File sending method and device, computer device, readable storage medium and program product

Abstract

The application relates to a file sending method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the field of big data. The method comprises the following steps: performing feature extraction on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features; performing file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result; adjusting the initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number; and performing file sending on the to-be-sent file according to the actual retransmission number. The method can take into account file sending efficiency and success rate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and particularly relates to a file sending method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] When sending a file, a file retransmission mechanism is usually set to ensure that the file can be accurately and completely sent to a target object.

[0003] At present, a fixed retransmission number is usually set, and then the system retransmits the file to the target object according to the fixed retransmission number.

[0004] However, if the fixed retransmission number is set too high, a large file may be repeatedly sent continuously, which occupies a large amount of system resources, affects the sending of other files, and reduces the efficiency of the system in sending files; if the fixed retransmission number is set too low, the file may not be accurately and completely sent to the target object, and the success rate of file sending is reduced. SUMMARY

[0005] Therefore, it is necessary to provide a file sending method, device, computer equipment, computer readable storage medium and computer program product which can balance the efficiency and success rate of file sending.

[0006] In a first aspect, the present application provides a file sending method, comprising:

[0007] performing feature extraction on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features;

[0008] performing file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result;

[0009] adjusting an initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number;

[0010] performing file sending on the to-be-sent file according to the actual retransmission number.

[0011] In one embodiment, the performing feature extraction on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features comprises:

[0012] performing feature extraction on the file attribute information to obtain file attribute information features;

[0013] performing feature extraction on the file sending time information to obtain time information features;

[0014] perform feature extraction on the file interaction party attribute information to obtain interaction party attribute information features;

[0015] fuse the file attribute information features, the time information features and the interaction party attribute information features to obtain file information features.

[0016] In one of the embodiments, the file interaction party attribute information comprises sender attribute information and receiver attribute information; and the performing feature extraction on the file interaction party attribute information to obtain interaction party attribute information features comprises:

[0017] extracting sender type information, sender network state information and file sending mode information from the sender attribute information;

[0018] extracting receiver type information and receiver cache state information from the receiver attribute information;

[0019] performing feature extraction on the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information to obtain interaction party attribute information features.

[0020] In one of the embodiments, the performing feature extraction on the file attribute information to obtain file attribute information features comprises:

[0021] extracting file size information and file quantity information of the to-be-sent file from the file attribute information;

[0022] performing feature extraction on the file size information and the file quantity information to obtain file attribute information features.

[0023] In one of the embodiments, the prediction result comprises a prediction value; and the adjusting the initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number comprises:

[0024] if the prediction value is less than or equal to a first preset threshold, adjusting the initial retransmission number of the to-be-sent file according to a difference between the prediction value and the first preset threshold to obtain an actual retransmission number;

[0025] if the prediction value is greater than the first preset threshold and less than a second preset threshold, taking the initial retransmission number of the to-be-sent file as an actual retransmission number;

[0026] if the prediction value is greater than the second preset threshold, increasing the initial retransmission number of the to-be-sent file according to a difference between the prediction value and the second preset threshold to obtain an actual retransmission number.

[0027] In one embodiment, before the step of adjusting the initial retransmission number of the to-be-sent file according to the prediction result to obtain the real retransmission number, the method further comprises:

[0028] correcting the prediction value according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent the importance of the to-be-sent file.

[0029] In a second aspect, the present application further provides a file sending device, comprising:

[0030] a feature extraction module, configured to extract features of file information of a to-be-sent file according to file attribute information, file sending time information and file interaction party attribute information of the to-be-sent file;

[0031] a prediction module, configured to perform file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result;

[0032] an adjustment module, configured to adjust the initial retransmission number of the to-be-sent file according to the prediction result to obtain a real retransmission number;

[0033] a file sending module, configured to perform file sending on the to-be-sent file according to the real retransmission number.

[0034] In one embodiment, the feature extraction module is further configured to:

[0035] extract features of the file attribute information to obtain file attribute information features, extract features of the file sending time information to obtain time information features, extract features of the file interaction party attribute information to obtain interaction party attribute information features, and fuse the file attribute information features, the time information features and the interaction party attribute information features to obtain the file information features.

[0036] In one embodiment, the file interaction party attribute information comprises sender attribute information and receiver attribute information, and the feature extraction module is further configured to:

[0037] extract sender type information, sender network state information and file sending mode information from the sender attribute information, extract receiver type information and receiver cache state information from the receiver attribute information, and extract features of the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information to obtain the interaction party attribute information features.

[0038] In one embodiment, the feature extraction module is further configured to:

[0039] extract file size information and file quantity information of each to-be-sent file from the file attribute information; and perform feature extraction on the file size information and the file quantity information to obtain file attribute information features.

