Data processing methods, devices, system, medium, and computer program product

Abstract

The present disclosure relates to data processing methods, devices, a system, a medium, and a computer program product. A data processing method executed by means of a first device comprises: processing first data on the basis of a correlation coefficient matrix and a principal component analysis algorithm, so as to obtain second data; and sending a first message to a second device, wherein the first message is obtained on the basis of the second data. The present disclosure can improve the accuracy of the second data, which is obtained by means of dimensionality reduction, and reduce the degree of distortion of data obtained by means of performing reconstruction on the basis of a dimensionality reduction result.

Description

Data processing method, device, system, medium and computer program product TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a data processing method, device, system, medium and computer program product. BACKGROUND

[0002] With the popularity of audio services, the use of audio scenarios increases. In order to reduce the uplink and downlink resource scheduling pressure caused by the transmission of large amount of audio data, a principal component analysis (PCA) algorithm can be used to reduce the dimension or compress the audio data before sending the audio data. However, how to obtain more optimal reduced dimension data and reduce the distortion degree of reconstructed data is an urgent problem to be solved.

[0003] SUMMARY

[0004] Embodiments of the present disclosure provide a data processing method, device, system, medium and computer program product.

[0005] According to a first aspect of embodiments of the present disclosure, a data processing method is provided, executed by a first device, and the method comprises: processing first data based on a correlation coefficient matrix and a principal component analysis algorithm to obtain second data; and sending a first message to a second device, the first message being obtained based on the second data.

[0006] According to a second aspect of embodiments of the present disclosure, a data processing method is provided, executed by a second device, and the method comprises: receiving a first message sent by a first device, the first message being obtained by the first device based on second data, the second data being obtained by the first device by processing first data based on a correlation coefficient matrix and a principal component analysis algorithm.

[0007] According to a third aspect of embodiments of the present disclosure, a first device is provided, comprising: a processing module configured to process first data based on a correlation coefficient matrix and a principal component analysis algorithm to obtain second data; and a transceiver module configured to send a first message to a second device, the first message being obtained based on the second data.

[0008] According to a fourth aspect of embodiments of the present disclosure, a second device is provided, comprising: a transceiver module configured to receive a first message sent by a first device, the first message being obtained by the first device based on second data, the second data being obtained by the first device by processing first data based on a correlation coefficient matrix and a principal component analysis algorithm.

[0009] According to a fifth aspect of the embodiments of the present disclosure, a first device is provided, including: one or more processors; a memory coupled to the processors, and having stored thereon executable instructions that, when executed by the processors, cause the first device to perform the data processing method of the first aspect.

[0010] According to a sixth aspect of the embodiments of the present disclosure, a second device is provided, including: one or more processors; a memory coupled to the processors, and having stored thereon executable instructions that, when executed by the processors, cause the second device to perform the data processing method of the second aspect.

[0011] According to a seventh aspect of the embodiments of the present disclosure, a communication system is provided, including a first device and a second device, wherein the first device is configured to implement the data processing method of the first aspect, and the second device is configured to implement the data processing method of the second aspect.

[0012] According to an eighth aspect of the embodiments of the present disclosure, a storage medium is provided, and the storage medium stores instructions, which, when executed on a communication device, cause the communication device to perform the data processing method of the first aspect or the second aspect.

[0013] According to a ninth aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program and / or instructions, which, when executed on a communication device, implement the data processing method of the first aspect or the second aspect.

[0014] With the above technical solutions, at least the following beneficial technical effects can be achieved:

[0015] Since the correlation coefficient matrix is less affected by the scale difference between data, the data dimension reduction processing manner of the present disclosure based on the correlation coefficient matrix and the principal component analysis algorithm can reduce the dimension reduction interference caused by the scale difference between data, improve the accuracy of the second data obtained by dimension reduction, and reduce the distortion degree of the data reconstructed according to the dimension reduction result. That is, the distortion degree of the data reconstructed according to the second data is lower. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following describes the drawings required for the embodiments, and the following drawings are only some embodiments of the present disclosure, and do not specifically limit the protection scope of the present disclosure.

[0017] FIG. 1 is one exemplary schematic diagram of the architecture of a communication system according to the embodiments of the present disclosure.

[0018] FIG. 2 is one of the interaction diagrams of a data processing method according to an embodiment of the present disclosure.

[0019] FIG. 3A is one of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0020] FIG. 3B is another of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0021] FIG. 3C is a third of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0022] FIG. 3D is a fourth of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0023] FIG. 4 is a fifth of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0024] FIG. 5 is another of the interaction diagrams of a data processing method according to an embodiment of the present disclosure.

[0025] FIG. 6A is a sixth of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0026] FIG. 6B is one of the original data matrix diagrams according to an embodiment of the present disclosure.

[0027] FIG. 6C is one of the reconstruction matrices corresponding to the way of principal component analysis using covariance matrix according to an embodiment of the present disclosure.

[0028] FIG. 6D is another of the reconstruction matrices corresponding to the way of principal component analysis using correlation coefficient matrix according to an embodiment of the present disclosure.

[0029] FIG. 6E is a seventh of the flow diagrams of a data processing method according to an embodiment of the present disclosure.

[0030] FIG. 6F is another of the original data matrix diagrams according to an embodiment of the present disclosure.

[0031] FIG. 6G is a third of the reconstruction matrices corresponding to the way of principal component analysis using covariance matrix according to an embodiment of the present disclosure.

[0032] FIG. 6H is a fourth of the reconstruction matrices corresponding to the way of combining Box-Cox algorithm and principal component analysis algorithm using covariance matrix according to an embodiment of the present disclosure.

[0033] FIG. 6I is a fifth of the reconstruction matrices corresponding to the way of combining Box-Cox and principal component analysis using correlation coefficient matrix according to an embodiment of the present disclosure.

[0034] FIG. 6J is a comparison diagram of verification results of two principal component analysis manners, according to an embodiment of the present disclosure.

[0035] FIG. 7A is a structural schematic diagram of a first device, according to an embodiment of the present disclosure.

[0036] FIG. 7B is a structural schematic diagram of a second device, according to an embodiment of the present disclosure.

[0037] FIG. 8A is a structural schematic diagram of a communication device, according to an embodiment of the present disclosure.

[0038] FIG. 8B is a structural schematic diagram of a chip, according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] The present disclosure provides a data processing method, device, system, medium and computer program product.

[0040] In the first aspect, the present disclosure provides a data processing method, performed by a first device, the method comprising: processing first data based on a correlation coefficient matrix and a principal component analysis algorithm to obtain second data; and sending a first message to a second device, the first message being obtained based on the second data.

[0041] In the above embodiments, since the correlation coefficient matrix is less affected by the scale difference between data, the principal component analysis of the first data based on the correlation coefficient matrix and the principal component analysis algorithm can reduce the dimension reduction interference caused by the scale difference between data, and improve the accuracy of the second data obtained by dimension reduction. Transmitting the second data after dimension reduction can improve transmission efficiency and reduce consumption of transmission resources. Specifically, the principal component analysis (PCA) algorithm based on the covariance matrix focuses more on data with larger values, and the correlation coefficient matrix is less affected by the scale difference between data than the covariance matrix. Compared with the principal component analysis of the first data based on the covariance matrix (for example, PCA), the way of performing data dimension reduction on the first data based on the correlation coefficient matrix can obtain more accurate dimension reduction results.

[0042] In some embodiments of the first aspect, the first data is multimedia data to be transmitted, and the multimedia data includes audio data.

[0043] In the above embodiments, the multimedia data, for example, audio data, can be processed by data dimension reduction based on the correlation coefficient matrix, so as to obtain an audio data dimension reduction result with high accuracy.

[0044] In some embodiments of the first aspect, in some embodiments, the data dimension reduction processing on the first data based on the correlation coefficient matrix and the principal component analysis algorithm to obtain the second data comprises: determining the correlation coefficient matrix corresponding to the first data; performing eigenvalue decomposition on the correlation coefficient matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors, wherein one eigenvalue corresponds to one eigenvector, and the eigenvalue indicates the variance of the first data distributed in a first direction, and the first direction is the direction of the eigenvector corresponding to the eigenvalue; selecting N eigenvectors from the plurality of eigenvectors to form a dimension reduction matrix, wherein N is a natural number; and projecting the first data to the space indicated by the dimension reduction matrix to obtain the second data.

[0045] Optionally, selecting N eigenvectors from the plurality of eigenvectors to form a dimension reduction matrix comprises: selecting N eigenvectors corresponding to N eigenvalues in descending order of the eigenvalues to form a dimension reduction matrix.

[0046] In the above embodiments, the correlation coefficient matrix can overcome the problem that the covariance matrix is difficult to process due to large data scale difference and abnormal values, and the selection of principal component components (i.e., main eigenvectors / core eigenvectors) needs the distribution of data variance as a basis for judgment. Although the correlation coefficient matrix does not directly represent the distribution of data variance like the covariance matrix, the correlation coefficient matrix can also effectively reflect the distribution of data variance. Therefore, when processing data with large data scale difference, the effect of selecting principal component components based on the correlation coefficient matrix is obviously better than that of selecting principal component components based on the covariance matrix, that is, the performance of the principal component analysis method based on the correlation coefficient matrix is better than that of the principal component analysis method based on the covariance matrix. That is, by performing eigenvalue decomposition on the correlation coefficient matrix of the first data, a dimension reduction matrix (i.e., a principal component matrix) with higher accuracy and retaining most of the information in the first data can be obtained, and more accurate second data can be obtained according to the dimension reduction matrix. The second data after dimension reduction is less likely to be distorted.

