WO2021017458A1

WO2021017458A1 - Auxiliary processing method, device, and system for image recognition

Info

Publication number: WO2021017458A1
Application number: PCT/CN2020/076063
Authority: WO
Inventors: 廖春安
Original assignee: 浙江口碑网络技术有限公司
Priority date: 2019-07-31
Filing date: 2020-02-20
Publication date: 2021-02-04
Also published as: CN110598186A

Abstract

The present application relates to the technical field of image recognition. Disclosed are an auxiliary processing method, device, and system for image recognition, capable for reducing paths and costs for obtaining information by a user and improving the efficiency and accuracy of editing recognition information by a user. The method comprises: outputting at least one input box comprising image recognition information, wherein items of sub-information in the image recognition information are displayed in respective corresponding input boxes; and receiving an information editing instruction and sending an identifier of an item to be filled corresponding to a selected input box, so as to highlight field information corresponding to the identifier of the item to be filled in an uploaded image while performing information editing in the selected input box. The present application is suitable for auxiliary processing for image recognition.

Description

Auxiliary processing method, device and system for image recognition

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on July 31, 2019, the application number is 201910702681.9, and the application name is "Image recognition auxiliary processing method, device and system", the entire content of which is incorporated by reference Applying.

Technical field

This application relates to the field of image recognition technology, and in particular to an auxiliary processing method, device and system for image recognition.

Background technique

With the development of science and technology, image recognition technology is more and more widely used. For example, the image recognition technology can be used to identify the business qualification information in the business license image, thereby helping the user to replace manual input, thereby improving the efficiency of the platform party in obtaining the business qualification information.

In the current traditional image recognition process, there may also be links where recognition errors require user editing. However, the inventor found that the prior art does not provide assistance in the process of editing the identification information by the user, which affects the efficiency and accuracy of editing the identification information by the user.

Summary of the invention

In view of this, this application provides an auxiliary processing method, device and system for image recognition. The main purpose is to solve the problem that the user is not assisted in editing the identification information in the traditional image recognition process, which affects the user's editing of the identification information. Technical issues of efficiency and accuracy.

According to one aspect of the present application, an auxiliary processing method for image recognition is provided, which can be applied to the client side. The method includes: outputting at least one input box containing image recognition information, wherein each item in the image recognition information The sub-information is displayed in the corresponding input box; the information editing instruction is received, and the item identification to be filled corresponding to the selected input box is sent, so as to edit the information in the selected input box while uploading the image Highlight the field information corresponding to the identifier of the item to be filled in.

Optionally, after information editing is performed in the selected input box, the method further includes: in the uploaded image, updating the prominent display form of the field information corresponding to the identifier of the item to be filled in, Wherein, the updated prominent display form is used to determine that the field information corresponding to the item identification to be filled in has an information editing operation.

Optionally, after information editing is performed in the selected input box, the method further includes: in the uploaded image, highlighting that the similarity of the field information corresponding to the item identification to be filled is greater than a preset Other field information of the threshold.

Optionally, the method further includes: recording the edited content information before and after the information is edited; and sending the edited content information to update the image recognition database.

Optionally, before the output of the at least one input box containing the image recognition information, the method further includes: receiving an image upload instruction, sending the uploaded image for image recognition; receiving the image recognition corresponding to the uploaded image Information; according to the respective identifiers of the items to be filled in corresponding to the input boxes, fill in the respective sub-information in the image identification information in their corresponding input boxes.

According to another aspect of the present application, another auxiliary processing method for image recognition is provided, which can be applied to the server side. The method includes: receiving the identifier of the item to be filled corresponding to the selected input box; Fill in the group ID corresponding to the item ID; obtain the field information corresponding to the group ID in the uploaded image, so that while editing the information in the selected input box, trigger the field information in the uploaded image Make a prominent display.

Optionally, the method further includes: receiving the uploaded image; using preset recognition matching rules corresponding to each item to be filled in, performing image recognition on the uploaded image to obtain image recognition information and return it, wherein the image The identification information contains the sub-information corresponding to the identification of each item to be filled in; the image-recognized field information in the uploaded image is grouped according to the corresponding identification and field content of the item to be filled in, and the field identified with the image is configured The group identifier corresponding to the information, and the mapping relationship between the group identifier and the corresponding item identifier.

Optionally, after performing image recognition on the uploaded image to obtain image recognition information using preset recognition matching rules corresponding to each item to be filled in, the method further includes: triggering to highlight each item in the uploaded image Field information that has been image-recognized.

Optionally, if image recognition of the uploaded image cannot be performed according to the preset recognition matching rule, the method further includes: returning a prompt message of an image upload error.

Optionally, image recognition is performed on the uploaded image based on OCR recognition technology.

