Data processing method and device for material marking

Abstract

The invention discloses a data processing method and device for material marking. Comprising the steps that to-be-processed request data is acquired, and the to-be-processed request data is used for representing material marking demand data; marking material extraction processing is carried out on the to-be-processed demand data, to-be-marked data are obtained, and the to-be-marked data comprise material data used for representing that marking needs to be carried out; marking the to-be-marked data based on a preset deep learning model to obtain process material label data; and updating the system material label database according to the process material label data to obtain material marking result data. The to-be-processed demand data is identified and extracted to obtain the material needing to be marked, the marking task is generated, the deep learning model is adopted to mark the material needing to be marked, the marking comprehensiveness of the material picture is improved, and then the technical effect of improving the marking accuracy of the material picture is achieved.

Description

Technical Field

[0001] The present application relates to the field of the Internet, and more specifically, to a data processing method and device for material labeling. Background Art

[0002] The DAM system, or Digital Asset Management, is a system used to efficiently manage and optimize digital assets. For companies that process images, a large amount of image data is stored in the DAM system.

[0003] The image materials uploaded to the DAM system need to be tagged with a lot of metadata. With these metadata tags, the DAM system can easily perform business operations such as classification and retrieval of the materials. In the prior art, the labeling of image materials is mainly done manually. Manual labeling has the following problems: each image material needs to be tagged with several or even dozens of tags, and the options for each tag range from several to hundreds. The workload is large and the work efficiency is low. Therefore, users will not label all the tags of the image materials, and will omit non-mandatory tags. In the long run, there will be many materials with missing tags in the DAM, which is not conducive to management and retrieval, and greatly weakens the management function of the DAM.

[0004] Therefore, the existing image labeling technology has the problem of low accuracy due to missing labels. Summary of the invention

[0005] The main purpose of this application is to provide a data processing method and device for material labeling, so as to solve the problem of low accuracy caused by missing labels in image labeling in the prior art, improve the comprehensiveness of material image labeling, and thus achieve the technical effect of improving the accuracy of material image labeling.

[0006] In order to achieve the above-mentioned purpose, in a first aspect of the present application, a data processing method for material marking is proposed, comprising:

[0007] Acquire the request data to be processed, wherein the request data to be processed is used to represent the material marking requirement data;

[0008] Extracting marking materials from the demand data to be processed to obtain data to be marked, wherein the data to be marked includes material data for indicating that marking is required;

[0009] Performing labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data;

[0010] The system material label database is updated according to the process material label data to obtain material labeling result data.

[0011] In some optional embodiments of the present application, the marking material extraction process is performed on the demand data to be processed, and the data to be marked includes:

[0012] Performing identification processing based on identity characteristics on the demand data to be processed to obtain user identity characteristic data, wherein the user identity characteristic data is used to represent the identity characteristic data of the user who requests material marking;

[0013] Matching the prompt word template corresponding to the data of the user identity feature in the preset system marking database to obtain reference prompt word template data;

[0014] The to-be-processed demand data is subjected to extraction processing based on the marking material to obtain the to-be-marked material data, wherein the to-be-marked material data is used to indicate the material data that needs to be marked;

[0015] A marking task generation process is performed according to the reference prompt word template data and the material data to be marked to obtain the data to be marked.

[0016] In some optional embodiments of the present application, the to-be-processed demand data is subjected to extraction processing based on the marking material, and the obtained to-be-marked material data includes:

[0017] Performing material extraction processing on the demand data to be processed to obtain process material data, wherein the process material data is used to represent all material data included in the demand data to be processed;

[0018] Performing identification processing based on the marking mode on the demand data to be processed to obtain marking mode feature data, wherein the marking mode feature data is feature data used to represent the material marking mode;

[0019] The process material data is subjected to material extraction processing based on the marking mode feature data to obtain the material data to be marked.