[0040] In one of the embodiments, the prediction result includes a predicted value; and the adjusting module is further configured to:

[0041] if the predicted value is less than or equal to a first preset threshold, then adjusting the initial retransmission number of the to-be-sent file according to a difference between the predicted value and the first preset threshold to obtain an actual retransmission number; if the predicted value is greater than the first preset threshold and less than a second preset threshold, then taking the initial retransmission number of the to-be-sent file as the actual retransmission number; and if the predicted value is greater than the first preset threshold and less than the second preset threshold, then increasing the initial retransmission number of the to-be-sent file according to a difference between the predicted value and the second preset threshold to obtain the actual retransmission number.

[0042] In one of the embodiments, the apparatus further includes:

[0043] a correcting module configured to correct the predicted value according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent an importance degree of the to-be-sent file.

[0044] In a third aspect, the present application further provides a computer device including a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0045] performing feature extraction on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features; performing file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result; adjusting an initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number; and performing file sending on the to-be-sent file according to the actual retransmission number.

[0046] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the following steps:

[0047] The file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file are subjected to feature extraction to obtain file information features; the to-be-sent file is subjected to file retransmission prediction according to the file information features to obtain a prediction result; the initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain an actual retransmission number; and the to-be-sent file is subjected to file sending according to the actual retransmission number.

[0048] In a fifth aspect, the present application provides a computer program product, comprising a computer program which, when executed by a processor, implements the following steps:

[0049] The file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file are subjected to feature extraction to obtain file information features; the to-be-sent file is subjected to file retransmission prediction according to the file information features to obtain a prediction result; the initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain an actual retransmission number; and the to-be-sent file is subjected to file sending according to the actual retransmission number.

[0050] The file sending method, device, computer device, computer readable storage medium and computer program product can, when file sending is needed, first extract the file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file to obtain file information features, then predict the file retransmission of the to-be-sent file according to the file information features to obtain a prediction result, and thus adjust the initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number, which realizes flexible setting of the actual retransmission number for the to-be-sent file. The actual retransmission number is adapted to the actual situation of the to-be-sent file, and thus file sending of the to-be-sent file according to the actual retransmission number can ensure the efficiency and success rate of file sending. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application or the related art. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0052] Figure 1 The application environment diagram of the file sending method in an embodiment of the present application;

[0053] Figure 2 The flowchart of the file sending method in an embodiment of the present application;

[0054] Figure 3 a flowchart for generating file information features in an embodiment of the present application;

[0055] Figure 4 a flowchart for adjusting the initial retransmission number of a to-be-sent file in an embodiment of the present application;

[0056] Figure 5 a structural block diagram of a file sending device in an embodiment of the present application;

[0057] Figure 6 an internal structural diagram of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the objectives, technical solutions and advantages of the present application clearer, further detailed description will be made to the present application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0059] The file sending method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on a cloud or other network server. The terminal 102 extracts features of file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file, to obtain file information features. The terminal 102 performs file retransmission prediction on the to-be-sent file according to the file information features, to obtain a prediction result. The terminal 102 adjusts the initial retransmission number of the to-be-sent file according to the prediction result, to obtain a real retransmission number. The terminal 102 sends the to-be-sent file to the server 104 according to the real retransmission number. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle-mounted device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0060] In an exemplary embodiment, as shown in Figure 2 , a file sending method is provided, and the method is applied inFigure 1 The terminal 102 in the system 100 is taken as an example to illustrate the method, including the following steps 202 to 208. Wherein:

[0061] Step 202, feature extraction is performed on file attribute information, file sending time information and file interaction party attribute information of the to-be-sent file, to obtain file information features.

[0062] The file attribute information can be file size, file quantity and the like of the to-be-sent file, the file sending time information can be time information of sending the to-be-sent file, and the file interaction party attribute information can be file sender attribute information and file receiver attribute information.

[0063] As an example, step 202 includes: obtaining file attribute information, file sending time information and file interaction party attribute information of the to-be-sent file; extracting file attribute feature values from the file attribute information, extracting time feature values from the file sending time information, and extracting interaction party attribute feature values from the file interaction party attribute information; and merging the file attribute feature values, the time feature values and the interaction party attribute feature values into file information features.

[0064] The file attribute feature values can be file size values and file quantity values and the like, the time feature values can be specific time values, and the interaction party attribute feature values can be sender type identification, sender network state identification, file sending mode identification, receiver type identification and receiver buffer state identification and the like.

[0065] Step 204, file retransmission prediction is performed on the to-be-sent file according to the file information features, to obtain a prediction result.

[0066] In this embodiment, a file retransmission prediction model is provided, which can be a decision tree model or other AI model.

[0067] As an example, step 204 includes: inputting the file information features into the file retransmission prediction model to perform file retransmission prediction on the to-be-sent file, to obtain a prediction result, wherein the prediction result can be a prediction value, which is used to represent how many times of file retransmission the to-be-sent file is adapted to, the greater the prediction value, the more times of file retransmission the to-be-sent file is adapted to, and the smaller the prediction value, the less times of file retransmission the to-be-sent file is adapted to.

[0068] Step 206, the initial retransmission times of the to-be-sent file are adjusted according to the prediction result, to obtain real retransmission times.