[0047] In some embodiments of the first aspect, in some embodiments, the determining the correlation coefficient matrix corresponding to the first data comprises: obtaining a data matrix of the first data; preprocessing the data matrix; and determining the correlation coefficient matrix based on the preprocessed data matrix.

[0048] In the above embodiments, the correlation coefficient matrix with high accuracy can be more easily calculated based on the preprocessed data matrix.

[0049] In some embodiments of the first aspect, in some embodiments, the preprocessing comprises at least one of the following:

[0050] power transformation processing;

[0051] standardization processing;

[0052] centering processing.

[0053] In the above embodiments, by performing at least one of the power transformation processing, the standardization processing, and the centering processing on the data matrix of the first data, the accuracy of the subsequent data processing result can be improved.

[0054] In some embodiments of the first aspect, in some embodiments, the preprocessing of the data matrix comprises: performing standardization processing on the data matrix, wherein each column vector of the data matrix after the standardization processing has a mean value of 0 and a variance of 1.

[0055] In the above embodiments, the importance of each feature in the first data in the dimensionality reduction process can be guaranteed to be the same, and thus the accuracy of the data processing result can be improved.

[0056] In some embodiments of the first aspect, in some embodiments, the preprocessing of the data matrix comprises: performing power transformation processing on the data matrix; and performing standardization processing on the data matrix after the power transformation processing.

[0057] In the above embodiments, the way of performing data dimensionality reduction processing on the first data based on the correlation coefficient matrix has a better dimensionality reduction effect when the data matrix of the first data conforms to the normal distribution. The power transformation processing can improve the normality of the vector data and make it more conform to the normal distribution. Therefore, by performing power transformation processing on the data matrix of the first data, the accuracy of the dimensionality reduction result can be improved. Since the power transformation processing increases the scale difference between data, the data matrix after the power transformation processing can be subjected to standardization processing to weaken the influence of the power transformation processing on the data scale.

[0058] In some embodiments of the first aspect, in some embodiments, the power transformation processing of the data matrix comprises: performing power transformation on the data matrix according to a Box-Cox algorithm.

[0059] In the above embodiments, the data matrix of the first data can be subjected to power transformation processing by the Box-Cox algorithm.

[0060] In some embodiments of the first aspect, in some embodiments, the preprocessing of the data matrix further comprises: performing centering processing on the data matrix after the standardization processing.

[0061] In the above embodiment, the data matrix after the standardization processing is subjected to the centering processing, so that the data calculation difficulty is reduced and the data processing efficiency is improved.

[0062] In a second aspect, the embodiments of the present disclosure provide a data processing method, executed by a second device, the method comprising: receiving a first message sent by a first device, the first message being obtained by the first device based on second data, the second data being obtained by the first device based on a correlation coefficient matrix and a principal component analysis algorithm for data dimension reduction processing on first data.

[0063] In some embodiments of the second aspect, in some embodiments, the first message further comprises a dimension reduction matrix, and the method further comprises: reconstructing the second data according to the dimension reduction matrix to obtain the first data.

[0064] In the above embodiment, the second data is reconstructed according to the dimension reduction matrix, so that the reconstructed result of the first data closer to the original data can be obtained, the data transmission efficiency is improved, the data loss is reduced, and the effectiveness of the data is guaranteed.

[0065] In some embodiments of the second aspect, in some embodiments, the first data is multimedia data, and the multimedia data comprises audio data.

[0066] In some embodiments of the second aspect, in some embodiments, the second data is obtained by the first device through the following formula: the first device determines the correlation coefficient matrix corresponding to the first data; the first device performs eigenvalue decomposition on the correlation coefficient matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors, wherein one eigenvalue corresponds to one eigenvector, and the eigenvalue represents the variance of the first data distributed in the direction of the corresponding eigenvector; the first device selects N eigenvectors in descending order of the eigenvalues to form a dimension reduction matrix, wherein N is a natural number; and the first device projects the first data to the space indicated by the dimension reduction matrix to obtain the second data.

[0067] In some embodiments of the second aspect, in some embodiments, the correlation coefficient matrix is determined by the first device through the following manner: the first device obtains a data matrix of the first data; the first device pre-processes the data matrix; and the first device calculates the correlation coefficient matrix according to the pre-processed data matrix.

[0068] In some embodiments of the second aspect, in some embodiments, the pre-processing comprises at least one of the following:

[0069] power transformation processing;

[0070] Standardization processing

[0071] Centralization processing.

[0072] In a third aspect, an embodiment of the present disclosure provides a first device, the first device comprising at least one of a transceiver module and a processing module; wherein the first device is configured to perform the optional implementation manner of the first aspect.

[0073] In a fourth aspect, an embodiment of the present disclosure provides a second device, the second device comprising at least one of a transceiver module and a processing module; wherein the second device is configured to perform the optional implementation manner of the second aspect.

[0074] In a fifth aspect, an embodiment of the present disclosure provides a first device, the first device comprising one or more processors; wherein the first device is configured to perform the optional implementation manner of the first aspect.

[0075] In a sixth aspect, an embodiment of the present disclosure provides a second device, the second device comprising one or more processors; wherein the second device is configured to perform the optional implementation manner of the second aspect.

[0076] In a seventh aspect, an embodiment of the present disclosure provides a communication system, the communication system comprising: a first device and a second device; wherein the first device is configured to perform the method described in the optional implementation manner of the first aspect, and the second device is configured to perform the method described in the optional implementation manner of the second aspect.

[0077] In an eighth aspect, an embodiment of the present disclosure provides a storage medium, the storage medium storing instructions, when the instructions are executed on a communication device, causing the communication device to perform the method described in the optional implementation manner of the first aspect and the second aspect.

[0078] In a ninth aspect, an embodiment of the present disclosure provides a program product, when the program product is executed by a communication device, causing the communication device to perform the method described in the optional implementation manner of the first aspect and the second aspect.

[0079] In a tenth aspect, an embodiment of the present disclosure provides a computer program, when the computer program is executed on a computer, causing the computer to perform the method described in the optional implementation manner of the first aspect and the second aspect.

[0080] In an eleventh aspect, an embodiment of the present disclosure provides a chip or a chip system. The chip or the chip system comprises processing circuitry configured to perform the method described in the optional implementation manner of the first aspect and the second aspect.

[0081] It is understood that the first device, the second device, the communication system, the storage medium, the program product, the computer program, the chip, or the chip system described above are all used to perform the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0082] This disclosure provides a data processing method, apparatus, system, medium, and computer program product. In some embodiments, the terms "data processing method" and "information processing method," "principal component analysis optimization method based on relational matrix," etc., can be used interchangeably; the terms "data processing apparatus" and "information processing apparatus," "principal component analysis optimization apparatus based on relational matrix," etc., can be used interchangeably; and the terms "communication system" and "data processing system," "information processing system," "principal component analysis optimization system based on relational matrix," etc., can be used interchangeably.

[0083] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0084] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0085] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0086] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0087] In the embodiments disclosed herein, "multiple" refers to two or more.

[0088] In some embodiments, the terms “at least one of,” “one or more of,” “a plurality of,” “multiple,” and the like can be used interchangeably.

[0089] In some embodiments, the recitations of “at least one of A, B,” “A and / or B,” “A in one case and B in another case,” “A in response to one case and B in response to another case,” and the like can include the following technical solutions according to the case: A is executed in some embodiments (A is executed regardless of B); B is executed in some embodiments (B is executed regardless of A); A and B are selectively executed in some embodiments (A and B are selectively executed); A and B are executed in some embodiments (A and B are both executed). When there are more branches such as A, B, C, and the like, the above is similar.

[0090] In some embodiments, the recitations of “A or B,” and the like, can include the following technical solutions according to the case: A is executed in some embodiments (A is executed regardless of B); B is executed in some embodiments (B is executed regardless of A); A and B are selectively executed in some embodiments (A and B are selectively executed). When there are more branches such as A, B, C, and the like, the above is similar.

[0091] The prefix words “first,” “second,” and the like in the embodiments of the present disclosure are merely used to distinguish different description objects, and do not constitute a limitation on the position, order, priority, quantity, or content of the description objects. The description of the description objects should refer to the description in the context of the claims or embodiments, and should not constitute an additional limitation because of the use of the prefix words. For example, the description objects are “fields,” and the ordinal words before “fields” in “first field” and “second field” do not limit the position or order between “fields,” and “first” and “second” do not limit whether the “fields” modified thereby are in the same message or not, nor do they limit the order of “first field” and “second field.” For another example, the description objects are “levels,” and the ordinal words before “levels” in “first level” and “second level” do not limit the priority between “levels.” For another example, the quantity of the description objects is not limited by the ordinal words, and can be one or more. For example, “first device,” where the quantity of “devices” can be one or more. In addition, the objects modified by different prefix words can be the same or different, for example, the description objects are “devices,” and “first device” and “second device” can be the same device or different devices, and their types can be the same or different; for another example, the description objects are “information,” and “first information” and “second information” can be the same information or different information, and their contents can be the same or different.