[0020] In some optional embodiments of the present application, the process material data is subjected to material extraction processing based on the marking mode feature data to obtain the material data to be marked, including:

[0021] If the marking mode corresponding to the marking mode characteristic data is the first marking mode, performing material extraction processing according to the first marking mode to obtain the material data to be marked, wherein the first marking mode is full-volume marking;

[0022] If the marking mode corresponding to the marking mode characteristic data is the second marking mode, material extraction processing is performed according to the second marking mode to obtain the material data to be marked, wherein the second marking mode is incremental marking.

[0023] In some optional embodiments of the present application, the data to be labeled is subjected to labeling processing based on a preset deep learning model, and the process material label data obtained includes:

[0024] Performing recognition processing on the data to be marked to obtain reference prompt word template data and material data to be marked;

[0025] Matching a deep learning model corresponding to the reference prompt word template data in a preset system marking model database to obtain a preset deep learning model corresponding to the reference prompt word template data;

[0026] The material data to be marked is subjected to material marking processing according to the preset deep learning model to obtain the process material label data.

[0027] In some optional embodiments of the present application, the system material label database is updated according to the process material label data to obtain the material labeling result data including:

[0028] Acquire first material data, wherein the first material is data of any one material in the process material label data;

[0029] Traversing the system material label database to determine whether the first material data exists in the system material label database,

[0030] If the first material data exists in the system material label database, matching the historical label data corresponding to the first material in the system material label database, identifying the process label data corresponding to the first material in the process material label data, generating material marking result data corresponding to the first material according to the historical label data and the process label data, and updating the data to the system material label database;

[0031] If the first material data does not exist in the system material label database, process label data corresponding to the first material in the process material label data is identified, material marking result data corresponding to the first material is generated according to the process label data, and updated to the system material label database.

[0032] According to a second aspect of the present application, a data processing device for material marking is proposed, comprising:

[0033] A demand acquisition module, used to acquire demand data to be processed, wherein the request data to be processed is used to represent material marking demand data;

[0034] A marking generation module, used for extracting marking materials from the required data to be processed to obtain data to be marked, wherein the data to be marked includes material data indicating that marking is required;

[0035] A material labeling module, used to perform labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data;

[0036] The material label updating module is used to update the system material label database according to the process material label data to obtain material labeling result data.

[0037] In some optional embodiments of the present application, the marking generation module includes:

[0038] An identity feature recognition module, used to perform identity feature recognition processing on the to-be-processed demand data to obtain user identity feature data, wherein the user identity feature data is used to represent the identity feature data of the user who requests the material to be marked;

[0039] A template matching module, used to match the prompt word template corresponding to the data of the user identity feature in a preset system marking database to obtain reference prompt word template data;

[0040] A material extraction module, used for performing extraction processing on the to-be-processed demand data based on the marking material to obtain the to-be-marked material data, wherein the to-be-marked material data is used to indicate the material data that needs to be marked;

[0041] The marking task generation module is used to perform marking task generation processing according to the reference prompt word template data and the material data to be marked to obtain the data to be marked.

[0042] According to a third aspect of the present application, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data processing method for material marking.

[0043] According to the fourth aspect of the present application, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the above-mentioned data processing method for material marking.

[0044] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0045] In the present application, by obtaining the demand data to be processed, wherein the request data to be processed is the demand data for indicating the material marking; extracting and processing the marking material of the demand data to be processed to obtain the data to be marked, wherein the data to be marked includes the material data for indicating the need for marking; marking the data to be marked based on a preset deep learning model to obtain process material label data; updating and processing the system material label database according to the process material label data to obtain material marking result data. By identifying and extracting the demand data to be processed to obtain the material to be marked and generating a marking task, and using a deep learning model to mark the material to be marked, the problem of low accuracy caused by missing labels in the image marking in the prior art is solved, the comprehensiveness of the material image marking is improved, and the technical effect of improving the accuracy of the material image marking is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0047] Figure 1 A flowchart of a data processing method for material marking provided in this application;

[0048] Figure 2 A flowchart of a data processing method for material marking provided in this application;