[0069] As an example, the step 206 comprises: if the prediction value is within the preset value range, taking the initial retransmission number of the to-be-sent file as the real retransmission number; if the prediction value is out of the preset value range, increasing or decreasing the initial retransmission number of the to-be-sent file to obtain the real retransmission number.

[0070] The step 208 comprises: sending the to-be-sent file according to the real retransmission number.

[0071] As an example, the step 208 comprises: repeatedly sending the to-be-sent file to the target object according to the real retransmission number.

[0072] In the file sending method, when file sending is needed, the file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file are extracted to obtain file information features, then the to-be-sent file is predicted for file retransmission according to the file information features to obtain a prediction result, and the initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain the real retransmission number, so that the real retransmission number of the to-be-sent file is flexibly set, and the real retransmission number is adapted to the actual situation of the to-be-sent file, and therefore, when the to-be-sent file is sent according to the real retransmission number, the efficiency and the success rate of the file sending can be ensured.

[0073] In an example embodiment, as shown in Figure 3 The file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file are extracted to obtain file information features, which comprises:

[0074] The step 302 comprises: extracting the file attribute information to obtain file attribute information features.

[0075] The to-be-sent file can be composed of multiple sub-files, and the file attribute information comprises global file attribute information corresponding to the to-be-sent file and local file attribute information corresponding to each sub-file.

[0076] As an example, the step 302 comprises: encoding the global file attribute information to obtain a first encoding feature; encoding each local file attribute information to obtain multiple second encoding features; splicing the first encoding feature and each second encoding feature to obtain a first splicing feature; and inputting the first splicing feature into a preset file attribute feature extraction model to extract the first splicing feature for file attribute features to obtain the file attribute information features.

[0077] The step 304 comprises: extracting the file sending time information to obtain time information features.

[0078] The file sending time information can be the start time of file sending, or can be composed of the start time of file sending and the estimated end time of file sending.

[0079] In step 306, the file interaction party attribute information is extracted to obtain the interaction party attribute information feature.

[0080] The file interaction party attribute information can be composed of the sender attribute information and the receiver attribute information.

[0081] As an example, step 306 includes: extracting the sender attribute information to obtain the sender attribute information feature; extracting the receiver attribute information to obtain the receiver attribute information feature; and fusing the sender attribute information feature and the receiver attribute information feature to obtain the interaction party attribute information feature.

[0082] In one embodiment, the file interaction party attribute information includes the sender attribute information and the receiver attribute information; and the file interaction party attribute information is extracted to obtain the interaction party attribute information feature, including:

[0083] The sender type information, the sender network state information and the file sending mode information are extracted from the sender attribute information; the receiver type information and the receiver cache state information are extracted from the receiver attribute information; and the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information are extracted to obtain the interaction party attribute information feature.

[0084] The type of the sender affects the number of retransmissions of the file to be sent, for example, if the sender is a large enterprise, the system hardware is more advanced and the system resources are more sufficient, so a higher number of retransmissions can be adapted; if the sender is a school or the like, the system hardware is relatively old and the system resources are limited, so a lower number of retransmissions is more suitable; the sender type information can be a sender type identifier. The type of the receiver also affects the number of retransmissions of the file to be sent, for example, if the receiver is a large enterprise, the system hardware is more advanced and the system resources are more sufficient, so a higher number of retransmissions can be adapted; if the receiver is a school or the like, the system hardware is relatively old and the system resources are limited, so a lower number of retransmissions is more suitable; the receiver type information can be a receiver type identifier.

[0085] In addition, the network status of the sender and the file sending mode usually affect the time and system resources required for each file sending, so the influence of the network status of the sender and the file sending mode on the number of retransmissions needs to be considered. The sender network status information can be a sender network status identifier, and the file sending mode information can be a file sending mode identifier. The cache status of the receiver usually affects the time required for each file receiving, so the influence of the cache status of the receiver on the number of retransmissions needs to be considered. The receiver cache status information can be a receiver cache status identifier.

[0086] Specifically, the sender type identifier, the sender network status identifier, and the file sending mode identifier are extracted from the sender attribute information. The receiver type identifier and the receiver cache status identifier are extracted from the receiver attribute information by receiving the receiving method attribute information sent by the receiver. The sender type identifier, the sender network status identifier, the file sending mode identifier, the receiver type identifier, and the receiver cache status identifier are concatenated into a feature vector, and the feature vector is used as the interaction party attribute information feature.

[0087] In step 308, the file attribute information feature, the time information feature, and the interaction party attribute information feature are fused to obtain the file information feature.

[0088] As an example, step 308 includes concatenating the file attribute information feature, the time information feature, and the interaction party attribute information feature to obtain a second concatenated feature, and using the second concatenated feature as the file information feature.

[0089] In this embodiment, the file attribute information is feature-extracted to obtain the file attribute information feature, the file sending time information is feature-extracted to obtain the time information feature, the file interaction party attribute information is feature-extracted to obtain the interaction party attribute information feature, the file attribute information feature, the time information feature, and the interaction party attribute information feature are fused to obtain the file information feature, which realizes the construction of the file information feature from the three dimensions of the file attribute, the file sending time, and the file interaction party attribute, so that the feature dimension of the file information feature is more abundant, which helps to improve the accuracy of file retransmission prediction.