According to another aspect of the present application, an auxiliary processing device for image recognition is provided, which can be applied to the client side. The device includes: an output module for outputting at least one input box containing image recognition information, wherein the The sub-information in the image recognition information is displayed in the corresponding input box; the sending module is used to receive the information editing instruction, and send the item identification corresponding to the selected input box to input the selected item While editing the information in the box, highlight the field information corresponding to the identifier of the item to be filled in the uploaded image.

Optionally, the device further includes: an update module, configured to update the prominent display form of the field information corresponding to the item identification to be filled in the uploaded image, wherein the updated prominent display form is When it is determined that the field information corresponding to the item identification to be filled in, there is an information editing operation. Optionally, the output module is further configured to highlight other field information whose content similarity is greater than a preset threshold in the field information corresponding to the item identification to be filled in in the uploaded image.

Optionally, the device further includes: a recording module; the recording module is used to record the edited content information before and after the information is edited; the sending module is also used to send the edited content information so as to update the image recognition database .

Optionally, the device further includes: a receiving module and a filling module;

The sending module is also used to receive an image upload instruction and send the uploaded image for image recognition; the receiving module is used to receive the image recognition information corresponding to the uploaded image; the filling module is used to follow The respective input boxes correspond to the identifiers of the items to be filled in, and each sub-information in the image identification information is filled in the respective input boxes.

According to another aspect of the present application, an auxiliary processing device for image recognition is provided, which can be applied to the server side. The device includes: a receiving module for receiving the identifier of the item to be filled corresponding to the selected input box; and querying The module is used to query the group ID corresponding to the item ID to be filled in; the sending module is used to obtain the field information corresponding to the group ID in the uploaded image, so as to edit the information in the selected input box At the same time, trigger the field information to be prominently displayed in the uploaded image.

Optionally, the device further includes: an identification module and a grouping module; the receiving module is further configured to receive the uploaded image; the identification module is configured to use preset identification matching rules corresponding to each item to be filled in, Perform image recognition on the uploaded image to obtain image recognition information, where the image recognition information contains sub-information corresponding to the identifiers of each item to be filled in; the sending module is also used to return the image recognition information; the grouping The module is used to group the image-recognized field information in the uploaded image according to the corresponding item identifiers and field contents, and configure the grouping identifier corresponding to the image-recognized field information, and the grouping The mapping relationship between the identifier and the corresponding identifier of the item to be filled in.

Optionally, the sending module is also used to trigger the prominent display of each image-recognized field information in the uploaded image.

Optionally, the sending module is further configured to, if image recognition of the uploaded image cannot be performed according to the preset recognition matching rule, return a prompt message of an image upload error. Optionally, image recognition is performed on the uploaded image based on OCR recognition technology.

According to another aspect of the present application, there is provided a non-volatile readable storage medium having computer readable instructions stored thereon, and when the computer readable instructions are executed by a processor, the foregoing image that can be applied to the client side is realized. Recognized auxiliary processing method.

According to another aspect of the present application, there is provided a client device, including a non-volatile readable storage medium, a processor, and a computer readable storage medium that is stored on the non-volatile readable storage medium and can run on the processor. Instructions, when the processor executes the computer-readable instructions, the foregoing auxiliary processing method applicable to image recognition on the client side is realized.

According to another aspect of the present application, there is provided a non-volatile readable storage medium having computer-readable instructions stored thereon, and the computer-readable instructions, when executed by a processor, realize the above-mentioned image applicable to the server side Recognized auxiliary processing method.

According to another aspect of the present application, there is provided a server device, including a non-volatile readable storage medium, a processor, and computer readable instructions stored on the non-volatile readable storage medium and running on the processor When the processor executes the computer-readable instruction, the above-mentioned auxiliary processing method applicable to image recognition on the server side is realized.

According to another aspect of the present application, an auxiliary processing system for image recognition is provided, including: the above-mentioned client device and the above-mentioned server device.

By virtue of the above technical solutions, the present application provides an image recognition auxiliary processing method, device and system. Compared with the current traditional image recognition process, this application uses the selected input box when receiving the information editing instruction. The corresponding identification of the item to be filled in can be edited in the input box while highlighting the field information corresponding to the identification of the item to be filled in the uploaded image, thereby assisting the user in editing, thus facilitating the user to understand in time The content of fields in the image related to the information being edited can help the user in the process of editing the identification information, reduce the path and cost for the user to obtain the information, and improve the efficiency and accuracy of the user's editing of the identification information.

