A method, apparatus and device for data compression

Abstract

The present invention discloses a method, device and equipment for data compression. The method includes: during the service transmission process, determining the currently used compression dictionary and compression algorithm, where initially the initialized compression dictionary and compression algorithm are used, and then when it is determined that the update condition is met, using the compression dictionary and compression algorithm output by the AI model to respectively update the currently used compression dictionary and compression algorithm; based on the currently used compression dictionary, using the currently used compression algorithm to compress or decompress the transmitted service data. By using the method disclosed in the present invention, the compression dictionary and compression algorithm are optimized through learning and training of the data, thereby improving the compression ratio.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular, to a method, device, and equipment for data compression. Background Art

[0002] In the LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution-Advance) system, the network can configure the UE (User Equipment) to use the UDC (Uplink Data Compression) function to compress the uplink data before transmission, so as to reduce the overhead of radio resources.

[0003] When performing uplink data compression, the transmitting UE uses a preset dictionary or the content in the compression cache as a dictionary to compress the data to be transmitted, thereby further improving the compression ratio; correspondingly, the base station side decompresses the received data according to the preset dictionary or uses the previously received data as a dictionary.

[0004] In the existing UDC mechanism, the generation of the dictionary uses the content in the compression cache as the dictionary. Among them, the compression cache can be preset with a dictionary or all zeros based on the configuration. When there is data transmission, the compression cache adopts the first-in-first-out strategy, and uses the new data to replace the original data as the new dictionary. Although the above method utilizes the correlation between data, it cannot achieve the best compression effect. In addition, in the existing UDC mechanism technology, the configured compression algorithm is used, and a flexible compression algorithm is not considered to improve the compression ratio. Summary of the Invention

[0005] The present invention provides a method, device, and equipment for data compression, which solves the problem that the algorithm for generating the compression dictionary in the prior art cannot achieve the best compression effect and does not consider using a flexible compression algorithm to improve the compression ratio.

[0006] In a first aspect, the present invention provides a method for data compression, which is applied to a data transmission device. The method includes:

[0007] During the service transmission process, determine the currently used compression dictionary and compression algorithm. Initially, the initialized compression dictionary and compression algorithm are used. After that, when the update condition is met, use the compression dictionary and compression algorithm output by the AI model to update the currently used compression dictionary and compression algorithm respectively;

[0008] Based on the currently used compression dictionary, use the currently used compression algorithm to compress or decompress the transmitted service data.

[0009] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, compress using different compression algorithms with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to adjust the model parameters of the AI model.

[0010] Optionally, the method further includes:

[0011] Initialize the currently used compression dictionary and compression algorithm according to the preset information; or

[0012] When establishing a service connection, initialize the currently used compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0013] Optionally, determining that the update condition is met includes at least one of the following steps:

[0014] Determine that the update condition is met when establishing a service connection;

[0015] Determine that the update condition is met when the set update period is reached after establishing a service connection;

[0016] Determine that the update condition is met when the event-triggering condition is met.

[0017] Optionally, determining that the event-triggering condition is met includes at least one of the following steps:

[0018] Determine that the event-triggering condition is met when the compression rate of the currently transmitted service data is lower than the preset threshold;

[0019] Determine that the event-triggering condition is met when the difference between the compression rate expected according to the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value.

[0020] Optionally, during the service transmission process, it further includes:

[0021] Obtain the compression dictionary and compression algorithm output by the local AI model; or

[0022] Obtain the compression dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or

[0023] Obtain the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0024] Obtain the compression dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device located at a functional node in the cloud or at the edge; or

[0025] Obtain the compressed dictionary and compression algorithm output by using the AI model from a third-party device, and send them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

[0026] Optionally, the method further includes:

[0027] Send the latest transmitted service data and the compression ratio of the service data that has been completed in transmission to the third-party device.

[0028] In a second aspect, the present invention provides a method for data compression, which is applied to a third-party device. The method includes:

[0029] In response to a request from the data transmission device, obtain the latest transmitted service data of the current service and the compression ratio of the service data that has been completed in transmission;

[0030] Input the latest transmitted service data into the AI model, and use the AI model to output a compressed dictionary and a compression algorithm;

[0031] Send the compressed dictionary and the compression algorithm to the data transmission device.

[0032] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compressed dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compressed dictionary, output the compression algorithm corresponding to the highest compression ratio, and use this highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0033] Optionally, sending the compressed dictionary and the compression algorithm to the data transmission device specifically includes:

[0034] When it is determined that the update condition is met, send the compressed dictionary and the compression algorithm to the data transmission device.

[0035] Optionally, determining that the update condition is met includes at least one of the following steps:

[0036] Determine that when the data transmission device establishes a service connection, the update condition is met;

[0037] Determine that when the set update period is reached after the data transmission device establishes a service connection, the update condition is met;

[0038] Determine that when the event-triggering condition is met, the update condition is met.

[0039] Optionally, determining that the event-triggering condition is met includes at least one of the following steps:

[0040] When it is determined that the compression ratio of the service data whose transmission has been completed currently is lower than the preset threshold, it is determined that the event-triggering condition is satisfied;

[0041] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data whose transmission has been completed currently is greater than the preset value, it is determined that the event-triggering condition is satisfied.

[0042] Thirdly, the present invention provides a data transmission device for data compression, including a memory, a transceiver, and a processor:

[0043] The memory is used for storing computer programs; the transceiver is used for transceiving data under the control of the processor; the processor is used for reading the computer programs in the memory and performing the following operations:

[0044] During the service transmission process, determine the currently adopted compression dictionary and compression algorithm, where initially the initialized compression dictionary and compression algorithm are adopted, and then when it is determined that the update condition is satisfied, use the compression dictionary and compression algorithm output by the AI model to update the currently adopted compression dictionary and compression algorithm respectively;

[0045] Based on the currently adopted compression dictionary, use the currently adopted compression algorithm to compress or decompress the transmitted service data.

[0046] Optionally, the AI model is used for feature extraction of the latest transmitted service data, outputs a compression dictionary according to the correlation between the extracted features and the service data, and uses different compression algorithms to compress with the current compression dictionary, outputs the compression algorithm corresponding to the highest compression ratio, and uses this highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0047] Optionally, the processor is further used for:

[0048] Initialize the currently adopted compression dictionary and compression algorithm according to the pre-set information; or

[0049] When establishing a service connection, initialize the currently adopted compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0050] Optionally, the processor determines that the update condition is satisfied, including at least one of the following steps:

[0051] Determine that when establishing a service connection, the update condition is satisfied;

[0052] Determine that when the set update period is reached after establishing a service connection, the update condition is satisfied;

[0053] Determine that when the event-triggering condition is satisfied, the update condition is satisfied.

[0054] Optionally, the processor determines that an event trigger condition is satisfied, including at least one of the following steps:

[0055] When it is determined that the compression ratio of the service data currently transmitted is lower than a preset threshold, it is determined that the event trigger condition is satisfied;

[0056] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data currently transmitted is greater than a preset value, it is determined that the event trigger condition is satisfied.

[0057] Optionally, during the service transmission process, the processor is further configured to:

[0058] Obtain the compression dictionary and compression algorithm output by the local AI model; or

[0059] Obtain the compression dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or

[0060] Obtain the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0061] Obtain the compression dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device located at a functional node in the cloud or at the edge; or

[0062] Obtain the compression dictionary and compression algorithm output by the AI model from a third-party device and send them to the peer data transmission device, where the third-party device is a device located at a functional node in the cloud or at the edge.

[0063] Optionally, the processor is further configured to:

[0064] Send the latest transmitted service data and the compression ratio of the service data currently transmitted to a third-party device.

[0065] In a fourth aspect, the present invention provides a third-party device for data compression, including a memory, a transceiver, and a processor:

[0066] The memory is used to store computer programs; the transceiver is used to transmit and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations:

[0067] In response to a request from a data transmission device, obtain the latest transmitted service data of the current service and the compression ratio of the service data currently transmitted;

[0068] Input the latest transmitted service data into an AI model and use the AI model to output a compression dictionary and a compression algorithm;

[0069] Send the compression dictionary and compression algorithm to the data transmission device.

[0070] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to adjust the model parameters of the AI model.

[0071] Optionally, send the compression dictionary and compression algorithm to the data transmission device, and the processor is specifically used for:

[0072] When it is determined that the update condition is met, send the compression dictionary and compression algorithm to the data transmission device.

