WO2020224215A1

WO2020224215A1 - Artificial intelligence-based image compression method and apparatus, device, and storage medium

Info

Publication number: WO2020224215A1
Application number: PCT/CN2019/117738
Authority: WO
Inventors: 郭勇
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-05-08
Filing date: 2019-11-13
Publication date: 2020-11-12
Also published as: CN110298895A

Abstract

An artificial intelligence-based image compression method and apparatus, a device, and a storage medium, the method comprising: receiving an image compression instruction inputted by a user (S101); compressing an original image according to a compression mode and at least one compression parameter to obtain a compressed image to be reviewed (S102); presenting the compressed image to be reviewed to the user such that the user reviews the compressed image (S103); when an instruction that review is not passed is received from the user, readjusting the compression parameter, re-compressing the original image using the newly adjusted compression parameter, and presenting the image to the user for review (S104); and when an instruction that review is passed is received from the user, uploading the compressed image confirmed by the user to a target location (S105). The described method allows a user to select a compression mode and compression parameter that match a target scene so as to compress an image to adapt to multiple different target scenes, and operation is easy; moreover, a parameter can be adjusted multiple times for re-compression, which can better meet the personal requirements of users.

Description

Artificial intelligence-based image compression method, device, equipment and storage medium

This application is based on the Chinese invention patent application filed on May 8, 2019 with the application number 201910383813.6, titled "artificial intelligence-based image compression method, device, equipment and storage medium", and claims its priority.

Technical field

The embodiments of the present application belong to the technical field of image compression, and in particular, relate to an artificial intelligence-based image compression method, device, device, and storage medium.

Background technique

The picture compression software in the prior art adapts to a single scene. For example, some scenes require high picture quality, some scenes require a small picture size, some scenes require a small picture memory, and some scenes are due to uploaded pictures. The size of the uploaded picture is not suitable for the need to zoom. In the process of implementing this application, the inventor realizes that the existing implementation at least has the following problem: for the aforementioned multiple different scenarios, only a variety of different compression software or Technology to adapt to various different scenarios, user operation is very inconvenient, and can only be compressed once, even if the compression effect is not good, it is impossible to change the parameters for compression, which cannot well meet the personal needs of users.

Summary of the invention

In order to solve the above problems, the embodiments of the present application provide an artificial intelligence-based image compression method, device, equipment, and storage medium to solve the problem that the prior art requires a variety of compression software to compress images for a variety of different scenarios. Convenience and inability to change parameters to better meet the needs of users.

In the first aspect, an embodiment of the present application provides an artificial intelligence-based image compression method, including:

Receiving a picture compression instruction input by a user, the instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

Compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

Present the compressed image to be reviewed to the user so that the user can review the compressed image;

When receiving the user's approval failure instruction, readjust the compression parameters, recompress the original picture with the newly adjusted compression parameters and present it to the user for approval;

When the user's approval instruction is received, the compressed image confirmed by the user is uploaded to the target location.

In the second aspect, an embodiment of the present application provides an artificial intelligence-based image compression device, including:

An instruction receiving module, configured to receive a picture compression instruction input by a user, the instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

A compression module, configured to compress the original picture according to the compression mode and at least one compression parameter to obtain a compressed picture to be reviewed;

The presentation module is used to present the compressed picture to be reviewed to the user, so that the user can review the compressed picture;

The adjustment parameter recompression module is used to readjust the compression parameters when the user's review failure instruction is received, and recompress the original picture with the newly adjusted compression parameters and present it to the user for review;

The image upload module is used to upload the compressed image confirmed by the user to the target location when the user's approval instruction is received.

Some embodiments of the present application also disclose a computer device in which computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, it implements the aforementioned artificial intelligence-based image compression method. step.

Some embodiments of the present application also disclose a computer nonvolatile readable storage medium, the computer nonvolatile readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor When realizing the steps of the image compression method based on artificial intelligence as described above.

Compared with the prior art, the technical solution disclosed in this application mainly has the following beneficial effects:

In the embodiment of this application, the user inputs a picture compression instruction matching the target scene, and the compression instruction carries the original picture and compression mode information; this application compresses the original picture according to the compression mode information; presents the compressed picture to the user, In order to allow users to review the compressed pictures; in this way, users can check whether the compression effect is what they want. If it is not what the user wants, they can automatically adjust the compression parameters to recompress and review, so as to meet the user's personal needs and realize the user In one software, the original picture is compressed by selecting the compression mode and compression parameters suitable for the target scene to adapt to a variety of different target scenes, avoiding the single defect of the existing compression software compression function, and convenient operation.

