Information processing method and computing device

Abstract

The present invention provides an information processing method and computing device, comprising: obtaining an object to be inspected provided by a target user; inputting the object to be inspected into a grade prediction model to obtain an initial pass grade for the object to be inspected; optimizing the initial pass grade using a grade optimization model to obtain a target pass grade for the object to be inspected; and outputting the target pass grade to the target user. The present invention achieves efficient object submission by accurately predicting the pass grade.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to an information processing method and computing device. Background Art

[0002] A trademark is a mark used to distinguish one business's goods or services from those of other businesses. It can include a combination of text, graphics, numbers, sounds, three-dimensional logos, and colors. Currently, before using a trademark, an application must be submitted to the Trademark Office, which then reviews the application. However, applicants often lack timely information on whether their application will pass review, leading to the submission of invalid trademarks and a reduced success rate for trademark applications. Summary of the Invention

[0003] In view of this, an embodiment of the present application provides an information processing method and a computing device to solve the technical problem of invalid trademark submission in the prior art, resulting in a low success rate of trademark applications.

[0004] In a first aspect, an embodiment of the present application provides an information processing method, including:

[0005] Obtain the object to be detected provided by the target user;

[0006] Inputting the object to be detected into a grade prediction model to obtain an initial passing grade of the object to be detected;

[0007] Performing a grade optimization process on the initial pass grade using a grade optimization model to obtain a target pass grade of the object to be detected;

[0008] The target passing level is output for the target user.

[0009] In a second aspect, an embodiment of the present application provides an information processing method, including:

[0010] Obtain the trademark to be tested provided by the target user;

[0011] Inputting the trademark to be tested into a grade prediction model to obtain an initial passing grade of the trademark to be tested;

[0012] Performing grade optimization processing on the initial pass grade using a grade optimization model to obtain a target pass grade for the trademark to be inspected;

[0013] The target passing level is output for the target user.

[0014] In a third aspect, an embodiment of the present application provides a computing device, comprising: a storage component and a processing component; the storage component is configured to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component;

[0015] The processing component is used to:

[0016] Obtain an object to be detected provided by a target user; input the object to be detected into a grade prediction model to obtain an initial pass grade of the object to be detected; use a grade optimization model to perform grade optimization processing on the initial pass grade to obtain a target pass grade of the object to be detected; and output the target pass grade to the target user.

[0017] In a fourth aspect, an embodiment of the present application provides a computing device, comprising a storage component and a processing component; the storage component is configured to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component;

[0018] The processing component is used to:

[0019] Obtain a trademark to be detected provided by a target user; input the trademark to be detected into a grade prediction model to obtain an initial pass grade of the trademark to be detected; use a grade optimization model to perform grade optimization processing on the initial pass grade to obtain a target pass grade of the trademark to be detected; and output the target pass grade to the target user.

[0020] In an embodiment of the present application, an object to be detected provided by a target user is obtained so that the object to be detected can be input into a grade prediction model to obtain an initial pass grade of the object to be detected. The grade prediction model makes a preliminary prediction of the pass grade of the object to be detected. Subsequently, the grade optimization model can be used to perform grade optimization processing on the initial pass grade to obtain a target pass grade of the object to be detected. The grade optimization model is used to further optimize the initial grade to improve the accuracy of the obtained target pass grade. Thus, when outputting the target pass grade for the target user, an effective pass grade prompt can be provided to the user, thereby improving pass efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 A flowchart of an embodiment of an information processing method provided in an embodiment of the present application;

[0023] Figure 2 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0024] Figure 3 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0025] Figure 4 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0026] Figure 5 This is an example diagram of displaying multiple category prompt information provided by an embodiment of the present application;

[0027] Figure 6 This is an example diagram of displaying multiple category prompt information provided by an embodiment of the present application;

[0028] Figure 7 This is an example diagram of displaying multiple category prompt information provided by an embodiment of the present application;

[0029] Figure 8 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0030] Figure 9 A flowchart of another embodiment of an information processing method provided in an embodiment of the present application;

[0031] Figure 10 An example diagram of an information processing method provided in an embodiment of the present application;

[0032] Figure 11 A schematic diagram of the structure of an embodiment of a computing device provided in an embodiment of the present application;

[0033] Figure 12 A schematic diagram of the structure of an embodiment of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] The terms used in the examples of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "the," and "the" used in the examples of this application and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two, but does not exclude the inclusion of at least one.

[0036] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0037] As used herein, the words “if” and “if” may be interpreted as “at the time of” or “when” or “in response to determining” or “in response to identifying,” depending on the context. Similarly, the phrases “if it is determined” or “if (stated condition or event) is identified” may be interpreted as “when it is determined” or “in response to determining” or “when identifying (stated condition or event)” or “in response to identifying (stated condition or event),” depending on the context.

[0038] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or system. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or system comprising the element.

[0039] The technical solution of the embodiment of the present application can be applied to the effective determination of trademarks. For the object to be detected, especially when the object to be detected is a trademark, the pass grade of the object to be detected can be accurately predicted by combining the grade prediction model and the grade optimization model to improve the user pass rate.

[0040] In the prior art, trademark applicants can submit their trademarks to the Trademark Office. The Trademark Office will then review the applicant's submitted trademarks to determine if they are acceptable. However, when submitting a trademark, applicants often have no idea whether their trademark will pass the review. To determine the applicability of a trademark, applicants typically conduct simple trademark searches and make simple judgments based on the comparison trademarks obtained. This results in applicants being uncertain about the likelihood of their trademark applications being approved, leading to the submission of invalid trademarks and the resulting invalid applications.

[0041] In an embodiment of the present application, the object to be detected of the target user can be obtained, and then the object to be detected can be input into the grade prediction model to obtain the initial pass grade of the object to be detected. At this time, the grade prediction model is used to make a preliminary prediction of the pass grade of the object to be detected. The grade optimization model is then used to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be detected. At this time, the grade optimization model is used to further grade optimize the initial predicted pass grade to obtain the target pass grade that accurately measures the performance of the object to be detected, so that when the target user outputs the target pass grade, the accurate target pass grade can be used to effectively prompt the target user of the possibility of passing the object to be detected to avoid generating invalid objects.

[0042] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0043] like Figure 1 FIG. 1 is a flowchart of an embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0044] 101: Obtain the object to be detected provided by the target user.

[0045] The information processing methods provided in the embodiments of this application can be applied to computing devices or servers. Computing devices may include, for example, mobile phones, tablet computers, laptop computers, netbooks, etc., and the embodiments of this application do not impose any particular restrictions on the specific types of computing devices. Servers may include, for example, ordinary servers such as computers and ultrabooks, or cloud servers, and the embodiments of this application do not impose any particular restrictions on the specific types of servers.

[0046] When the technical solution provided by this application is applied to a computing device, the object to be detected can be collected by the computing device. When the technical solution provided by this application is applied to a server, the object to be processed can be collected by a user terminal used by the target user and sent to the server.

[0047] The object to be detected can be provided by the target user. In practical applications, the object to be detected can be a trademark that needs to be confirmed. In addition, the object to be detected can also be an image, text, or video that needs to be confirmed.

[0048] In the scenario of judging the possibility of trademark approval, the target user may be the trademark applicant.

[0049] 102: Input the object to be detected into the grade prediction model to obtain an initial passing grade of the object to be detected.

[0050] Optionally, the grade prediction model can be pre-trained. The model parameters of the grade prediction model used in step 102 are known. In this case, the object to be detected is input into the grade prediction model with known parameters to obtain the initial passing grade of the object to be detected.

[0051] The grade prediction model may be a deep neural network model, and the training object and the reference results corresponding to the training object may be used to perform parameter training on the grade prediction model to obtain the grade prediction model. The grade prediction model in the embodiments of the present application may be a deep neural network model, and the specific type of the deep neural network model is not excessively limited in the embodiments of the present application.

[0052] The initial passing grade may be a passing grade obtained by the grade prediction model through a preliminary prediction of the possibility of passing the object to be inspected.

[0053] The level prediction model can predict the level of the input object to be detected, wherein at least one passing level can be preset in the level prediction model, for example, at least one passing level can include: low level, lower level, medium level, higher level and high level, etc.

[0054] The initial pass level can be any one of at least one pass level preset in the level prediction model. For example, when the level prediction model predicts a similar object with a meaning similarity of 90% to the object to be detected, the initial pass level can be confirmed as a low pass level.

[0055] 103: Utilizing the grade optimization model to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be processed.