[0073] Optionally, the processor determines that the update condition is met, including at least one of the following steps:

[0074] When it is determined that the data transmission device establishes a service connection, the update condition is met;

[0075] When it is determined that after the data transmission device establishes a service connection and reaches the set update period, the update condition is met;

[0076] When it is determined that the event-triggering condition is met, the update condition is met.

[0077] Optionally, the processor determines that the event-triggering condition is met, including at least one of the following steps:

[0078] When it is determined that the compression rate of the currently transmitted service data is lower than the preset threshold, it is determined that the event-triggering condition is met;

[0079] When the difference between the expected compression rate of the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value, it is determined that the event-triggering condition is met.

[0080] In a fifth aspect, the present invention provides a device for data compression, including:

[0081] A dictionary algorithm determination unit, configured to determine the currently used compression dictionary and compression algorithm during the service transmission process, where initially, the initialized compression dictionary and compression algorithm are used, and then when it is determined that the update condition is met, the compression dictionary and compression algorithm output by the AI model are used to update the currently used compression dictionary and compression algorithm respectively;

[0082] A compression unit, configured to compress or decompress the transmitted service data based on the currently used compression dictionary using the currently used compression algorithm.

[0083] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the relevance between the extracted features and the service data, compress using different compression algorithms with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to adjust the model parameters of the AI model.

[0084] Optionally, the dictionary algorithm determination unit is further configured to:

[0085] Initialize the currently used compression dictionary and compression algorithm according to the preset information; or

[0086] When establishing a service connection, initialize the currently used compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0087] Optionally, the dictionary algorithm determination unit determines that the update condition is met, including at least one of the following steps:

[0088] Determine that the update condition is met when establishing a service connection;

[0089] Determine that the update condition is met when the set update period is reached after establishing a service connection;

[0090] Determine that the update condition is met when the event-triggering condition is met.

[0091] Optionally, the dictionary algorithm determination unit determines that the event-triggering condition is met, including at least one of the following steps:

[0092] Determine that the event-triggering condition is met when the compression rate of the currently transmitted service data is lower than the preset threshold;

[0093] Determine that the event-triggering condition is met when the difference between the compression rate expected according to the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value.

[0094] Optionally, during the service transmission process, the dictionary algorithm determination unit is further configured to:

[0095] Obtain the compression dictionary and compression algorithm output by the local AI model; or

[0096] Obtain the compression dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or

[0097] Obtain the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0098] Obtain a compression dictionary and a compression algorithm output by an AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or

[0099] Obtain a compression dictionary and a compression algorithm output by an AI model from a third-party device, and send them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

[0100] Optionally, the compression unit is further configured to:

[0101] Send the latest transmitted service data and the compression ratio of the service data that has been transmitted currently to the third-party device.

[0102] In a sixth aspect, the present invention provides a device for data compression, including:

[0103] A data receiving unit, configured to obtain the latest transmitted service data of the current service and the compression ratio of the service data that has been transmitted currently in response to a request from a data transmission device;

[0104] A dictionary algorithm generation unit, configured to input the latest transmitted service data into an AI model, and output a compression dictionary and a compression algorithm by using the AI model;

[0105] A data sending unit, configured to send the compression dictionary and the compression algorithm to the data transmission device.

[0106] Optionally, the AI model is used to perform feature extraction on the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression ratio, and use the highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0107] Optionally, when sending the compression dictionary and the compression algorithm to the data transmission device, the data sending unit is specifically configured to:

[0108] When it is determined that an update condition is satisfied, send the compression dictionary and the compression algorithm to the data transmission device.

[0109] Optionally, the data sending unit determines that the update condition is satisfied, including at least one of the following steps:

[0110] Determine that when the data transmission device establishes a service connection, the update condition is satisfied;

[0111] Determine that when a set update period arrives after the data transmission device establishes a service connection, the update condition is satisfied;

[0112] Determine that when an event-triggering condition is satisfied, the update condition is satisfied.

[0113] Optionally, the data sending unit determines that the event trigger condition is met, including at least one of the following steps:

[0114] When it is determined that the compression ratio of the service data that has been transmitted currently is lower than a preset threshold, it is determined that the event trigger condition is met;

[0115] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data that has been transmitted currently is greater than a preset value, it is determined that the event trigger condition is met.

[0116] In a seventh aspect, the present invention provides a computer program medium, on which a computer program is stored, and when the program is executed by a processor, the steps of a method for data compression provided in the first aspect above are implemented.

[0117] In an eighth aspect, the present invention provides a chip, which is coupled to a memory in a device, so that when the chip runs, it calls program instructions stored in the memory to implement the methods for data compression in each of the above aspects of this application embodiment and any possible aspects involved in each aspect.

[0118] In a ninth aspect, the present invention provides a computer program product, when the computer program product runs on an electronic device, the electronic device is enabled to execute the methods for data compression in each of the above aspects of this application embodiment and any possible aspects involved in each aspect.

[0119] A method, device and equipment for data compression provided by the present invention have the following beneficial effects:

[0120] During the data transmission process, by using the compression dictionary and compression algorithm output by the AI model, the currently adopted compression dictionary and compression algorithm are respectively updated correspondingly, the compression dictionary is optimized, and a flexible compression algorithm is adopted, so that the sending end and receiving end of the data synchronously update the compression dictionary and compression algorithm, and use the updated compression dictionary and compression algorithm for data compression and decompression, thereby improving the compression ratio. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] Figure 1 It is a schematic diagram of a data compression system given in an embodiment of the present invention;

[0122] Figure 2 It is a schematic diagram of a base station obtaining a compression dictionary and compression algorithm output by a local AI model for data compression provided in an embodiment of the present invention;

[0123] Figure 3Schematic diagram for obtaining, from a third-party device, data compression using a compression dictionary and a compression algorithm output by an AI model provided by an embodiment of the present invention;

[0124] Figure 4 Schematic diagram for obtaining, from a third-party device, a compression dictionary and a compression algorithm output by an AI model and with the update condition being to determine the establishment of a service connection for data compression provided by an embodiment of the present invention;

[0125] Figure 5 Flowchart of a method for a data transmission device to perform data compression provided by an embodiment of the present invention;

[0126] Figure 6 Flowchart of a method for a third-party device to perform data compression provided by an embodiment of the present invention;

[0127] Figure 7 Schematic diagram of a data transmission device for performing data compression provided by an embodiment of the present invention;

[0128] Figure 8 Schematic diagram of a third-party device for performing data compression provided by an embodiment of the present invention;

[0129] Figure 9 Schematic diagram of a device for a data transmission device to perform data compression provided by an embodiment of the present invention;

[0130] Figure 10 Schematic diagram of a device for a third-party device to perform data compression provided by an embodiment of the present invention. Detailed implementation manners

[0131] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0132] In an LTE (Long-Term Evolution) / LTE-A (Long-Term Evolution-Advance) system, the network can configure a UE (User Equipment) to use the UDC (Uplink Data Compression) function to compress the uplink data before transmission, so as to reduce the overhead of radio resources.

[0133] When performing uplink data compression, the transmitting UE uses a preset dictionary or the content in the compression cache as a dictionary to compress the data to be transmitted, thereby further improving the compression ratio. Correspondingly, the base station side decompresses the received data according to the preset dictionary or uses the previously received data as a dictionary.

[0134] The following is a detailed introduction to the UDC compression mechanism and the compression mechanism based on a preset dictionary:

[0135] 1) UDC compression mechanism

[0136] 1.1) The transmitting end maintains a compression cache, and the receiving end maintains a decompression cache. Both the compression and decompression caches are first-in, first-out queues.

[0137] 1.2) Before sending data, the transmitting end first compresses the data to be sent:

[0138] a) In the data packet to be sent, find the target field that meets the following characteristics:

[0139] The length exceeds the preset threshold;

[0140] The target field is the same as a certain field in the compression cache or in this data packet before the target field.

[0141] b) If the above target field is found, replace the above target field with an offset and length combination:

[0142] The offset is the position offset between the target field and the same field before the target field;

[0143] The length is the length of the target field;

[0144] Because the length of the offset and length combination is shorter than the length of the target field itself, it has a compression effect. In a data packet, there may be multiple fields that meet the above characteristics, and these fields can all be compressed.