[0092] In some embodiments, "comprising", "including", "to indicate", "carrying", can be interpreted as directly carrying A, or indirectly indicating A.

[0093] In some embodiments, the terms "in response to", "in response to determining", "in the case of", "when", "when", "if", "if" and the like can be replaced with each other.

[0094] In some embodiments, the terms "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", "above" and the like can be replaced with each other, and the terms "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", "below" and the like can be replaced with each other.

[0095] In some embodiments, the device and the like can be interpreted as physical or virtual, and the name is not limited to the name described in the embodiments. The terms "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", "subject" and the like can be replaced with each other.

[0096] In some embodiments, "network" can be interpreted as a device (for example, access network device, core network device, etc.) contained in the network.

[0097] In some embodiments, the terms “access network device (AN device),” “radio access network device (RAN device),” “base station (BS),” “radio base station,” “fixed station,” “node,” “access point,” “transmission point (TP),” “reception point (RP),” “transmission / reception point (TRP),” “panel,” “antenna panel,” “antenna array,” “cell,” “macro cell,” “small cell,” “femto cell,” “pico cell,” “sector,” “cell group,” “serving cell,” “carrier,” “component carrier,” “bandwidth part (BWP),” and the like can be used interchangeably.

[0098] In some embodiments, the terms "terminal," "terminal device," "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," and so on can be replaced with each other.

[0099] In some embodiments, the access network device, the core network device, or the network device can be replaced with a terminal. For example, the embodiments of the present disclosure can also be applied to a structure in which communication between the access network device, the core network device, or the network device and the terminal is replaced with communication between a plurality of terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the terminal can also be configured to have all or part of the functions of the access network device. In addition, the terms "uplink," "downlink," and the like can also be replaced with terms corresponding to the inter-terminal communication (e.g., "side"). For example, the uplink channel, the downlink channel, and the like can be replaced with the side channel, and the uplink, the downlink, and the like can be replaced with the sidelink.

[0100] In some embodiments, the terminal can be replaced with the access network device, the core network device, or the network device. In this case, the access network device, the core network device, or the network device can also be configured to have all or part of the functions of the terminal.

[0101] In some embodiments, the data, information, etc. can be obtained in compliance with the laws and regulations of the country in which the location is situated.

[0102] In some embodiments, the data, information, etc. can be obtained after obtaining the consent of the user.

[0103] In addition, each element, each row, or each column in the table of the embodiments of the present disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0104] FIG. 1 is a schematic diagram of an architecture of a communication system according to an embodiment of the present disclosure. As shown in FIG. 1, the communication system 100 can include a first device 101 and a second device 102.

[0105] In some embodiments, the first device 101 includes at least one of a mobile phone, a wearable device, an Internet of Things device, a car with communication function, a smart car, a Pad, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in smart city, a wireless terminal device in smart home, etc., but is not limited thereto.

[0106] In some embodiments, the first device 101 can include at least one of an access network device and a core network device.

[0107] Optionally, the first device 101 is an access network device. Optionally, the access network device is at least one of a node or device that accesses a terminal to a wireless network, and the access network device can include at least one of an evolved node B (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation node B (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an open base station (Open RAN), a cloud base station (Cloud RAN), a base station in other communication systems, an access node in a Wi-Fi system, but is not limited thereto.

[0108] In some embodiments, the first device 101 is a base station. Optionally, the base station is at least one of a macro base station, a micro base station (also referred to as a small station), a relay station, an access point, a 5G base station or a future base station, a satellite, a transmitting and receiving point (TRP), a transmitting point (TP), a mobile switching center, or other devices that perform a base station function in a communication system, etc., and the embodiments of the present disclosure do not make specific limitations thereto. For the convenience of description, in all embodiments of the present disclosure, the apparatus that provides a wireless communication function for a terminal device is collectively referred to as a network device, an access network device, or a base station.

[0109] In some embodiments, the first device 101 is a core network device. Optionally, the core network device can be one device including all or part of the first network element, the second network element, etc., or can be a plurality of devices or device groups including all or part of the first network element, the second network element, etc. The network element can be virtual or physical. The core network includes at least one of an evolved packet core (EPC), a 5G core network (5GCN), a next generation core (NGC), for example.

[0110] In some embodiments, the second device 102 includes at least one of a mobile phone, a wearable device, an Internet of Things device, a communication-capable car, a smart car, a tablet (Pad), a wireless transceiver-equipped computer, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical surgery, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, a wireless terminal device in a smart home, and the like, but is not limited thereto.

[0111] In some embodiments, the second device 102 can include at least one of an access network device and a core network device.

[0112] Optionally, the second device 102 is an access network device. Optionally, the access network device is at least one of a node or a device that accesses a terminal to a wireless network, and the access network device can include at least one of an evolved NodeB (eNB) in a 5G communication system, a next generation eNB (ng-eNB), a next generation NodeB (gNB), a node B (NB), a home node B (HNB), a home evolved node B (HeNB), a wireless backhaul device, a radio network controller (RNC), a base station controller (BSC), a base transceiver station (BTS), a base band unit (BBU), a mobile switching center, a base station in a 6G communication system, an Open RAN, a Cloud RAN, a base station in other communication systems, an access node in a Wi-Fi system, and the like, but is not limited thereto.

[0113] In some embodiments, the second device 102 is a base station. Optionally, the base station is, for example, a macro base station, a micro base station (also known as a small station), a relay station, an access point, a 5G base station or a future base station, a satellite, a transmitting and receiving point (TRP), a transmitting point (TP), a mobile switching center, or other devices that perform the functions of a base station in a communication system, and the like, and the embodiments of the present disclosure are not limited thereto. For the convenience of description, in all embodiments of the present disclosure, the apparatuses that provide wireless communication functions for terminal devices are collectively referred to as network devices, access network devices, or base stations.

[0114] In some embodiments, the second device 102 is a core network device. Optionally, the core network device can be one device including all or part of the first network element, the second network element, and the like, or can be a plurality of devices or device groups including all or part of the first network element, the second network element, and the like, respectively. The network element can be virtual or physical. The core network includes, for example, at least one of an evolved packet core (EPC), a 5G core network (5GCN), and a next generation core (NGC).

[0115] In some embodiments, the technical solutions of the present disclosure can be applied to an Open RAN architecture, at which time the interfaces between or within the access network devices involved in the embodiments of the present disclosure can become internal interfaces of the Open RAN, and the processes and information interactions between these internal interfaces can be implemented through software or programs.

[0116] In some embodiments, the access network device can be composed of a central unit (CU) and a distributed unit (DU), where the CU can also be referred to as a control unit. The CU-DU structure can split the protocol layers of the access network device, and some of the functions of the protocol layers are controlled by the CU, and the remaining or all of the functions of the protocol layers are distributed in the DU and controlled by the CU, but are not limited thereto.

[0117] It can be understood that the communication system described in the embodiments of the present disclosure is for more clearly illustrating the technical solutions of the embodiments of the present disclosure, and does not constitute a limitation on the technical solutions proposed in the embodiments of the present disclosure. It can be known by those skilled in the art that, as the system architecture evolves and new business scenarios appear, the technical solutions proposed in the embodiments of the present disclosure are also applicable to similar technical problems.

[0118] The following embodiments of the present disclosure can be applied to the communication system 100 shown in FIG. 1, or part of the subjects, but are not limited thereto. The subjects shown in FIG. 1 are illustrative, and the communication system can include all or part of the subjects in FIG. 1, or other subjects other than those in FIG. 1. The number and form of each subject is arbitrary, each subject can be physical or virtual, the connection relationship between each subject is illustrative, each subject can not be connected or can be connected, and the connection can be in any manner, can be direct connection or indirect connection, can be wired connection or wireless connection.

[0119] Embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (Bluetooth (registered trademark)), Public Land Mobile Network (PLMN) network, Device-to-Device (D2D) system, Machine to Machine (M2M) system, Internet of Things (IoT) system, Vehicle-to-Everything (V2X), system using other communication methods, next-generation system expanded based thereon, and the like. Further, a plurality of systems can be applied in combination (for example, combination of LTE or LTE-A and 5G, and the like).

[0120] In some embodiments, the principal component analysis algorithm belongs to the field of multivariate statistical analysis. Multivariate statistical analysis is a branch of statistics that deals with the relationships between multiple variables, and PCA is a method used in multivariate statistical analysis to reduce the dimensionality of data and extract the main features. In addition, due to the advantages of PCA in feature extraction, dimensionality reduction, and data analysis, it can be applied to many different fields to help extract key information, simplify data representation, and improve the efficiency of algorithms, and the embodiments of the present disclosure apply it to the field of compression processing of audio signals.