[0090] In one embodiment, the file attribute information is feature-extracted to obtain the file attribute information feature, including:

[0091] The file size information and the file quantity information of the file to be sent are extracted from the file attribute information, and the file size information and the file quantity information are feature-extracted to obtain the file attribute information feature.

[0092] The to-be-sent file can include a plurality of subfiles, the file size information includes a global file size corresponding to the to-be-sent file and a subfile size of each subfile, and the file quantity information refers to a quantity of subfiles in the to-be-sent file.

[0093] Specifically, a first feature value corresponding to the global file size, a second feature value corresponding to the size of each subfile, and a third feature value corresponding to the quantity of subfiles are extracted from the file attribute information; the first feature value, the plurality of second feature values, and the third feature value are spliced into a feature vector; and the feature vector is taken as the file attribute information feature. For example, assuming that the global file size corresponding to the to-be-sent file is 100, the to-be-sent file includes two subfiles, and the size of each subfile is 50, the first feature value is 100, the two second feature values are both 50, and the third feature value is 2, and thus the file information feature is the feature vector (100, 50, 50, 2).

[0094] In the above embodiment, the file size information and the file quantity information of the to-be-sent file are extracted from the file attribute information; the file size information and the file quantity information are subjected to feature extraction to obtain the file attribute information feature, so that the file information feature can be constructed from three dimensions of the global file size of the to-be-sent file, the size of each subfile, and the quantity of subfiles, the feature dimension of the file attribute information feature is enriched, and thus the information richness of the finally constructed file information feature is improved, laying a foundation for improving the accuracy of file retransmission prediction.

[0095] In one embodiment, as shown in FIG. 4, Figure 4 The prediction result includes a prediction value; and according to the prediction result, the initialization retransmission quantity of the to-be-sent file is adjusted to obtain the real retransmission quantity, including:

[0096] In step 402, if the prediction value is less than or equal to the first preset threshold, the initialization retransmission quantity of the to-be-sent file is reduced according to a difference between the prediction value and the first preset threshold to obtain the real retransmission quantity.

[0097] In step 404, if the prediction value is greater than the first preset threshold and less than a second preset threshold, the initialization retransmission quantity of the to-be-sent file is taken as the real retransmission quantity.

[0098] In step 406, if the prediction value is greater than the second preset threshold, the initialization retransmission quantity of the to-be-sent file is increased according to a difference between the prediction value and the second preset threshold to obtain the real retransmission quantity.

[0099] The prediction result can be a prediction value, and the prediction value is used to represent the file retransmission quantity adapted to the to-be-sent file.

[0100] As an example, the steps 402 to 406 include: if the prediction value is less than or equal to a first preset threshold, calculating a first difference between the prediction value and the first preset threshold, if the first difference is less than a first preset difference threshold, decreasing the initial retransmission number of the to-be-sent file by a first preset number to obtain the real retransmission number, if the first difference is greater than or equal to the first preset difference threshold, decreasing the initial retransmission number of the to-be-sent file by a second preset number to obtain the real retransmission number, wherein the second preset number is greater than the first preset number; if the prediction value is greater than the first preset threshold and less than a second preset threshold, taking the initial retransmission number of the to-be-sent file as the real retransmission number; if the prediction value is greater than the second preset threshold, calculating a second difference between the prediction value and the second preset threshold, if the second difference is less than a second preset difference threshold, increasing the initial retransmission number of the to-be-sent file by the first preset number to obtain the real retransmission number, if the second difference is greater than or equal to the second preset difference threshold, increasing the initial retransmission number of the to-be-sent file by the second preset number.

[0101] As an example, the first preset number can be set to 1, and the second preset number can be set to 2.

[0102] As an example, the steps 402 to 406 further include: if the prediction value is less than or equal to the first preset threshold, searching for a corresponding adjustment amplitude according to the difference between the prediction value and the first preset threshold to obtain a first adjustment amplitude; subtracting the first adjustment amplitude from the initial retransmission number of the to-be-sent file to obtain the real retransmission number; if the prediction value is greater than the first preset threshold and less than the second preset threshold, taking the initial retransmission number of the to-be-sent file as the real retransmission number; if the prediction value is greater than the second preset threshold, searching for a corresponding adjustment amplitude according to the difference between the prediction value and the second preset threshold to obtain a second adjustment amplitude, and adding the second adjustment amplitude to the initial retransmission number of the to-be-sent file to obtain the real retransmission number.

[0103] It should be noted that, in order to ensure that the real retransmission number will not be too high or too low without limit, a retransmission number upper limit value and a retransmission number lower limit value can be set to limit the real retransmission number of the to-be-sent file to be not higher than the retransmission number upper limit value and not lower than the first retransmission number lower limit value.