[0049] Figure 3 A flowchart of a data processing method for material marking provided in this application;

[0050] Figure 4 A schematic diagram of a data processing device for material marking provided in this application;

[0051] Figure 5 A schematic diagram of another data processing device for material marking provided in the present application. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution 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. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0055] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0056] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0057] The image materials uploaded to the DAM system need to be tagged with a lot of metadata tags. With these metadata tags, the DAM system can easily classify, retrieve and other business operations on the materials. In the prior art, the labeling of image materials is mainly done manually. Each image material needs to be tagged with several or even dozens of tags, and the options for each tag range from several to hundreds. The workload is large and the work efficiency is low. Users will not label all the tags of the image materials, and will omit non-mandatory tags, which will lead to the lack of metadata tags for the image materials of the DAM system. The DAM system will perform inaccurate business operations such as classification and retrieval of the materials based on the metadata tags. Therefore, the present application proposes a data processing method for material labeling to label the image materials. The problem of low accuracy caused by missing tags in the image labeling in the prior art is solved, the comprehensiveness of the material image labeling is improved, and the technical effect of improving the accuracy of the material image labeling is achieved.

[0058] In an optional embodiment of the present application, a data processing method for material marking is provided. Figure 1 A flowchart of a data processing method for material marking provided in this application, such as Figure 1 As shown, the method comprises the following steps:

[0059] S101: Obtaining demand data to be processed;

[0060] The request data to be processed is used to indicate the material marking requirement data;

[0061] S102: extracting marking materials from the required data to be processed to obtain data to be marked;

[0062] The data to be marked include data used to represent the material that needs to be marked. The data to be marked include the material data to be marked and user business characteristic data. The user business characteristic data is the reference prompt template data corresponding to the user. The reference prompt word template for the user to mark the material is determined according to the user's business characteristics, and the deep learning model used for material marking is determined according to the reference prompt word template. By determining the deep learning model corresponding to the business characteristics according to the user's business characteristic data, the accuracy of marking the material to be marked is improved.

[0063] In another optional embodiment of the present application, a data processing method for material tagging is provided, which is applied to the DAM system, and the user uploads the picture material to the DAM system to tag the picture material. In the system, the prompt word template corresponding to the user configuration includes: obtaining the user data to be configured, performing identification processing based on the business characteristics of the user data to be configured, and obtaining the business characteristic data to be configured; generating a prompt word template corresponding to the user according to the business characteristic data to be configured, wherein the prompt word template is a prompt word template for requesting a deep learning model, and for example, when tagging the picture to be tagged, select one or more label values ​​from each of the following label categories in the label range, and return a JSON object. If there is no suitable option in a certain category, the option value is none, and the name of the category in the return value does not need to be returned. The identifier corresponding to the category and the option value array corresponding to the category are returned, and all parent contents are spliced ​​at the node to obtain the corresponding label by splicing; matching the associated material data corresponding to the prompt word template, and completing the configuration of the user in the DAM system according to the above-mentioned business characteristic data to be configured, the prompt word template and the associated material data.

[0064] In an optional embodiment of the present application, a data processing method for material marking is provided. Figure 2 A flowchart of a data processing method for material marking provided in this application, such as Figure 2 As shown, the method comprises the following steps:

[0065] S201: performing identification processing on the demand data to be processed based on identity characteristics to obtain user identity characteristic data;

[0066] The user identity feature data is used to represent the identity feature data of the user who requests material labeling. It identifies the identity features of the user who proposes the request to be processed, and determines the material label database corresponding to the user and the prompt word template corresponding to the user based on the user identity features, so as to determine the corresponding deep learning model based on the prompt word template, so as to improve the accuracy of user material labeling.