[0121] In some embodiments, the PCA algorithm belongs to the data dimensionality reduction algorithm used for feature extraction in the field of multivariate statistical analysis. Common data dimensionality reduction algorithms include PCA, Multiple Dimensional Scaling (MDS), and Independent Component Analysis (ICA), etc. Among them, PCA is one of the earliest and most classic data dimensionality reduction methods, which projects the original data to a new low-dimensional space through linear transformation. PCA is widely used in feature selection, visualization, and data preprocessing, etc. MDS is a statistical technique used to analyze and visualize the similarity or distance of data, which can map high-dimensional data to low-dimensional space (usually two or three dimensions) to better understand the relationship and structure between data. ICA is a method that decomposes multiple random variables into independent components, which can also be used for data dimensionality reduction. ICA assumes that data is mixed by multiple independent components, and tries to decompose data into these independent components.

[0122] In some embodiments, PCA is a commonly used data dimensionality reduction algorithm that extracts core features from a data matrix. It projects the original data to a new feature space through linear transformation to obtain a principal component matrix, and the original data information is concentrated in the principal component matrix with a large variance proportion. At this time, only the principal component vector with a large variance proportion in the principal component matrix needs to be retained to retain most of the information in the data, while reducing the dimensionality of the data.

[0123] In some embodiments, the basic steps of the PCA dimensionality reduction algorithm include the following steps:

[0124] Step 1, data standardization.

[0125] For example, the data matrix A of the original data is standardized to obtain matrix B, so that the mean of each feature is 0 and the variance is 1. This step is to ensure that each feature has the same importance to the result of PCA.

[0126] For example, assuming that the original data has 10 samples, each sample has 5 features, then the data matrix A of the original data can be a 10x5 matrix.

[0127] Step 2, Compute Covariance Matrix B T B.

[0128] For example, the covariance matrix between features is computed from the standardized data matrix B. The covariance matrix describes the linear relationship between features.

[0129] Step 3, Compute Eigenvalues and Eigenvector Matrix V.

[0130] For example, eigenvalue decomposition is performed on the covariance matrix to obtain eigenvalues and corresponding eigenvectors. Eigenvalues represent the variance of data in the direction of eigenvectors, and eigenvectors represent the direction of data in the new feature space.

[0131] Step 4, Select Principal Component Matrix Vk.

[0132] For example, according to the size of the eigenvalue, the eigenvectors corresponding to the largest k eigenvalues are selected as the principal components, where k is the desired dimension to reduce.

[0133] Step 5, Data Projection.

[0134] For example, the original data is projected onto the selected principal components to obtain the reduced dimension data Y = B × Vk.

[0135] In some embodiments, the advantages of the PCA dimension reduction algorithm include at least one of the following:

[0136] Reducing dimension, PCA can reduce high-dimensional data to lower dimension, reducing storage space and computational cost.

[0137] Removing redundant information, PCA can remove redundant information in data by selecting principal components, retaining the most important features.

[0138] In some embodiments, the limitations of the PCA algorithm include at least one of the following:

[0139] Linear relationship, PCA assumes that data is linearly related and is not good at handling data with strong non-linear relationship.

[0140] Variance explanation, when PCA selects principal components, it mainly considers the degree of variance explanation. In some cases, features with small variance but important may be ignored.

[0141] In some embodiments, the Box-Cox transformation is a general power transformation method proposed by Box and Cox in 1964, which is a commonly used data transformation in statistical modeling for continuous response variables that do not meet the normal distribution. That is, the Box-Cox algorithm is a statistical method for data transformation, aiming to change the distribution of data to make it closer to the normal distribution. The Box-Cox algorithm relies on a parameter called lambda, which determines the specific variance of data transformation. The calculation equation of the Box-Cox algorithm is as follows:

[0142] In some embodiments, the process of the Box-Cox algorithm is as follows: Box-Cox power transformation is performed on the input data, the value of the lambda parameter is calculated using the maximum likelihood estimation method based on the transformed data, and the output data of the Box-Cox transformation is calculated after the value of lambda is calculated. Where y represents the original data.

[0143] In some embodiments, the PCA dimensionality reduction algorithm based on power operation is obtained based on the inspiration of the Box-Cox algorithm, which can improve the normality of vector data and make it more consistent with the normal distribution. The PCA dimensionality reduction algorithm has better dimensionality reduction effect when the data matrix meets the normal distribution.

[0144] In some embodiments, the Box-Cox algorithm and the PCA dimensionality reduction algorithm are combined to obtain the BOXCOX-PCA algorithm. In the BOXCOX-PCA algorithm, the Box-Cox algorithm can improve the normality of data, and the data matrix is obtained after the Box-Cox transformation of each column vector of the data matrix, and then the data matrix is used as the input of the PCA dimensionality reduction algorithm.

[0145] In some embodiments, it can be seen from the calculation equation of the Box-Cox algorithm that the Box-Cox algorithm is actually a power transformation equation. The Box-Cox algorithm performs a series of power operations on the elements in the column vector through the lambda parameter. In the Box-Cox algorithm, the lambda parameter that makes the column vector closest to the normal distribution needs to be found. In solving the optimal lambda parameter, Box-Cox has its own one-dimensional estimation equation about the lambda parameter to calculate the value of lambda based on the normality of data.

[0146] In some embodiments, the BOXCOX-PCA algorithm is implemented in the embodiments of the present disclosure. The BOXCOX-PCA algorithm improves the normality of each column vector of the data matrix using the Box-Cox algorithm, and has a certain improvement effect on the performance of the PCA dimension reduction algorithm. However, some shortcomings and deficiencies of the algorithm are also found in the experiment process. First, although the Box-Cox algorithm can improve the normality of the column vector, a large amount of data is required in this process. If the number of elements in the column vector is insufficient, the Box-Cox algorithm may derive an incorrect λ parameter in the case of insufficient input data, or even make the normality of the column vector worse. Second, the Box-Cox algorithm requires that the input data must be all positive numbers, which can be seen from the equation formula of the Box-Cox algorithm. The data that can be processed by the Box-Cox algorithm has great limitations.

[0147] Therefore, the embodiments of the present disclosure provide a data processing method, device, system, medium and computer program product, which optimize the principal component analysis method and improve the accuracy of dimension reduction results.

[0148] FIG. 2 is one of the interaction schematic diagrams of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 2, the embodiments of the present disclosure relate to a data processing method, which is executed by the communication system 100. The method comprises the following steps:

[0149] In step S201, the first device 101 determines a data matrix of first data.

[0150] In some embodiments, the first data is data to be sent, for example, the first data is multimedia data to be sent. For example, the multimedia data can include audio data.

[0151] In some embodiments, the name of the first data is not limited, which is, for example, original data, data to be dimension reduced, information to be sent, etc.

[0152] In some embodiments, the first data can be converted into a data matrix. For example, the first data is processed by encoding, transformation, etc. to obtain a data matrix representing the first data.

[0153] For example, assuming that the first data is audio data, the audio data can be any type of audio data generated in any service scenario, for example, an audio signal. After being processed by audio encoding, discrete Fourier transform, etc., the audio data can be represented as a data matrix.

[0154] In some embodiments, in the data matrix, a row represents a sample and a column represents a feature.

[0155] In step S202, the first device 101 pre-processes the data matrix.

[0156] In some embodiments, the preprocessing comprises at least one of the following:

[0157] power transformation processing;

[0158] standardization processing;

[0159] centering processing.

[0160] In some embodiments, the standardization processing comprises normalization processing.

[0161] For example, the implementation of preprocessing the data matrix comprises standardization processing of the data matrix. The mean of each column vector of the data matrix after the standardization processing is 0, and the variance is 1. This can ensure that each feature has the same importance on the dimensionality reduction result.

[0162] For example, the implementation of preprocessing the data matrix comprises power transformation processing of the data matrix, and then standardization processing of the data matrix after the power transformation processing. In this way, since the data matrix of the first data conforms to the normal distribution, better dimensionality reduction results can be obtained, and the power transformation processing can improve the normality of the vector data, so that it conforms to the normal distribution more. Therefore, by performing power transformation processing on the data matrix of the first data, the accuracy of the dimensionality reduction result can be improved. Since the power transformation processing increases the scale difference between data, the data matrix after the power transformation processing can be standardized to weaken the influence of the power transformation processing on the data scale. Thus, the accuracy of the data processing result is further improved.

[0163] In some embodiments, the data matrix can be power transformed according to the Box-Cox algorithm. The calculation principle of the Box-Cox algorithm can be referred to the calculation formula and related explanations in the foregoing embodiments, which will not be described here.

[0164] For example, the implementation of preprocessing the data matrix comprises centering processing of the data matrix. For example, the data matrix is first standardized, and then the data matrix after the standardization processing is centered. The centering processing is beneficial to simplify the subsequent processing.

[0165] In some embodiments, step S202 can be omitted.

[0166] In step S203, the first device 101 calculates a correlation coefficient matrix.

[0167] In some embodiments, the first device calculates a correlation coefficient matrix corresponding to the data matrix.

[0168] In some embodiments, the first device calculates the correlation coefficient matrix according to the preprocessed data matrix.

[0169] In some embodiments, the correlation coefficient matrix is a matrix composed of correlation coefficients, which is not limited in name, for example, coefficient matrix, relationship matrix, correlation coefficient matrix, etc.