[0104] In the above embodiment, after the predicted value of the file retransmission prediction is obtained, the initial retransmission number of the to-be-sent file can be flexibly reduced according to the difference between the predicted value and the first preset threshold to obtain the real retransmission number when the predicted value is less than or equal to the first preset threshold; the initial retransmission number of the to-be-sent file is taken as the real retransmission number when the predicted value is greater than the first preset threshold and less than the second preset threshold; and the initial retransmission number of the to-be-sent file is flexibly increased according to the difference between the predicted value and the second preset threshold to obtain the real retransmission number when the predicted value is greater than the second preset threshold. In this way, the initial retransmission number of the to-be-sent file can be quantitatively adjusted according to the specific size of the predicted value to obtain the real retransmission number, so that the adjustment of the initial retransmission number is more reasonable, and the accuracy of the real retransmission number can be improved.

[0105] In one embodiment, before the initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain the real retransmission number, the method further comprises:

[0106] The predicted value is corrected according to a file type identifier of the to-be-sent file, where the file type identifier is used to represent the importance of the to-be-sent file.

[0107] Generally, the higher the file retransmission number is, the higher the success rate of accurately and completely sending the to-be-sent file to the target object is. Therefore, a higher file retransmission number should be set for a to-be-sent file with higher importance.

[0108] Specifically, the file type identifier of the to-be-sent file is obtained, where the file type identifier is used to represent the importance of the to-be-sent file; if the file type identifier is a preset type identifier, the predicted value is corrected by multiplying the predicted value by a preset correction coefficient, where the preset correction coefficient is greater than 1; and if the file type identifier is not the preset type identifier, the predicted value remains unchanged, where the preset type identifier is the file type identifier of an important file.

[0109] In this embodiment, the file type identifier of the to-be-sent file is detected, and the file retransmission number is increased by correcting the size of the predicted value when the file type identifier is the preset type identifier, which means that the to-be-sent file is an important file. In this way, the file sending success rate of the important file can be improved.

[0110] In one embodiment, firstly, file attribute information of a to-be-sent file, file sending time information, and file interaction party attribute information are acquired, wherein the to-be-sent file can be composed of multiple sub-files, the file attribute information includes global file attribute information corresponding to the to-be-sent file and local file attribute information corresponding to each sub-file, and the file interaction party attribute information can be composed of sender attribute information and receiver attribute information; the global file attribute information is encoded to obtain a first encoded feature; each local file attribute information is encoded to obtain multiple second encoded features; the first encoded feature and each second encoded feature are spliced to obtain a first spliced feature; the first spliced feature is input into a preset file attribute feature extraction model to perform file attribute feature extraction on the first spliced feature, and file attribute information features are obtained; time information features are obtained by performing feature extraction on the file sending time information; sender attribute information features are obtained by performing feature extraction on the sender attribute information; receiver attribute information features are obtained by performing feature extraction on the receiver information; interaction party attribute information features are obtained by fusing the sender attribute information features and the receiver attribute information features; and file information features are obtained by fusing the file attribute information features, the time information features, and the interaction party attribute information features.

[0111] Further, the file information features are input into a file retransmission prediction model to perform file retransmission prediction on the to-be-sent file, and a prediction result is obtained, wherein the prediction result can be a prediction value, the prediction value is used to represent how many times of file retransmission the to-be-sent file is adapted to, the greater the prediction value is, the more times of file retransmission the to-be-sent file is adapted to, and the smaller the prediction value is, the less times of file retransmission the to-be-sent file is adapted to; if the prediction value is less than or equal to a first preset threshold value, a first difference value between the prediction value and the first prediction threshold value is calculated, if the first difference value is less than a first preset difference threshold value, the initial retransmission number of the to-be-sent file is reduced by a first preset number to obtain a real retransmission number, if the first difference value is greater than or equal to the first prediction difference threshold value, the initial retransmission number of the to-be-sent file is reduced by a second preset number, wherein the second preset number is greater than the first preset number; if the prediction value is greater than the first preset threshold value and less than a second preset threshold value, the initial retransmission number of the to-be-sent file is taken as the real retransmission number; if the prediction value is greater than the second preset threshold value, a second difference value according to the prediction value and the second preset threshold value is calculated, if the second difference value is less than a second preset difference threshold value, the initial retransmission number of the to-be-sent file is increased by the first preset number to obtain the real retransmission number, if the second difference value is greater than or equal to the second preset difference threshold value, the initial retransmission number of the to-be-sent file is increased by the second preset number; finally, the to-be-sent file is repeatedly sent to a target object according to the real retransmission number.

[0112] In the embodiment, the initialization retransmission number of the to-be-sent file can be reasonably and accurately adjusted to obtain the real retransmission number, so that the real retransmission number is flexibly set for the to-be-sent file, and the real retransmission number is adapted to the actual situation of the to-be-sent file. Therefore, the to-be-sent file is sent according to the real retransmission number, so that the efficiency and success rate of file sending can be ensured.

[0113] It should be understood that, although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0114] Based on the same inventive concept, the embodiments of the present application also provide a file sending device for implementing the above-mentioned file sending method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more file sending device embodiments provided below can refer to the limitations of the file sending method in the above text, and will not be repeated here.