[0056] The grade optimization model can optimize the initial pass grade. In practice, trademark examination approval is influenced not only by similarity but also by examination rules. For example, the same applicant can apply for a second application based on an existing trademark, and in this case, the second application has a higher probability of approval. By optimizing the initial pass grade using the grade optimization model, the target pass grade obtained is more closely aligned with the actual trademark examination approval probability, thereby improving the accuracy of the target pass grade.

[0057] Alternatively, in a trademark examination scenario, the grade optimization model can be determined by some trademark examination rules. Of course, in order to realize the automated examination of the examination rules, the grade optimization model can be designed as some examination process processing steps. For details, please refer to the description of the subsequent embodiments.

[0058] 104: Output the target passing level for the target user.

[0059] When the embodiment of the present application is applied to a computing device, the computing device can directly output the target passing level to the target user through the display component.

[0060] When the embodiment of the present application is applied to a server, the server may provide the target pass level to a user terminal corresponding to the target user, and the display component of the user terminal outputs the target pass level to the target user.

[0061] In the embodiment of the present application, the object to be detected of the target user can be obtained, and then the object to be detected can be input into the grade prediction model to obtain the initial pass grade of the object to be detected. At this time, the pass grade of the object to be detected is preliminarily predicted using the grade prediction model. Then the initial pass grade is grade optimized using the grade optimization model to obtain the target pass grade of the object to be detected. At this time, the pass grade of the initial prediction is further grade optimized using the grade optimization model to obtain the target pass grade of the object to be detected, so that when the target user outputs the target pass grade, the target user can be effectively prompted with the accurate target pass grade to avoid generating invalid objects. Especially when the object to be detected is a trademark, the trademark registration success rate can be improved.

[0062] like Figure 2 FIG. 1 is a schematic diagram of a structure of another embodiment of an information processing method provided by an embodiment of the present application. The method may include the following steps:

[0063] 201: Obtain the object to be detected provided by the target user.

[0064] 202: Input the object to be detected into the similar object detection sub-model to obtain at least one similar object that matches the object to be detected and the similarity between the at least one similar object and the object to be detected.

[0065] 203: Based on the similarity corresponding to at least one similar object, perform a level division process according to the level division sub-model to obtain an initial passing level of the object to be detected.

[0066] The hierarchical optimization model may include: a similar object detection sub-model and a hierarchical division sub-model.

[0067] The similar object detection sub-model can detect similar objects for the object to be detected. In practical applications, the similar object detection model can be a deep neural network model, which can search for similar objects similar to the object to be detected from the database and determine the similarity between the similar objects and the object to be detected.

[0068] The similar objects can be objects similar to the object to be detected. Taking the object to be detected as "Mile" as an example, the similar objects detected by the similar object detection sub-model for this object to be detected can be "Mishu", "Senmi", "Mile", "Mile" (misspelled as "Mile" here), etc. At this time, the similarity between the object to be detected "Mile" and "Mishu" can be "0.965", the similarity with "Senmi" is 0.574, the similarity with "Mile" is 0.965, and the similarity with "Mile" (misspelled) is 0.965.

[0069] The passing grade of the object to be detected is negatively correlated with the similarity of at least one corresponding similar object. Among them, if the similarity between the object to be detected and the similar object is higher, it means the two objects are more similar. At this time, the possibility of the object to be detected passing the review is lower; if the similarity between the object to be detected and the similar object is higher, it means the two objects are less similar. At this time, the possibility of the object to be detected passing the review is higher. That is, the similarity corresponding to at least one similar object is inversely proportional to at least one passing grade in the grade division sub-model. The higher the similarity, the lower the category level of the passing grade, and the lower the similarity, the higher the category level of the passing grade. In some embodiments, the grade division sub-model can preset at least one passing grade. For example, at least one passing grade can include: low grade, relatively low grade, medium grade, relatively high grade, and high grade, etc. Based on the similarity corresponding to at least one similar object respectively, perform grade division processing according to the grade division sub-model. The initial passing grade obtained for the object to be detected can include: determining, according to the similarity corresponding to at least one similar object respectively, the passing grade that matches the object to be detected in at least one passing grade as the initial passing grade.

[0070] 204: Use the grade optimization model to perform grade optimization processing on the initial passing grade to obtain the target passing grade of the object to be detected.

[0071] 205: Output the target passing grade to the target user.

[0072] In an embodiment of the present application, after obtaining the object to be detected provided by the target user, the object to be detected can be input into a similar object detection sub-model to obtain at least one similar object that matches the object to be detected and the similarity between at least one similar object and the object to be detected. By detecting similar objects, it can be determined whether there is an object with a high similarity to the object to be detected. Then, a grade division process is performed based on the similarity between each of the at least one similar object found and the object to be detected to obtain an initial pass grade for the object to be detected. By performing grade division based on the similarity detection results, an effective preliminary grade division can be achieved, an initial pass grade is obtained, and the accuracy of the initial pass grade is improved. Afterwards, the initial pass grade is graded and optimized using a grade optimization model to obtain a target pass grade for the object to be detected. At this point, the grade optimization model is used to further grade-optimize the initially predicted pass grade to obtain a target pass grade that accurately measures the performance of the object to be detected. Therefore, when the target user outputs the target pass grade, the accurate target pass grade can be used to effectively indicate to the target user the likelihood of passing the object to be detected, thereby avoiding the generation of invalid objects. In particular, when the object to be detected is a trademark, the success rate of trademark registration can be improved.

[0073] As an example, different pass levels can be set to clearly indicate the likelihood of passing. The level division sub-model can be provided with at least one pass level. When the input object to be inspected matches any of the at least one pass level, the actual level of the initial pass level is obtained.

[0074] Based on the similarity corresponding to at least one similar object, performing a level division process according to the level division sub-model to obtain an initial passing level of the object to be detected may include:

[0075] Obtaining at least one passing level corresponding to each of the graded sub-models, and a similarity range corresponding to each of the at least one passing level;

[0076] Determining a target similarity range in at least one similarity range based on the similarities respectively corresponding to the at least one similar object;

[0077] The passing level corresponding to the target similarity range is determined as the initial passing level.

[0078] There is a negative correlation between the level of at least one category and the size of the similarity range. The higher the level, the smaller the similarity range of the passing level, and the lower the level, the larger the similarity range of the passing level.

[0079] For example, when at least one passing level is low level, lower level, medium level, higher level and high level, the corresponding similarity ranges can be, for example: low level: similarity range is greater than 90%; lower level: similarity range is 80% to 90%; medium level: similarity range is 60% to 80%; higher level: similarity range is 30% to 60%; and high level: similarity range is less than 30%.

[0080] The pass level corresponds to a similarity range. The initial pass level can be quickly determined by similarity range matching, thereby increasing the effective speed of obtaining the pass level.

[0081] As a possible implementation manner, determining a target similarity range in at least one similarity range based on the similarities corresponding to at least one similar object may include:

[0082] Determining a maximum similarity among the similarities corresponding to at least one similar object;

[0083] A target similarity range corresponding to the maximum similarity in at least one similarity range is determined.

[0084] Determining the maximum similarity among the similarities corresponding to the at least one similar object may include arranging the similarities corresponding to the at least one similar object in descending order, and obtaining the first similarity as the maximum similarity. Determining the target similarity range corresponding to the maximum similarity in the at least one similarity range may specifically include searching for the target similarity range within the at least one similarity range in which the maximum similarity lies, thereby determining the similarity range within which the maximum similarity lies.

[0085] The target similarity range can be quickly determined through the maximum similarity.

[0086] As another possible implementation, determining the target similarity range in the at least one similarity range based on the similarities corresponding to the at least one similar object may include:

[0087] Determining, according to the similarity ranges respectively corresponding to the at least one passing level, the similarity range to which the similarity respectively corresponding to the at least one similar object belongs, so as to obtain the similarity respectively corresponding to the at least one similarity range;

[0088] Counting the number of similarities in any similarity range to obtain the number of similar objects in the similarity range, thereby obtaining the number of similar objects corresponding to at least one similarity range;

[0089] determining at least one candidate similarity range having a number of similar objects greater than 1;

[0090] Obtain a target similarity range with the highest range among at least one candidate similarity range.

[0091] Based on at least one similarity range corresponding to each level, the similarity range to which the similarity corresponding to at least one similar object belongs is determined, and the number of similarities in any similarity range is counted to obtain the number of similar objects in that similarity range. This is to obtain the number of similar objects corresponding to at least one similarity range. This is to group objects with similarities belonging to the same similarity range into the same group, and count the number of similarities in each group. Since similarities correspond to similar objects, the number of corresponding similar objects is obtained. After obtaining the number of similar objects corresponding to at least one similarity range, similarity ranges with a number of similar objects greater than 1 can be used as candidate similarity ranges.