[0067] S202: matching a prompt word template corresponding to the data of the user identity feature in a preset system marking database to obtain reference prompt word template data;

[0068] S203: extracting and processing the required data to be processed based on the marking material to obtain the material data to be marked;

[0069] The material data to be marked is used to indicate the material data to be marked;

[0070] In an optional embodiment of the present application, a data processing method for material marking is provided. Figure 3A flowchart of a data processing method for material marking provided in this application, such as Figure 3 As shown, the method comprises the following steps:

[0071] S301: extracting materials from the demand data to be processed to obtain process material data;

[0072] The process material data is used to represent all material data included in the demand data to be processed. The demand data to be processed includes uploaded materials and uploaded material locations. The uploaded materials may include marked materials and unmarked materials. The uploaded material location is in the material group. The material group may be a historical material group or a newly added material group. The historical material group may also include historical materials. The newly added material group contains all materials uploaded in the processing demand data. When the uploaded material location is the historical material group, the obtained process material includes the historical materials in the material group and the above-mentioned uploaded materials. When the uploaded material location is the newly added material group, the obtained process material is the above-mentioned uploaded material.

[0073] S302: performing identification processing based on the marking pattern on the demand data to be processed to obtain marking pattern feature data;

[0074] The marking mode characteristic data is characteristic data used to represent the material marking mode, and the material marking mode includes full-amount marking and incremental marking.

[0075] S303: performing material extraction processing on the process material data based on the marking mode feature data to obtain the material data to be marked.

[0076] In an optional embodiment of the present application, a data processing method for material marking is provided, comprising:

[0077] If the marking mode corresponding to the marking mode characteristic data is the first marking mode, material extraction and processing are performed according to the first marking mode to obtain material data to be marked, wherein the first marking mode is full marking; when the process material data is fully marked, all materials in the process material data are marked to obtain material data to be marked including all materials in the process material data.

[0078] If the marking mode corresponding to the marking mode characteristic data is the second marking mode, material extraction processing is performed according to the second marking mode to obtain material data to be marked, wherein the second marking mode is incremental marking; when incremental marking is performed on the process material data, the material in the process material data is screened to screen the unmarked material in the process material data, so as to mark the unmarked material in the screened process material data to obtain material data to be marked, which is the unmarked material in the process material data.

[0079] S204: Perform labeling task generation processing according to the reference prompt word template data and the material data to be labeled to obtain the data to be labeled.

[0080] A marking batch is created according to the above-mentioned material data to be marked, and a marking sub-table record is generated. Each data in the sub-table corresponds to a material. The request parameters are assembled according to the reference prompt word template data and the above-mentioned material data to be marked to generate a marking task.

[0081] In an optional embodiment of the present application, a data processing method for material tagging is proposed. The method is applied to a DAM system. In the system, the request parameters are assembled according to the reference prompt word template data and the above-mentioned material data to be tagged. After the tagging task is generated, the tagging task is submitted to the dispatching center in the system. The dispatching center queues, controls the speed and priority of requesting the large model, and forwards the data to the content processing; the content processing center requests the large model and receives the callback of the large model, and is provided with a retry mechanism to obtain the request data of the content center requesting the large model, and judges the request success for the request data. If successful, the large model processes the tagging task; if unsuccessful, the content center retries the large model request until the request is successful or the number of requests is greater than the preset threshold, and stops the request; when the number of requests is greater than the preset threshold, a request failure prompt message is generated and output to the user, and the success rate is improved by setting a retry mechanism. After receiving the result of the large model, the content processing calls back to the dispatching center; the dispatching center calls back to the business party DAM according to the configuration, and the DAM updates the material label according to the tagging result to obtain the result data.

[0082] S103: performing labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data;

[0083] In an optional embodiment of the present application, a data processing method for material marking is provided, comprising:

[0084] The data to be marked is identified and processed to obtain reference prompt word template data and material data to be marked; the deep learning model corresponding to the reference prompt word template data is matched in the preset system marking model database to obtain the preset deep learning model corresponding to the reference prompt word template data; the material data to be marked is marked according to the preset deep learning model to obtain process material label data.