The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented in accordance with the content of the specification, and to make the above and other purposes, features and advantages of this application more obvious and understandable. , The following specifically cite the specific implementation of this application.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 shows a schematic flowchart of an auxiliary processing method for image recognition provided by an embodiment of the present application;

2 shows a schematic flowchart of another auxiliary processing method for image recognition provided by an embodiment of the present application;

FIG. 3 shows a schematic flowchart of yet another image recognition auxiliary processing method provided by an embodiment of the present application;

FIG. 4 shows a schematic flowchart of yet another image recognition auxiliary processing method provided by an embodiment of the present application;

FIG. 5 shows a schematic flowchart of an application scenario provided by an embodiment of the present application;

FIG. 6 shows an example schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 7 shows a schematic structural diagram of an auxiliary processing device for image recognition provided by an embodiment of the present application;

FIG. 8 shows a schematic structural diagram of another image recognition auxiliary processing device provided by an embodiment of the present application;

FIG. 9 shows a schematic structural diagram of an auxiliary processing system for image recognition provided by an embodiment of the present application.

Detailed ways

Hereinafter, the application will be described in detail with reference to the drawings and in conjunction with embodiments. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other if there is no conflict.

For the current traditional image recognition process, there is no assistance in the process of editing the identification information by the user, which affects the efficiency and accuracy of the user's editing of the identification information. This embodiment provides an auxiliary processing method for image recognition, as shown in FIG. 1, which can be applied to the client side, and the method includes:

101. The client outputs at least one input box containing image recognition information.

Among them, each sub-information in the image recognition information is displayed in their corresponding input boxes. The image identification information is obtained by sending the uploaded image to the server for identification. In this embodiment, each item to be filled has a corresponding input box, and the content displayed in the input box is the image recognition content corresponding to the item to be filled. If there is a recognition error or the user needs to modify the recognition content, the user can manually edit the content displayed in the input box, such as adding, deleting, or replacing some text. The execution subject of this embodiment may be an auxiliary processing client device or device for image recognition, which is used to better guide the user to quickly identify the fields that need to be edited in the process of editing image recognition information. Specifically, the process shown in step 102 may be executed.

102. Receive an information editing instruction, and send the identifier of the item to be filled in corresponding to the selected input box to the server, so that while editing information in the selected input box, highlight the corresponding item identifier in the uploaded image The field information.

When the user needs to edit the image recognition information displayed in a certain input box, he can select the input box, such as tapping, clicking, etc., and then input the information editing instruction. Correspondingly, when the client receives the information editing instruction, it can obtain the identifier of the item to be filled in corresponding to the selected input box, and then send the identifier of the item to be filled to the server, and the server will query the upload image according to the identifier. And then trigger it to highlight in the uploaded image (such as highlighting, bolding, adding shading, frame selection, underline and other display forms different from other fields), and then it can be displayed on the client side in the While editing the information in the selected input box, highlight the corresponding field information in the uploaded image. Compared with the current traditional image recognition process, the method of this embodiment can be used to edit information in the input box while highlighting the corresponding field information in the uploaded image, thereby assisting the user in editing, thereby facilitating the user to understand in time The content of fields in the image related to the information being edited can help the user in the process of editing the identification information, reduce the path and cost for the user to obtain the information, and improve the efficiency and accuracy of the user's editing of the identification information.

Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully explain the specific implementation process of this embodiment, another auxiliary processing method that can be applied to image recognition on the client side is provided, as shown in FIG. 2 As shown, the method includes:

201. The client receives an image upload instruction and sends the uploaded image to the server for image recognition.

For example, the user can tap or click the upload button, select the image file to be uploaded, and then click to confirm the upload and input the image upload instruction. On the client side, upon receiving the image upload instruction, the uploaded image selected by the user is sent to the server for image recognition.

202. Receive image identification information corresponding to the uploaded image returned by the server.

In this embodiment, when performing image recognition on the uploaded image, the server can identify the sub-information corresponding to each item to be filled in, and then return the image recognition information to the client.

203. Fill in each item of sub-information in the received image identification information in the respective input boxes according to the respective identifiers of the items to be filled in corresponding to the input boxes.

For example, fill in the sub-information corresponding to item A to be filled in the image recognition information in the input box corresponding to item A on the client side; fill in the sub-information corresponding to item B to be filled in the image recognition information in the customer In the input box corresponding to item B on the end side.

204. Output at least one input box containing image recognition information.

Among them, each sub-information in the image recognition information is displayed in their corresponding input boxes. For this embodiment, after image recognition, in order to enable the user to know in time the fields in the uploaded image that have been recognized by the image, optionally, the server can perform image recognition on the uploaded image to identify the fields in the uploaded image. Mark and trigger highlight display. Correspondingly, on the client side, while outputting at least one input box, each image-recognized field information can be highlighted in the uploaded image. Through this optional method, the user can clearly identify which fields in the image have been identified, and find those unidentified fields in time, which can be manually edited and added later to facilitate searching, thereby improving the efficiency of information input. Further optionally, when each recognized field is prominently displayed in the uploaded image, the corresponding identifier of the item to be filled out or the identifier of the corresponding input box can be attached to facilitate the user to check the error and find the information of the identification error in time.