[0092] After determining at least one candidate similarity range in which the number of similar objects is greater than 1, in some embodiments, after determining the similarity range to which the similarity corresponding to at least one similar object belongs according to the similarity range corresponding to at least one passing level, and obtaining the similarity corresponding to at least one similarity range, invalidation can be performed on the similar objects corresponding to the similarities in each similarity range, and the similarities corresponding to the invalidated similar objects can be deleted from the similarity range to obtain the valid similarities corresponding to at least one similarity range. At this time, the number of valid similarities in any similarity range can be counted to obtain the number of similar objects in the similarity range, thereby obtaining the number of similar objects corresponding to at least one similarity range.

[0093] In actual trademark examination scenarios, the grade optimization model can be determined by some trademark examination rules. Of course, in order to realize the automated review of examination rules, the grade optimization model can be designed as some examination process processing steps.

[0094] As an embodiment, performing level optimization processing on the initial pass level using the level optimization model to obtain the target pass level of the object to be inspected may include:

[0095] Determine the first category corresponding to the object to be detected at the specified category level;

[0096] determining a second category corresponding to each of the at least one similar object at a specified category level;

[0097] Determining whether there is a target category identical to the first category in the second category corresponding to at least one similar object;

[0098] If so, based on the initial passing grade, a target passing grade is determined;

[0099] If not, the target passing level is determined to be the highest passing level among the at least one passing level corresponding to the graded sub-model.

[0100] The designated category level may be a subdirectory level under the first category level. The first category level is the highest category level under the category classification standard, and the category level of the designated category level is lower than the highest category level. Determining the first category corresponding to the object to be detected at the designated category level may include: determining the first category corresponding to the object to be detected at the designated category level based on the third category of the object to be detected at the first category level.

[0101] The first category corresponding to the object to be detected at the specified category level may be the first category selected by the target user for the object to be detected at the specified category level.

[0102] Determining the second category corresponding to each of the at least one similar object at the specified category level may include: determining the second category corresponding to each of the at least one similar object based on the fourth category corresponding to each of the at least one similar object at the first category level. Specifically, the second category corresponding to each of the similar objects at the specified category level may be determined based on the fourth category corresponding to each of the similar objects at the first category level.

[0103] In actual application, all trademarks and services are divided into 45 categories to form the "Classification of Trademark Registration Supplies and Services". For example, the first category is chemicals, which can include "0101" industrial gases and "0102" industrial chemical raw materials. The second category is color dyes, which can include "0201" dyes. The ninth category includes instruments, appliances, and magnetic data carriers, which can include "0901" electronic computers and their peripheral equipment, "0902" records, vending machines and other counting detectors, etc.

[0104] In the trademark registration supplies and services classification scenario, the first category level can be the category level to which the first, second, or ninth categories in the aforementioned examples belong, and the designated category can be a category in the category level below the first, second, or ninth categories. For example, assuming that a category under the first category level is "2501" clothing, there can also be second-category-level categories in the subordinate categories of this category, such as "250010" overalls, "250034" sweaters, and other secondary categories. This example is only to illustrate some category division examples in the trademark scenario, and is not a specific limitation on the category division in the embodiments of this application. In actual applications, more division methods and category levels can be included, as well as specific categories corresponding to each category level.

[0105] In a trademark application scenario, when the trademarks are similar to a certain extent, when the categories of the two trademarks are the same, the possibility of the newly applied trademark being authorized is lower. When the categories of the two trademarks are different, the possibility of the newly applied trademark being authorized is higher. Therefore, in an embodiment of the present application, the categories of the object to be detected and at least one similar object are matched at a specified category level. When the object to be detected and the similar object belong to different categories, the possibility of the object to be detected passing the review is higher. At this time, the target pass level can be set to the highest pass level. If there is a similar object that is the same as the first category of the object to be detected, the pass level of the object to be detected can remain unchanged. At this time, if it exists, determining the target pass level based on the initial pass level can specifically include: determining the target pass level corresponding to the initial pass level.

[0106] In this embodiment, category matching is performed on the first category of the object to be detected and the second category corresponding to at least one similar object at a specified category level, and the target category that is the same as the first category in at least one second category is searched, so that the object to be detected and at least one similar object are matched at the specified category level, and the objects to be detected are grouped and optimized for matching through category inspection and judgment, so as to achieve optimization of the pass level of the objects to be detected.

[0107] In order to further optimize the pass level, user information can be used to determine the object to be detected and similar objects. In one possible design, if present, based on the initial pass level, determining the target pass level includes:

[0108] If so, determining target user information of the target user and similar user information corresponding to at least one similar user;

[0109] Determining whether at least one similar user information includes target user information;

[0110] If not, the initial passing grade is determined to be the target passing grade;

[0111] If so, the target passing level is determined to be the highest passing level among the at least one passing level corresponding to the level-dividing sub-model.

[0112] In trademark application scenarios, the same user may apply for the same trademark multiple times, for example, multiple trademark applications in different trademark registration areas. If the user information is the same, the newly applied trademark is more likely to pass the review. Therefore, when similar user information exists as the target user information, the highest pass level among at least one pass level can be used as the target pass level. In this embodiment, by detecting user identity information, the association between the identity information of the object to be detected and the user is improved, user identity optimization is provided, and the accuracy of the target pass level of the object to be detected is improved.

[0113] As another embodiment, the similar object detection sub-model in the grade prediction model is trained in the following manner:

[0114] determining at least one training object and at least one reference result respectively corresponding to the training object;

[0115] Build a similar object detection sub-model;

[0116] The model parameters of the similar object detection sub-model are obtained by training, with the detection results of the similar object detection sub-model on at least one training object being the same as the reference results corresponding to at least one training object.

[0117] In an embodiment of the present application, a training method for a similar object detection sub-model is provided. The model parameters of the similar object detection sub-model can be trained through at least one training object and at least one reference result corresponding to each training object, so as to obtain accurate model parameters to facilitate the use of the similar object detection sub-model.

[0118] Among them, using a similar object detection sub-model to train at least one detection result of each training with the same training target as at least one reference result corresponding to each training, training to obtain the model parameters of the similar object detection sub-model can specifically include: initializing the model parameters of the similar object detection sub-model to obtain reference model parameters; inputting at least one training object into the similar object detection sub-model corresponding to the reference model parameters in sequence to obtain the detection results corresponding to at least one training object; determining the training error based on the detection results corresponding to at least one training object and the reference results corresponding to at least one training object; judging whether the training error meets the convergence condition, and if so, determining the reference model parameters as the model parameters; if not, updating the reference model parameters based on the training error, and returning to the step of inputting at least one training object into the similar object detection sub-model corresponding to the reference model parameters in sequence to obtain the detection results corresponding to at least one training object. The model parameters of the similar object detection sub-model can be trained and obtained through the above training method.

[0119] In a trademark detection scenario, determining at least one training object and a reference result corresponding to each of the at least one training object includes:

[0120] Read at least one trademark rejection document;

[0121] parsing at least one trademark rejection document to obtain at least one target trademark and at least one cited trademark corresponding to the target trademark;

[0122] At least one target trademark is determined as at least one training object, and cited trademarks corresponding to the at least one target trademark are determined as reference results corresponding to the at least one training object.

[0123] In trademark applications, training objects and their corresponding reference results can be obtained by analyzing trademark rejection documents. By analyzing at least one rejection document, at least one training object and its corresponding reference result can be obtained, enabling the parsed acquisition of the training object.

[0124] In some embodiments, the object to be detected may include text information to be detected or image information to be detected. In this case, the similar object detection model may include a text detection unit and an image detection unit.

[0125] Inputting the object to be detected into the similar object detection sub-model, and obtaining at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected may include:

[0126] Inputting the text information to be detected into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to the at least one text-similar object;

[0127] Alternatively, the image to be detected is input into an image detection unit, and at least one image-similar object and the image similarity corresponding to the at least one image-similar object are detected and obtained;

[0128] Determining at least one text-similar object as at least one similar object, and determining the text similarities respectively corresponding to the at least one text-similar object as the similarities respectively corresponding to the at least one similar object;

[0129] Alternatively, at least one image-similar object is determined as at least one similar object, and the image similarities respectively corresponding to the at least one image-similar object are determined as the similarities respectively corresponding to the at least one image-similar object.