[0145] 1.3) The transmitting end sends the compressed data packet to the peer; at the same time, fills the corresponding original data packet, that is, the uncompressed data, into the compression cache;

[0146] 1.4) The receiving end decompresses the received data packet based on the above offset and length, and the decompression cache; then, fills the decompressed data packet into the decompression cache.

[0147] 2) Compression mechanism based on a preset dictionary

[0148] As an optimization of UDC, the compression mechanism based on a preset dictionary can, based on service characteristics, write a preset dictionary for frequently occurring fields and store them in the compression and decompression caches of the compression end and the decompression end respectively before UDC is started.

[0149] In this way, when the UDC is just started, the compression and decompression caches are not empty. Instead, they store a preset dictionary of high-frequency fields, which can effectively increase the discovery probability of target fields and improve the compression ratio.

[0150] Obviously, to implement the above mechanism, before the UDC is started, the terminal and the base station need to obtain the preset dictionary to be used respectively, that is, complete the preset dictionary synchronization process.

[0151] Based on the principle of the above compression mechanism based on the preset dictionary, when the UDC is just started, the compression and decompression caches may be configured as empty. The probability that the compression end finds the target field in the current packet to be sent is low, and the compression ratio is correspondingly low. After the UDC runs for a period of time, the compression cache gradually increases, and the probability that the compression end finds the target field in the current packet to be sent increases, and the compression ratio can be correspondingly increased.

[0152] In the existing UDC mechanism, the dictionary is generated by using the content in the compression cache as the dictionary. Among them, the compression cache can be preset with a dictionary or all zeros based on the configuration. When there is data transmission, the compression cache adopts the first-in-first-out strategy, and uses new data to replace the original data as the new dictionary. Although the above method utilizes the correlation between data, it cannot achieve the best compression effect. In addition, the existing UDC mechanism uses a configured compression algorithm and does not consider using a flexible compression algorithm to improve the compression ratio.

[0153] To solve the above problems, the embodiments of the present application provide a method, device and equipment for data compression, which optimize the compression dictionary and compression algorithm through learning and training of data, thereby improving the compression ratio. The following gives the implementation manners of a method, device and equipment for data compression provided by the embodiments of the present invention.

[0154] Embodiment 1

[0155] As Figure 1 shown, the embodiment of the present invention gives a schematic diagram of a system for data compression, including:

[0156] A first data transmission device 101 as a sending end, which is used to determine the currently adopted compression dictionary and compression algorithm during the service transmission process. Initially, the initialized compression dictionary and compression algorithm are adopted, and then when it is determined that the update condition is met, the compression dictionary and compression algorithm output by the AI model are used to update the currently adopted compression dictionary and compression algorithm respectively;

[0157] Based on the currently adopted compression dictionary, the service data to be transmitted is compressed by using the currently adopted compression algorithm;

[0158] It should be noted that when the first data transmission device 101 serves as a sender, a compression operation is performed; when the first data transmission device 101 serves as a receiver, a decompression operation is performed.

[0159] The second data transmission device 102 as a receiver is used to determine the currently adopted compression dictionary and compression algorithm during the service transmission process. Initially, the initialized compression dictionary and compression algorithm are adopted. After that, when it is determined that the update condition is met, the compression dictionary and compression algorithm output by the AI model are used to update the currently adopted compression dictionary and compression algorithm respectively.

[0160] Based on the currently adopted compression dictionary, the service data to be transmitted is decompressed by using the currently adopted compression algorithm.

[0161] It should be noted that when the second data transmission device 102 serves as a sender, a compression operation is performed; when the second data transmission device 102 serves as a receiver, a decompression operation is performed.

[0162] It should be noted that the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to adjust the model parameters of the AI model.

[0163] It should be noted that during the service transmission, the identities of the first data transmission device 101 and the second data transmission device 102 as a sender and a receiver can be changed. For example, after the first data transmission device 101 compresses the service data by using the currently adopted compression dictionary and compression algorithm, it sends it to the second data transmission device 102. The second data transmission device 102 decompresses the transmitted service data by using the currently adopted compression dictionary and compression algorithm. At this time, the first data transmission device 101 is the sender of the data, and the second data transmission device 102 is the receiver of the data; after the second data transmission device 102 compresses the service data by using the currently adopted compression dictionary and compression algorithm, it sends it to the first data transmission device 101. The first data transmission device 101 decompresses the transmitted service data by using the currently adopted compression dictionary and compression algorithm. At this time, the first data transmission device 101 is the receiver of the data, and the second data transmission device 102 is the sender of the data.

[0164] As an optional implementation manner, during the service transmission process, it further includes:

[0165] (1) The above-mentioned first data transmission device 101 obtains the compression dictionary and compression algorithm output by the local AI model and sends them to the above-mentioned second data transmission device 102;

[0166] (2) The above-mentioned second data transmission device 102 obtains the compression dictionary and compression algorithm output by the local AI model and sends them to the above-mentioned first data transmission device 101;

[0167] (3) The above-mentioned first data transmission device 101 and / or the above-mentioned second data transmission device 102 obtain the compression dictionary and compression algorithm output by using the AI model from a third-party device, and the third-party device is a device located at a functional node in the cloud or at the edge.

[0168] It should be noted that when the above-mentioned third-party device sends the output compression dictionary and compression algorithm to any one of the above-mentioned first data transmission device 101 or the above-mentioned second data transmission device 102, the data transmission device that receives the above-mentioned compression dictionary and compression algorithm will send the above-mentioned compression dictionary and compression algorithm to the peer data transmission device.

[0169] As an optional implementation manner, sending the compression dictionary and compression algorithm includes:

[0170] Sending the compression dictionary and compression algorithm through an RRC message;

[0171] Sending the compression dictionary and compression algorithm through a control unit MAC CE;

[0172] Sending the compression dictionary and compression algorithm by carrying the compression dictionary and compression algorithm in the packet data convergence protocol PDCP header of the first data packet;

[0173] Sending the compression dictionary and compression algorithm by carrying the compression dictionary and compression algorithm indication information in the PDCP header of the first data packet and using the PDCP sub-PDU to carry the compression dictionary and compression algorithm.

[0174] It should be noted that for any one of the sending end and the receiving end of the above-mentioned data transmission device, in the case where the compression dictionary and compression algorithm are output by itself using the AI model, the new compression dictionary and / or compression algorithm are directly transmitted between the above-mentioned sending end and the receiving end; for the case where the compression dictionary and compression algorithm are output by the third-party device using the AI model, for example, the above-mentioned third-party device is a functional node in the cloud or at the edge, the above-mentioned sending end and the receiving end obtain the compression dictionary and / or compression algorithm from the above-mentioned functional node.

[0175] When adopting the above-mentioned (3) implementation manner of receiving the compression dictionary and compression algorithm from a third-party device, the above-mentioned system further includes:

[0176] A third-party device 103, which is configured to obtain the latest transmitted service data of the current service and the compression ratio of the service data that has been transmitted and completed currently in response to a request from the data transmission device; input the latest transmitted service data into an AI model, and use the AI model to output a compression dictionary and a compression algorithm; and send the compression dictionary and the compression algorithm to the data transmission device.

[0177] It should be noted that the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression ratio, and use the highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0178] As an optional implementation, the data transmission device sends a request message for requesting a compression dictionary and a compression algorithm to the above-mentioned third-party device.

[0179] As an optional implementation, for the above-mentioned implementation of receiving a compression dictionary and a compression algorithm from a third-party device, it further includes:

[0180] Send the latest transmitted service data and the compression ratio of the service data that has been transmitted and completed currently to the third-party device.

[0181] It should be noted that the above operation of sending the latest transmitted service data and the compression ratio of the service data that has been transmitted and completed currently to the third-party device can be executed by either the sending end or the receiving end of the data transmission device.

[0182] As an optional implementation, the above-mentioned third-party device actively senses the latest transmitted service data and the compression ratio of the service data that has been transmitted and completed currently.

[0183] As an optional implementation, sending the compression dictionary and the compression algorithm to the data transmission device specifically includes:

[0184] When it is determined that the update condition is met, send the compression dictionary and the compression algorithm to the data transmission device.

[0185] It should be noted that the above system architecture is only an example of the system architecture applicable to the embodiments of the present invention. The system architecture applicable to the embodiments of the present invention may have other entities added or some entities reduced compared to Figure 1 the system architecture shown.

[0186] As an optional implementation, the above-mentioned data transmission device 101 is a user terminal UE, the above-mentioned data transmission device 102 is a base station, and the above-mentioned third-party device 103 is a cloud or edge function node deployed with the above-mentioned AI model, such as an AI compression server.