[0085] In an embodiment of the present application, based on a preset deep learning model, a processing flow for material labeling is constructed. The materials to be labeled are obtained by identifying and extracting the required data to be processed and generating a labeling task. The deep learning model is used to label the materials to be labeled, which solves the problem of missing labels in image labeling in the prior art and has the technical effect of improving the accuracy of material image labeling.

[0086] S104: updating the system material label database according to the process material label data to obtain material labeling result data.

[0087] In an optional embodiment of the present application, a data processing method for material labeling is provided, comprising: obtaining first material data, wherein the first material is data of any one material in the process material label data;

[0088] Traversing the system material label database, determining whether there is first material data in the system material label database, if the first material data exists in the system material label database, matching historical label data corresponding to the first material in the system material label database, identifying process label data corresponding to the first material in process material label data, generating material labeling result data corresponding to the first material according to the historical label data and the process label data, and updating the data to the system material label database;

[0089] If the first material data does not exist in the system material label database, process label data corresponding to the first material in the process material label data is identified, material marking result data corresponding to the first material is generated according to the process label data, and updated to the system material label database.

[0090] In an embodiment of the present application, a data processing device for material marking is provided. Figure 4 A schematic diagram of a data processing device for material marking provided in this application, such as Figure 4 As shown, the device comprises:

[0091] The demand acquisition module 41 is used to acquire the demand data to be processed, wherein the request data to be processed is used to represent the material marking demand data;

[0092] The marking generation module 42 is used to extract marking materials from the required data to be processed to obtain data to be marked, wherein the data to be marked includes material data indicating that marking is required;

[0093] The material labeling module 43 is used to perform labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data;

[0094] The material label updating module 44 is used to update the system material label database according to the process material label data to obtain material labeling result data.

[0095] In an embodiment of the present application, another data processing device for material marking is provided. Figure 5 A schematic diagram of another data processing device for material marking provided in this application, such as Figure 5 As shown, the device comprises:

[0096] The identity feature recognition module 51 is used to perform identity feature recognition processing on the processing demand data to be processed, and obtain user identity feature data, wherein the user identity feature data is the identity feature data used to represent the user who requests the material to be marked;

[0097] A template matching module 52, used to match the prompt word template corresponding to the data of the user identity feature in a preset system marking database to obtain reference prompt word template data;

[0098] The material extraction module 53 is used to extract the required data to be processed based on the marking material to obtain the material data to be marked, wherein the material data to be marked is used to indicate the material data that needs to be marked;

[0099] The marking task generating module 54 is used to perform marking task generating processing according to the reference prompt word template data and the material data to be marked, so as to obtain the data to be marked.

[0100] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0101] In summary, in the present application, by obtaining the demand data to be processed, wherein the request data to be processed is the demand data for representing the material marking; extracting and processing the marking material of the demand data to be processed to obtain the data to be marked, wherein the data to be marked includes the material data for representing the material to be marked; marking the data to be marked based on a preset deep learning model to obtain process material label data; updating and processing the system material label database according to the process material label data to obtain material marking result data. By identifying and extracting the demand data to be processed to obtain the material to be marked and generating a marking task, and using a deep learning model to mark the material to be marked, the problem of low accuracy caused by missing labels in the image marking in the prior art is solved, the comprehensiveness of the material image marking is improved, and the technical effect of improving the accuracy of the material image marking is achieved.

[0102] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0103] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0104] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for material marking, characterized in that: include: Acquire the request data to be processed, wherein the request data to be processed is used to represent the material marking requirement data; Extracting marking materials from the demand data to be processed to obtain data to be marked, wherein the data to be marked includes material data for indicating that marking is required; Performing labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data; The system material label database is updated according to the process material label data to obtain material labeling result data.