[0130] In practical applications, the object to be detected may include text and / or images. In particular, when the object to be detected is a trademark, the trademark may include text and images. The image is based on text and combined with different trademark styles in a certain combination method. It can realize the detection of different contents of the object to be detected, so as to achieve a more comprehensive detection plan.

[0131] Furthermore, in some embodiments, the object to be detected may include both textual information and image information. In this case, the similar object detection model may include a text detection unit and an image detection unit. When both textual information and images are included, similarities can be identified separately and then fused to obtain an accurate similarity, thereby obtaining an accurate target pass level.

[0132] Inputting the object to be detected into the similar object detection sub-model, and obtaining at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected may include:

[0133] Inputting the text information to be detected into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to the at least one text-similar object;

[0134] And, inputting the image to be detected into the image detection unit, detecting and obtaining at least one image-similar object and the image similarity corresponding to the at least one image-similar object;

[0135] Determining a text object identifier corresponding to at least one text-similar object and an image object identifier corresponding to at least one image-similar object;

[0136] Determine a first object identifier having the same text object identifier as the image object identifier;

[0137] Determining that a second object identifier other than the first object identifier in at least one text object identifier, a third object identifier next to the first object identifier in at least one image object identifier, and an object corresponding to the first object identifier are at least one similar object;

[0138] Determining a comprehensive similarity corresponding to the first object identifier based on the text similarity and the image similarity corresponding to the first object identifier;

[0139] The similarity corresponding to the at least one object identifier is determined according to the comprehensive similarity corresponding to the first object identifier, the text similarity corresponding to the second object identifier, and the image similarity corresponding to the third object identifier.

[0140] Optionally, determining the comprehensive similarity corresponding to the first object identifier based on the text similarity and the image similarity corresponding to the first object identifier may include: selecting the smaller of the text similarity and the image similarity corresponding to the first object identifier as the comprehensive similarity corresponding to the first object identifier.

[0141] Optionally, determining the comprehensive similarity corresponding to the first object identifier based on the text similarity and image similarity corresponding to the first object identifier may include: performing weighted summation of the text similarity and image similarity corresponding to the first object identifier to obtain the comprehensive similarity corresponding to the first object identifier.

[0142] As an embodiment, after inputting the object to be detected into the similar object detection sub-model and obtaining at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected, the method may further include:

[0143] Generate optimization prompt information based on at least one similar object.

[0144] Output optimization prompt information for the target object.

[0145] Optimization prompt information may be generated based on the at least one similar object. After obtaining the at least one similar object, an optimization suggestion may be generated for the at least one similar object to prompt the user to optimize the object to be detected.

[0146] Optionally, based on at least one similar object, generating optimization prompt information may include: comparing the object to be detected with at least one similar object to obtain at least one comparison result, and using the at least one comparison result to generate an adjustment suggestion, and using the adjustment suggestion to generate optimization prompt information.

[0147] Optionally, based on at least one similar object, generating optimization prompt information can also specifically include: arranging at least one similar object in order of similarity from high to low, and generating an information prompt page in detail according to the detailed object information corresponding to at least one similar object, and using the information prompt page as the optimization prompt information.

[0148] In another embodiment, generating optimization prompt information based on at least one similar object may include: sending the at least one similar object and the object to be detected to an optimization user, so that the optimization user generates optimization suggestions for the object to be detected based on the at least one similar object, and feeding back the optimization suggestions;

[0149] Receiving the optimization suggestions fed back by the optimization users;

[0150] Generate the optimization prompt information corresponding to the optimization suggestion.

[0151] Among them, the optimization user can optimize the optimization device end for a third-party user, and the optimization device end can receive at least one similar object and an object to be detected, so as to display at least one similar object and an object to be detected for the optimization user, and detect the optimization user's optimization suggestions for the object to be detected, so as to feed back the optimization suggestions obtained from the detection to a computing device configured with the information processing method provided by this application.

[0152] Optionally, the optimization suggestion may include at least one of a purchase suggestion, a modification suggestion, or a reapplication suggestion.

[0153] like Figure 3 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0154] 301: Obtain the object to be detected provided by the target user and sent by the target client.

[0155] 302: Input the object to be detected into the grade prediction model to obtain an initial passing grade of the object to be detected.

[0156] 303: Optimizing the initial pass level using the level optimization model to obtain a target pass level of the object to be detected.

[0157] 304: Generate level prompt information based on the target passing level.

[0158] 305: Sending level prompt information to the target client, so that the target client can display the level prompt information and the target user can know the target passing level.

[0159] In an embodiment of the present application, the server can obtain the object to be detected provided by the target user sent by the target client, so as to input the object to be detected into the grade prediction model, obtain the initial pass grade of the object to be detected, and realize a preliminary prediction of the pass grade of the object to be detected. Afterwards, the grade optimization model can be used to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be detected, realize further optimization processing of the pass grade, and improve the accuracy of grade estimation. The grade prompt information generated based on the target pass grade is sent to the target user terminal, and the target user terminal displays the grade prompt information, so that the target user can know the target pass grade. In this embodiment, in addition to accurately obtaining the pass grade of the target user, the configuration of the client and the server is also adopted to send the object to be detected collected by the user terminal to the server terminal for identification processing, so as to improve the efficiency of grade determination of the object to be detected, reduce the processing pressure of the client, maintain the usage performance of the client, and enhance the user experience.

[0160] As an embodiment, based on the target passing level, generating level prompt information may include:

[0161] At least one passing grade in the grade prediction model is determined.

[0162] Generate a level bar control and a scale control corresponding to the level bar control;

[0163] Based on at least one passing level, dividing the level bar control into at least one sub-control in an order of at least one passing level from low to high or from high to low;

[0164] Adjust the control position of the scale control to the sub-control corresponding to the target pass level in the level bar control to obtain the level prompt information.

[0165] like Figure 4 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0166] 401: Get the object to be detected provided by the target user.

[0167] 402: Determine multiple third categories corresponding to the first category level.

[0168] The first category level may be the first category level in the trademark field, that is, the highest category level. The first category level is higher than the designated category level in the aforementioned embodiment.

[0169] The first category level may include multiple third categories. Any third category may be divided into multiple secondary categories according to the second category level under the first category level. That is, when the designated category level is the second category level, the designated category level may include multiple fourth categories.

[0170] 403: Input the object to be detected into a grade prediction model corresponding to any third category to obtain an initial passing grade of the object to be detected corresponding to the third category, thereby obtaining initial passing grades of the object to be detected corresponding to multiple third categories respectively.

[0171] The difference between the rank prediction models for different categories lies only in the search scope within the object prediction sub-model. The search method and process remain the same. The rank classification sub-model used by different categories is the same.

[0172] It should be noted that the object to be detected in the embodiment of the present application may have a corresponding classification category. In the process of actually applying the grade prediction model and the grade optimization model to predict and optimize the target passing grade of the object to be detected, the grade prediction model under different categories can achieve corresponding predictions, and the grade optimization model can be used to perform grade optimization. That is, the specific method of inputting the object to be detected into the grade prediction model corresponding to any third category and obtaining the initial passing grade of the object to be detected in the third category is the same as Figure 2 In the embodiment shown, the steps of inputting the object to be detected into the similar object detection sub-model to obtain at least one similar object matching the object to be detected and the similarity between at least one similar object and the object to be detected are the same. In addition, the level prediction models under different categories can be trained separately or simultaneously. The prediction methods and training processes of different level prediction models are the same. Figure 3 The implementation methods of the illustrated embodiments are the same and will not be described again here.

[0173] 404: Performing level optimization processing on the initial pass levels corresponding to the plurality of third categories using the level optimization model to obtain target pass levels corresponding to the plurality of third categories of the object to be detected.

[0174] 405: Outputting target passing levels corresponding to multiple third categories for the target user.

[0175] In this embodiment, the object to be detected may correspond to categories at all levels. When obtaining the object to be detected provided by the target user, multiple third categories corresponding to the first category level may be determined. Multiple third categories are category divisions at the first category level. When determining the pass level of the object to be detected, the object to be detected may be similarly matched in categories at all levels. At this time, the object to be detected may be input into a grade prediction model corresponding to any third category to obtain the initial pass level corresponding to the third category of the object to be detected, so as to obtain the initial pass levels corresponding to the multiple third categories of the object to be detected. By performing grade optimization processing on the initial pass levels corresponding to each third category through the grade optimization model, the target pass levels corresponding to the multiple third categories of the object to be detected may be obtained, and the classified acquisition of the initial pass levels of multiple third categories may be realized, and the pass level analysis of multiple categories may be realized, thereby improving the analysis efficiency.