205. Receive the information editing instruction and send the identifier of the item to be filled in corresponding to the selected input box to the server, so that while editing the information in the selected input box, highlight the corresponding identifier of the item to be filled in the uploaded image The field information.

Specifically, when highlighting the field information, if other field information has already been highlighted, then perform differentiated highlight display (such as using different color shading or background color, thicker, increasing the number of underlined lines, or canceling other field information Highlight display effects, etc.). In order to highlight the field information in the image corresponding to the information being edited.

Further, after editing the information in the selected input box, in order to make the user clarify that the identification content of the field in the image has been re-edited, optionally, in the uploaded image, the identification corresponding to the item to be filled in The prominent display form of the field information is updated, wherein the updated prominent display form is used to determine that the field information corresponding to the item identification to be filled has an information editing operation. For example, a differentiated highlight display is performed to remind the user that the identification content of the field in the uploaded image has been re-edited, which is convenient for the user to check errors and edit management in time.

Since a unified recognition method is used in the image recognition process, the same field content in the image is usually recognized as the same content, that is, there are multiple identical recognition information. If the user re-edits one of the recognition information, then It is likely that several other identification information will be re-edited, so in order to improve the efficiency of information editing, it is further optional. After editing the information in the selected input box, you can highlight and fill in the uploaded image The item identifier corresponds to other field information whose content similarity is greater than a preset threshold.

Among them, the preset threshold can be preset according to actual needs, and the higher the threshold is set, the more similar the content. The highlight display here is used to remind the user where in the image the field corresponding to the other identification information that is similar or identical to the information editing, so that the user can find the corresponding input box in time according to the identification of the item to be filled, and then continue Re-edit several other identical or similar identification information. In this way, the efficiency and accuracy of user information editing can be improved, and the identification information that needs to be re-edited can be avoided.

The process of re-editing the information by the user indicates to a certain extent that image recognition may have a certain error. Therefore, in order to improve the accuracy of subsequent image recognition, it is further optional. This embodiment may also include: editing before and after editing the recorded information Content information; and then send the edited content information to the server to update the image recognition database. Furthermore, the subsequent server can perform a more accurate image recognition process on the newly uploaded image through the updated data.

The content of the above embodiment is the auxiliary processing process of image recognition described on the client side. Further, in order to fully explain the implementation of this embodiment, this embodiment also provides another auxiliary processing method of image recognition, which can be applied to On the server side, as shown in Figure 3, the method includes:

301. The server receives the identifier of the item to be filled in corresponding to the selected input box.

302. Query the group identifier corresponding to the identifier of the item to be filled in.

In this embodiment, the server may pre-calculate the identifiers of the items to be filled in the client, such as A1, A2, A3. When performing image recognition on uploaded images, you can group the recognized fields, for example, group according to the identifiers of the items to be filled, and mark the groups as B1, B2, and B3 in turn, where A1 corresponds to B1, A2 corresponds to B2 , A3 corresponds to B3. Therefore, if the server receives that the item to be filled in corresponding to the selected input box is identified as A1, the corresponding group identification can be queried as B1.

303. Obtain field information corresponding to the group identifier in the uploaded image, so that while editing the information in the selected input box, trigger the field information to be highlighted in the uploaded image.

Since each identified field information in the uploaded image has been grouped, the position information of the corresponding field information can be obtained in the image through the grouping identifier, and then according to the position information, the client side edits the information in the input box while triggering The corresponding field information is highlighted in the image.

Through the above-mentioned auxiliary processing method for image recognition that can be applied to the server side, compared with the current prior art, while editing information in the input box, the corresponding field information can be highlighted in the uploaded image, thereby assisting The role of user editing, so as to facilitate the user to understand the field content related to the information being edited in the image in time, and to help the user in the process of editing the identification information, reduce the path and cost for the user to obtain information, and improve the efficiency of the user to edit the identification information And accuracy. Further, as a refinement and extension of the specific implementation of the above-mentioned embodiment, in order to fully explain the specific implementation process of this embodiment, another auxiliary processing method that can be applied to the image recognition on the server side is provided, as shown in FIG. 4 As shown, the method includes:

401. The server receives the uploaded image sent by the client.

402. Perform image recognition on the uploaded image by using preset recognition matching rules corresponding to each item to be filled in to obtain image recognition information and return it to the client.

