculate the information entropy of the mutual information between each group of uplink users through the mutual information network. If the information entropy corresponding to the mutual information is lower than the first threshold, that is, the amount of useful information in the difference part is low, then it is identified as common information of multiple users, that is, the group of data expresses the same semantics, and this part of information only needs to be transmitted once between the two users. Any user terminal of UE1 and UE2 can send the common information to the base station. In this way, UE1 and UE2 do not need to send it once each, which saves the transmission time and bandwidth for transmitting the common information and improves communication efficiency.

[0166] As an optional implementation, the information division module 602 further includes:

[0167] The second calculation unit is configured to divide the first semantic information into common information and individual information, calculate the variance of the common information between multiple user terminals, and determine whether the multiple common information have the same or opposite signal directions according to the variance.

[0168] Specifically, the common information between multiple user terminals is the group of data that expresses the same semantics. The variance of this part of the common information is calculated. If the variance is small, it is considered to be the same-sign common information (the signal direction is the same), and if the variance is large, it is the different-sign common information (the signal direction is opposite). When the user terminal uploads the common information to the base station, it can indicate through instructions that it is the same-sign common information and the different-sign common information, which is convenient for the base station to identify.

[0169] As an optional implementation manner, before the user end uploads the common information and the individual information to the base station end, the method further includes:

[0170] A request module, arranged at the user end, configured to send a scheduling request to the base station end;

[0171] An allocation module, arranged at the base station end, configured to allocate uplink resources to the user end according to the scheduling request;

[0172] A first judgment module is provided at the user end and is configured to judge whether the uplink resources allocated by the base station end meet the data upload requirements;

[0173] The first transmission module uploads common information and individual information to the base station in response to the uplink resources satisfying the data upload requirement;

[0174] In response to the uplink resources not meeting the data upload requirement, the first transmission module sends a buffer status report to the base station; wherein the buffer status report is used to apply for uplink resources from the base station.

[0175] like Figure 2 As shown, in the semantic communication scenario, a base station (gNB) can accommodate multiple user terminals (UE). When the UE is not transmitting data, the gNB will not allocate transmission resources to the UE to avoid wasting resources. When UE1 needs to transmit, it needs to extract the corresponding semantic information from the transmission content, that is, the source on the terminal side using an artificial intelligence model, and send a scheduling request SR to the gNB side, indicating that UE1 applies to the base station for scheduling uplink resources. The SR information does not include the required resource information. The SR information is generally transmitted on the PUCCH channel. After receiving it, the base station gNB sends a confirmation instruction to UE1 to allocate resources to UE1. When UE1 uploads data on the PUSCH channel, it stops sending SR information. UE1 determines whether the resources allocated by the gNB meet the data transmission requirements. If so, it sends it directly to the base station. If not, it sends BSR information. The BSR information is a cache status report used to apply for uplink scheduling resources and notify the gNB of the required resources. The information carried by the BSR is as follows Figure 3 As shown, it includes the knowledge base information corresponding to the semantic information (which knowledge base the semantic information belongs to), the semantic encoding model information and the buffer size information.

[0176] Furthermore, after receiving the BSR information sent by UE1, the gNB waits for a period of time and searches for users UE2, UE3...UEn from the same signal source as UE1 among other user terminals that have sent BSR information. If no uplink user from the same signal source as UE1 is found, the transmission data volume requested in the BSR request information is allocated to UE1, and a transmission permission instruction is sent to UE1 on the PDCCH channel. After receiving the instruction, UE1 starts to transmit on the PUSCH channel. If uplink users UE2, UE3...UEn from the same signal source as UE1 are found, the base station gNB allocates resources to UE1 and UE2, UE3...UEn and other users from the same signal source base as UE1 according to their transmission data volume, and sends a transmission permission instruction to UE1 and UE2, UE3...UEn users through PDCCH.