[0187] The user terminal UE involved in the embodiments of this application can be a device that provides voice and / or data connectivity to users, a handheld device with wireless connection capabilities, or other processing devices connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device can be called a user equipment (UE). The wireless terminal device can communicate with one or more core networks via a Radio Access Network (RAN). The wireless terminal device can be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it can be a portable, pocket-sized, handheld, computer-integrated, or vehicle-mounted mobile device that exchanges language and / or data with the wireless access network. For example, devices such as personal communication service (PCS) phones, cordless phones, session initiated protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), etc. The wireless terminal device can also be called a system, a subscriber unit, a subscriber station, a mobile station, a mobile, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, a user device, which is not limited in the embodiments of this application.

[0188] The base station involved in the embodiments of the present application can also be referred to as an access point according to different specific application scenarios, or it can be a device that communicates with wireless terminal devices through one or more sectors on the air interface in the access network, or other names. The network device can be used to mutually convert the received air frames and Internet Protocol (IP) packets, and act as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an IP communication network. The network device can also coordinate the attribute management of the air interface. For example, the network device involved in the embodiments of the present application can be a network device (Base Transceiver Station, BTS) in a Global System For Mobile communications (GSM) or Code Division Multiple Access (CDMA), or a network device (NodeB) in a Wide-band Code Division Multiple Access (WCDMA), or an evolved network device (evolutional NodeB, eNB or e-NodeB) in a Long Term Evolution (LTE) system, a 5G base station in a 5G network architecture (Next generation System), or a Home evolved nodeB (HeNB), a Relay Node, a femto, a pico, etc. The embodiments of the present application do not limit this.

[0189] As an alternative implementation, the above AI model is integrated into the AI module, and the above AI module can achieve:

[0190] (1) Generation of an AI model for the compression dictionary and compression algorithm;

[0191] (2) Compression ratio feedback, using the AI compression dictionary and compression algorithm to compress the transmission data, calculating the compression ratio and feeding it back to the AI training model;

[0192] (3) Using the AI training model to perform AI learning on new transmission data and generating a new compression dictionary and compression algorithm.

[0193] It should be noted that the above AI module can be located at either the sending end or the receiving end of the data transmission device, or in a third-party device, such as a functional node in the cloud or at the edge.

[0194] As an alternative implementation, in the above three implementation manners, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the relevance between the extracted features and the service data, and use different compression algorithms to perform compression with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to adjust the model parameters of the AI model.

[0195] It should be noted that the above AI model can adopt an existing feedback neural network model, continuously adjust the parameters of the AI model through a self-learning mechanism, and continuously strengthen the ability to extract dictionary words by analyzing the correlation features of input data. With the continuous input of service data, the effect of the recognition dictionary is adjusted in the positive direction of increasing the compression rate. The AI model calculates the data compression rate using different compression algorithms, and the above different compression algorithms are existing algorithms, such as Huffman coding, Rice coding, run-length coding, etc. In addition, the process of specifically feeding back the compression rate to the AI model and adjusting the model parameters can adopt existing methods, which will not be elaborated here.

[0196] Particularly, when the above data transmission device initially establishes a connection and performs service transmission for the first time, it is necessary to determine the initialized compression dictionary and compression algorithm to be used initially.

[0197] As an alternative implementation, initialize the currently used compression dictionary and compression algorithm according to the pre-set information; or

[0198] When establishing a service connection, initialize the currently used compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0199] It should be noted that the above initialization of the currently used compression dictionary according to the pre-set information includes:

[0200] Initialize the currently used compression dictionary as a compression dictionary configured based on service characteristics according to the pre-set information; or

[0201] Initialize the currently used compression dictionary to be empty according to the pre-setting.

[0202] It should be noted that the above initialization of the currently used compression algorithm according to the pre-set information includes:

[0203] Initialize the currently used compression algorithm as the default compression algorithm according to the pre-set information; or

[0204] Initialize the currently used compression algorithm as a pre-configured compression algorithm according to the pre-set information; or

[0205] Initialize the currently adopted compression algorithm as the compression algorithm selected according to the service characteristics based on the preset information.

[0206] It should be noted that the above AI model extracts features from the service data transmitted each time, outputs a compression dictionary according to the relevance between the extracted features and the service data, and compresses with different compression algorithms using the current compression dictionary, and outputs the compression algorithm corresponding to the highest compression rate, that is, adjusts the compression dictionary and compression algorithm according to the data transmitted each time for business. However, only when the update condition is met, the compression dictionary and compression algorithm output by the AI model are used to update the currently adopted compression dictionary and compression algorithm respectively.

[0207] As an optional implementation manner, determining that the update condition is met includes at least one of the following steps:

[0208] Determine that when a service connection is established, the update condition is met;

[0209] Determine that after a service connection is established, when the set update period is reached, the update condition is met;

[0210] Determine that when the event-triggering condition is met, the update condition is met.

[0211] It should be noted that determining that the update condition is met includes any one or any combination of the above three conditions, that is, determining that the update condition is met means determining that one of the above three conditions or any combination of any two of the above conditions or all three conditions is met.

[0212] For the above three methods of determining that the update condition is met, specific implementation manners are given:

[0213] Implementation manner a: Determine the update by determining the establishment of a service connection.

[0214] For each service for which compression transmission is performed, after the above service connection is established, synchronize the compression dictionary and compression algorithm for the above service once, and do not update the compression dictionary and compression algorithm during the communication process.

[0215] The update of the compression dictionary and compression algorithm based on the transmission data and the compression rate is used for the next communication of this service, that is, only after the service connection is established, the compression dictionary and compression algorithm are updated once, and the compression dictionary and compression algorithm used during a service connection remain unchanged.

[0216] Implementation manner b: Determine the update by determining that after the establishment of a service connection, the set update period is reached.

[0217] For each service that performs data compression and transmission, after the service connection is established, the compression dictionary and compression algorithm are synchronized once for the service. During the communication process, the compression dictionary and compression algorithm are updated periodically. When the period is reached, they are updated using the compression dictionary and compression algorithm output by the current model. The compression dictionary and compression algorithm used within one period remain unchanged.

[0218] Embodiment c: Determine the update by determining that the event-triggering condition is met.

[0219] As an alternative embodiment, determining that the event-triggering condition is met includes at least one of the following steps:

[0220] When it is determined that the compression rate of the service data that has been transmitted currently is lower than the preset threshold, it is determined that the event-triggering condition is met;

[0221] When the difference between the compression rate expected by the compression dictionary and compression algorithm output by the current AI model and the compression rate of the service data that has been transmitted currently is greater than the preset value, it is determined that the event-triggering condition is met.

[0222] It should be noted that the compression rate expected by the compression dictionary and compression algorithm output by the above-mentioned current AI model is the compression rate expected when using the compression dictionary and compression algorithm output by the current AI model to compress the latest transmitted service data.

[0223] It should be noted that the above event-triggering condition is only an example and does not form a specific limitation on the event-triggering condition. The specific event-triggering condition can be set according to the specific implementation situation. For example, the event-triggering condition is set as follows: When the compression rate expected by the compression dictionary and compression algorithm output by the current AI model is greater than the preset value, it is determined that the event-triggering condition is met.

[0224] Based on the above embodiments, the embodiments of the present invention provide three specific implementation manners to specifically illustrate the above method for data compression.

[0225] Embodiment 1: The base station obtains the compression dictionary and compression algorithm output by the local AI model.

[0226] As Figure 2 shown, the embodiments of the present invention provide a schematic diagram of a base station obtaining the compression dictionary and compression algorithm output by the local AI model for data compression.

[0227] The PDCP (Packet Data Convergence Protocol) layer is responsible for data compression and decompression, and performs uplink and downlink compressed data transmission over the Uu interface. The base station obtains the compression dictionary and compression algorithm output by the local AI model, and the updated compression dictionary and / or compression algorithm are directly synchronized via the Uu interface.

[0228] It should be noted that the following Embodiment 2 and Embodiment 3 both adopt the above transmission method, and will not be elaborated here.

[0229] It should be noted that in this embodiment, the data transmission devices are the base station and the user terminal UE.

[0230] Step 1: Establish a connection between the user terminal UE and the base station.

[0231] It should be noted that the interaction process between the user terminal UE and the core network is not described here, and the interaction between the user terminal UE and the core network is completed before Step 2.