[0176] As an embodiment, outputting target passing levels corresponding to multiple third categories for the target user may include:

[0177] Sort the target pass levels corresponding to the multiple third categories in descending order of pass levels;

[0178] The target passing levels corresponding to the plurality of third categories are output in descending order.

[0179] In an embodiment of the present application, after sorting the target pass levels corresponding to multiple third categories in descending order, the target pass levels corresponding to multiple third categories can be displayed in the sorted order to achieve output in order of level and improve the prompt effect.

[0180] As another embodiment, outputting target passing levels corresponding to a plurality of third categories for the target user includes:

[0181] Sort the targets corresponding to the multiple third categories by level according to the order of the corresponding third categories;

[0182] Output target passing levels corresponding to multiple third categories in order from high to low.

[0183] In an embodiment of the present application, the target pass levels corresponding to multiple third categories are sorted according to the category order of the third categories, and then the target pass levels corresponding to multiple third categories are displayed in sequence according to the category order, so as to achieve sequential output in the category order and improve the display effect.

[0184] As yet another embodiment, after determining a plurality of third categories corresponding to the first category level, the method may further include:

[0185] Detect the monitoring category selected by the target user from multiple third categories.

[0186] Outputting target passing levels corresponding to multiple third categories for target users may include:

[0187] Determining a first display mode for the monitoring category and a second display mode for each of the third categories other than the monitoring category in the plurality of third categories;

[0188] Display the target passing level corresponding to the monitoring category according to the preset first display mode;

[0189] The target passing levels of the third categories other than the monitoring category in the plurality of third categories are displayed in a preset second display manner.

[0190] The first display mode is different from the second display mode. The display effect of the first display mode is better than that of the second display mode, and the display effect of the first display mode is more prominent.

[0191] Further, optionally, obtaining the monitoring category selected by the target user from the plurality of third categories may include: generating category input prompt information for the plurality of third categories, displaying the category input prompt information to the target user, and obtaining the monitoring category selected or input by the target user in the category input prompt information.

[0192] The target user's client can detect the third category selected or input by the target user in the category input prompt information, obtain the monitoring category, and send the monitoring category and the object to be detected to the server. The category input prompt information can be used to prompt the target user to select or input the third category to be monitored.

[0193] The category input prompt information may provide input and selection controls for multiple third categories. The category input prompt information may include multiple third categories.

[0194] Further, optionally, the first display mode may include: a first display shape, a first display position corresponding to the center of the first display shape, and a first display color;

[0195] The second display manner may include: a second display shape, a second display position corresponding to the center of the second display shape, and a second display color.

[0196] In this embodiment, the monitoring category selected by the target user can be detected, and different display methods can be used to display the passing level obtained under the monitoring category selected by the user and the passing level under the category not selected by the user, so as to distinguish the display methods of the two categories, focus on displaying the monitoring category selected by the target user, and achieve targeted display.

[0197] As another embodiment, after performing grade optimization processing on the initial pass grades corresponding to the plurality of third categories using the grade optimization model to obtain the target pass grades of the object to be detected corresponding to the plurality of third categories, the method may further include:

[0198] Based on the target passing levels of the object to be detected corresponding to the multiple third categories, category prompt information of each of the multiple third categories is generated respectively; and the category prompt information corresponding to the multiple third categories is output.

[0199] Among them, any category prompt information is used to prompt the object to be detected to pass the target level of the corresponding third category.

[0200] In actual application, the category prompt information corresponding to multiple third categories can be output together for the target user to select and view the passing level of the corresponding category. The output of the category prompt information can include multiple output forms.

[0201] The first output form: Output the category prompt information corresponding to multiple third categories in the form of controls. The more common output method may include establishing a topological structure of multiple third categories in the form of nodes, and associating each node with the target pass level of the object to be detected in the third category, so that when the user clicks any node in the topological structure, the target pass level corresponding to the node is displayed. For ease of understanding, refer to Figure 5 , which is a method of displaying category prompt information corresponding to multiple third categories in a spherical topology structure provided in an embodiment of the present application.

[0202] The second output form: generate a level prompt control for each of the multiple third categories, and associate each level prompt control with the target pass level of the corresponding third category, and display the level prompt controls corresponding to the multiple third categories in a certain arrangement and display method, and when the target user clicks any level prompt control, the corresponding target pass level is displayed. Among them, the more common arrangement and display method may include: arranging the level prompt controls in a circular form, and adjusting the control size and control position according to the radius of the circular ring. For ease of understanding, refer to Figure 6 An embodiment of the present application provides a display method in which category prompt information is displayed in a circular prompt control and the circular prompt controls corresponding to multiple category prompt information are arranged in a ring form.

[0203] In order to enable the user to quickly find the target passing level corresponding to the required third category, in some embodiments, outputting the category prompt information corresponding to the plurality of third categories may include:

[0204] Displaying the category prompt information corresponding to the plurality of third categories to generate comprehensive prompt information; detecting a movement operation of the target user with respect to the comprehensive prompt information;

[0205] In response to the move operation, performing corresponding move control processing on the plurality of third categories in the comprehensive prompt information to obtain the comprehensive prompt information after the move;

[0206] The comprehensive prompt information after the movement is displayed.

[0207] Optionally, the comprehensive prompt information generated by the category prompt information corresponding to the multiple third categories can be located in the central area of ​​the display interface before it moves. The moving operation may include: a click operation, a sliding operation, a drag operation, a rotation operation or a translation operation of a preset mobile control, and the mobile control processing corresponding to the mobile operation may specifically be to identify the movement trajectory and movement type of the mobile operation, and perform a movement processing corresponding to the movement trajectory and movement type of the mobile operation. Among them, the mobile control is a control generated for the comprehensive prompt information and used to perform predefined control operations. For example, the more common zoom-in control or zoom-out control. When the target user clicks the mobile control, the comprehensive mobile information can move according to the mobile operation pre-associated with the mobile control.

[0208] refer to Figure 5 The comprehensive prompt information is displayed in the form of a spherical topological structure. The nodes corresponding to the multiple third categories can be the category prompt information corresponding to the third category. The topological structure is displayed in the form of a spherical three-dimensional image. To facilitate user movement and viewing, the spherical topological structure can be associated with a three-dimensional mobile control 501. When the user clicks or rotates the mobile control, a movement operation for the comprehensive prompt information can be triggered.

[0209] refer to Figure 6 The comprehensive prompt information is displayed in the form of a circular ring structure. In the two-dimensional ring structure, prompt controls for category prompt information corresponding to multiple third categories are displayed. When the target user triggers the category prompt control, in some embodiments, detailed information of the third category can be displayed. When displaying the detailed information of the third category, it can be displayed in the form of an information sub-page.

[0210] In addition, the target user can also use dragging and other mobile operations to control the movement of comprehensive prompt information, refer to Figure 5 , a display interface in which the comprehensive prompt information is displayed in the center area of ​​the display interface 502 before the movement. Assuming that the movement is a 45-degree sliding operation to the upper left corner, the movement processing corresponding to the 45-degree sliding operation can be performed. The display result of the comprehensive prompt information after the movement can be specifically referred to Figure 7 .

[0211] When a user views the category prompt information corresponding to multiple third categories, the category prompt information corresponding to the multiple third categories can be moved. When moving the category prompt information corresponding to the multiple third categories, the category prompt information corresponding to the multiple third categories can be moved as a whole. In this embodiment, the category prompt information corresponding to the multiple third categories is generated into a comprehensive prompt information to detect the target user's movement operation on the comprehensive prompt information, and perform movement control processing corresponding to the movement operation, so that the target user can obtain comprehensive prompt information displayed at different angles, directions and areas, realize interactive category information display prompts, and improve display effectiveness.

[0212] In some embodiments, when the target user triggers any category prompt information by clicking, sliding through, etc., the target passing level of the third category corresponding to the category prompt information selected by the target user can be displayed to the target user. Specifically, it can be displayed in the form of a prompt subpage.

[0213] Outputting the category prompt information corresponding to the plurality of third categories may include:

[0214] Outputting a category prompt page corresponding to the category prompt information respectively corresponding to the plurality of third categories;

[0215] Detect a selection operation triggered by a target user on any third category among multiple third categories to obtain the focused category.

[0216] Generate a level prompt subpage based on the target passing level corresponding to the target user's output of the category of interest;

[0217] The category prompt information of the level prompt subpage is displayed to the target user.

[0218] In actual applications, displaying the level prompt subpage for the target user can specifically overlay the level prompt subpage on the display page of the category prompt information corresponding to the plurality of third categories. That is, in this case, outputting the category prompt information corresponding to the plurality of third categories can specifically include: outputting the category prompt page corresponding to the category prompt information corresponding to the plurality of third categories.