[0170] In some embodiments, the correlation coefficient matrix corresponding to the preprocessed data matrix can be calculated according to a Pearson correlation coefficient calculation method. The calculation principle of the Pearson correlation coefficient calculation method can be referred to in related technologies, which will not be described here.

[0171] It should be explained that according to the calculation principle of the correlation coefficient, the correlation coefficient can be regarded as a special covariance, that is, a special covariance after removing the dimensional influence of two variables and standardizing processing, which eliminates the influence of the change range of two variables and only reflects the similarity of the change of two variables per unit. That is, the correlation coefficient matrix is less affected by the scale difference between data, and the correlation coefficient matrix can also effectively reflect the distribution of data variance.

[0172] In summary, the correlation coefficient matrix can overcome the problems of covariance matrix that is difficult to process due to large data scale differences and abnormal values, etc. The selection of principal component components (i.e. main eigenvectors / core eigenvectors) needs the distribution of data variance as a basis for judgment. Although the correlation coefficient matrix does not directly represent the distribution of data variance like the covariance matrix, the correlation coefficient matrix can also effectively reflect the distribution of data variance. Therefore, when processing data with large scale differences, the effect of selecting principal component components based on the correlation coefficient matrix is obviously better than that of selecting principal component components based on the covariance matrix, that is, the performance of the principal component analysis method based on the correlation coefficient matrix is better than that of the principal component analysis method based on the covariance matrix. That is, by performing eigenvalue decomposition on the correlation coefficient matrix of the first data, a dimension reduction matrix (i.e. principal component matrix) with higher accuracy and retaining most of the information in the first data can be obtained, and a more accurate dimension reduction result can be obtained according to the dimension reduction matrix, which is less likely to be distorted.

[0173] In step S204, the first device 101 performs eigenvalue decomposition on the correlation coefficient matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors.

[0174] In some embodiments, eigenvalue decomposition can be referred to as characteristic decomposition. Eigenvalue decomposition can obtain eigenvalues and eigenvectors, the eigenvalues represent how important the feature is, and the eigenvectors represent what the feature is. Each eigenvector can be understood as a linear subspace, for example, these eigenvectors can be understood as mutually orthogonal coordinate axes in a new space.

[0175] In some embodiments, one eigenvalue corresponds to one eigenvector, and the eigenvalue represents the variance of the first data in the direction of the corresponding eigenvector. The greater the variance, the more important the corresponding eigenvector.

[0176] The principle followed by the eigenvalue decomposition can be referred to related art, which is not described herein.

[0177] In step S205, the first device 101 selects N eigenvectors from the plurality of eigenvectors to form a dimension reduction matrix.

[0178] In some embodiments, the first device selects N eigenvectors corresponding to N eigenvalues in descending order of the eigenvalues to form the dimension reduction matrix.

[0179] In some embodiments, N is a natural number. In some embodiments, the value of N can be preset or indicated by a network device. In some embodiments, the value of N can be calculated according to the degree of dimension reduction.

[0180] In some embodiments, the name of the dimension reduction matrix is not limited, which is, for example, a principal component matrix, a compression matrix, a conversion matrix, etc.

[0181] In some embodiments, the dimension reduction matrix is an orthogonal matrix. The column vectors of the dimension reduction matrix are the eigenvectors of the correlation coefficient matrix, which are sorted according to the size of the eigenvalues.

[0182] In some embodiments, the eigenvectors can be referred to as component components, and the selected N eigenvectors can be referred to as N principal component components.

[0183] In step S206, the first device 101 projects the first data into the space indicated by the dimension reduction matrix to obtain second data.

[0184] In some embodiments, the name of the second data is not limited, which is, for example, a dimension reduction result, a dimension reduction data, a compression matrix, a projection matrix, etc.

[0185] In some embodiments, the dimension reduction matrix includes N eigenvectors of the correlation coefficient matrix, and each eigenvector is understood as a linear subspace, i.e., a coordinate axis. The N eigenvectors are mutually orthogonal. The space indicated by the dimension reduction matrix is a space composed of N mutually orthogonal coordinate axes.

[0186] In some embodiments, the first data can be projected into the space indicated by the dimension reduction matrix by means of translation, rotation, etc. to obtain the second data. The second data is the dimension reduction result. For example, the data matrix of the first data is multiplied by the dimension reduction matrix to obtain a dimension reduction matrix. In the dimension reduction matrix, each row represents a sample, and each column represents a reconstructed feature after dimension reduction.

[0187] Step S207, the first device 101 sends the second data to the second device 102.

[0188] In some embodiments, the second device receives the second data. For example, the second device 102 receives the second data sent by the first device 101.

[0189] In some embodiments, the first device sends a first message to the second device, the first message including or indicating the second data. The second device receives the first message and obtains the second data.

[0190] Step S208, the second device 102 reconstructs the first data according to the second data.

[0191] In some embodiments, the first message further includes a dimension reduction matrix. The second device reconstructs the first data according to the second data based on the dimension reduction matrix.

[0192] It should be noted that there may be errors between the first data reconstructed by the second device and the original first data on the first device due to dimension reduction and reconstruction operations.

[0193] In some embodiments, the term “reconstruction” can be replaced by the terms “reconstruction”, “dimension increase”, “restoration” and the like.

[0194] In some embodiments, the names of information and the like are not limited to the names described in the embodiments, and the terms “information”, “message”, “signal”, “signaling”, “report”, “configuration”, “indication”, “instruction”, “command”, “channel”, “parameter”, “domain”, “field”, “symbol”, “codebook”, “codeword”, “code point”, “bit”, “data”, “program”, “chip” and the like can be replaced by each other.

[0195] In some embodiments, “acquire”, “obtain”, “get”, “receive”, “transmit”, “bidirectional transmission”, “send and / or receive” can be replaced by each other, which can be interpreted as receiving from other subjects, obtaining from protocols, obtaining from higher layers, processing to obtain, independently implementing and the like.

[0196] In some embodiments, the terms “sending”, “transmitting”, “reporting”, “issuing”, “transferring”, “bidirectional transferring”, “sending and / or receiving” and the like can be replaced by each other.

[0197] In some embodiments, the terms “certain”, “preseted”, “preset”, “set”, “indicated”, “certain”, “arbitrary”, “first” and the like can be replaced by each other, “certain A”, “preset A”, “preset A”, “set A”, “indicated A”, “certain A”, “arbitrary A”, “first A” can be interpreted as A specified in advance in a protocol or the like, A obtained by setting, configuration, or indication, or A specific, certain, arbitrary, or first A, but not limited thereto.

[0198] The data processing method related to the embodiments of the present disclosure can include at least one of steps S201-S208. For example, step S206 can be implemented as an independent embodiment, step S207 can be implemented as an independent embodiment, steps S201, S203, S204, S205, S206 can be implemented as independent embodiments, but not limited thereto.

[0199] In some embodiments, the order between any two steps of steps S201-S208 can be exchanged or executed simultaneously.

[0200] In some embodiments, steps S201-S205, S207, S208 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0201] In some embodiments, steps S201-S206, S208 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0202] In some embodiments, other optional implementations described before or after the corresponding description of FIG. 2 can be referred to.

[0203] FIG. 3A is one of the flow diagrams of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 3A, the data processing method related to the embodiments of the present disclosure is executed by a first device, and the method comprises:

[0204] Step S3101, determining the data matrix of the first data.

[0205] The optional implementation of step S3101 can refer to the optional implementation of step S201 of FIG. 2 and other related parts in the embodiments related to FIG. 2, which will not be repeated here.

[0206] In step S3102, the data matrix is preprocessed.

[0207] The optional implementation of step S3102 can refer to the optional implementation of step S202 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0208] In step S3103, the correlation coefficient matrix is calculated according to the preprocessed data matrix.

[0209] The optional implementation of step S3103 can refer to the optional implementation of step S203 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0210] In step S3104, the eigenvalue decomposition is performed on the correlation coefficient matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors.

[0211] The optional implementation of step S3104 can refer to the optional implementation of step S204 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0212] In step S3105, the eigenvectors corresponding to the N largest eigenvalues are selected to form a dimension reduction matrix.

[0213] The optional implementation of step S3105 can refer to the optional implementation of step S205 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0214] In step S3106, the first data is projected into the space indicated by the dimension reduction matrix to obtain a data dimension reduction result.

[0215] The optional implementation of step S3106 can refer to the optional implementation of step S206 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0216] In step S3107, the data dimension reduction result is sent.

[0217] The optional implementation of step S3107 can refer to the optional implementation of step S207 in FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0218] In some embodiments, the first device 101 sends the data dimension reduction result to the second device 102, but is not limited thereto, and can also send the data dimension reduction result to other subjects.

[0219] The data processing method related to the embodiments of the present disclosure can include at least one of steps S3101-S3107. For example, step S3106 can be implemented as an independent embodiment, step S3107 can be implemented as an independent embodiment, and step S3106 and step S3107 can be implemented as independent embodiments, but are not limited thereto.

[0220] In some embodiments, the order between any two of steps S3101-S3107 can be exchanged or executed simultaneously.