Description of the drawings

In order to explain the solution of the present application more clearly, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. As far as personnel are concerned, they can obtain other drawings based on these drawings without creative work.

FIG. 1 is a flowchart of a picture compression method provided by an embodiment of the application;

FIG. 2 is a flowchart of an embodiment of a picture compression method provided by this application;

FIG. 3 is a flowchart of another embodiment of a picture compression method provided by this application;

4 is a structural block diagram of an artificial intelligence-based image compression device provided by an embodiment of the application;

FIG. 5 is a structural block diagram of another embodiment of the image compression device based on artificial intelligence in this application;

Fig. 6 is a block diagram of the hardware structure of a computer device provided by an embodiment of the application.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of this application. The terms used in the specification of the application herein are only for the purpose of describing specific embodiments, and are not intended to limit the application. The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

Reference to "embodiments" herein means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

An embodiment of the present application provides an artificial intelligence-based image compression method, as shown in FIG. 1, which is a flowchart of the image compression method provided by an embodiment of the application;

The method includes:

S101. Receive a picture compression instruction input by a user, where the picture compression instruction carries an original picture and compression mode information, and the compression mode information includes a compression mode and at least one compression parameter in the compression mode.

Specifically, a variety of compression mode information for picture compression adapted to different target scenes are preset, the compression mode information includes a compression mode, and the compression mode includes at least one compression parameter, and the compression mode information is stored for use When encountering different target scenes, the user can input the compression mode information that matches the target scene in a selective input mode or a manual input mode.

When only one compression parameter is included in the compression mode, it is called the default parameter;

When the compression mode includes at least two compression parameters, the compression parameters are set with priority levels. For example, the priority levels of the first parameter, the second parameter, and the third parameter may be successively increased or decreased.

Among them, for a variety of different target scenarios, the compression mode set in this embodiment includes but is not limited to the following modes:

a. Preset compression ratio (compression ratio = actual size of space occupied / size of space occupied before compression) mode:

Applicable target scenarios: Nowadays, almost all websites can upload pictures. Photos taken by mobile phones are generally high-definition pictures with relatively high pixels, which take up a lot of storage space. Every user uploading a 3M picture will occupy a lot of space. Storage space, the cost of hard disks and storage disks will increase; on the other hand, the picture memory is too large, and the same network speed will cause users to wait too long to load web pages, reducing user experience, in order to avoid users loading Webpage waiting time is too long, either increase the network speed or reduce the image memory, and the cost of the network speed is too high, so the best way is to reduce the image memory, you can compress the image, by setting a different compression ratio, for example, the compression ratio can be But not limited to 1.0, 0.5, 0.3, 0.1, the compression parameters in this compression mode include a preset compression ratio. The compression mode contains at least one compression parameter. One or more compression parameters can be set according to the needs and experience of the corresponding target scene. When there is only one compression parameter, it is called the default parameter. When multiple compression parameters are set, The compression parameter has a priority level, for example, the first parameter has the highest priority, the second parameter has the second priority, and the third parameter has the lowest priority.

b. Zoom mode:

Applicable target scenarios: In some scenarios, such as uploading some small icons of avatars in QQ, WeChat, Weibo and APP on some websites, the pictures are only used for distinguishing and identifying, so that people can know the avatar at a glance. Who does not need to know the specific content information of the picture at all, and can scale the size of the picture;

Including proportional zoom and non-constant zoom.

The compression parameters in the compression mode include the scaling ratio (size after compression/size before compression), such as 80%, 70%, 50%, 20%, and so on.

The compression mode contains at least one compression parameter. One or more compression parameters can be set according to the needs and experience of the corresponding target scene. When there is only one compression parameter, it is called the default parameter. When multiple compression parameters are set, The compression parameters are provided with priority levels, for example, the priority levels of the first parameter, the second parameter, and the third parameter are sequentially increased or decreased.

S102. Compress the original picture according to the compression mode and at least one compression parameter to obtain a compressed picture to be reviewed.

S103. Present the compressed picture to be reviewed to the user, so that the user can review the compressed picture.

Specifically, the compressed image to be reviewed is presented to the user through an interface, so that the user can review the compressed image.