2. The data processing method according to claim 1, characterized in that: The marking material is extracted from the required data to be processed, and the data to be marked includes: Performing identification processing based on identity characteristics on the demand data to be processed to obtain user identity characteristic data, wherein the user identity characteristic data is used to represent the identity characteristic data of the user who requests material marking; Matching the prompt word template corresponding to the data of the user identity feature in the preset system marking database to obtain reference prompt word template data; The to-be-processed demand data is subjected to extraction processing based on the marking material to obtain the to-be-marked material data, wherein the to-be-marked material data is used to indicate the material data that needs to be marked; A marking task generation process is performed according to the reference prompt word template data and the material data to be marked to obtain the data to be marked.

3. The data processing method according to claim 2, characterized in that: The to-be-processed demand data is subjected to extraction processing based on the marking material, and the obtained to-be-marked material data includes: Performing material extraction processing on the demand data to be processed to obtain process material data, wherein the process material data is used to represent all material data included in the demand data to be processed; Performing identification processing based on the marking mode on the demand data to be processed to obtain marking mode feature data, wherein the marking mode feature data is feature data used to represent the material marking mode; The process material data is subjected to material extraction processing based on the marking mode feature data to obtain the material data to be marked.

4. The data processing method according to claim 3, characterized in that: The material data to be marked is subjected to material extraction processing based on the marking mode feature data to obtain the material data to be marked, including: If the marking mode corresponding to the marking mode characteristic data is the first marking mode, performing material extraction processing according to the first marking mode to obtain the material data to be marked, wherein the first marking mode is full-volume marking; If the marking mode corresponding to the marking mode characteristic data is the second marking mode, material extraction processing is performed according to the second marking mode to obtain the material data to be marked, wherein the second marking mode is incremental marking.

5. The data processing method according to claim 1, characterized in that: The data to be labeled is subjected to labeling processing based on a preset deep learning model, and the process material label data obtained includes: Performing recognition processing on the data to be marked to obtain reference prompt word template data and material data to be marked; Matching a deep learning model corresponding to the reference prompt word template data in a preset system marking model database to obtain a preset deep learning model corresponding to the reference prompt word template data; The material data to be marked is subjected to material marking processing according to the preset deep learning model to obtain the process material label data.

6. The data processing method according to claim 1, characterized in that: The system material label database is updated according to the process material label data to obtain material labeling result data including: Acquire first material data, wherein the first material is data of any one material in the process material label data; Traversing the system material label database to determine whether the first material data exists in the system material label database, If the first material data exists in the system material label database, matching the historical label data corresponding to the first material in the system material label database, identifying the process label data corresponding to the first material in the process material label data, generating material marking result data corresponding to the first material according to the historical label data and the process label data, and updating the data to the system material label database; If the first material data does not exist in the system material label database, process label data corresponding to the first material in the process material label data is identified, material marking result data corresponding to the first material is generated according to the process label data, and updated to the system material label database.

7. A data processing device for material marking, characterized in that: include: A demand acquisition module, used to acquire demand data to be processed, wherein the request data to be processed is used to represent material marking demand data; A marking generation module, used for extracting marking materials from the required data to be processed to obtain data to be marked, wherein the data to be marked includes material data indicating that marking is required; A material labeling module, used to perform labeling processing on the data to be labeled based on a preset deep learning model to obtain process material label data; The material label updating module is used to update the system material label database according to the process material label data to obtain material labeling result data.

8. The data processing device according to claim 7, characterized in that: The marking generation module includes: An identity feature recognition module, used to perform identity feature recognition processing on the to-be-processed demand data to obtain user identity feature data, wherein the user identity feature data is used to represent the identity feature data of the user who requests the material to be marked; A template matching module, used to match the prompt word template corresponding to the data of the user identity feature in a preset system marking database to obtain reference prompt word template data; A material extraction module, used for performing extraction processing on the to-be-processed demand data based on the marking material to obtain the to-be-marked material data, wherein the to-be-marked material data is used to indicate the material data that needs to be marked; The marking task generation module is used to perform marking task generation processing according to the reference prompt word template data and the material data to be marked to obtain the data to be marked.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data processing method for material marking according to any one of claims 1-6.

10. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the data processing method for material marking as described in any one of claims 1-6.

Images