[0221] In some embodiments, steps S3101-S3105 and step S3107 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0222] In some embodiments, steps S3101-S3106 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0223] FIG. 3B is a flow diagram of another data processing method according to an embodiment of the present disclosure. As shown in FIG. 3B, the data processing method related to the embodiments of the present disclosure is executed by a first device, and the method includes:

[0224] Step S3201, determining a data matrix of the first data.

[0225] The optional implementation of step S3201 can refer to the optional implementation of step S201 of FIG. 2, the optional implementation of step S3101 of FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which will not be repeated here.

[0226] Step S3202, determining a correlation coefficient matrix corresponding to the data matrix.

[0227] The optional implementation of step S3202 can refer to the optional implementation of step S203 of FIG. 2 and other associated parts in the embodiments related to FIG. 2, which will not be repeated here.

[0228] Step S3203, performing eigenvalue decomposition on the correlation coefficient matrix to obtain a dimension reduction matrix.

[0229] The optional implementation of step S3203 can refer to the optional implementation of steps S204 and S205 of FIG. 2, the optional implementation of steps S3104 and S3105 of FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which will not be repeated here.

[0230] Step S3204, performing dimension reduction processing on the first data according to the dimension reduction matrix to obtain a data dimension reduction result.

[0231] The optional implementation of step S3204 can refer to the optional implementation of step S206 in FIG. 2, step S3106 in FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which are not described herein again.

[0232] The data processing method related to the embodiments of the present disclosure can include at least one of steps S3201 to S3204. For example, step S3204 can be implemented as an independent embodiment, and steps S3201 and S3204 can be implemented as independent embodiments, but are not limited thereto.

[0233] In some embodiments, the order between any two of steps S3201 to S3204 can be exchanged or executed simultaneously.

[0234] In some embodiments, steps S3201 to S3203 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0235] In some embodiments, steps S3202 and S3203 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0236] In the embodiments of the present disclosure, step S3202 can be combined with step S3102 in FIG. 3A, and step S3204 can be combined with step S3107 in FIG. 3A.

[0237] FIG. 3C is a third flow diagram of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 3C, the data processing method related to the embodiments of the present disclosure is executed by a first device, and the above method includes:

[0238] Step S3301, determining a data matrix of first data.

[0239] The optional implementation of step S3301 can refer to the optional implementation of step S201 in FIG. 2, step S3101 in FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which are not described herein again.

[0240] Step S3302, determining a correlation coefficient matrix corresponding to the data matrix.

[0241] The optional implementation of step S3302 can refer to the optional implementation of step S203 in FIG. 2 and other associated parts in the embodiments related to FIG. 2, which are not described herein again.

[0242] Step S3303, performing data dimension reduction processing on the first data based on the correlation coefficient matrix to obtain second data.

[0243] The optional implementation of step S3303 can refer to the optional implementation of step S204, step S205, step S206 of FIG. 2, step S3104, step S3105, step S3106 of FIG. 3A, and other associated parts in the embodiments of FIG. 2 and FIG. 3A, which are not described herein again.

[0244] The data processing method according to the embodiments of the present disclosure can include at least one of step S3301 to step S3303. For example, step S3303 can be implemented as an independent embodiment, and step S3302 and step S3303 can be implemented as independent embodiments, but are not limited thereto.

[0245] In some embodiments, the order between any two of step S3301 to step S3303 can be exchanged or executed simultaneously.

[0246] In some embodiments, step S3301 and step S3302 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0247] In some embodiments, step S3301 and step S3303 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0248] In some embodiments, step S3302 and step S3303 are optional, and one or more of these steps can be omitted or replaced in different embodiments.

[0249] In the embodiments of the present disclosure, step S3302 can be combined with step S3102 of FIG. 3A, and step S3303 can be combined with step S3107 of FIG. 3A.

[0250] FIG. 3D is a fourth flow diagram of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 3D, the data processing method according to the embodiments of the present disclosure is executed by a first device, and the method includes:

[0251] Step S3401, performing data dimension reduction processing on the first data based on the correlation coefficient matrix to obtain second data.

[0252] The optional implementation of step S3401 can refer to the optional implementation of step S201, step S202, step S203, step S204, step S205, step S206 of FIG. 2, step S3101, step S3102, step S3103, step S3104, step S3105, step S3106 of FIG. 3A, and other associated parts in the embodiments of FIG. 2 and FIG. 3A, which are not described herein again.

[0253] Step S3402: sending, to the second device, a first message, the first message comprising the second data.

[0254] The optional implementation of step S3402 can refer to step S207 of FIG. 2, the optional implementation of step S3107 of FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which are not described herein again.

[0255] The data processing method related to the embodiments of the present disclosure can comprise at least one of step S3401 and step S3402. For example, step S3401 can be implemented as an independent embodiment, and step S3402 can be implemented as an independent embodiment, but is not limited thereto.

[0256] In some embodiments, the order between step S3401 and step S3402 can be exchanged or executed simultaneously.

[0257] In some embodiments, step S3401 is optional, and can be omitted or replaced in different embodiments.

[0258] In some embodiments, step S3402 is optional, and can be omitted or replaced in different embodiments.

[0259] In the embodiments of the present disclosure, step S3401 can be combined with step S3101 of FIG. 3A, and step S3303 can be combined with step S3102 of FIG. 3A.

[0260] FIG. 4 is a flow diagram of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 4, the data processing method related to the embodiments of the present disclosure is executed by a second device, and the above method comprises:

[0261] Step S401: receiving a first message, the first message being obtained based on second data.

[0262] The optional implementation of step S401 can refer to the optional implementation of step S207 of FIG. 2 and other associated parts in the embodiments related to FIG. 2, which are not described herein again.

[0263] In some embodiments, the first device 101 receives the first message sent by the second device 102, but is not limited thereto, and can also receive the first message sent by other subjects.

[0264] In some embodiments, the first device 101 obtains the first message specified by a protocol.

[0265] In some embodiments, the first device 101 obtains the first message from an upper layer.

[0266] In some embodiments, the first device 101 processes to obtain the first message.

[0267] In some embodiments, the step S401 is omitted, and the first device 101 autonomously implements the function indicated by the first message, or the function is default or default.

[0268] Step S402, reconstructing the first data according to the second data.

[0269] The optional implementation of step S402 can refer to the optional implementation of step S208 of FIG. 2 and other associated parts in the embodiments involved in FIG. 2, which will not be repeated here.

[0270] The data processing method involved in the embodiments of the present disclosure can include at least one of steps S401 and S402. For example, step S401 can be implemented as an independent embodiment, and step S402 can be implemented as an independent embodiment, but not limited thereto.

[0271] In some embodiments, the order between steps S401 and S402 can be exchanged or executed simultaneously.

[0272] In some embodiments, step S401 is optional, and this step can be omitted or replaced in different embodiments.

[0273] In some embodiments, step S402 is optional, and this step can be omitted or replaced in different embodiments.

[0274] FIG. 5 is a second interaction diagram of a data processing method according to an embodiment of the present disclosure. As shown in FIG. 5, the embodiments of the present disclosure involve a data processing method, and the method includes:

[0275] Step S501, the first device processes the first data based on the correlation coefficient matrix and the principal component analysis algorithm to obtain the second data.

[0276] The optional implementation of step S501 can refer to the optional implementation of steps S201, S202, S203, S204, S205, S206 of FIG. 2, steps S3101, S3102, S3103, S3104, S3105, S3106 of FIG. 3A, and other associated parts in the embodiments involved in FIG. 2 and FIG. 3A, which will not be repeated here.

[0277] Step S502, the first device sends a first message to the second device, and the first message is obtained based on the second data.

[0278] The optional implementation of step S502 can refer to the optional implementation of step S207 in FIG. 2, step S3107 in FIG. 3A, and other associated parts in the embodiments related to FIG. 2 and FIG. 3A, which will not be repeated here.

[0279] Step S503, reconstructing the first data according to the second data.

[0280] The optional implementation of step S503 can refer to the optional implementation of step S208 in FIG. 2 and other associated parts in the embodiments related to FIG. 2, which will not be repeated here.

[0281] In some embodiments, the above method can include the method described in the embodiments of the above communication system side, the first device side, the second device side, and the like, which will not be repeated here.

[0282] In some embodiments of the present disclosure, the use of the relationship characteristic matrix (i.e., the correlation matrix / correlation coefficient matrix) instead of the covariance matrix is studied to improve and optimize the principal component analysis algorithm. In the experiment, the correlation coefficient matrix, the rank correlation coefficient matrix, and the distance matrix are used to replace the covariance matrix to help the principal component analysis algorithm select principal component components. The selection of principal component components needs the distribution of data variance as the basis for judgment. The rank correlation coefficient matrix and the distance matrix cannot reflect the distribution of data variance, so the experimental results of the two are not ideal. The correlation coefficient matrix and the covariance matrix are both linear matrices that reflect the linear relationship of data. The correlation coefficient matrix can overcome the problems that the covariance matrix cannot handle, such as large data scale difference and outliers. Moreover, the correlation coefficient matrix does not directly represent the distribution of data variance like the covariance matrix, but it can also effectively reflect the distribution of data variance. Therefore, when processing data with large scale differences, the principal component analysis algorithm based on the correlation coefficient matrix performs better.