[0177] As an optional implementation, Figure 4 As shown, the first transmission module of the user terminal sends a buffer status report (BSR) to the base station terminal, including:

[0178] Step S401, the user terminal applies for uplink resources from the base station;

[0179] Step S402, the user end determines whether uplink resources allow sending a buffer status report to the base station end;

[0180] Step S403, in response to the uplink resource being allowed to send a buffer status report to the base station, the user terminal sends a buffer status report to the base station;

[0181] Step S404: After the user terminal sends the buffer status report to the base station, it continues to determine whether the uplink resources allocated by the base station can upload the common information and the individual information:

[0182] If yes, go to step S405 to upload common information and individual information to the base station;

[0183] If not, return to step S402 to determine whether uplink resources allow sending a buffer status report to the base station;

[0184] Step S406: In response to the uplink resource not allowing the buffer status report to be sent to the base station, the user terminal continues to determine whether the uplink resource is allowed to send a scheduling request to the base station:

[0185] If yes, go to step S407, send a scheduling request to the base station, and after obtaining sufficient resources to send a BSR, go to step S404;

[0186] If not, go to step S408, initiate a competitive random access process, apply for uplink resources from the base station, and after the base station allocates enough uplink resources to send BSR, go to step S404 to continue to determine whether the uplink resources allocated by the base station can send semantic information (common information and individual information). Among them, competitive random access means that the access resources are randomly obtained by the UE itself, rather than allocated by the base station.

[0187] For example, if UE1 has enough uplink resources on the PUSCH channel to send BSR, it can directly send request information to gNB through the PUSCH channel without sending SR to request the base station to allocate resources in the PUSCH channel. If UE1 does not have enough resources on the PUSCH channel to send BSR, it needs to send SR to request the base station to allocate resources until sufficient resources are obtained to send BSR. If it is determined in step S406 that the uplink resources are not sufficient to send SR, competitive random access can be initiated as a backup to ensure that the user end can obtain sufficient resources to send BSR, thereby ensuring the stability of data uploaded by the user end.

[0188] As an optional implementation manner, the information integration module integrates the common information and the individual information to obtain the second semantic information including:

[0189] According to the knowledge base information and semantic coding model information provided by the user, the common information and the individual information are integrated to obtain the second semantic information.

[0190] Exemplarily, UE1 sends BSR information to gNB, and the BSR information includes the resources required for its data transmission, the knowledge base information to which the data to be transmitted by UE1 belongs, and the semantic coding model information used by UE1, wherein the knowledge base information indicates to which knowledge base the semantic information to be sent by UE1 to the base station belongs, and the semantic coding model information includes the parameters of the semantic coding model used by UE1 to extract the first semantic information. The base station can integrate the common information and individual information transmitted separately to ensure the integrity and accuracy of the semantic information integration.

[0191] As an optional embodiment, the device further includes:

[0192] A second judgment module is provided at the base station end and is configured to judge whether the first semantic information to be uploaded by multiple user terminals belongs to the same semantic knowledge base before the information division module divides the first semantic information into common information and individual information;

[0193] A second transmission module, disposed at the base station end, is configured to send a transmission permission request to the multiple user terminals simultaneously in response to the first semantic information to be uploaded by the multiple user terminals belonging to the same semantic knowledge base;

[0194] The information division module divides the first semantic information into common information and individual information according to the transmission permission request.

[0195] For example, after receiving the BSR information from UE1, the gNB receives the BSR information from UE2. By comparison, if the data to be transmitted by the two users belongs to the same semantic knowledge base, a transmission permission request is sent to UE1 and UE2 at the same time. If the semantic information uploaded by the two user terminals does not belong to the same semantic knowledge base, it means that the semantics expressed by the two are not the same or similar, and it is impossible to distinguish between common information and individual information.

[0196] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0197] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0198] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0199] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0200] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0201] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning objective function algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as an uplink multiple access method. For example, in some embodiments, the uplink multiple access method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the uplink multiple access method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the uplink multiple access method in any other appropriate manner (e.g., by means of firmware).