In some scenes that require smaller memory, because different websites allow different image memory sizes to be uploaded, the target scenes corresponding to different websites require different compression parameters, or the size of the images uploaded each time may vary. There is a big difference. Some photos are only a few megabytes, and some photos are tens of megabytes. Using the same compression parameter to compress in the same mode may not meet the needs of users (such as sharpness requirements, etc.) or cause abnormalities. Upload to the target location (target website); for example, in some scenarios where the size of the image is small, because the size of the image required by the target website is different each time or because the size of the image to be uploaded is different each time, Using the same compression parameter in the same mode may not meet the needs of the user or cause the upload to the target location not to be normal; in the case of the user being dissatisfied or unable to upload to the target location normally, the user can follow the preset operating instructions to indicate I am dissatisfied with the current compressed picture, and the review fails.

S104: When receiving the user's disapproval instruction, readjust the compression parameter, and recompress the original picture with the newly adjusted compression parameter and present it to the user for review.

S105: When the user's approval instruction is received, upload the compressed picture confirmed by the user to the target location.

Referring to FIG. 2, FIG. 2 is a flowchart of an embodiment of an artificial intelligence-based image compression method provided by this application;

In this embodiment,

S201. Receive a picture compression instruction input by a user, where the instruction carries an original picture and compression mode information, and the compression mode information includes a compression mode and at least two compression parameters with priority levels in the compression mode.

S202: Compress the original picture according to the compression mode and the compression parameter with the highest priority.

S203. Present the compressed picture to be reviewed to the user, so that the user can review the compressed picture.

S204. When receiving the user's disapproval instruction, select the compression parameter of the next level in the order of priority as the newly adjusted compression parameter, and recompress the original picture with the newly adjusted compression parameter and present it to the user Audit.

Specifically, taking two compression parameters as an example, the original picture is compressed according to the compression mode and the compression parameter with the highest priority, such as the first parameter, and the recompressed picture is re-presented to the user, so that the user can feel the compressed picture Re-audit, when receiving the user's failed audit instruction, because there are still parameters, according to the order of priority, select the second parameter in the picture compression instruction as the newly adjusted compression parameter, and use the newly adjusted compression parameter to The original picture is recompressed, and the recompressed picture is re-presented to the user so that the user can review the compressed picture again.

S205: When the user's approval instruction is received, upload the compressed picture confirmed by the user to the target location. The advantage of this setting is that when the original picture with the highest priority compression parameter is used for compression and cannot pass the user's review, other parameters in the compression parameter are replaced for recompression, which increases the chance of meeting user needs.

Further, please refer to FIG. 3, which is a flowchart of another embodiment of the picture compression method provided by this application;

If all the compression parameters still cannot meet the needs of the user after replacing all the compression parameters, and there are no other parameters to replace at this time, that is, in the order of priority level, select the compression parameters as the newly adjusted compression parameters in the picture compression command, and use the newly adjusted compression After the parameter recompresses the original picture and re-presents the recompressed picture to the user so that the user can review the compressed picture again, it also includes:

S301: If the pictures compressed using all the compression parameters fail to pass the user's review, the value of the compression parameter with the highest priority level is gradually increased and/or decreased according to the preset interval and preset step length;

S302: Use the compression parameters that are gradually increased and/or decreased as the newly adjusted compression parameters, and recompress the original pictures respectively to obtain the compressed pictures to be selected;

S303: Present the compressed picture to be selected to the user at the same time, so as to obtain the user's choice of the compressed picture to be selected. Wherein, the simultaneous presentation of the compressed pictures to be selected to the user means that the compressed pictures to be selected are presented to the user in the order of gradually increasing and/or decreasing compression parameters; the preset interval may be to increase the value of the compression parameter or An interval formed by floating down a certain range, such as [compression parameter value*(1-10%), compression parameter value*(1+10%)], [compression parameter value*(1-10%) , Compression parameter value], [Compression parameter value, compression parameter value*(1+10%)], etc.; the value of the preset step size can be divided into several small segments evenly, such as the preset interval 1%, 2%, 5% of, can be the preset step size and so on.

If the user is dissatisfied with all compressed pictures and issues a deselect command, then

S304: When the user cancels the selection instruction, issue an instruction to acquire the custom compression parameter to the user;

S305. Receive the custom compression parameter input by the user, and recompress the original picture according to the custom compression parameter input by the user and present it to the user for review.

S306: Return to step S305 when receiving the user's disapproval instruction.

If the user issues an instruction to confirm the selection, then

S307: When receiving the selection instruction confirmed by the user, upload the compressed picture selected by the user to the target location.

In this embodiment, the value of the compression parameter with the highest priority level is gradually increased and/or decreased according to the preset interval and preset step length; the compression parameter gradually increased and/or decreased as the newly adjusted compression parameter, Recompress and review the original pictures separately, and you can compress more pictures with different effects for users to choose the one that best meets their needs.