Among them, the image identification information includes sub-information corresponding to each item identifier to be filled in. The preset identification matching rules can be determined according to the content form of the items to be filled in. For example, if the items to be filled in are the items on the date of establishment of the company, the identification matching rules can be determined according to the matching rules on XXXX year XX month XX; The matching rule for is determined; if the item to be filled is the filled-in item of the registered capital, then the identification matching rule can be determined according to the matching rule of the capitalized number combination + currency. In this embodiment, the server prepares the identification of the item to be filled out in advance, and establishes one-to-one identification matching rules. Different identification and matching rules may have differences, which are determined according to the content form of the item to be filled out, so that each of the uploaded images can be identified. Accurate identification of the field information corresponding to the item to be filled in.

Further, in order to enable the user to know the image-recognized fields in the uploaded image in time, optionally, after step 402, it may further include: the server triggers to highlight the information of each image-recognized field in the uploaded image. Correspondingly, on the client side, while outputting at least one input box, each image-recognized field information can be highlighted in the uploaded image. Through this optional method, the user can clearly identify which fields in the image have been identified, and find those unidentified fields in time, which can be manually edited and added later to facilitate searching, thereby improving the efficiency of information input.

Furthermore, if the uploaded image cannot be recognized according to these preset recognition and matching rules, it means that the uploaded image does not meet the requirements. It is likely that the user uploaded an image error. Therefore, a prompt message of the image upload error can be returned to help the user correct in time. .

Optionally, in this embodiment, image recognition may be performed on the uploaded image based on the optical character recognition (Optical Character Recognition, OCR) recognition technology. As the current OCR recognition technology is relatively perfect, it can meet the accuracy of image recognition.

403. Group the image-recognized field information in the uploaded image according to the corresponding item identification and field content, and configure the group identification corresponding to the image-recognized field information, as well as the group identification and the corresponding item identification The mapping relationship between.

404. The server receives the identifier of the item to be filled in corresponding to the input box selected by the user sent by the client.

405. Use the established mapping relationship to query the group identifier corresponding to the identifier of the item to be filled in.

406. Obtain field information corresponding to the group identifier in the uploaded image, so as to trigger the field information to be highlighted in the uploaded image while editing information in the selected input box.

In order to further explain the implementation process of the method in this embodiment, the following application scenarios are given, but not limited to this: For example, if the merchant needs to create its own online store on the platform side, in order to ensure security, the platform will review the qualification of the merchant side Information, and the current way to replace the user’s manual input of information is to upload business license information, and then identify the corresponding business qualification information through OCR recognition technology. However, in practice, there is likely to be a link in which recognition errors need to be edited, so how to better guide users in the editing process to quickly identify the fields that need to be edited and improve input efficiency and accuracy, there is room for optimization.

In order to achieve the above purpose, as shown in Figure 5, the back-end server can prepare in advance the field names to be filled in (such as A1, A2, A3, etc.), and establish a one-to-one identification matching rule; then the user uploads the picture of the business license; the back-end server Receive the image information, fill the recognized fields into the input box, group the recognized fields (name + content as a group), and mark the groups in turn (such as B1, B2, B3, etc., where A1 corresponds to B1 , A2 corresponds to B2, A3 corresponds to B3...); the user clicks any input box (such as A1) to trigger the editing instruction; the background server triggers the highlight display of the corresponding field (such as A1=B1), and the B1 field information is identified in the picture . The specific form can be shown in Figure 6.

By applying the above solution, based on the OCR recognition technology, the identified fields in the picture are marked. When the user edits the corresponding fields, the input box is activated to trigger the marked fields, and the corresponding fields are displayed in the picture. Furthermore, through picture annotation, help users are provided in the process of editing fields, and the path and cost for users to obtain information are reduced.

Further, as a specific implementation of the method shown in FIG. 1 and FIG. 2, an embodiment of the present application provides an auxiliary processing device applicable to image recognition on the client side. As shown in FIG. 7, the device includes: an output module 51. Sending module 52.

The output module 51 can be used to output at least one input box containing image recognition information, wherein each sub-information in the image recognition information is displayed in their respective input boxes;

The sending module 52 can be used to receive information editing instructions, and send the item identification corresponding to the selected input box, so that while editing the information in the selected input box, highlight the information in the uploaded image. Field information corresponding to the identifier of the item to be filled in.

In a specific application scenario, the output module 51 may also be used to highlight the field information of each image recognized in the uploaded image while outputting the at least one input box.

In a specific application scenario, the device also includes: an update module 53;

The update module 53 can be used to update the prominent display form of the field information corresponding to the identification of the item to be filled in the uploaded image, wherein the updated prominent display form is used to determine the same as the identification of the item to be filled. The corresponding field information has an information editing operation.

In a specific application scenario, the output module 51 may also be used to highlight other field information whose content similarity is greater than a preset threshold in the field information corresponding to the item identifier to be filled in in the uploaded image.

In specific application scenarios, the device further includes: a recording module 54;

The recording module 54 can be used to record the edited content information before and after the information is edited;

The sending module 52 can also be used to send the edited content information so as to update the image recognition database.