[0202] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0203] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0204] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0205] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0206] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0207] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0208] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0209] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An uplink multiple access method, applied to a scenario where multiple user terminals simultaneously upload first service information to the same base station terminal, characterized in that: include: The user end encodes the first service information to be uploaded by using a semantic coding model to obtain first semantic information; The user terminal divides the first semantic information into common information and individual information; The user terminal uploads the common information and the individual information to the base station: any one of the user terminals having the common information uploads the common information to the base station, and each of the user terminals having the individual information uploads the corresponding individual information to the base station; After receiving the common information and the individual information, the base station integrates the common information and the individual information to obtain second semantic information; The base station decodes the second semantic information through a semantic decoding model to obtain second service information.

2. The method according to claim 1, wherein: The user terminal divides the first semantic information into common information and individual information including: Calculating mutual information between the first semantic information corresponding to a plurality of the user terminals; Determining whether the information entropy of the mutual information is lower than a first threshold; In response to the information entropy of the mutual information being lower than the first threshold, determining that the mutual information is the common information; In response to the information entropy of the mutual information being not lower than the first threshold, determining the mutual information as the personal information.

3. The method according to claim 1 or 2, after the user terminal divides the first semantic information into common information and individual information, further comprising: The user end calculates the variance of the common information between the multiple user ends, and determines whether the multiple common information have the same or opposite signal directions according to the variance.

4. The method according to claim 1, wherein: Before the user terminal uploads the common information and the individual information to the base station terminal, the method further includes: The user terminal sends a scheduling request to the base station terminal; The base station allocates uplink resources to the user terminal according to the scheduling request; The user terminal determines whether the uplink resource allocated by the base station terminal meets the data upload requirement; In response to the uplink resource satisfying the data upload requirement, the user terminal uploading the common information and the individual information to the base station terminal; In response to the uplink resource not meeting the data upload requirement, the user terminal sends a buffer status report to the base station terminal; wherein the buffer status report is used to apply for the uplink resource from the base station terminal.

5. The method according to claim 4, wherein: The user terminal sending a buffer status report to the base station terminal includes: The user end determines whether the uplink resource allows sending the buffer status report to the base station end; In response to the uplink resource being allowed to send the buffer status report to the base station, the user terminal sends the buffer status report to the base station; After the user terminal sends the buffer status report to the base station terminal, the user terminal continues to determine whether the uplink resource allocated by the base station terminal can upload the common information and the individual information: If yes, uploading the common information and the individual information to the base station; If not, returning to the step of determining whether the uplink resource allows sending the buffer status report to the base station; In response to the uplink resource not allowing the buffer status report to be sent to the base station, the user terminal continues to determine whether the uplink resource is allowed to send the scheduling request to the base station: If yes, sending the scheduling request to the base station until the uplink resources are sufficient to send the buffer status report; If not, a contention random access process is initiated to apply for the uplink resource from the base station until the uplink resource is sufficient to send the buffer status report.

6. The method according to claim 4 or 5, wherein: The cache status report includes the following information: knowledge base information corresponding to the first semantic information, semantic coding model information, and buffer size information.

7. The method according to claim 6, wherein: The step of integrating the common information and the individual information to obtain the second semantic information includes: The base station integrates the common information and the individual information according to the knowledge base information and the semantic coding model information provided by the user terminal to obtain the second semantic information.

8. The method according to claim 1 or 2, before the user terminal divides the first semantic information into common information and individual information, further comprising: The base station determines whether the first semantic information to be uploaded by the plurality of user terminals belongs to the same semantic knowledge base; In response to the first semantic information to be uploaded by the multiple user terminals belonging to the same semantic knowledge base, simultaneously sending a transmission permission request to the multiple user terminals; The user terminal divides the first semantic information into common information and individual information according to the transmission permission request.