Optionally, in some other embodiments, only one compression parameter is included in the compression mode, which is also called a default parameter; the step S102 of compressing the original picture according to the compression mode and the at least one compression parameter includes:

The original picture is compressed according to the compression mode and the default parameters in the compression mode.

The step of re-adjusting compression parameters when receiving a user's disapproval instruction, and recompressing the original picture with the newly adjusted compression parameters and presenting it to the user for review includes:

Gradually increasing and/or decreasing the value of the default parameter according to the preset interval and the preset step length;

Taking the gradually increasing and decreasing compression parameters as the newly adjusted compression parameters, the original pictures are respectively recompressed to obtain the compressed pictures to be selected.

Present the compressed pictures to be selected to the user at the same time to obtain the user's choice of compressed pictures to be selected.

When receiving the user's confirmation selection instruction, upload the compressed picture selected by the user to the target location.

If the user is not satisfied with all the compressed pictures and issues a deselection instruction, after the step of presenting the compressed pictures to be selected to the user at the same time to obtain the user's selection of the compressed pictures, it also includes: when the user's deselection is received When instructing, issue a user-defined compression parameter instruction to the user, receive the user-defined compression parameter input, and re-compress the original image according to the user-defined compression parameter input and present it to the user for review; when the user’s review is received When the instruction is passed, upload the compressed picture confirmed by the user to the target location. When receiving the user's disapproval instruction, return to the step to receive the custom compression parameter input by the user, and recompress the original picture according to the custom compression parameter input by the user and present it to the user for review.

In this embodiment, when only one compression parameter is included in the compression mode, when a user's review failure instruction is received, the value of the default parameter is gradually increased and/or decreased according to a preset interval and a preset step; Using the gradually increasing and decreasing compression parameters as the newly adjusted compression parameters, the original pictures are recompressed separately, and more pictures with different effects can also be compressed for users to choose the pictures that best meet their needs.

When a user cancel selection instruction is received, that is, when the user is not satisfied with all the compressed pictures and the cancel selection instruction is issued, the user is issued an instruction to obtain custom compression parameters;

Receiving a custom compression parameter instruction input by the user, and recompressing the original image according to the custom compression parameter input by the user and presenting it to the user for review;

When receiving the user's approval instruction, upload the compressed image confirmed by the user to the target location;

When the user is not satisfied with the compression effect of the preset compression parameters of the compression mode itself, they can choose to input the compression parameters by themselves. The benefits of this setting can better adapt to the user's needs and increase the probability of the user obtaining qualified compressed pictures.

An embodiment of the present application also provides a picture compression device based on artificial intelligence, as shown in FIG. 4, which is a structural block diagram of the picture compression device provided by an embodiment of the application. The device includes:

The instruction receiving module 1 is configured to receive a picture compression instruction input by a user, the instruction carrying an original picture and compression mode information, and the compression mode information includes a compression mode and at least one compression parameter in the compression mode;

The compression module 2 is configured to compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

The presentation module 3 is used to present the compressed picture to be reviewed to the user, so that the user can review the compressed picture;

The adjustment parameter recompression module 5 is used to readjust the compression parameters when receiving a user's unapproved instruction, and recompress the original picture with the newly adjusted compression parameters and present it to the user for review;

The picture upload module 4 is used to upload the compressed picture confirmed by the user to the target location when the user's approval instruction is received.

In the embodiment of the present application, the instruction receiving module 1 receives a picture compression instruction carrying compression mode information input by the user, and the compression module 2 responds to the picture compression instruction and compresses the original picture according to the compression mode and at least one compression parameter to obtain Compressed pictures to be reviewed; in this way, the user can input picture compression instructions that match the target scene, compress the original pictures according to the compression mode information, and get compressed pictures to be reviewed; the presentation module 3 presents the compressed pictures to be reviewed to the user, so that the user Review the compressed image; so that the user can check whether the compression effect is what they want, and if it is what the user wants, then confirm it. The image upload module 4 receives the user’s approval instruction and uploads the compressed image confirmed by the user to the target Position, realize user-defined selection of compression mode suitable for the target scene and compression parameters to compress the original picture.