[0115] In one exemplary embodiment, as shown in Figure 5 a file sending device is provided, comprising: a feature extraction module 502, a prediction module 504, an adjustment module 506 and a file sending module 508, wherein:

[0116] The feature extraction module 502 is configured to extract features of file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features.

[0117] The prediction module 504 is configured to perform file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result.

[0118] The adjustment module 506 is configured to adjust an initialization retransmission number of the to-be-sent file according to the prediction result to obtain a real retransmission number.

[0119] The file sending module 508 is configured to perform file sending on the to-be-sent file according to the real retransmission number.

[0120] In one of the embodiments, the feature extraction module is further configured to:

[0121] extracting features from the file attribute information to obtain file attribute information features, extracting features from the file sending time information to obtain time information features, extracting features from the file interaction party attribute information to obtain interaction party attribute information features, and fusing the file attribute information features, the time information features and the interaction party attribute information features to obtain file information features.

[0122] In one of the embodiments, the file interaction party attribute information comprises sender attribute information and receiver attribute information; and the feature extraction module is further configured to:

[0123] extracting sender type information, sender network state information and file sending mode information from the sender attribute information, and extracting receiver type information and receiver cache state information from the receiver attribute information; and extracting features from the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information to obtain interaction party attribute information features.

[0124] In one of the embodiments, the feature extraction module is further configured to:

[0125] extracting file size information and file quantity information of each file to be sent from the file attribute information, and extracting features from the file size information and the file quantity information to obtain file attribute information features.

[0126] In one of the embodiments, the prediction result comprises a predicted value; and the adjustment module is further configured to:

[0127] if the predicted value is less than or equal to a first preset threshold, adjusting the initial retransmission number of the file to be sent to obtain an actual retransmission number according to a difference between the predicted value and the first preset threshold; if the predicted value is greater than the first preset threshold and less than a second preset threshold, taking the initial retransmission number of the file to be sent as the actual retransmission number; and if the predicted value is greater than the first preset threshold and less than the second preset threshold, increasing the initial retransmission number of the file to be sent to obtain an actual retransmission number according to a difference between the predicted value and the second preset threshold.

[0128] In one of the embodiments, the device further comprises:

[0129] a correction module configured to correct the predicted value according to a file type identifier of the file to be sent, wherein the file type identifier is used to represent an importance of the file to be sent.

[0130] The modules in the file sending device can be implemented by software, hardware, or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the modules.

[0131] In an exemplary embodiment, a computer device, which can be a terminal, is provided. An internal structure diagram of the computer device can be as shown in Figure 6 The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected through a system bus. The communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to perform wired or wireless communication with external terminals. The wireless communication can be achieved through WIFI, mobile cellular network, near field communication (NFC), or other technologies. The computer program is executed by the processor to implement a file sending method.

[0132] Those skilled in the art can understand that Figure 6 The structure shown in the above description is only a block diagram of part of the structure related to the scheme of the present application, and does not limit the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the diagram, or combine certain components, or have a different arrangement of components.

[0133] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the following steps:

[0134] Feature extraction is performed on file attribute information, file sending time information, and file interaction party attribute information of a to-be-sent file to obtain file information features;

[0135] File retransmission prediction is performed on the to-be-sent file according to the file information features to obtain a prediction result;

[0136] The initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain an actual retransmission number;

[0137] According to the real retransmission number, the file to be sent is sent.

[0138] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0139] The file attribute information is feature extracted to obtain file attribute information features;

[0140] The file sending time information is feature extracted to obtain time information features;

[0141] The file interaction party attribute information is feature extracted to obtain interaction party attribute information features;

[0142] The file attribute information features, the time information features and the interaction party attribute information features are fused to obtain file information features.

[0143] In one embodiment, the file interaction party attribute information includes sender attribute information and receiver attribute information; the processor, when executing the computer program, also implements the following steps:

[0144] Sender type information, sender network state information and file sending mode information are extracted from the sender attribute information;

[0145] Receiver type information and receiver cache state information are extracted from the receiver attribute information;

[0146] The sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information are feature extracted to obtain interaction party attribute information features.

[0147] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0148] File size information and file quantity information of the file to be sent are extracted from the file attribute information;

[0149] The file size information and the file quantity information are feature extracted to obtain file attribute information features.

[0150] In one embodiment, the prediction result includes a predicted value; the processor, when executing the computer program, also implements the following steps:

[0151] If the predicted value is less than or equal to a first preset threshold value, the initialization retransmission number of the file to be sent is reduced according to a difference between the predicted value and the first preset threshold value to obtain a real retransmission number;

[0152] If the predicted value is greater than the first preset threshold and less than the second preset threshold, the initial retransmission number of the to-be-sent file is taken as the real retransmission number;

[0153] If the predicted value is greater than the second preset threshold, the initial retransmission number of the to-be-sent file is increased according to a difference between the predicted value and the second preset threshold, to obtain the real retransmission number.