In a specific application scenario, the device further includes: a receiving module 55 and a filling module 56;

The sending module 52 may also be used to receive an image upload instruction, and send the uploaded image for image recognition;

The receiving module 55 may be used to receive the image identification information corresponding to the uploaded image;

The filling module 56 can be used to fill in each sub-information of the image identification information in the corresponding input box according to the identifier of the item to be filled in each corresponding input box.

It should be noted that, for other corresponding descriptions of the functional units involved in the auxiliary processing device for image recognition on the user client side provided by this embodiment, refer to the corresponding descriptions in FIG. 1 and FIG. 2. No longer.

Further, as a specific implementation of the methods shown in FIGS. 3 and 4, an embodiment of the present application provides an auxiliary processing device for image recognition that can be applied to the server side. As shown in FIG. 8, the device includes: a receiving module 61. The query module 62 and the sending module 63.

The receiving module 61 can be used to receive the identifier of the to-be-filled item corresponding to the selected input box;

The query module 62 can be used to query the group identifier corresponding to the identifier of the item to be filled in;

The sending module 63 can be used to obtain field information corresponding to the group identifier in the uploaded image, so as to trigger the field information to be highlighted in the uploaded image while editing information in the selected input box Show.

In a specific application scenario, the device further includes: an identification module 64 and a grouping module 65;

The receiving module 61 may also be used to receive the uploaded image;

The recognition module 64 can be used to perform image recognition on the uploaded image to obtain image recognition information by using preset recognition matching rules corresponding to each item to be filled in, wherein the image recognition information contains the corresponding identification of each item to be filled in. Sub information

The sending module 63 may also be used to return the image identification information;

The grouping module 65 can be used to group the image-recognized field information in the uploaded image according to the corresponding to-be-filled item identifiers and field content, and configure a grouping identifier corresponding to the image-recognized field information, And the mapping relationship between the group identifier and the corresponding item identifier to be filled in. In a specific application scenario, the sending module 63 may also be used to trigger the prominent display of each image-recognized field information in the uploaded image. In a specific application scenario, the sending module 63 may also be configured to return an image upload error prompt message if the uploaded image cannot be image recognized according to the preset recognition matching rule. In a specific application scenario, optionally, image recognition is performed on the uploaded image based on OCR recognition technology.

It should be noted that, for other corresponding descriptions of the functional units involved in the auxiliary processing device for image recognition on the server side provided by this embodiment, please refer to the corresponding descriptions in FIGS. 3 and 4, which will not be described here. Repeat it again.

Based on the above-mentioned method shown in FIG. 1 and FIG. 2, correspondingly, an embodiment of the present application also provides a non-volatile readable storage medium on which computer-readable instructions are stored, and the computer-readable instructions are When executed, the auxiliary processing method shown in FIG. 1 and FIG. 2 that can be applied to the image recognition on the user client side is realized. Based on the above-mentioned method shown in FIG. 3 and FIG. 4, the embodiment of the present application also provides another non-volatile readable storage medium, on which computer-readable instructions are stored, when the computer-readable instructions are executed by the processor The above-mentioned auxiliary processing method of image recognition applicable to the server side as shown in FIG. 3 and FIG. 4 is realized.

Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.), including several The instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods in each implementation scenario of the present application.

Based on the above-mentioned methods shown in Figures 1 and 2 and the virtual device embodiment shown in Figure 7, in order to achieve the above-mentioned purpose, an embodiment of the present application also provides a client device, which can specifically be business management equipment, personal Computers, POS devices, tablets, smart phones, smart watches, smart bracelets, or other network devices, etc. The client device includes a non-volatile readable storage medium and a processor; a non-volatile readable storage medium, It is used to store computer-readable instructions; the processor is used to execute the computer-readable instructions to implement the aforementioned auxiliary processing method for image recognition applicable to the user client side as shown in FIG. 1 and FIG.

Based on the above methods shown in Figures 3 and 4, and the virtual device embodiment shown in Figure 8, in order to achieve the above objective, an embodiment of the present application also provides a server device, which may specifically be a gateway device, a server, or Other network equipment, etc. The device includes a non-volatile readable storage medium and a processor; the non-volatile readable storage medium is used to store computer readable instructions; and the processor is used to execute computer readable instructions to implement the above-mentioned Figures 3 and The auxiliary processing method shown in 4 can be applied to the image recognition on the server side.

Optionally, both of the foregoing two physical devices may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and so on. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, and the like. The network interface can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

Those skilled in the art can understand that the physical device structure of the client device and the server device provided in this embodiment does not constitute a limitation on the two physical devices, and may include more or fewer components, or combine certain components. Components, or different component arrangements. The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above two physical devices, and supports the operation of information processing programs and other software and/or programs. The network communication module is used to realize the communication between the various components in the storage medium, and the communication with other hardware and software in the information processing entity device.