[0219] After the target user moves, the category prompt information of any third category can be used to trigger a selection operation to obtain the category of interest. Figure 7 , assuming that the target user triggers a selection operation on the category prompt information of “39 Transportation and Storage”, a level prompt subpage 701 corresponding to the third category of the category prompt information may be displayed.

[0220] It should be noted that if the technical solution of the embodiment of the present application is configured in a server, such as a cloud server, Figures 5 to 7Prompt examples or page examples can be generated in the server and sent to the target user's client for display. The specific generation process can be referred to the description in the aforementioned embodiment and will not be repeated here.

[0221] like Figure 8 FIG. 1 is a flowchart of another embodiment of an information processing method provided by an embodiment of the present application. The method may include:

[0222] 801: Obtain the object to be detected provided by the target user.

[0223] 802: Determine multiple third categories corresponding to the first category level.

[0224] 803: Obtain the target category selected by the target user from multiple third categories.

[0225] In actual applications, multiple third categories can be prompted separately to allow users to select the target category that requires level confirmation. Multiple third categories can be used as prompt nodes and prompted in the form of a topological output structure. Multiple third categories can also be used as prompt objects, and each generates a prompt control, such as a circular control, a spherical control, or a polygonal control, etc., and each prompt control is used to prompt the corresponding third category. In addition, in order to improve the effectiveness of the display, the target category can be highlighted. For example, the shape and color of the prompt control of the target category selected by the user are set to be more prominent than the shape and color of the remaining prompt controls to improve the prompt effect.

[0226] 804: Input the object to be detected into the grade prediction model corresponding to the target category to obtain the initial passing grade of the object to be detected in the target category.

[0227] 805: Optimizing the initial pass level using the level optimization model to obtain a target pass level of the object to be detected.

[0228] 806: Outputting the target passing level corresponding to the target category to the target user.

[0229] In this embodiment, the target user provides an object to be detected, and multiple third categories corresponding to the first category levels can be determined. The target category selected by the target user from the multiple third categories can then be obtained. The target category can be a category of particular interest to the target user. By setting the target category, a targeted level estimation can be performed, resulting in an accurate level estimation target and improved effectiveness of the level estimation.

[0230] The acquiring of the target category selected by the target user from the plurality of third categories includes:

[0231] generating category input prompt information for the plurality of third categories;

[0232] Displaying the category input prompt information for the target user;

[0233] The target category is obtained by selecting or inputting the prompt information of the category input by the target user.

[0234] Optionally, the category input prompt information may be a text input control for category input. The user may directly enter the target category in the text input control for category input. The text input control may further include multiple selection prompt sub-controls corresponding to respective third categories. When the target user's cursor is detected to have selected the text input control, the multiple selection prompt sub-controls corresponding to respective third categories may be displayed to the target user to prompt the target user to select a category, and the target category selected by the target user may be detected.

[0235] Take the trademark to be tested as an example, Figure 9 A flowchart of another embodiment of an information processing method provided by an embodiment of the present application is shown. The method may include:

[0236] 901: Obtain the trademark to be detected provided by the target user.

[0237] 902: Input the trademark to be tested into the grade prediction model to obtain the initial passing grade of the trademark to be tested.

[0238] 903: Optimize the initial pass grade using the grade optimization model to obtain the target pass grade of the trademark to be inspected.

[0239] 904: Outputting a target passing level for the target user.

[0240] In this embodiment, the trademark to be detected of the target user can be obtained, and then the trademark to be detected can be input into the grade prediction model to obtain the initial pass grade of the trademark to be detected. At this time, the grade prediction model is used to make a preliminary prediction of the pass grade of the trademark to be detected. The initial pass grade is then grade-optimized using the grade optimization model to obtain the target pass grade of the trademark to be detected. At this time, the grade optimization model is used to further grade-optimize the initial predicted pass grade to obtain the target pass grade that accurately measures the performance of the trademark to be detected, so that when the target user outputs the target pass grade, the accurate target pass grade can be used to effectively prompt the target user of the possibility of passing the trademark to be detected, so as to avoid the generation of invalid trademarks. In particular, when the trademark to be detected is a trademark, the success rate of trademark registration can be improved.

[0241] For ease of understanding, the technical solution of the embodiment of the present application is introduced in detail by taking the object to be detected as a trademark as an example.

[0242] Figure 10In the example, the target user can use the user terminal M1 to input the trademark to be detected. In one possible design, the user terminal M1 can display an input interface for the trademark to be detected. The target user U1 can enter the trademark's text information and image information into the text input control 1001 and image input control 1002 provided in the input interface. At this point, the user terminal M1 can detect the trademark to be detected, which is composed of the text information and image information entered by the target user, and send the trademark to be detected to the server M2.

[0243] Furthermore, in some embodiments, the target user may further specify the information type of the trademark. Specifically, a prompt of candidate information types may be provided, such as a text, graphic, or combined text and graphic prompt control shown in 1003. The user may select the trademark information type by triggering the prompt control. Furthermore, in still other embodiments, the target user may select a monitoring category from multiple third categories. In this case, a category selection input prompt control 1004 may be displayed in the trademark input interface. The user may trigger this selection control 1004 to select the corresponding monitoring category.

[0244] Server M2 can obtain a trademark to be inspected, provided by a target user, which may include, for example, textual information and image information of the trademark. Server M2 can then input the trademark to be inspected into a grade prediction model to obtain an initial pass grade for the inspected object. After obtaining the initial pass grade, the grade optimization model can be used to optimize the initial pass grade to obtain a target pass grade for the trademark to be inspected. The target pass grade can then be output to the target user.

[0245] In actual application, the server M2 outputs the target pass level and can output the target pass level to the user terminal M1, and the target pass level is output by the display of the user terminal M1. When outputting the target pass level, the target pass level can be output in the form of a level bar control. For details, please refer to Figure 7 The level bar control 1005 shown in .

[0246] In addition, in some embodiments, the passing levels of the trademark to be detected under multiple third categories can be predicted separately, and the passing levels of the trademark to be detected under different third categories can be obtained and prompted separately. Figure 10 The target pass level prompt information 1006 corresponding to the target trademark under inspection in multiple third categories is shown in 1006. The multiple target pass level prompt information shown in 1006 is displayed in the order of categories. In addition, 1006 also shows the target pass level prompt information of multiple fourth categories under the second category level under the first category level of the third category.

[0247] In addition, in some embodiments, the category prompt information corresponding to the trademark in multiple third categories can be displayed in a spherical topological structure, referring to Figure 10 The category prompt information 1007 is arranged in a circular form. In the prompt information 1007, the category prompt information of the third category "20 furniture supplies" selected by the target user is highlighted to improve the prompt effect.

[0248] like Figure 11 FIG2 is a schematic diagram of a structure of an embodiment of a computing device provided by an embodiment of the present application. The device may include: a storage component 1101 and a processing component 1102; the storage component 1101 is used to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component 1102;

[0249] The processing component 1102 is used to:

[0250] Obtain the object to be detected provided by the target user; input the object to be detected into the grade prediction model to obtain the initial pass grade of the object to be detected; use the grade optimization model to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be detected; output the target pass grade to the target user.

[0251] As an embodiment, the processing component inputs the object to be detected into the grade prediction model, and obtaining the initial passing grade of the object to be detected may specifically include:

[0252] Inputting the object to be detected into the similar object detection sub-model to obtain at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected;

[0253] Based on the similarity corresponding to at least one similar object, a level division process is performed according to the level division sub-model to obtain an initial passing level of the object to be detected.

[0254] In some embodiments, the processing component performs a grading process according to the grading sub-model based on the similarity corresponding to at least one similar object, and obtaining an initial passing grade of the object to be detected may specifically include:

[0255] Obtaining at least one passing level corresponding to the graded sub-model and a similarity range corresponding to each of the at least one passing level;

[0256] Determining a target similarity range in at least one similarity range based on the similarities respectively corresponding to the at least one similar object;

[0257] The passing level corresponding to the target similarity range is determined as the initial passing level.

[0258] In one possible design, the processing component may determine the target similarity range in the at least one similarity range based on the similarities corresponding to the at least one similar object, and specifically may include:

[0259] Determining a maximum similarity among the similarities corresponding to at least one similar object;

[0260] A target similarity range corresponding to the maximum similarity in at least one similarity range is determined.