[0154] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0155] The predicted value is corrected according to a file type identifier of the to-be-sent file, where the file type identifier is used to represent an importance degree of the to-be-sent file.

[0156] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program, when executed by a processor, implements the following steps:

[0157] File attribute information, file sending time information, and file interaction party attribute information of a to-be-sent file are extracted to obtain file information features;

[0158] The to-be-sent file is predicted for file retransmission according to the file information features, to obtain a predicted result;

[0159] The initial retransmission number of the to-be-sent file is adjusted according to the predicted result, to obtain a real retransmission number;

[0160] The to-be-sent file is sent according to the real retransmission number.

[0161] In one embodiment, the computer program, when executed by the processor, also implements the following steps:

[0162] The file attribute information is extracted to obtain file attribute information features;

[0163] The file sending time information is extracted to obtain time information features;

[0164] The file interaction party attribute information is extracted to obtain interaction party attribute information features;

[0165] The file attribute information features, the time information features, and the interaction party attribute information features are fused to obtain file information features.

[0166] In one embodiment, the file interaction party attribute information includes sender attribute information and receiver attribute information; and the computer program, when executed by the processor, also implements the following steps:

[0167] extract sender type information, sender network state information and file sending mode information from the sender attribute information;

[0168] extract receiver type information and receiver buffer state information from the receiver attribute information;

[0169] perform feature extraction on the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver buffer state information to obtain interaction party attribute information features.

[0170] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0171] extract file size information and file quantity information of the to-be-sent file from the file attribute information;

[0172] perform feature extraction on the file size information and the file quantity information to obtain file attribute information features.

[0173] In one embodiment, the prediction result includes a predicted value; the computer program, when executed by the processor, further implements the following steps:

[0174] if the predicted value is less than or equal to a first preset threshold, then adjust down the initial retransmission number of the to-be-sent file according to a difference between the predicted value and the first preset threshold to obtain an actual retransmission number;

[0175] if the predicted value is greater than the first preset threshold and less than a second preset threshold, then take the initial retransmission number of the to-be-sent file as the actual retransmission number;

[0176] if the predicted value is greater than the second preset threshold, then adjust up the initial retransmission number of the to-be-sent file according to a difference between the predicted value and the second preset threshold to obtain the actual retransmission number.

[0177] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0178] correct the predicted value according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent the importance of the to-be-sent file.

[0179] In one embodiment, a computer program product is provided, including a computer program which, when executed by the processor, implements the following steps:

[0180] perform feature extraction on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information features;

[0181] According to the file information feature, file retransmission prediction is performed on the to-be-sent file, and a prediction result is obtained;

[0182] According to the prediction result, the initial retransmission number of the to-be-sent file is adjusted, and a real retransmission number is obtained;

[0183] According to the real retransmission number, file sending is performed on the to-be-sent file.

[0184] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0185] Feature extraction is performed on the file attribute information to obtain file attribute information features;

[0186] Feature extraction is performed on the file sending time information to obtain time information features;

[0187] Feature extraction is performed on the file interaction party attribute information to obtain interaction party attribute information features;

[0188] The file attribute information features, the time information features, and the interaction party attribute information features are fused to obtain file information features.

[0189] In one embodiment, the file interaction party attribute information includes sender attribute information and receiver attribute information; and the computer program, when executed by the processor, further implements the following steps:

[0190] Sender type information, sender network state information, and file sending method information are extracted from the sender attribute information;

[0191] Receiver type information and receiver cache state information are extracted from the receiver attribute information;

[0192] Feature extraction is performed on the sender type information, the sender network state information, the file sending method information, the receiver type information, and the receiver cache state information to obtain interaction party attribute information features.

[0193] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0194] File size information and file quantity information of the to-be-sent file are extracted from the file attribute information;

[0195] Feature extraction is performed on the file size information and the file quantity information to obtain file attribute information features.

[0196] In one embodiment, the prediction result includes a prediction value; and the computer program, when executed by the processor, further implements the following steps:

[0197] If the predicted value is less than or equal to a first preset threshold, then the initial retransmission number of the to-be-sent file is reduced according to a difference between the predicted value and the first preset threshold, to obtain a real retransmission number;

[0198] If the predicted value is greater than the first preset threshold and less than a second preset threshold, then the initial retransmission number of the to-be-sent file is taken as the real retransmission number;

[0199] If the predicted value is greater than the second preset threshold, then the initial retransmission number of the to-be-sent file is increased according to a difference between the predicted value and the second preset threshold, to obtain the real retransmission number.

[0200] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0201] The predicted value is corrected according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent an importance degree of the to-be-sent file.

[0202] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0203] In the technical solutions of the present application, the acquisition, transmission, storage, use, processing, etc. of data comply with the relevant regulations of national laws and regulations, and it should be noted that in the embodiments of the present application, some industry existing solutions, components, models, etc. may be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0204] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0205] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0206] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A file transmission method characterized by, The method comprises: characteristic extraction is performed on file attribute information, file sending time information and file interaction party attribute information of a to-be-sent file to obtain file information characteristics; file retransmission prediction is performed on the to-be-sent file according to the file information characteristics to obtain a prediction result; the initial retransmission number of the to-be-sent file is adjusted according to the prediction result to obtain an actual retransmission number; file sending is performed on the to-be-sent file according to the actual retransmission number.