[0232] Step 2: The base station determines the initialized compression dictionary and compression algorithm to be adopted.

[0233] It should be noted that the above initialized compression dictionary and compression algorithm can be determined according to the pre-set information; or determined according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0234] Step 3: The base station sends the initialized compression dictionary and compression algorithm to the user terminal UE.

[0235] It should be noted that the sending method can be an RRC message, a MAC CE, carrying the AI compression dictionary and compression algorithm in the PDCP header of the first data packet, or carrying the AI compression dictionary and compression algorithm indication information in the PDCP header of the first data packet, and using the PDCP subPDU to carry the AI compression dictionary and compression algorithm.

[0236] Step 4: The data sending ends in the base station and the user terminal UE use the above initialized compression dictionary and compression algorithm to compress and transmit the data, and the receiving end uses the above initialized compression dictionary and compression algorithm to decompress the data, and the compression ratio is statistically calculated during this process.

[0237] It should be noted that when the base station / user terminal UE is the data sending end, the data is compressed using the above initialized compression dictionary and compression algorithm, and the compressed data is sent to the user terminal UE / base station; when the base station / user terminal UE is the data receiving end, the compressed data sent by the user terminal UE / base station is received, and the above compressed data is decompressed using the above initialized compression dictionary and compression algorithm.

[0238] It should be noted that the user terminal UE sends the statistically obtained compression ratio to the base station.

[0239] Step 5: The base station adjusts the training model based on the transmitted data and the data compression ratio, and generates a new compression dictionary and compression algorithm.

[0240] It should be noted that when the base station is the data sender, the data to be transmitted is input into the AI model. The AI model extracts features from the latest transmitted service data, outputs a compression dictionary according to the correlation between the extracted features and the service data, and uses different compression algorithms to compress with the current compression dictionary, outputs the compression algorithm corresponding to the highest compression ratio, and uses the highest compression ratio as feedback input to adjust the model parameters of the AI model; when the base station is the data receiver, it receives the compressed data sent by the user terminal UE, decompresses the compressed data using the above-mentioned initialized compression dictionary and compression algorithm, inputs the decompressed data into the AI model, the AI model extracts features from the latest transmitted service data, outputs a compression dictionary according to the correlation between the extracted features and the service data, and uses different compression algorithms to compress with the current compression dictionary, outputs the compression algorithm corresponding to the highest compression ratio, and uses the highest compression ratio as feedback input to adjust the model parameters of the AI model.

[0241] It should be noted that the process of adjusting the training model and generating a new compression dictionary and compression algorithm is continuously carried out during the data transmission process.

[0242] Step 6: When it is determined that the update condition is met, the base station sends the updated compression dictionary and compression algorithm to the user terminal UE.

[0243] It should be noted that the update condition in the above Step 6 can be based on a period or event-triggered.

[0244] It should be noted that the sending method used in the above Step 6 is the same as that in Step 3, and will not be elaborated here.

[0245] Step 7: The data sender in the base station and the user terminal UE uses the new compression dictionary and compression algorithm to compress and transmit the data, and the receiver uses the new compression dictionary and compression algorithm to decompress the data, and the compression ratio is statistically obtained during this process.

[0246] It should be noted that the above implementation manner is also applicable to the implementation manner in which the user terminal UE obtains the compression dictionary and compression algorithm output by the local AI model for data compression. By swapping the operations of the base station and the user terminal UE in the above process, it can be achieved.

[0247] Embodiment 2: Obtain the compressed dictionary and compression algorithm output by the AI model from a third-party device.

[0248] As Figure 3 shown, an embodiment of the present invention provides a schematic diagram of obtaining a compressed dictionary and a compression algorithm output by an AI model from a third-party device for data compression.

[0249] It should be noted that in this embodiment, the data transmission device is a base station and a user terminal UE, and the third-party device is a cloud or edge AI compression server.

[0250] Step 1: Establish a connection between the user terminal UE and the base station.

[0251] It should be noted that for the sake of simplicity of description, the interaction process between the user terminal UE and the core network is not described here, and the interaction between the user terminal UE and the core network is completed before Step 2.

[0252] Step 2a / 2b: The user terminal UE and / or the base station request the compressed dictionary and the compression algorithm from the AI compression server.

[0253] It should be noted that the above steps can be that both sides of the data transmission device request from the AI compression server, or one end requests from the AI compression server.

[0254] Step 3: The AI compression server determines the initialized compressed dictionary and compression algorithm to be used.

[0255] It should be noted that the above initialized compressed dictionary and compression algorithm can be determined according to the pre-set information; or determined according to the compressed dictionary and compression algorithm output by the AI model when the last service transmission was completed.

[0256] Step 4a / 4b: The AI compression server sends the initialized compressed dictionary and compression algorithm to the base station and the user terminal UE.

[0257] It should be noted that in this step, the AI compression server can send the compressed dictionary and the compression algorithm to both sides of the data transmission device, or one end sends the compressed dictionary and the compression algorithm to the other end after obtaining them from the AI compression server.

[0258] Step 5: The data sending end in the base station and the user terminal UE uses the above initialized compressed dictionary and compression algorithm to compress and transmit the data, and the receiving end uses the above initialized compressed dictionary and compression algorithm to decompress the data, and the compression ratio is statistically calculated during this process.

[0259] It should be noted that when the base station / user equipment UE is the data sender, the above initialized compression dictionary and compression algorithm are used to compress the data, and the compressed data is sent to the user equipment UE / base station; when the base station / user equipment UE is the data receiver, it receives the compressed data sent by the user equipment UE / base station, and uses the above initialized compression dictionary and compression algorithm to decompress the above compressed data.

[0260] It should be noted that in this process, the base station and / or the user equipment UE send the compression ratio of the latest transmitted service data and the currently completed transmitted service data to the AI compression server.

[0261] Step 6: The AI compression server adjusts the training model based on the compression ratio of the latest transmitted service data and the currently completed transmitted service data, and generates a new compression dictionary and compression algorithm.

[0262] It should be noted that the AI compression server receives the compression ratio of the latest transmitted service data and the currently completed transmitted service data sent by the base station and / or the user equipment UE.

[0263] It should be noted that the AI compression server inputs the latest transmitted service data into the AI model, uses the AI model to extract features from the latest transmitted service data, outputs a compression dictionary according to the correlation between the extracted features and the service data, and uses different compression algorithms to compress with the current compression dictionary, outputs the compression algorithm corresponding to the highest compression ratio, and uses the highest compression ratio as the feedback input to adjust the model parameters of the AI model.

[0264] Step 7a / 7b: When it is determined that the update condition is met, the AI compression server sends the updated compression dictionary and compression algorithm to the base station and the user equipment UE.

[0265] It should be noted that the update condition of the above step 7a / 7b can be based on a period or triggered based on an event.

[0266] It should be noted that the above sending method can be that the AI compression server sends the compression dictionary and compression algorithm to both sides of the data transmission device, or one end obtains the compression dictionary and compression algorithm from the AI compression server and then sends it to the other end.

[0267] Step 8: The data sender in the base station and the user equipment UE uses the new compression dictionary and compression algorithm to compress and transmit the data, the receiver uses the new compression dictionary and compression algorithm to decompress the data, and counts the compression ratio during this process, and feeds back the data and the compression ratio to the AI compression server.

[0268] As an alternative implementation, based on the above-described second embodiment, after the above step 5, add the steps: for the connection release of this service, after the above step 6, add the steps: for the re - establishment of the connection of this service, and the step: the user equipment UE and / or the base station request a compression dictionary and a compression algorithm from the AI compression server, obtaining the third embodiment with the update condition being the determination of establishing a service connection. As Figure 4 shown, the embodiment of the present invention provides a schematic diagram of obtaining a compression dictionary and a compression algorithm output by an AI model from a third - party device and performing data compression with the update condition being the determination of establishing a service connection.

[0269] Embodiment 2

[0270] The embodiment of the present invention provides a flowchart of a method for a data transmission device to perform data compression. As Figure 5 shown, it includes:

[0271] Step S501, during the service transmission, determine the currently adopted compression dictionary and compression algorithm. Initially, an initialized compression dictionary and compression algorithm are adopted. After that, when the update condition is met, use the compression dictionary and compression algorithm output by the AI model to update the currently adopted compression dictionary and compression algorithm respectively;

[0272] Step S502, based on the currently adopted compression dictionary, use the currently adopted compression algorithm to compress or decompress the transmitted service data.