9. An uplink multiple access device, applied to a scenario where multiple user terminals upload first service information to the same base station terminal at the same time, characterized in that: include: A semantic coding module, disposed at the user terminal, configured to encode the first service information to be uploaded through a semantic coding model to obtain first semantic information; An information division module, provided at the user terminal, configured to divide the first semantic information into common information and individual information; A first transmission module is provided at the user terminal and is configured to upload the common information and the individual information to the base station: any one of the user terminals having the common information uploads the common information to the base station, and each of the user terminals having the individual information uploads the corresponding individual information to the base station; An information integration module, disposed at the base station, configured to receive the common information and the individual information, and then integrate the common information and the individual information to obtain second semantic information; The semantic decoding module is arranged at the base station end, and is configured to decode the second semantic information through a semantic decoding model to obtain second service information.

10. The device according to claim 9, wherein: The information division module comprises: A first calculation unit is configured to calculate mutual information between the first semantic information corresponding to a plurality of the user terminals; A judging unit, configured to judge whether the information entropy of the mutual information is lower than a first threshold; In response to the information entropy of the mutual information being lower than the first threshold, determining that the mutual information is the common information; In response to the information entropy of the mutual information being not lower than the first threshold, determining the mutual information as the personal information.

11. The device according to claim 9 or 10, wherein: The information division module also includes: The second calculation unit is configured to divide the first semantic information into common information and individual information, calculate the variance of the common information between multiple user terminals, and determine whether the multiple common information have the same or opposite signal directions based on the variance.

12. The device according to claim 9, wherein: Before the user terminal uploads the common information and the individual information to the base station terminal, the method further includes: A request module, provided at the user terminal, configured to send a scheduling request to the base station terminal; An allocation module, arranged at the base station end, configured to allocate uplink resources to the user end according to the scheduling request; A first judgment module, provided at the user terminal, is configured to judge whether the uplink resource allocated by the base station terminal meets the data upload requirement; The first transmission module uploads the common information and the individual information to the base station in response to the uplink resource satisfying the data upload requirement; In response to the uplink resources not meeting the data upload requirement, the first transmission module sends a buffer status report to the base station; wherein the buffer status report is used to apply for the uplink resources from the base station.

13. The device according to claim 12, wherein: The first transmission module sending a buffer status report to the base station includes: The first judgment module judges whether the uplink resource allows sending the buffer status report to the base station; In response to the uplink resource allowing the buffer status report to be sent to the base station, the first transmission module sends the buffer status report to the base station; After the first transmission module sends the buffer status report to the base station, the first transmission module continues to determine whether the uplink resource allocated by the base station can upload the common information and the individual information: If yes, uploading the common information and the individual information to the base station; If not, returning to the step of determining whether the uplink resource allows sending the buffer status report to the base station; In response to the uplink resource not allowing the buffer status report to be sent to the base station, the first transmission module continues to determine whether the uplink resource is allowed to send the scheduling request to the base station: If yes, sending the scheduling request to the base station until the uplink resources are sufficient to send the buffer status report; If not, a contention random access process is initiated to apply for the uplink resource from the base station until the uplink resource is sufficient to send the buffer status report.

14. The device according to claim 12 or 13, wherein: The cache status report includes the following information: knowledge base information corresponding to the first semantic information, semantic coding model information, and buffer size information.

15. The device according to claim 14, wherein: The second semantic information obtained by the information integration module after integrating the common information and the individual information includes: The common information and the individual information are integrated according to the knowledge base information and the semantic coding model information provided by the user terminal to obtain the second semantic information.

16. The device according to claim 9 or 10, wherein: Also includes: A second judgment module is provided at the base station end and is configured to judge whether the first semantic information to be uploaded by the plurality of user ends belongs to the same semantic knowledge base before the information division module divides the first semantic information into common information and individual information; A second transmission module, arranged at the base station, is configured to send a transmission permission request to the plurality of user terminals simultaneously in response to the first semantic information to be uploaded by the plurality of user terminals belonging to the same semantic knowledge base; The information division module divides the first semantic information into common information and individual information according to the transmission permission request.

17. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

19. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.