2. The method of claim 1, wherein, The characteristic extraction on the file attribute information, the file sending time information and the file interaction party attribute information of the to-be-sent file to obtain the file information characteristics comprises: characteristic extraction is performed on the file attribute information to obtain file attribute information characteristics; characteristic extraction is performed on the file sending time information to obtain time information characteristics; characteristic extraction is performed on the file interaction party attribute information to obtain interaction party attribute information characteristics; the file attribute information characteristics, the time information characteristics and the interaction party attribute information characteristics are fused to obtain the file information characteristics.

3. The method of claim 2, wherein, The file interaction party attribute information comprises sender attribute information and receiver attribute information; the characteristic extraction on the file interaction party attribute information to obtain the interaction party attribute information characteristics comprises: sender type information, sender network state information and file sending mode information are extracted from the sender attribute information; receiver type information and receiver cache state information are extracted from the receiver attribute information; characteristic extraction is performed on the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information to obtain the interaction party attribute information characteristics.

4. The method of claim 2, wherein, The characteristic extraction on the file attribute information to obtain the file attribute information characteristics comprises: file size information and file quantity information of the to-be-sent file are extracted from the file attribute information; characteristic extraction is performed on the file size information and the file quantity information to obtain the file attribute information characteristics.

5. The method of claim 1, wherein, The prediction result comprises a prediction value; the adjustment of the initial retransmission number of the to-be-sent file according to the prediction result to obtain the actual retransmission number comprises: if the prediction value is less than or equal to a first preset threshold, the initial retransmission number of the to-be-sent file is reduced according to a difference between the prediction value and the first preset threshold to obtain the actual retransmission number; if the prediction value is greater than the first preset threshold and less than a second preset threshold, the initial retransmission number of the to-be-sent file is taken as the actual retransmission number; if the prediction value is greater than the second preset threshold, the initial retransmission number of the to-be-sent file is increased according to a difference between the prediction value and the second preset threshold to obtain the actual retransmission number.

6. The method of claim 5, wherein, Before the adjustment of the initial retransmission number of the to-be-sent file according to the prediction result to obtain the actual retransmission number, the method further comprises: the prediction value is corrected according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent the importance of the to-be-sent file.

7. A file transmitting apparatus characterized by comprising: The device comprises: The feature extraction module is configured to perform feature extraction on file attribute information, file sending time information and file interaction party attribute information of the to-be-sent file to obtain file information features. The prediction module is configured to perform file retransmission prediction on the to-be-sent file according to the file information features to obtain a prediction result. The adjustment module is configured to adjust the initial retransmission number of the to-be-sent file according to the prediction result to obtain an actual retransmission number. The file sending module is configured to perform file sending on the to-be-sent file according to the actual retransmission number.

8. The apparatus of claim 7, wherein, The feature extraction module is further configured to: perform feature extraction on the file attribute information to obtain file attribute information features, perform feature extraction on the file sending time information to obtain time information features, perform feature extraction on the file interaction party attribute information to obtain interaction party attribute information features, and fuse the file attribute information features, the time information features and the interaction party attribute information features to obtain the file information features.

9. The apparatus of claim 8, wherein, The file interaction party attribute information includes sender attribute information and receiver attribute information, and the feature extraction module is further configured to: extract sender type information, sender network state information and file sending mode information from the sender attribute information, and extract receiver type information and receiver cache state information from the receiver attribute information; perform feature extraction on the sender type information, the sender network state information, the file sending mode information, the receiver type information and the receiver cache state information to obtain the interaction party attribute information features.

10. The apparatus of claim 8, wherein, The feature extraction module is further configured to: extract file size information and file quantity information of each to-be-sent file from the file attribute information, and perform feature extraction on the file size information and the file quantity information to obtain the file attribute information features.

11. The apparatus of claim 7, wherein, The prediction result includes a prediction value, and the adjustment module is further configured to: if the prediction value is less than or equal to a first preset threshold, adjust the initial retransmission number of the to-be-sent file downward according to a difference between the prediction value and the first preset threshold to obtain the actual retransmission number; if the prediction value is greater than the first preset threshold and less than a second preset threshold, take the initial retransmission number of the to-be-sent file as the actual retransmission number; if the prediction value is greater than the first preset threshold and less than the second preset threshold, adjust the initial retransmission number of the to-be-sent file upward according to a difference between the prediction value and the second preset threshold to obtain the actual retransmission number.

12. The apparatus of claim 11, wherein, The device further includes: a correction module configured to correct the prediction value according to a file type identifier of the to-be-sent file, wherein the file type identifier is used to represent the importance of the to-be-sent file.

13. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method in any one of claims 1 to 6.

14. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

15. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6. The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images