[0273] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to adjust the model parameters of the AI model.

[0274] Optionally, the method further includes:

[0275] According to the pre - set information, initialize the currently adopted compression dictionary and compression algorithm; or

[0276] When establishing a service connection, initialize the currently adopted compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the last service transmission was completed.

[0277] Optionally, determining that the update condition is met includes at least one of the following steps:

[0278] When determining that a service connection is established, the update condition is met;

[0279] When it reaches the set update period after determining that a service connection is established, the update condition is met;

[0280] When it is determined that the event trigger condition is satisfied, the update condition is satisfied.

[0281] Optionally, determining that the event trigger condition is satisfied includes at least one of the following steps:

[0282] When it is determined that the compression ratio of the service data currently transmitted is lower than a preset threshold, it is determined that the event trigger condition is satisfied;

[0283] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data currently transmitted is greater than a preset value, it is determined that the event trigger condition is satisfied.

[0284] Optionally, during the service transmission process, it further includes:

[0285] Obtaining the compression dictionary and compression algorithm output by the local AI model; or

[0286] Obtaining the compression dictionary and compression algorithm output by the local AI model and sending them to the peer data transmission device; or

[0287] Obtaining the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0288] Obtaining the compression dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or

[0289] Obtaining the compression dictionary and compression algorithm output by the AI model from a third-party device and sending them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

[0290] Optionally, the method further includes:

[0291] Sending the latest transmitted service data and the compression ratio of the service data currently transmitted to a third-party device.

[0292] An embodiment of the present invention provides a method flowchart for data compression by a third-party device, as Figure 6 shown, including:

[0293] Step S601, in response to a request from a data transmission device, obtaining the latest transmitted service data of the current service and the compression ratio of the service data currently transmitted;

[0294] Step S602, inputting the latest transmitted service data into an AI model and using the AI model to output a compression dictionary and a compression algorithm;

[0295] Step S603, sending the compression dictionary and the compression algorithm to the data transmission device.

[0296] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary based on the correlation between the extracted features and the service data, compress using different compression algorithms with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to adjust the model parameters of the AI model.

[0297] Optionally, sending the compression dictionary and the compression algorithm to the data transmission device specifically includes:

[0298] When it is determined that the update condition is met, send the compression dictionary and the compression algorithm to the data transmission device.

[0299] Optionally, determining that the update condition is met includes at least one of the following steps:

[0300] Determine that the update condition is met when the data transmission device establishes a service connection;

[0301] Determine that the update condition is met when the set update period is reached after the data transmission device establishes a service connection;

[0302] Determine that the update condition is met when the event-triggering condition is met.

[0303] Optionally, determining that the event-triggering condition is met includes at least one of the following steps:

[0304] Determine that the event-triggering condition is met when the compression rate of the currently transmitted service data is lower than the preset threshold;

[0305] Determine that the event-triggering condition is met when the difference between the expected compression rate based on the compression dictionary and the compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value.

[0306] The data transmission device for data compression provided by the embodiments of the present invention belongs to the same inventive concept as the data transmission device in Embodiment 1 of the present invention above. The various implementation manners of data compression by the data transmission device in the system provided in the above embodiments can be applied to the method for data compression in this embodiment, and will not be repeated here.

[0307] The third-party device for data compression provided by the embodiments of the present invention belongs to the same inventive concept as the third-party device in Embodiment 1 of the present invention above. The various implementation manners of data compression by the third-party device in the system provided in the above embodiments can be applied to the method for data compression in this embodiment, and will not be repeated here.

[0308] The schematic diagram of a data transmission device for data compression provided by an embodiment of the present invention is as follows Figure 7 shown, including:

[0309] a memory 701, a processor 702, a transceiver 703, and a bus interface 704.

[0310] The processor 702 is responsible for managing the bus architecture and general processing. The memory 701 can store the data used by the processor 702 when performing operations. The transceiver 703 is used to receive and transmit data under the control of the processor 702.

[0311] The bus architecture can include any number of interconnected buses and bridges, specifically various circuits represented by one or more processors represented by the processor 702 and the memory represented by the memory 701 are linked together. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore will not be further described herein. The bus interface provides an interface. The processor 702 is responsible for managing the bus architecture and general processing. The memory 701 can store the data used by the processor 702 when performing operations.

[0312] The process disclosed in the embodiment of the present invention can be applied to or implemented by the processor 702. During the implementation process, each step of the signal processing process can be completed by the integrated logic circuit in the hardware of the processor 702 or the instructions in the form of software. The processor 702 can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by the hardware processor, or executed by the combination of the hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. This storage medium is located in the memory 701, and the processor 702 reads the information in the memory 701 and combines its hardware to complete the steps of the signal processing process.

[0313] Specifically, the processor 702 is used to read the program in the memory 701 and execute:

[0314] During the service transmission process, determine the currently adopted compression dictionary and compression algorithm. Initially, the initialized compression dictionary and compression algorithm are adopted. After that, when it is determined that the update condition is met, use the compression dictionary and compression algorithm output by the AI model to update the currently adopted compression dictionary and compression algorithm respectively.

[0315] Based on the currently adopted compression dictionary, use the currently adopted compression algorithm to compress or decompress the transmitted service data.

[0316] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to adjust the model parameters of the AI model.

[0317] Optionally, the processor is further configured to:

[0318] Initialize the currently adopted compression dictionary and compression algorithm according to the pre-set information; or

[0319] When establishing a service connection, initialize the currently adopted compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0320] Optionally, when the processor determines that the update condition is met, it includes at least one of the following steps:

[0321] Determine that when establishing a service connection, the update condition is met;

[0322] Determine that when the set update period is reached after establishing a service connection, the update condition is met;

[0323] Determine that when the event-triggering condition is met, the update condition is met.

[0324] Optionally, when the processor determines that the event-triggering condition is met, it includes at least one of the following steps:

[0325] Determine that when the compression rate of the currently transmitted service data is lower than the preset threshold, the event-triggering condition is met;

[0326] Determine that when the difference between the compression rate expected according to the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value, the event-triggering condition is met.

[0327] Optionally, during the service transmission process, the processor is further configured to:

[0328] Obtain the compression dictionary and compression algorithm output by the local AI model; or

[0329] Obtain the compressed dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or

[0330] Obtain the compressed dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0331] Obtain the compressed dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or

[0332] Obtain the compressed dictionary and compression algorithm output by the AI model from a third-party device and send them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

[0333] Optionally, the processor is further configured to:

[0334] Send the compression ratio of the latest transmitted service data and the service data that has been transmitted currently to the third-party device.

[0335] An embodiment of the present invention provides a schematic diagram of a third-party device for data compression, as Figure 8 shown, including:

[0336] A memory 801, a processor 802, a transceiver 803, and a bus interface 804.

[0337] The processor 802 is responsible for managing the bus architecture and general processing. The memory 801 can store the data used by the processor 802 when performing operations. The transceiver 803 is used to receive and send data under the control of the processor 802.

[0338] The bus architecture may include any number of interconnected buses and bridges, specifically various circuits of one or more processors represented by the processor 802 and the memory represented by the memory 801 are linked together. The bus architecture can also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, so they will not be further described herein. The bus interface provides an interface. The processor 802 is responsible for managing the bus architecture and general processing. The memory 801 can store the data used by the processor 802 when performing operations.

[0339] The process disclosed in the embodiments of the present invention can be applied to or implemented by the processor 802. During implementation, each step of the signal processing process can be completed by the integrated logic circuit of the hardware in the processor 802 or the instructions in the form of software. The processor 802 can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by the hardware processor, or executed by the combination of the hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory 801, and the processor 802 reads the information in the memory 801 and combines its hardware to complete the steps of the signal processing process.

[0340] Specifically, the processor 802 is configured to read the program in the memory 801 and execute:

[0341] In response to the request of the data transmission device, obtain the service data of the latest transmission of the current service and the compression ratio of the service data that has been completed in the current transmission;

[0342] Input the service data of the latest transmission into the AI model, and use the AI model to output a compression dictionary and a compression algorithm;

[0343] Send the compression dictionary and the compression algorithm to the data transmission device.

[0344] Optionally, the AI model is used to extract features from the service data of the latest transmission, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression ratio, and use this highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0345] Optionally, when sending the compression dictionary and the compression algorithm to the data transmission device, the processor is specifically configured to:

[0346] When it is determined that the update condition is met, send the compression dictionary and the compression algorithm to the data transmission device.