In some scenes that require smaller memory, because different websites allow different image memory sizes to be uploaded, the target scenes corresponding to different websites require different compression parameters, or the size of the images uploaded each time may vary. There is a big difference. Some photos are only a few megabytes, and some photos are tens of megabytes. In the same mode, using the highest priority parameters for compression may not meet the needs of users (such as sharpness requirements, etc.) or may result in failure Normally upload to the target location such as the target website. Or in some scenes where the size of the image required is small, due to the difference in the size of the image required by the target website each time or because the size of the image to be uploaded each time is different, the priority level is adopted in the same mode Compression with the highest parameter may not meet the needs of users or may result in failure to upload to the target location normally. In the case that the user is not satisfied or cannot upload to the target location normally, the user can follow the preset operation instructions to indicate that the review is not passed.

The adjustment parameter recompression module 5 is used to re-adjust the compression parameters when receiving a user’s unapproved instruction, and recompress the original picture with the newly adjusted compression parameters; the presentation module 3 is used to recompress the recompressed picture It is presented to the user to enable the user to review the compressed image again, and then the image upload module 4 uploads the compressed image confirmed by the user to the target location when the user’s approval instruction is received. By setting the adjustment parameter re-compression module 5, different compression parameters can be changed and compressed to meet the requirements of users and satisfy users.

Specifically, in some feasible embodiments, the compression mode carried in the image compression instruction input by the user received by the instruction receiving module 1 includes at least two compression parameters with priority levels;

At this time, the compression module 2 is configured to compress the original picture according to the compression mode and the compression parameter with the highest priority;

The adjustment parameter recompression module 5 is configured to select the compression parameter of the next level as the newly adjusted compression parameter in the order of priority level, and recompress the original picture with the newly adjusted compression parameter and present it to the user for review.

More specifically, taking two compression parameters as an example, the compression module 2 compresses the original picture according to the compression mode and the compression parameter with the highest priority, such as the first parameter; the adjustment parameter recompression module 5 receives the user’s review and does not When the instruction is passed, the second parameter can be replaced as a new compression parameter to recompress the original picture.

There may be a situation where the user has passed the review and issued an instruction for approval, and the image upload module 4 is used to upload the compressed image confirmed by the user to the target location when the user's approval instruction is received.

Due to the limited number of compression parameters in the compression mode of the artificial intelligence-based image compression device of this application, it may happen that the parameters are changed until all the compression parameters have been used, but all the compressed images cannot pass the user’s review. In the embodiment, the device is based on the embodiment of FIG. 4, and the adjustment parameter recompression module 5 is also used to adjust the priority level when all the pictures compressed by the compression parameter in the picture compression instruction fail to pass the user's review. The value of the highest compression parameter is gradually increased and/or decreased according to the preset interval and preset step length; the compression parameter after the gradual increase and/or decrease is used as the newly adjusted compression parameter, and the original image is recompressed respectively to obtain The compressed picture to be selected; the presentation module 3 is also used to present the compressed picture to be selected to the user at the same time, so as to obtain the user's choice of the compressed picture to be selected; the picture upload module 4 is also used to send the user a selection instruction confirmed by the user The selected compressed image is uploaded to the target location.

Wherein, presenting the compressed pictures to be selected to the user at the same time means that the compressed pictures to be selected are arranged and presented to the user in the order of the size of the compression parameter after gradually increasing and/or decreasing.

Please refer to FIG. 5. FIG. 5 is a structural block diagram of an embodiment of a picture compression apparatus of this application.

This embodiment further includes a custom parameter acquisition and recompression module 6 on the basis of the embodiment in FIG. 4.

Specifically, the custom parameter acquisition and recompression module 6 is used to issue a custom compression parameter acquisition instruction to the user when receiving a user's deselection instruction, receive the custom compression parameter instruction input by the user, and compress according to the custom compression input by the user The parameters recompress the original picture and present it to the user for review.

The picture upload module 4 is also used to upload the compressed picture confirmed by the user to the target location when the user's approval instruction is received.

In this embodiment, the user can input the custom parameters by himself when the user is not satisfied with the audit once or after re-adjusting the parameters for many times, so that the compression is more in line with the target scene and the needs of the user.

Further, the compression module 2 includes:

A priority compression unit, configured to compress the original picture according to the compression mode and the compression parameter with the highest priority;

The recompression unit is configured to select the compression parameter of the next level as the newly adjusted compression parameter in the order of priority level, and recompress the original picture with the newly adjusted compression parameter and present it to the user for review.