[0261] In another possible design, the processing component may determine the target similarity range in the at least one similarity range based on the similarities corresponding to the at least one similar object, and specifically may include:

[0262] Determining, according to the similarity ranges respectively corresponding to the at least one passing level, the similarity range to which the similarity respectively corresponding to the at least one similar object belongs, so as to obtain the similarity respectively corresponding to the at least one similarity range;

[0263] Counting the number of similarities in any similarity range to obtain the number of similar objects in the similarity range, thereby obtaining the number of similar objects corresponding to at least one similarity range;

[0264] determining at least one candidate similarity range having a number of similar objects greater than 1;

[0265] A target similarity range having the highest range among the at least one candidate similarity range is determined.

[0266] In some embodiments, the processing component uses the grade optimization model to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be inspected, which may specifically include:

[0267] Determine the first category corresponding to the object to be detected at the specified category level;

[0268] determining a second category corresponding to each of the at least one similar object at a specified category level;

[0269] Determining whether there is a target category identical to the first category in the second category corresponding to at least one similar object;

[0270] If so, based on the initial passing grade, a target passing grade is determined;

[0271] If not, the target passing level is determined to be the highest passing level among at least one passing level corresponding to the graded sub-model.

[0272] The first category corresponding to the object to be detected at the specified category level may be the first category selected by the target user for the object to be detected at the specified category level.

[0273] In one possible design, if the processing component processing exists, then based on the initial pass level, determining the target pass level may specifically include:

[0274] If so, determining target user information of the target user and similar user information corresponding to at least one similar object;

[0275] Determining whether at least one similar user information includes target user information;

[0276] If not, the initial passing grade is determined to be the target passing grade;

[0277] If so, the target passing level is determined to be the highest passing level among the at least one passing level corresponding to the level division sub-model.

[0278] As another embodiment, the processing component trains the similar object detection sub-model in the grade prediction model in the following manner:

[0279] determining at least one training object and at least one reference result respectively corresponding to the training object;

[0280] Build a similar object detection sub-model;

[0281] The model parameters of the similar object detection sub-model are obtained by training with the detection results of the similar object detection sub-model on at least one training object being the same as the reference results respectively corresponding to the at least one training object.

[0282] Further, optionally, the processing component determining the at least one training object and the at least one reference result corresponding to the training object may specifically include:

[0283] Read at least one trademark rejection document;

[0284] parsing at least one trademark rejection document to obtain at least one target trademark and at least one cited trademark corresponding to the target trademark;

[0285] At least one target trademark is determined as at least one training object, and cited trademarks corresponding to the at least one target trademark are determined as reference results corresponding to the at least one training object.

[0286] In a possible design, the object to be detected includes: text information to be detected or image information to be detected; the similar object detection sub-model includes: a text detection unit and an image detection unit;

[0287] The processing component inputs the object to be detected into the similar object detection sub-model, and obtains at least one similar object that matches the object to be detected and the similarity between the at least one similar object and the object to be detected, which may specifically include:

[0288] Inputting the text information to be detected into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to the at least one text-similar object;

[0289] Alternatively, the image information to be detected is input into an image detection unit, and at least one image-similar object and the image similarity corresponding to the at least one image-similar object are detected and obtained;

[0290] Determining at least one similar object corresponding to at least one text-similar object, and the text similarities respectively corresponding to at least one text-similar object as the similarities respectively corresponding to the at least one similar object;

[0291] Alternatively, at least one similar object corresponding to at least one image-similar object and the image similarities respectively corresponding to at least one image-similar object are determined as the similarities respectively corresponding to the at least one similar object.

[0292] In another possible design, the object to be detected includes: text information to be detected and image information to be detected;

[0293] The processing component inputs the object to be detected into the similar object detection sub-model, and obtains at least one similar object that matches the object to be detected and the similarity between the at least one similar object and the object to be detected, which may specifically include:

[0294] Inputting the text information to be detected into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to the at least one text-similar object;

[0295] And, inputting the image information to be detected into the image detection unit, detecting and obtaining at least one image-similar object and the image similarity corresponding to the at least one image-similar object;

[0296] determining an object identifier of at least one text-similar object and an object identifier of at least one image-similar object;

[0297] performing object deduplication processing based on the object identifier of at least one text-similar object and the object identifier of at least one image-similar object to obtain at least one similar object;

[0298] Determining similarity of similar objects with the same object identifier based on text similarity of text similar objects and image similarity of image similar objects;

[0299] The text similarity of text-similar objects with non-overlapping object identifiers is used as the similarity of the corresponding similar objects, and the image similarity of image-similar objects with non-overlapping object identifiers is used as the similarity of the corresponding similar objects to obtain the object similarity of at least one similar object.

[0300] In some embodiments, the processing component may also be used to:

[0301] Generate optimization prompt information based on at least one similar object;

[0302] Output optimization prompt information for the target object.

[0303] As a possible implementation manner, the processing component generating the optimization prompt information based on the at least one similar object may include:

[0304] Sending the at least one similar object and the object to be detected to an optimization user, so that the optimization user generates an optimization suggestion for the object to be detected based on the at least one similar object and feeds back the optimization suggestion;

[0305] Receiving the optimization suggestions fed back by the optimization users;

[0306] Generate optimization prompt information corresponding to the optimization suggestion.

[0307] As another embodiment, the processing component obtaining the object to be detected provided by the target user may specifically include:

[0308] Obtain the target object to be detected provided by the target user and sent by the target client;

[0309] Outputting target pass levels for target users includes:

[0310] Generate level prompt information based on the target passing level;

[0311] The level prompt information is sent to the target client so that the target client can display the level prompt information and let the target user know the target passing level.

[0312] In some embodiments, the processing component generates level prompt information based on the target passing level, which may specifically include:

[0313] determining at least one passing grade in a grade prediction model;

[0314] Generate a level bar control and a scale control corresponding to the level bar control;

[0315] Based on at least one passing level, dividing the level bar control into at least one sub-control in an order of at least one passing level from low to high or from high to low;

[0316] Adjust the control position of the scale control to the sub-control corresponding to the target pass level in the level bar control to obtain the level prompt information.

[0317] In some embodiments, the processing component inputs the object to be detected into the grade prediction model, and obtaining the initial passing grade of the object to be detected may specifically include:

[0318] Determine multiple third categories corresponding to the first category level;

[0319] Inputting the object to be detected into a grade prediction model corresponding to any third category to obtain an initial passing grade of the object to be detected corresponding to the third category, thereby obtaining initial passing grades of the object to be detected corresponding to multiple third categories respectively;

[0320] The processing component uses the grade optimization model to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be inspected, which may specifically include:

[0321] Using the grade optimization model, grade optimization processing is performed on the initial pass grades corresponding to the multiple third categories to obtain the target pass grades corresponding to the multiple third categories of the object to be detected;

[0322] The processing component outputs the target passing level for the target user and specifically may include:

[0323] Output target passing levels corresponding to multiple third categories for the target user.

[0324] In a possible design, the processing component outputs target passing levels corresponding to multiple third categories for the target user, which may specifically include:

[0325] Sort the target pass levels corresponding to the multiple third categories in descending order of pass levels;

[0326] The target passing levels corresponding to the plurality of third categories are output in descending order.

[0327] In another possible design, the processing component outputs a plurality of target passing levels corresponding to the third categories for the target user, which may specifically include:

[0328] Sort the targets corresponding to the multiple third categories by level according to the order of the corresponding third categories;

[0329] Output target passing levels corresponding to multiple third categories in order from high to low.

[0330] As a possible implementation, the processing component can also be used to:

[0331] Detecting a monitoring category selected by a target user from multiple third categories;

[0332] The processing component outputs target passing levels corresponding to multiple third categories for the target user, which may specifically include:

[0333] Determining a first display mode for the monitoring category and a second display mode for each of the plurality of third categories except the monitoring category;

[0334] Display the target passing level corresponding to the monitoring category according to the preset first display mode;

[0335] The target passing levels of the respective categories other than the monitoring category in the plurality of third categories are displayed in a preset second display manner.

[0336] In some embodiments, the processing component obtaining the monitoring category selected by the target user from multiple third categories may specifically include:

[0337] Generate multiple third-category category input prompt information;

[0338] Display category input prompt information for target users;

[0339] Get the monitoring category selected or entered by the target user in the category input prompt information.

[0340] Further, optionally, the first display mode includes: a first display shape, a first display position corresponding to the center of the first display shape, and a first display color;

[0341] The second display mode includes: a second display shape, a second display position corresponding to the center of the second display shape, and a second display color.