[0283] In some embodiments, the correlation coefficient matrix is used instead of the covariance matrix to improve and optimize the principal component analysis algorithm. The optimized principal component analysis process, i.e., the data processing process, is shown in FIG. 6A, which includes the following steps:

[0284] Step S6101, reading the original data matrix.

[0285] Step S6102, calculating the correlation coefficient matrix.

[0286] Step S6103, eigenvalue decomposition to obtain the principal component matrix.

[0287] Step S6104, using the principal component matrix to perform dimensionality reduction mapping on the original data to obtain the data dimensionality reduction result.

[0288] In the embodiments of the present disclosure, part or all of the steps, and optional implementation manners thereof, can be combined with part or all of the steps in other embodiments, or combined with optional implementation manners of other embodiments.

[0289] In some embodiments, using the correlation coefficient matrix in the PCA algorithm can be more suitable for processing scenarios where the data scale difference between column vectors is too large. For example, verification is performed using the original data matrix shown in FIG. 6B. The verification results are shown in FIG. 6C, which shows the reconstruction matrix corresponding to the principal component analysis using the covariance matrix, and FIG. 6D, which shows the reconstruction matrix corresponding to the principal component analysis using the correlation coefficient matrix. It is assumed that the offset between the reconstruction matrix and the original matrix is used as the standard for judging the effect. A matrix with a large scale difference between column vectors in FIG. 6B is selected for testing, and two principal component components are selected during dimensionality reduction operation. Through testing, the reconstruction matrix using the covariance matrix has an offset of 0.93, while the reconstruction matrix obtained using the correlation coefficient matrix has an offset of 0.82. Further analysis shows that the reconstruction effect of the last two columns of data in the reconstruction matrix obtained using the covariance matrix is much better than that of the first two columns of data with smaller values, and the second column with smaller values has the worst effect, which is the main reason for the larger overall offset. This is because the covariance matrix cannot avoid the influence of data scale, and the principal component analysis algorithm will focus more on data with larger values. In the reconstruction matrix obtained using the correlation coefficient matrix, although each column has some deviation, the second column of data is closer to the original matrix than the two columns with larger values in FIG. 6C, and the overall offset is smaller than that of the covariance reconstruction matrix. This is because the correlation coefficient matrix is less affected by the scale difference between data, so that each scale of data can be treated equally.

[0290] In some embodiments, in the Box-Cox transformation, the index value of some transformation equations can be large, thereby causing a large change in the data scale. In some embodiments, in the process of using the Box-Cox transformation to improve the PCA dimensionality reduction algorithm, the power transformation operation of the Box-Cox can increase the scale difference between dimensions. At this time, the effect of using the correlation coefficient matrix for principal component analysis is much better than that of using the covariance matrix for principal component analysis.

[0291] In some embodiments, using the correlation coefficient matrix instead of the covariance matrix in the PCA algorithm combined with the improved Box-Cox transformation can further improve the dimensionality reduction performance. Specifically, referring to the flowchart shown in FIG. 6E, the following steps are included:

[0292] Step S6501, reading a data matrix.

[0293] Step S6502, Box-Cox transformation processing is performed.

[0294] Step S6503, centering processing is performed.

[0295] Step S6504, a correlation coefficient matrix is calculated.

[0296] Step S6505, principal component components are obtained.

[0297] The principal component components constitute a principal component matrix.

[0298] Step S6506, original data is mapped to the direction of the principal component components.

[0299] In the embodiments of the present disclosure, part or all of the steps, and optional implementation manners thereof, can be combined with part or all of the steps in other embodiments, or can be combined with optional implementation manners of other embodiments.

[0300] In some embodiments, whether the correlation coefficient matrix is more suitable to be used together with the Box-Cox transformation than the covariance matrix is verified using the original data matrix shown in FIG. 6F. In the experiment, the number of principal component components selected is 2, and the reconstruction matrix offset d is used as the standard for judging the effect. As can be known from the reconstruction matrix corresponding to the principal component analysis using the covariance matrix shown in FIG. 6G, the reconstruction matrix corresponding to the principal component analysis algorithm using the covariance matrix in combination with the Box-Cox algorithm shown in FIG. 6H, and the reconstruction matrix corresponding to the principal component analysis using the correlation coefficient matrix in combination with the Box-Cox shown in FIG. 6I, the correlation coefficient matrix is more suitable to be used together with the Box-Cox transformation than the covariance matrix.

[0301] In some embodiments, in order to verify the advantages of the improved Box-Cox transformation combined with the correlation coefficient matrix method more accurately, the method is tested using randomly generated test data. When the test is performed, the test data is composed of 1000 n*4 random matrices, the matrix elements are randomly selected in the interval (-100, 100), and the number of principal component components is selected as two. The number of the offset of the reconstructed matrix after processing in 1000 matrices is less than the offset of the reconstructed matrix of the principal component analysis algorithm alone, and the result is shown in FIG. 6J. Referring to FIG. 6J, the experimental results show that, when other conditions are the same, using only the improved Box-Cox transformation method, about 70% of the data matrices in 1000 random matrices have a reconstructed matrix that is lower than the offset of the original principal component analysis algorithm and is closer to the original matrix. When the correlation coefficient matrix is used instead of the covariance matrix and the Box-Cox transformation method is applied, about 77% of the data matrices in 1000 random matrices have a reconstructed matrix that is closer to the original matrix than the original principal component analysis algorithm. This is because in the BOX-COX transformation process, the exponent of the power operation variance is too large for some data matrices, resulting in a large change in the scale of the data. The correlation coefficient matrix is more suitable for processing matrices with large scale differences than the covariance matrix due to its standardization, so the test results of the Box-Cox transformation combined with the correlation coefficient matrix for principal component analysis are better.

[0302] The embodiments of the present disclosure further provide a device for implementing any of the above methods. For example, a device is provided, which includes units or modules for implementing the steps performed by the first device (e.g., a terminal, an access network device, a core network function node, a core network device, etc.) in any of the above methods. For another example, another device is provided, which includes units or modules for implementing the steps performed by the second device (e.g., a terminal, an access network device, a core network function node, a core network device, etc.) in any of the above methods.

[0303] It should be understood that the division of each unit or module in the above apparatus is only a logical function division, and all or part of them can be integrated into a physical entity or physically separated in actual implementation. In addition, the units or modules in the apparatus can be implemented in the form of processor calling software: for example, the apparatus includes a processor connected with a memory, the memory stores instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the units or modules of the above apparatus, wherein the processor is, for example, a general processor such as a central processing unit (CPU) or a microprocessor, and the memory is a memory in the apparatus or a memory outside the apparatus. Alternatively, the units or modules in the apparatus can be implemented in the form of hardware circuit, and the functions of part or all of the units or modules can be realized by the design of the hardware circuit. The above hardware circuit can be understood as one or more processors; for example, in one implementation, the above hardware circuit is an application-specific integrated circuit (ASIC), and the functions of part or all of the units or modules are realized by the design of the logical relationship of the elements in the circuit; for another example, in another implementation, the above hardware circuit is a programmable logic device (PLD), and a field programmable gate array (FPGA) is taken as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by a configuration file, so as to realize the functions of part or all of the units or modules. All units or modules of the above apparatus can be implemented in the form of processor calling software, or all units or modules can be implemented in the form of hardware circuit, or part of the units or modules are implemented in the form of processor calling software, and the remaining part is implemented in the form of hardware circuit.

[0304] In the embodiments of the present disclosure, the processor is a circuit with signal processing capability. In one implementation, the processor can be a circuit with instruction reading and running capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), a digital signal processor (DSP), or the like. In another implementation, the processor can implement certain functions through a logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In the reconfigurable hardware circuit, the processor loads a configuration document to implement the configuration of the hardware circuit. It can be understood that the processor loads instructions to implement the functions of the above part or all units or modules. In addition, the hardware circuit can also be designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), or the like.

[0305] FIG. 7A is a structural schematic diagram of a first device according to an embodiment of the present disclosure. As shown in FIG. 7A, the first device 7100 can include at least one of a transceiver module 7101, a processing module 7102, and the like. In some embodiments, the processing module 7101 is configured to perform data dimension reduction processing on the first data based on the correlation coefficient matrix to obtain second data. In some embodiments, the transceiver module 7102 is configured to send a first message to a second device, where the first message includes the second data. Optionally, the transceiver module 7101 is configured to perform at least one of the communication steps (for example, step S207, but not limited thereto) performed by the first device 101 in any of the above methods, and details are not described herein. Optionally, the processing module 7102 is configured to perform at least one of the other steps (for example, steps S201, S202, S203, S204, S205, S206, and S208, but not limited thereto) performed by the first device 101 in any of the above methods, and details are not described herein.