Further, the image compression device based on artificial intelligence further includes:

The dynamic parameter adjustment module is used to gradually increase and/or decrease the value of the compression parameter with the highest priority according to the preset interval and preset step length if the image compressed by all the compression parameters fails to pass the user's review ；

The to-be-selected compressed picture determining module is used to use the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters to re-compress the original pictures to obtain the to-be-selected compressed pictures;

The picture display module is used to present the compressed pictures to be selected to the user at the same time, so as to obtain the user's choice of the compressed pictures to be selected;

The picture transmission module is used to upload the compressed picture selected by the user to the target location when the selection instruction confirmed by the user is received.

In order to solve the above technical problems, an embodiment of the present application also discloses a computer device. For details, please refer to FIG. 6, which is a block diagram of the basic structure of the computer device 100 in the embodiment of the application.

As shown in FIG. 6, the computer device 100 includes a memory 101, a processor 102, and a network interface 103 that are communicatively connected to each other through a system bus. It should be pointed out that FIG. 6 only shows the computer device 100 with the components 101-103, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculation and/or information processing in accordance with pre-set or stored instructions. Its hardware includes but is not limited to microprocessors, dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Programmable Gate Array (Field-Programmable Gate Array, FPGA), Digital Processor (Digital Signal Processor, DSP), embedded devices, etc.

The computer device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The computer device can interact with the user through a keyboard, a mouse, a remote control, a touch panel, or a voice control device.

The memory 101 includes at least one type of non-volatile readable storage medium, and the non-volatile readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), Random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), magnetic memory, magnetic disk, optical disk Wait. In some embodiments, the memory 101 may be an internal storage unit of the computer device 100, such as a hard disk or memory of the computer device 100. In other embodiments, the memory 101 may also be an external storage device of the computer device 100, such as a plug-in hard disk, a smart media card (SMC), and a secure digital device equipped on the computer device 100. (Secure Digital, SD) card, Flash Card, etc. Of course, the memory 101 may also include both an internal storage unit of the computer device 100 and an external storage device thereof. In this embodiment, the memory 101 is generally used to store an operating system and various application software installed in the computer device 100, such as the above-mentioned artificial intelligence-based image compression method. In addition, the memory 101 can also be used to temporarily store various types of data that have been output or will be output.

The processor 102 may be a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 102 is generally used to control the overall operation of the computer device 100. In this embodiment, the processor 102 is configured to execute computer-readable instructions or process data stored in the memory 101, such as computer-readable instructions for executing the above-mentioned artificial intelligence-based image compression method.

The network interface 103 may include a wireless network interface or a wired network interface. The network interface 103 is generally used to establish a communication connection between the computer device 100 and other electronic devices.

This application also provides another embodiment, that is, to provide a computer non-volatile readable storage medium, the computer non-volatile readable storage medium stores computer readable instructions, and the computer readable instructions can Is executed by at least one processor, so that the at least one processor executes the steps of any one of the foregoing artificial intelligence-based image compression methods.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiments can be implemented by means of software plus the necessary general hardware platform, of course, through hardware, but in many cases the former is better.的实施例。 Example. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, The optical disc) includes several instructions to enable a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the method described in each embodiment of the present application.

Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all of the embodiments. The drawings show preferred embodiments of the present application, but do not limit the patent scope of the present application. This application can be implemented in many different forms. On the contrary, the purpose of providing these examples is to make the understanding of the disclosure of this application more thorough and comprehensive. Although the application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or equivalently replace some of the technical features. . All equivalent structures made using the contents of the description and drawings of this application, directly or indirectly used in other related technical fields, are similarly within the scope of patent protection of this application.

Claims

An artificial intelligence-based image compression method, characterized in that it includes:

Receiving a picture compression instruction input by a user, the picture compression instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

Compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

Present the compressed image to be reviewed to the user so that the user can review the compressed image;

When receiving the user's approval failure instruction, readjust the compression parameters, recompress the original picture with the newly adjusted compression parameters and present it to the user for approval;

When the user's approval instruction is received, the compressed image confirmed by the user is uploaded to the target location.
The artificial intelligence-based image compression method according to claim 1, wherein the compression mode includes at least two compression parameters with priority levels; the compression mode and the at least one compression parameter are used to compare the original image The steps to compress include:

Compress the original picture according to the compression mode and the compression parameter with the highest priority;

The step of re-adjusting the compression parameters, re-compressing the original picture with the newly adjusted compression parameters and presenting it to the user for review includes:

The compression parameter of the next level is selected in the order of priority level as the newly adjusted compression parameter, and the original picture is recompressed with the newly adjusted compression parameter and presented to the user for review.
The artificial intelligence-based image compression method according to claim 2, wherein after the step of re-adjusting the compression parameters, recompressing the original image with the newly adjusted compression parameters and presenting it to the user for review, further include:

If the pictures compressed with all the compression parameters fail to pass the user's review, the value of the compression parameter with the highest priority is gradually increased and/or decreased according to the preset interval and preset step length;

Using the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters, recompress the original pictures respectively to obtain the compressed pictures to be selected;

Present the compressed pictures to be selected to the user at the same time to obtain the user's choice of compressed pictures to be selected;

When receiving the selection instruction confirmed by the user, upload the compressed picture selected by the user to the target location.
The artificial intelligence-based picture compression method according to claim 3, wherein the simultaneous presentation of the compressed pictures to be selected to the user is to present the compressed pictures to be selected in the order of gradually increasing and/or decreasing compression parameters. The arrangement is presented to the user.
The artificial intelligence-based image compression method according to claim 3, wherein after the step of simultaneously presenting the compressed image to be selected to the user to obtain the user's selection of the compressed image to be selected, the method further comprises:

When receiving the user's deselection instruction, issue the user-defined compression parameter instruction to the user;

The custom compression parameter input by the user is received, and the original picture is recompressed according to the custom compression parameter input by the user and presented to the user for review.
The artificial intelligence-based image compression method according to claim 1, wherein said compression mode contains only one compression parameter; said when receiving a user’s approval failure instruction, readjust the compression parameters to The steps of recompressing the original picture with the newly adjusted compression parameters and presenting it to the user for review include:

Gradually increasing and/or decreasing the value of the compression parameter according to a preset interval and a preset step length;

Using the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters, recompress the original pictures respectively to obtain the compressed pictures to be selected;

Present the compressed pictures to be selected to the user at the same time to obtain the user's choice of compressed pictures to be selected;

When receiving the user's confirmation selection instruction, upload the compressed picture selected by the user to the target location.
The artificial intelligence-based picture compression method according to claim 6, wherein after the step of simultaneously presenting the compressed pictures to be selected to the user to obtain the user's selection of the compressed pictures to be selected, the method further comprises:

When receiving the user's deselection instruction, issue the user-defined compression parameter instruction to the user;

The custom compression parameter input by the user is received, and the original picture is recompressed according to the custom compression parameter input by the user and presented to the user for review.
A picture compression device based on artificial intelligence, characterized in that it comprises:

An instruction receiving module, configured to receive a picture compression instruction input by a user, the instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

The compression module is configured to respond to the picture compression instruction and compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

The presentation module is used to present the compressed picture to be reviewed to the user, so that the user can review the compressed picture;

The adjustment parameter recompression module is used to readjust the compression parameters when the user's review failure instruction is received, and recompress the original picture with the newly adjusted compression parameters and present it to the user for review;

The image upload module is used to upload the compressed image confirmed by the user to the target location when the user's approval instruction is received.
The image compression device based on artificial intelligence according to claim 8, wherein the compression module comprises:

A priority compression unit, configured to compress the original picture according to the compression mode and the compression parameter with the highest priority;

The recompression unit is configured to select the compression parameter of the next level as the newly adjusted compression parameter in the order of priority level, and recompress the original picture with the newly adjusted compression parameter and present it to the user for review.
The artificial intelligence-based picture compression device according to claim 9, wherein the artificial intelligence-based picture compression device further comprises:

The dynamic parameter adjustment module is used to gradually increase and/or decrease the value of the compression parameter with the highest priority according to the preset interval and preset step length if the image compressed by all the compression parameters fails to pass the user's review ；

The to-be-selected compressed picture determining module is used to use the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters to re-compress the original pictures to obtain the to-be-selected compressed pictures;

The picture display module is used to present the compressed pictures to be selected to the user at the same time, so as to obtain the user's choice of the compressed pictures to be selected;

The picture transmission module is used to upload the compressed picture selected by the user to the target location when the selection instruction confirmed by the user is received.
A computer device includes a memory and a processor, wherein the memory stores computer readable instructions, and the processor implements the following steps of the artificial intelligence-based image compression method when the processor executes the computer readable instructions:

Receiving a picture compression instruction input by a user, the picture compression instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

Compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

Present the compressed image to be reviewed to the user so that the user can review the compressed image;

When receiving the user's approval failure instruction, readjust the compression parameters, recompress the original picture with the newly adjusted compression parameters and present it to the user for approval;

When the user's approval instruction is received, the compressed image confirmed by the user is uploaded to the target location.
The computer device according to claim 11, wherein the compression mode includes at least two compression parameters with priority levels; the step of compressing the original picture according to the compression mode and at least one compression parameter comprises :