[0347] Optionally, the processor determines that the update condition is met, including at least one of the following steps:

[0348] When it is determined that the data transmission device establishes a service connection, the update condition is met;

[0349] It is determined that when the data transmission device establishes a service connection and reaches the set update period, the update condition is satisfied;

[0350] It is determined that when the event-triggering condition is satisfied, the update condition is satisfied.

[0351] Optionally, the processor determines that the event-triggering condition is satisfied, including at least one of the following steps:

[0352] When it is determined that the compression ratio of the service data currently transmitted is lower than the preset threshold, it is determined that the event-triggering condition is satisfied;

[0353] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data currently transmitted is greater than the preset value, it is determined that the event-triggering condition is satisfied.

[0354] The data transmission device for data compression provided by the embodiments of the present invention belongs to the same inventive concept as the data transmission device in Embodiment 1 of the present invention above. Various implementation manners of data compression by the data transmission device in the system provided by the above embodiments can be applied to the data transmission device for data compression in this embodiment, and will not be repeated here.

[0355] The third-party device for data compression provided by the embodiments of the present invention belongs to the same inventive concept as the third-party device in Embodiment 1 of the present invention above. Various implementation manners of data compression by the third-party device in the system provided by the above embodiments can be applied to the third-party device for data compression in this embodiment, and will not be repeated here.

[0356] An embodiment of the present invention provides a schematic diagram of a device for data compression by a data transmission device, as Figure 9 shown, including:

[0357] A dictionary algorithm determination unit 901, configured to determine the currently adopted compression dictionary and compression algorithm during the service transmission process, where initially the initialized compression dictionary and compression algorithm are adopted, and then when it is determined that the update condition is satisfied, the compression dictionary and compression algorithm output by the AI model are used to update the currently adopted compression dictionary and compression algorithm respectively;

[0358] A compression unit 902, configured to compress or decompress the transmitted service data based on the currently adopted compression dictionary and using the currently adopted compression algorithm.

[0359] Optionally, the AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, compress using different compression algorithms with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to adjust the model parameters of the AI model.

[0360] Optionally, the dictionary algorithm determination unit is further configured to:

[0361] Initialize the currently used compression dictionary and compression algorithm according to preset information; or

[0362] When establishing a service connection, initialize the currently used compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed.

[0363] Optionally, the dictionary algorithm determination unit determines that the update condition is satisfied, including at least one of the following steps:

[0364] Determine that when establishing a service connection, the update condition is satisfied;

[0365] Determine that when the set update period is reached after establishing a service connection, the update condition is satisfied;

[0366] Determine that when the event-triggering condition is satisfied, the update condition is satisfied.

[0367] Optionally, the dictionary algorithm determination unit determines that the event-triggering condition is satisfied, including at least one of the following steps:

[0368] Determine that when the compression rate of the currently transmitted service data is lower than the preset threshold, the event-triggering condition is satisfied;

[0369] Determine that when the difference between the compression rate expected according to the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value, the event-triggering condition is satisfied.

[0370] Optionally, during the service transmission process, the dictionary algorithm determination unit is further configured to:

[0371] Obtain the compression dictionary and compression algorithm output by the local AI model; or

[0372] Obtain the compression dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or

[0373] Obtain the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or

[0374] Obtain a compression dictionary and a compression algorithm output by an AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or

[0375] Obtain a compression dictionary and a compression algorithm output by an AI model from a third-party device, and send them to a peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

[0376] Optionally, the compression unit is further configured to:

[0377] Send the latest transmitted service data and the compression ratio of the service data that has been currently transmitted to a third-party device.

[0378] An embodiment of the present invention provides a device for a third-party device to perform data compression, as Figure 10 shown, including:

[0379] A data receiving unit 1001, configured to obtain the latest transmitted service data of the current service and the compression ratio of the service data that has been currently transmitted in response to a request from a data transmission device;

[0380] A dictionary algorithm generation unit 1002, configured to input the latest transmitted service data into an AI model, and output a compression dictionary and a compression algorithm by using the AI model;

[0381] A data sending unit 1003, configured to send the compression dictionary and the compression algorithm to the data transmission device.

[0382] Optionally, the AI model is used to perform feature extraction on the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression ratio, and use this highest compression ratio as a feedback input to adjust the model parameters of the AI model.

[0383] Optionally, when sending the compression dictionary and the compression algorithm to the data transmission device, the data sending unit is specifically configured to:

[0384] Determine that when an update condition is met, send the compression dictionary and the compression algorithm to the data transmission device.

[0385] Optionally, the data sending unit determines that an update condition is met, including at least one of the following steps:

[0386] Determine that when the data transmission device establishes a service connection, the update condition is met;

[0387] Determine that when a set update period arrives after the data transmission device establishes a service connection, the update condition is met;

[0388] When it is determined that the event-triggering condition is met, the update condition is met.

[0389] Optionally, the data sending unit determines that the event-triggering condition is met, including at least one of the following steps:

[0390] When it is determined that the compression ratio of the service data currently transmitted is lower than the preset threshold, it is determined that the event-triggering condition is met;

[0391] When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data currently transmitted is greater than the preset value, it is determined that the event-triggering condition is met.

[0392] The data compression device provided in the embodiments of the present invention belongs to the same inventive concept as the data transmission device in Embodiment 1 of the present invention above. The various implementation manners of data compression by the data transmission device in the system provided in the above embodiments can be applied to the data compression device in this embodiment, and will not be repeated here.

[0393] The data compression device provided in the embodiments of the present invention belongs to the same inventive concept as the third-party device in Embodiment 1 of the present invention above. The various implementation manners of data compression by the third-party device in the system provided in the above embodiments can be applied to the data compression device in this embodiment, and will not be repeated here.

[0394] The present invention also provides a processor-readable storage medium, which stores a computer program for causing the processor to execute the steps of a data compression method applied to a data transmission device provided in Embodiment 1 above.

[0395] The present invention also provides a processor-readable storage medium, which stores a computer program for causing the processor to execute the steps of a data compression method applied to a third-party device provided in Embodiment 1 above.

[0396] In the several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the device or module can be in an electrical, mechanical or other form.

[0397] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module, that is, it may be located in one place, or it may be distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0398] In addition, in each embodiment of this application, each functional module can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0399] In the above embodiment, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0400] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. 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 a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0401] The above has introduced the technical solution provided by this application in detail. Specific examples are used in this application to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

[0402] Those skilled in the art should understand that the embodiments of this application can be provided as a method, a system, or a computer program product. Therefore, this application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0403] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0404] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements in the process Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0405] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0406] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

1. A method for data compression, applied to a data transmission device, characterized in that The method includes: During the service transmission process, determine the currently adopted compression dictionary and compression algorithm. Initially, an initialized compression dictionary and compression algorithm are adopted. After that, when it is determined that the update condition is met, use the compression dictionary and compression algorithm output by the AI model to update the currently adopted compression dictionary and compression algorithm respectively. When establishing a service connection, initialize the currently adopted compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed; Based on the currently adopted compression dictionary, use the currently adopted compression algorithm to compress or decompress the transmitted service data, where: The AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as a feedback input to continuously adjust the parameters of the AI model through a self-learning mechanism, continuously strengthen the ability to extract dictionary words by analyzing the correlation features of the input data, and adjust in the positive direction of increasing the compression rate; During the service transmission process, it also includes: Obtain the compression dictionary and compression algorithm output by the local AI model; or Obtain the compression dictionary and compression algorithm output by the local AI model and send them to the peer data transmission device; or Obtain the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or Obtain the compression dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or Obtain the compression dictionary and compression algorithm output by the AI model from a third-party device and send them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

2. The method according to claim 1, wherein Determining that the update condition is met includes at least one of the following steps: Determine that when establishing a service connection, the update condition is met; Determine that when the set update period is reached after establishing a service connection, the update condition is met; Determine that when the event-triggering condition is met, the update condition is met.

3. The method according to claim 2, characterized in that, Determining that the event-triggering condition is met includes at least one of the following steps: Determine that when the compression rate of the currently transmitted service data is lower than the preset threshold, the event-triggering condition is met; When the difference between the expected compression rate according to the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently transmitted service data is greater than the preset value, determine that the event-triggering condition is met.

4. The method according to claim 1, wherein It also includes: Send the latest transmitted service data and the compression rate of the currently transmitted service data to the third-party device.