[0306] FIG. 7B is a structural schematic diagram of a second device according to an embodiment of the present disclosure. As shown in FIG. 7B, the second device 7200 can include at least one of a transceiver module 7201, a processing module 7202, and the like. In some embodiments, the transceiver module 7202 is configured to receive a first message sent by a first device, where the first message includes second data obtained by performing data dimension reduction processing on first data based on a correlation coefficient matrix. Optionally, the transceiver module 7201 is configured to perform at least one of the communication steps (for example, step S207, but not limited thereto) performed by the second device 102 in any of the above methods, and details are not described herein again. Optionally, the processing module 7202 is configured to perform at least one of the steps (for example, steps S201, S202, S203, S204, S205, S206, S208, but not limited thereto) performed by the second device 102 in any of the above methods, and details are not described herein again.

[0307] In some embodiments, the transceiver module can include a sending module and / or a receiving module, which can be separate or integrated together. Optionally, the transceiver module can be replaced by a transceiver.

[0308] In some embodiments, the processing module can be a module or can include multiple sub-modules. Optionally, the multiple sub-modules perform all or part of the steps required to be performed by the processing module. Optionally, the processing module can be replaced by a processor.

[0309] FIG. 8A is a structural schematic diagram of a communication device 8100 according to an embodiment of the present disclosure. The communication device 8100 can be a network device (for example, an access network device, a core network device, and the like), a terminal (for example, a user equipment, and the like), a chip, a chip system, or a processor supporting the network device to implement any of the above methods, or a chip, a chip system, or a processor supporting the terminal to implement any of the above methods. The communication device 8100 can be used to implement the methods described in the above method embodiments, and details can be referred to the descriptions in the above method embodiments.

[0310] As shown in FIG. 8A, the communication device 8100 includes one or more processors 8101. The processor 8101 can be a general processor or a special-purpose processor, etc., such as a baseband processor or a central processing unit. The baseband processor can be configured to process communication protocols and communication data, and the central processing unit can be configured to control a communication apparatus (e.g., a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process data of the programs. Optionally, the communication device 8100 is configured to perform any of the above methods. Optionally, the one or more processors 8101 are configured to invoke instructions to cause the communication device 8100 to perform any of the above methods.

[0311] In some embodiments, the communication device 8100 further includes one or more transceivers 8102. When the communication device 8100 includes the one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps (e.g., step S207, but not limited thereto) in the above methods, and the processor 8101 performs at least one of the other steps (e.g., steps S201, S202, S203, S204, S205, S206, S208, but not limited thereto). In optional embodiments, the transceiver can include a receiver and / or a transmitter, which can be separate or integrated together. Optionally, the terms transceiver, transceiving unit, transceiver, transceiving circuit, interface circuit, interface, etc. can be replaced with each other, and the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc. can be replaced with each other, and the terms receiver, receiving unit, receiver, receiving circuit, etc. can be replaced with each other.

[0312] In some embodiments, the communication device 8100 further includes one or more memories 8103 for storing data. Optionally, all or part of the memory 8103 can also be outside the communication device 8100. In optional embodiments, the communication device 8100 can include one or more interface circuits 8104. Optionally, the interface circuit 8104 is connected to the memory 8103, and the interface circuit 8104 can be configured to receive data from the memory 8103 or other devices, and can be configured to send data to the memory 8103 or other devices. For example, the interface circuit 8104 can read data stored in the memory 8103 and send the data to the processor 8101.

[0313] The communication device 8100 described in the above embodiments can be a network device or a terminal, but the scope of the communication device 8100 described in the present disclosure is not limited thereto, and the structure of the communication device 8100 can not be limited by FIG. 8A. The communication device can be a standalone device or can be part of a larger device. For example, the communication device can be: 1) a standalone integrated circuit (IC), or a chip, or a chip system or subsystem; (2) a set of one or more ICs, which can optionally also include storage components for storing data, programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, a smart terminal device, a cellular phone, a wireless device, a handset, a mobile unit, a vehicle-mounted device, a network device, a cloud device, an artificial intelligence device, and the like; (6) other devices, and the like.

[0314] FIG. 8B is a structural schematic diagram of a chip 8200 according to an embodiment of the present disclosure. For the case where the communication device 8100 can be a chip or a chip system, the structural schematic diagram of the chip 8200 shown in FIG. 8B can be referred to, but is not limited thereto.

[0315] The chip 8200 includes one or more processors 8201. The chip 8200 is configured to perform any of the above methods.

[0316] In some embodiments, the chip 8200 further includes one or more interface circuits 8202. Optionally, the terms interface circuit, interface, transceiver pin, and the like can be replaced with each other. In some embodiments, the chip 8200 further includes one or more memories 8203 for storing data. Optionally, all or part of the memory 8203 can be outside the chip 8200. Optionally, the interface circuit 8202 is connected with the memory 8203, and the interface circuit 8202 can be configured to receive data from the memory 8203 or other devices, and the interface circuit 8202 can be configured to send data to the memory 8203 or other devices. For example, the interface circuit 8202 can read data stored in the memory 8203 and send the data to the processor 8201.

[0317] In some embodiments, the interface circuit 8202 performs at least one of the communication steps (for example, step S207, but not limited thereto) of transmitting and / or receiving in the above methods. The interface circuit 8202 performing the communication steps such as transmitting and / or receiving in the above methods means that the interface circuit 8202 performs data interaction between the processor 8201, the chip 8200, the memory 8203, or a transceiver device. In some embodiments, the processor 8201 performs at least one of the other steps (for example, steps S201, S202, S203, S204, S205, S206, S208, but not limited thereto).

[0318] The modules and / or devices described in various embodiments of virtual devices, physical devices, chips, etc. can be combined or separated according to circumstances. Alternatively, part or all of the steps can also be performed by multiple modules and / or devices in cooperation, which is not limited here.

[0319] The disclosure also proposes a storage medium, and the storage medium stores instructions, which, when executed on the communication device 8100, causes the communication device 8100 to perform any of the above methods. Alternatively, the storage medium is an electronic storage medium. Alternatively, the storage medium is a computer readable storage medium, but is not limited to this, and it can also be a storage medium readable by other devices. Alternatively, the storage medium can be a non-transitory storage medium, but is not limited to this, and it can also be a transitory storage medium.

[0320] The disclosure also proposes a program product, which, when executed by the communication device 8100, causes the communication device 8100 to perform any of the above methods. Alternatively, the program product is a computer program product.

[0321] The disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any of the above methods.

Claims

1. A data processing method, characterized by, The method is executed by a first device, and the method comprises: processing the first data based on a correlation coefficient matrix and a principal component analysis algorithm to obtain second data; sending a first message to a second device, the first message being obtained based on the second data.

2. The method of claim 1, wherein, The first data is multimedia data to be sent, and the multimedia data comprises audio data.

3. The method according to claim 1 or 2, characterized in that, The processing of the first data based on the correlation coefficient matrix and the principal component analysis algorithm to obtain the second data comprises: determining the correlation coefficient matrix corresponding to the first data; performing eigenvalue decomposition on the correlation coefficient matrix to obtain a plurality of eigenvalues and a plurality of eigenvectors, wherein one eigenvalue corresponds to one eigenvector, and the eigenvalue indicates the variance of the first data distributed in a first direction, and the first direction is the direction of the eigenvector corresponding to the eigenvalue; selecting N eigenvectors from the plurality of eigenvectors to form a dimension reduction matrix, wherein N is a natural number; projecting the first data to a space indicated by the dimension reduction matrix to obtain the second data.

4. The method of claim 3, wherein, The determination of the correlation coefficient matrix corresponding to the first data comprises: obtaining a data matrix of the first data; preprocessing the data matrix; determining the correlation coefficient matrix based on the preprocessed data matrix.

5. The method of claim 4, wherein, The preprocessing comprises at least one of: power transformation processing; standardization processing; centering processing.

6. The method of claim 4, wherein, The preprocessing of the data matrix comprises: performing standardization processing on the data matrix, and the mean of each column vector of the data matrix after the standardization processing is 0, and the variance is 1.

7. The method of claim 4, wherein, The preprocessing of the data matrix comprises: performing power transformation processing on the data matrix; performing standardization processing on the data matrix after the power transformation processing.

8. The method of claim 7, wherein, The power transformation processing on the data matrix comprises: performing power transformation on the data matrix based on a Box-Cox algorithm.

9. The method according to any one of claims 6-8, characterized in that, The preprocessing of the data matrix further comprises: performing centering processing on the data matrix after the standardization processing.

10. A first device, comprising: The method comprises: a processing module configured to process the first data based on a correlation coefficient matrix and a principal component analysis algorithm to obtain second data; a transceiver module configured to send a first message to a second device, the first message being obtained based on the second data.

11. A first device, comprising: The method comprises: one or more processors; a memory coupled to the processors, the memory having stored thereon executable instructions that, when executed by the processors, cause the first device to perform the data processing method of any one of claims 1-9.

12. A communication system, characterized by The method comprises:

13. A storage medium, the storage medium storing instructions, wherein, a first device and a second device, wherein the first device is configured to implement the data processing method of any one of claims 1-9.

14. A computer program product comprising computer programs and / or instructions, characterized in that, The instructions, when executed on a communication device, cause the communication device to perform the data processing method of any one of claims 1-9. The computer program and / or instructions, when executed on a communication device, implement the data processing method of any one of claims 1-9.

Images