Compress the original picture according to the compression mode and the compression parameter with the highest priority;

The step of re-adjusting the compression parameters, re-compressing the original picture with the newly adjusted compression parameters and presenting it to the user for review includes:

The compression parameter of the next level is selected in the order of priority level as the newly adjusted compression parameter, and the original picture is recompressed with the newly adjusted compression parameter and presented to the user for review.
The computer device according to claim 12, characterized in that, after the step of re-adjusting the compression parameters to recompress the original picture with the newly adjusted compression parameters and present it to the user for review, the processor executes all The following steps are also implemented when the computer-readable instructions are described:

If the pictures compressed with all the compression parameters fail to pass the user's review, the value of the compression parameter with the highest priority is gradually increased and/or decreased according to the preset interval and preset step length;

Using the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters, recompress the original pictures respectively to obtain the compressed pictures to be selected;

Present the compressed pictures to be selected to the user at the same time to obtain the user's choice of compressed pictures to be selected;

When receiving the selection instruction confirmed by the user, upload the compressed picture selected by the user to the target location.
The computer device according to claim 13, wherein the simultaneous presentation of the compressed pictures to be selected to the user is to arrange and present the compressed pictures to be selected to the user in the order of gradually increasing and/or decreasing compression parameters.
The computer device according to claim 13, wherein after the step of simultaneously presenting the compressed picture to be selected to the user to obtain the user's selection of the compressed picture to be selected, the processor executes the computer-readable instruction It also implements the following steps:

When receiving the user's deselection instruction, issue the user-defined compression parameter instruction to the user;

The custom compression parameter input by the user is received, and the original picture is recompressed according to the custom compression parameter input by the user and presented to the user for review.
A computer non-volatile readable storage medium is characterized in that computer readable instructions are stored on the computer non-volatile readable storage medium. When the computer readable instructions are executed by a processor, the following is The steps of the smart image compression method:

Receiving a picture compression instruction input by a user, the picture compression instruction carrying an original picture and compression mode information, the compression mode information including a compression mode and at least one compression parameter in the compression mode;

Compress the original picture according to the compression mode and at least one compression parameter to obtain the compressed picture to be reviewed;

Present the compressed image to be reviewed to the user so that the user can review the compressed image;

When receiving the user's approval failure instruction, readjust the compression parameters, recompress the original picture with the newly adjusted compression parameters and present it to the user for approval;

When the user's approval instruction is received, the compressed image confirmed by the user is uploaded to the target location.
The non-volatile readable storage medium according to claim 16, wherein the compression mode contains at least two compression parameters with priority levels; the compression mode and the at least one compression parameter are compared to the original The steps for image compression include:

Compress the original picture according to the compression mode and the compression parameter with the highest priority;

The step of re-adjusting the compression parameters, re-compressing the original picture with the newly adjusted compression parameters and presenting it to the user for review includes:

The compression parameter of the next level is selected in the order of priority level as the newly adjusted compression parameter, and the original picture is recompressed with the newly adjusted compression parameter and presented to the user for review.
The non-volatile readable storage medium according to claim 17, wherein after the step of re-adjusting the compression parameter, recompressing the original picture with the newly adjusted compression parameter and presenting it to the user for review, When the computer-readable instructions are executed by the processor, the processor further executes the following steps:

If the pictures compressed with all the compression parameters fail to pass the user's review, the value of the compression parameter with the highest priority is gradually increased and/or decreased according to the preset interval and preset step length;

Using the gradually increasing and/or decreasing compression parameters as the newly adjusted compression parameters, recompress the original pictures respectively to obtain the compressed pictures to be selected;

Present the compressed pictures to be selected to the user at the same time to obtain the user's choice of compressed pictures to be selected;

When receiving the selection instruction confirmed by the user, upload the compressed picture selected by the user to the target location.
The non-volatile readable storage medium according to claim 18, wherein the simultaneous presentation of the compressed pictures to be selected to the user is to display the compressed pictures to be selected according to the size of the compression parameter after gradually increasing and/or decreasing. The order is presented to the user.
The non-volatile readable storage medium according to claim 18, wherein after the step of simultaneously presenting the compressed picture to be selected to the user to obtain the user's selection of the compressed picture to be selected, the computer readable When the instruction is executed by the processor, the processor further executes the following steps:

When receiving the user's deselection instruction, issue the user-defined compression parameter instruction to the user;

The custom compression parameter input by the user is received, and the original picture is recompressed according to the custom compression parameter input by the user and presented to the user for review.