5. A method for data compression, characterized in that, Applied to a third-party device, it includes: In response to the request of the data transmission device, obtain the latest transmitted service data and the compression rate of the currently transmitted service data of the current service; Input the latest transmitted service data into the AI model and use the AI model to output a compression dictionary and compression algorithm; Send the compression dictionary and compression algorithm to the data transmission device, where: The AI model is used to extract features from the latest transmitted service data, output a compression dictionary based on the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to continuously adjust the parameters of the AI model through a self-learning mechanism, continuously strengthening the ability to extract dictionary words by analyzing the correlation features of the input data, and adjusting in the positive direction of increasing the compression rate.

6. The method according to claim 5, wherein Sending the compression dictionary and the compression algorithm to the data transmission device specifically includes: When it is determined that the update condition is met, sending the compression dictionary and the compression algorithm to the data transmission device.

7. The method according to claim 6, wherein Determining that the update condition is met includes at least one of the following steps: When it is determined that the data transmission device establishes a service connection, the update condition is met; When it is determined that after the data transmission device establishes a service connection, when the set update period is reached, the update condition is met; When it is determined that the event-triggering condition is met, the update condition is met.

8. The method according to claim 7, wherein Determining that the event-triggering condition is met includes at least one of the following steps: When it is determined that the compression rate of the currently completed transmitted service data is lower than the preset threshold, it is determined that the event-triggering condition is met; When the difference between the expected compression rate based on the compression dictionary and compression algorithm output by the current AI model and the compression rate of the currently completed transmitted service data is greater than the preset value, it is determined that the event-triggering condition is met.

9. A data transmission device for performing data compression, characterized in that, Including a memory, a transceiver, and a processor: The memory is used to store computer programs; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations: During the service transmission process, determine the currently used compression dictionary and compression algorithm. Initially, the initialized compression dictionary and compression algorithm are used. After that, when it is determined that the update condition is met, use the compression dictionary and compression algorithm output by the AI model to update the currently used compression dictionary and compression algorithm respectively. Among them, when establishing a service connection, initialize the currently used compression dictionary and compression algorithm according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed; Based on the currently used compression dictionary, use the currently used compression algorithm to compress or decompress the transmitted service data, where: The AI model is used to extract features from the latest transmitted service data, output a compression dictionary based on the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to continuously adjust the parameters of the AI model through a self-learning mechanism, continuously strengthening the ability to extract dictionary words by analyzing the correlation features of the input data, and adjusting in the positive direction of increasing the compression rate; During the service transmission process, the processor is further used for: Obtaining the compression dictionary and compression algorithm output by the local AI model; or Obtaining the compression dictionary and compression algorithm output by the local AI model and sending them to the peer data transmission device; or Obtain the compressed dictionary and compression algorithm output by the AI model from the peer data transmission device; or Obtain the compressed dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or Obtain the compressed dictionary and compression algorithm output by the AI model from a third-party device and send them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

10. The data transmission device according to claim 9, characterized in that, The processor determines that the update condition is satisfied, including at least one of the following steps: Determine that the update condition is satisfied when a service connection is established; Determine that the update condition is satisfied when the set update period is reached after the service connection is established; Determine that the update condition is satisfied when an event-triggering condition is satisfied.

11. The data transmission device according to claim 10, wherein, The processor determines that the event-triggering condition is satisfied, including at least one of the following steps: Determine that the event-triggering condition is satisfied when the compression ratio of the service data currently transmitted is lower than a preset threshold; Determine that the event-triggering condition is satisfied when the difference between the compression ratio expected by the compressed dictionary and compression algorithm output by the current AI model and the compression ratio of the service data currently transmitted is greater than a preset value.

12. The data transmission device according to claim 9, wherein The processor is further configured to: Send the latest transmitted service data and the compression ratio of the service data currently transmitted to the third-party device.

13. A third-party device for data compression, characterized in that, Including a memory, a transceiver, and a processor: The memory is used to store computer programs; the transceiver is used to transmit and receive data under the control of the processor; the processor is used to read the computer programs in the memory and perform the following operations: In response to a request from the data transmission device, obtain the latest transmitted service data of the current service and the compression ratio of the service data currently transmitted; Input the latest transmitted service data into the AI model and use the AI model to output a compressed dictionary and a compression algorithm; Send the compressed dictionary and the compression algorithm to the data transmission device, where: The AI model is used to extract features from the latest transmitted service data, output a compressed dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compressed dictionary, output the compression algorithm corresponding to the highest compression ratio, and use the highest compression ratio as a feedback input, continuously adjust the parameters of the AI model through a self-learning mechanism, continuously strengthen the ability to extract dictionary words by analyzing the correlation features of the input data, and adjust in the positive direction of increasing the compression ratio.

14. The third-party device according to claim 13, wherein Send the compressed dictionary and the compression algorithm to the data transmission device, and the processor is specifically configured to: When it is determined that the update condition is satisfied, send the compressed dictionary and the compression algorithm to the data transmission device.

15. The third-party device according to claim 14, wherein The processor determines that the update condition is satisfied, including at least one of the following steps: Determine that the update condition is satisfied when the data transmission device establishes a service connection; Determine that the update condition is satisfied when the set update period is reached after the data transmission device establishes a service connection; Determine that the update condition is satisfied when an event-triggering condition is satisfied.

16. The third-party device according to claim 15, wherein, The processor determines that the event-triggering condition is satisfied, including at least one of the following steps: When it is determined that the compression ratio of the service data that has completed transmission currently is lower than the preset threshold, it is determined that the event trigger condition is met; When the difference between the compression ratio expected by the compression dictionary and compression algorithm output by the current AI model and the compression ratio of the service data that has completed transmission currently is greater than the preset value, it is determined that the event trigger condition is met.

17. A device for data compression, characterized in that, It includes: A dictionary algorithm determination unit, which is used to determine the compression dictionary and compression algorithm currently adopted during the service transmission process. Initially, the initialized compression dictionary and compression algorithm are adopted. After that, when it is determined that the update condition is met, the compression dictionary and compression algorithm output by the AI model are used to update the compression dictionary and compression algorithm currently adopted respectively. Among them, when establishing a service connection, according to the compression dictionary and compression algorithm output by the AI model when the previous service transmission was completed, the compression dictionary and compression algorithm currently adopted are initialized; A compression unit, which is used to compress or decompress the transmitted service data based on the currently adopted compression dictionary and using the currently adopted compression algorithm, where: The AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression ratio, and use the highest compression ratio as the feedback input. Through the self-learning mechanism, the parameters of the AI model are continuously adjusted, and the ability to extract dictionary words by analyzing the correlation features of the input data is continuously strengthened, and it is adjusted in the positive direction of increasing the compression ratio; During the service transmission process, the dictionary algorithm determination unit is also used for: Obtaining the compression dictionary and compression algorithm output by the local AI model; or Obtaining the compression dictionary and compression algorithm output by the local AI model and sending them to the peer data transmission device; or Obtaining the compression dictionary and compression algorithm output by the AI model from the peer data transmission device; or Obtaining the compression dictionary and compression algorithm output by the AI model from a third-party device, where the third-party device is a device of a functional node located in the cloud or at the edge; or Obtaining the compression dictionary and compression algorithm output by the AI model from a third-party device and sending them to the peer data transmission device, where the third-party device is a device of a functional node located in the cloud or at the edge.

18. A device for data compression, characterized in that, It includes: A data receiving unit, which is used to obtain the latest transmitted service data of the current service and the compression ratio of the service data that has completed transmission currently in response to the request of the data transmission device; A dictionary algorithm generation unit, which is used to input the latest transmitted service data into the AI model and use the AI model to output a compression dictionary and a compression algorithm; A data sending unit, which is used to send the compression dictionary and compression algorithm to the data transmission device, where: The AI model is used to extract features from the latest transmitted service data, output a compression dictionary according to the correlation between the extracted features and the service data, and use different compression algorithms to compress with the current compression dictionary, output the compression algorithm corresponding to the highest compression rate, and use the highest compression rate as feedback input to continuously adjust the parameters of the AI model through a self-learning mechanism, continuously strengthen the ability to extract dictionary words by analyzing the correlation features of the input data, and adjust in the positive direction of increasing the compression rate.

19. A processor-readable storage medium, characterized in that, The processor-readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the method according to any one of claims 1 to 4 or claims 5 to 8.

Images