Based on the above content, further, an embodiment of the present application also provides an auxiliary processing system for image recognition. As shown in FIG. 9, the system includes a server device 71 and a client device 72; wherein, the client device 72 can be used to execute In the methods shown in FIGS. 1 and 2, the server device 71 can be used to execute the methods shown in FIGS. 3 and 4.

The client device 72 can be used to send the uploaded image to the server device 71 for image recognition; and then receive the image recognition information corresponding to the uploaded image returned by the server device 71; then, according to the respective identifiers of the items to be filled in the input boxes, the image Each sub-information in the identification information is filled in the corresponding input box. At least one input box containing image recognition information is output, wherein each sub-information in the image recognition information is displayed in the corresponding input box. When the information editing instruction is received, the identifier of the item to be filled corresponding to the selected input box is sent to the server device 71. So that while editing the information in the selected input box, the field information corresponding to the identifier of the item to be filled is highlighted in the uploaded image.

The server device 71 can be used to receive the uploaded image sent by the client device 72 for image recognition, and then return to the client device 72 corresponding image recognition information. Receive the item identifier corresponding to the selected input box sent by the client device 72; then query the group identifier corresponding to the item identifier; obtain the field information corresponding to the group identifier in the uploaded image so that While editing information in the selected input box, trigger the field information to be highlighted in the uploaded image.

Through the description of the foregoing implementation manners, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform, or by hardware. By applying the technical solution of this application, based on the image recognition technology, the identified fields in the picture are marked. When the user edits the corresponding fields, the input box is activated to trigger the marked fields, and the corresponding fields are displayed in the picture. . Furthermore, through picture annotation, help users are provided in the process of editing fields, and the path and cost for users to obtain information are reduced.

Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of preferred implementation scenarios, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing this application. Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be changed to be located in one or more devices different from the implementation scenario. The modules of the above implementation scenarios can be combined into one module or further divided into multiple sub-modules.

The above serial number of this application is only for description, and does not represent the merits of implementation scenarios. The above disclosures are only a few specific implementation scenarios of the application, but the application is not limited to these, and any changes that can be thought of by those skilled in the art should fall into the protection scope of the application.

Claims

An auxiliary processing method for image recognition, including:

Outputting at least one input box containing image recognition information, wherein each sub-information in the image recognition information is displayed in respective input boxes;

Receive the information editing instruction and send the item identifier corresponding to the selected input box, so that while editing the information in the selected input box, highlight the item corresponding to the item identifier in the uploaded image Field information.
The method according to claim 1, after editing information in the selected input box, the method further comprises: highlighting the field information corresponding to the identification of the item to be filled in the uploaded image The display form is updated, wherein the updated prominent display form is used to determine that the field information corresponding to the item identification to be filled has an information editing operation.
The method according to claim 1, after editing information in the selected input box, the method further comprises: highlighting the field information content corresponding to the identification of the item to be filled in the uploaded image Other field information whose similarity is greater than the preset threshold.
The method according to claim 1, further comprising: recording the edited content information before and after the information is edited; and sending the edited content information to update the image recognition database.
The method according to claim 1, before the output of the at least one input box containing image recognition information, the method further comprises: receiving an image upload instruction, sending the uploaded image for image recognition; receiving the corresponding uploaded image The image recognition information; according to the respective identifiers of the items to be filled out corresponding to the input boxes, the sub-information of the image recognition information is filled in the respective input boxes.
An auxiliary processing method for image recognition, including:

Receive the item identification to be filled corresponding to the selected input box;

Query the group identifier corresponding to the identifier of the item to be filled in;

Obtaining the field information corresponding to the group identifier in the uploaded image, so as to trigger the field information to be prominently displayed in the uploaded image while editing information in the selected input box.
The method according to claim 6, the method further comprising: receiving the uploaded image; using preset recognition matching rules corresponding to each item to be filled in, performing image recognition on the uploaded image to obtain image recognition information and return it, Wherein, the image identification information contains the sub-information corresponding to the identification of each item to be filled in; the field information that has been image-recognized in the uploaded image is grouped according to the identification of the item to be filled in and the content of the field, and configured with the The group identifier corresponding to the image-recognized field information, and the mapping relationship between the group identifier and the corresponding item identifier.
The method according to claim 7, after said using the preset recognition matching rules corresponding to each item to be filled in, performing image recognition on the uploaded image to obtain image recognition information, the method further comprises: triggering the upload The image highlights the field information that has been recognized by the image.
According to the method of claim 7, if image recognition of the uploaded image cannot be performed according to the preset recognition matching rule, the method further comprises: returning a prompt message of an image upload error.
According to the method of claim 7, image recognition is performed on the uploaded image based on optical character recognition OCR recognition technology.
An auxiliary processing device for image recognition, including:

The output module is configured to output at least one input box containing image recognition information, wherein each sub-information in the image recognition information is displayed in their respective input boxes;

The sending module is used to receive the information editing instruction and send the identifier of the item to be filled in corresponding to the selected input box, so that while editing the information in the selected input box, it will highlight the information and the to-be-filled in the uploaded image. Fill in the field information corresponding to the item ID.
The apparatus according to claim 11, further comprising:

The update module is used to update the prominent display form of the field information corresponding to the item identification to be filled in the uploaded image, wherein the updated prominent display form is used to determine that it corresponds to the identification of the item to be filled There is an information editing operation for the field information.
The device according to claim 11, the output module is further configured to highlight, in the uploaded image, other field information whose content similarity of the field information corresponding to the item identification to be filled is greater than a preset threshold.
The device according to claim 11, the device further comprising: a recording module; the recording module is used to record the edited content information before and after the information is edited; the sending module is also used to send the edited content information for Update the image recognition database.
The device according to claim 11, the device further comprising: a receiving module and a filling module; the sending module is further configured to receive an image upload instruction, and send the uploaded image for image recognition; the receiving module is configured to Receiving the image recognition information corresponding to the uploaded image; the filling module is configured to fill in each sub-information of the image recognition information in the corresponding input boxes according to the respective identifiers of the items to be filled in the input boxes .
An auxiliary processing device for image recognition, including:

The receiving module is used to receive the identifier of the item to be filled in corresponding to the selected input box;

The query module is used to query the group identifier corresponding to the identifier of the item to be filled in;

The sending module is used to obtain the field information corresponding to the group identifier in the uploaded image, so that while editing the information in the selected input box, trigger the field information to be prominently displayed in the uploaded image .
The device according to claim 16, the device further comprising: an identification module and a grouping module; the receiving module is also used to receive the uploaded image; the identification module is used to use the preset corresponding to each item to be filled in Set identification matching rules, perform image identification on the uploaded image to obtain image identification information, where the image identification information contains sub-information corresponding to the identification of each item to be filled in; the sending module is also used to return the image identification Information; the grouping module is used to group the image-recognized field information in the uploaded image according to the corresponding to-be-filled item identifier and field content, and configure the grouping identifier corresponding to the image-recognized field information , And the mapping relationship between the group identifier and the corresponding item identifier to be filled in.
The device according to claim 17, wherein the sending module is further configured to trigger the prominent display of each image-recognized field information in the uploaded image.
The device according to claim 17, wherein the sending module is further configured to, if image recognition of the uploaded image cannot be performed according to the preset recognition matching rule, return a prompt message of an image upload error.
The device according to claim 17, based on optical character recognition (OCR) recognition technology to perform image recognition on the uploaded image.
A non-volatile readable storage medium having computer readable instructions stored thereon, and an auxiliary processing method for image recognition when the computer readable instructions are executed by a processor, comprising: outputting at least one input containing image recognition information Box, wherein each sub-information in the image recognition information is displayed in the corresponding input box; receiving the information editing instruction, and sending the identifier of the item to be filled corresponding to the selected input box, so that the While editing the information in the input box, highlight the field information corresponding to the identifier of the item to be filled in the uploaded image.
A client device includes a non-volatile readable storage medium, a processor, and computer readable instructions stored on the non-volatile readable storage medium and running on the processor, and the processor executes the The auxiliary processing method for realizing image recognition when computer readable instructions include: outputting at least one input box containing image recognition information, wherein each sub-information in the image recognition information is displayed in respective input boxes; receiving information Editing instruction to send the item identifier corresponding to the selected input box, so that while editing information in the selected input box, the field information corresponding to the item identifier is highlighted in the uploaded image .
A non-volatile readable storage medium, on which computer readable instructions are stored, and when the computer readable instructions are executed by a processor, an auxiliary processing method for image recognition is realized, which includes: receiving an input corresponding to a selected input box The identifier of the item to be filled in; query the group identifier corresponding to the identifier of the item to be filled in; obtain the field information corresponding to the group identifier in the uploaded image, so as to trigger the information editing in the selected input box The field information is prominently displayed in the uploaded image.
A server device includes a storage medium, a processor, and computer-readable instructions stored on a non-volatile readable storage medium and that can run on the processor. The processor implements an image when the computer-readable instruction is executed. The auxiliary processing method for identification includes: receiving the item identifier corresponding to the selected input box; querying the group identifier corresponding to the item identifier; obtaining the field information corresponding to the group identifier in the uploaded image, In order to trigger the field information to be displayed prominently in the uploaded image while editing information in the selected input box.
An auxiliary processing system for image recognition, comprising: the client device according to claim 22 and the server device according to claim 24.