[0342] In yet other embodiments, the processing component may also be configured to:

[0343] Generating category prompt information for each of the plurality of third categories based on the target passing levels of the object to be detected corresponding to the plurality of third categories respectively;

[0344] Outputting category prompt information corresponding to each of the plurality of third categories;

[0345] The processing component outputting the category prompt information corresponding to the plurality of third categories may specifically include:

[0346] Displaying the category prompt information corresponding to the plurality of third categories to generate comprehensive prompt information; detecting a movement operation of the target user with respect to the comprehensive prompt information;

[0347] In response to the move operation, performing corresponding move control processing on the plurality of third categories in the comprehensive prompt information to obtain the comprehensive prompt information after the move;

[0348] The comprehensive prompt information after the movement is displayed.

[0349] In some embodiments, the processing component outputting the category prompt information corresponding to the plurality of third categories may specifically include:

[0350] Outputting a category prompt page corresponding to the category prompt information respectively corresponding to the plurality of third categories;

[0351] detecting a selection operation triggered by the target user on any third category among the plurality of third categories to obtain an attention category;

[0352] Generate a level prompt subpage based on the target passing level corresponding to the concerned category input by the target user;

[0353] The level prompt subpage is displayed for the target user.

[0354] As yet another example, the processing group can also be used to:

[0355] Determine multiple third categories corresponding to the first category level;

[0356] Obtaining a target category selected by the target user from multiple third categories;

[0357] The processing component inputs the object to be detected into a grade prediction model, and obtaining the initial passing grade of the object to be detected may specifically include:

[0358] Inputting the object to be detected into a grade prediction model corresponding to the target category to obtain an initial passing grade of the object to be detected in the target category;

[0359] The processing component outputting the target passing level for the target user may specifically include:

[0360] Output the target passing level corresponding to the target category for the target user.

[0361] As an embodiment, the processing component obtaining the target category selected by the target user from the multiple third categories may specifically include:

[0362] generating category input prompt information for the plurality of third categories;

[0363] Displaying the category input prompt information for the target user;

[0364] The target category is obtained by selecting or inputting the prompt information of the category input by the target user.

[0365] Figure 11 The computing device can execute Figure 1The implementation principle and technical effects of the information processing method of the embodiment shown are not described in detail. The specific manner of each step executed by the processing component in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0366] In addition, the embodiment of the present application also provides a computer readable storage medium, which is used to store a computer program. When the computer program is executed, it can perform the following operations: Figure 1 The information processing method in the illustrated embodiment.

[0367] like Figure 12 FIG2 is a schematic diagram of a structure of another embodiment of a computing device provided by an embodiment of the present application. The device may include: a storage component 1201 and a processing component 1202; the storage component 1201 is used to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component 1202;

[0368] The processing component 1202 can be used to:

[0369] Obtain the trademark to be tested provided by the target user; input the trademark to be tested into the grade prediction model to obtain the initial pass grade of the trademark to be tested; use the grade optimization model to optimize the initial pass grade to obtain the target pass grade of the trademark to be tested; output the target pass grade for the target user.

[0370] Figure 12 The computing device can execute Figure 9 The implementation principle and technical effects of the information processing method of the embodiment shown are not described in detail. The specific manner of each step executed by the processing component in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0371] In addition, the embodiment of the present application also provides a computer readable storage medium, which is used to store a computer program. When the computer program is executed, it can perform the following operations: Figure 6 The information processing method in the illustrated embodiment.

[0372] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0373] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product. This application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0374] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0375] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0376] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0377] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0378] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0379] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0380] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An information processing method, characterized in that: include: Obtain the object to be detected provided by the target user; Inputting the object to be detected into a grade prediction model to obtain an initial passing grade of the object to be detected; Performing a grade optimization process on the initial pass grade using a grade optimization model to obtain a target pass grade of the object to be detected; outputting the target passing grade for the target user; Inputting the object to be detected into a grade prediction model to obtain an initial passing grade of the object to be detected includes: Determine multiple third categories corresponding to the first category level; Inputting the object to be detected into a grade prediction model corresponding to any third category to obtain an initial passing grade of the object to be detected corresponding to the third category, thereby obtaining initial passing grades of the object to be detected corresponding to multiple third categories respectively; The performing grade optimization processing on the initial pass grade by using the grade optimization model to obtain the target pass grade of the object to be detected comprises: Using a grade optimization model, grade optimization processing is performed on the initial pass grades corresponding to the plurality of third categories to obtain target pass grades corresponding to the objects to be detected in the plurality of third categories; Outputting the target passing level for the target user includes: Outputting target passing levels corresponding to the plurality of third categories respectively to the target user.

2. The method according to claim 1, characterized in that Inputting the object to be detected into a grade prediction model to obtain an initial passing grade of the object to be detected includes: Inputting the object to be detected into a similar object detection sub-model to obtain at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected; Based on the similarities respectively corresponding to the at least one similar object, a level division process is performed according to the level division sub-model to obtain an initial passing level of the object to be detected.

3. The method according to claim 2, characterized in that The step of performing a level division process according to a level division sub-model based on the similarities respectively corresponding to the at least one similar object to obtain an initial passing level of the object to be detected includes: Obtaining at least one passing level corresponding to the graded sub-model and a similarity range corresponding to each of the at least one passing level; Determining a target similarity range in at least one similarity range based on the similarities respectively corresponding to the at least one similar object; The passing level corresponding to the target similarity range is determined as the initial passing level.

4. The method according to claim 3, characterized in that The determining, based on the similarities respectively corresponding to the at least one similar object, a target similarity range in at least one similarity range includes: Determining a maximum similarity among the similarities respectively corresponding to the at least one similar object; A target similarity range corresponding to the maximum similarity in at least one similarity range is determined.

5. The method according to claim 3, characterized in that The determining, based on the similarities respectively corresponding to the at least one similar object, a target similarity range in at least one similarity range includes: Determining, according to the similarity ranges respectively corresponding to the at least one passing level, the similarity ranges to which the similarities respectively corresponding to the at least one similar object belong, to obtain the similarities respectively corresponding to the at least one similarity range; Counting the number of similarities in any similarity range to obtain the number of similar objects in the similarity range, thereby obtaining the number of similar objects corresponding to at least one similarity range; determining at least one candidate similarity range having a number of similar objects greater than 1; A target similarity range having the highest range among the at least one candidate similarity range is determined.

6. The method according to claim 2, characterized in that The performing grade optimization processing on the initial pass grade by using the grade optimization model to obtain the target pass grade of the object to be detected comprises: Determining a first category corresponding to the object to be detected at a specified category level; Determining the second category corresponding to each of the at least one similar object at the specified category level; Determining whether there is a target category identical to the first category in the second category corresponding to the at least one similar object; If so, determining the target pass level based on the initial pass level; If not, the target passing level is determined to be the highest passing level among the at least one passing level corresponding to the level division sub-model.

7. The method according to claim 6, characterized in that If present, determining the target pass level based on the initial pass level includes: If so, determining target user information of the target user and similar user information corresponding to the at least one similar object; Determining whether the at least one similar user information includes the target user information; If not, determining the initial pass level as the target pass level; If yes, the target passing grade is determined to be the highest passing grade among the at least one passing grade corresponding to the grade division sub-model.

8. The method according to claim 2, characterized in that The similar object detection sub-model in the grade prediction model is trained in the following way: Determining at least one training object and a reference result respectively corresponding to the at least one training object; Build a similar object detection sub-model; The model parameters of the similar object detection sub-model are obtained by training with the training goal that the detection results of the similar object detection sub-model on each of the at least one training object are the same as the reference results respectively corresponding to the at least one training object.

9. The method according to claim 8, characterized in that The determining of at least one training object and a reference result respectively corresponding to the at least one training object comprises: Read at least one trademark rejection document; parsing the at least one trademark rejection document to obtain at least one target trademark and a cited trademark corresponding to the at least one target trademark; The at least one target trademark is determined to be the at least one training object, and the cited trademarks corresponding to the at least one target trademark are determined to be the reference results corresponding to the at least one training object.

10. The method according to claim 2, characterized in that The object to be detected includes: text information to be detected or image information to be detected; the similar object detection sub-model includes: a text detection unit and an image detection unit; Inputting the object to be detected into the similar object detection sub-model to obtain at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected includes: Inputting the to-be-detected text information into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to each of the at least one text-similar object; Alternatively, the image information to be detected is input into the image detection unit, and at least one image-similar object and the image similarity corresponding to the at least one image-similar object are detected and obtained; Determining at least one similar object corresponding to the at least one text-similar object, and determining the text similarities respectively corresponding to the at least one text-similar object as the similarities respectively corresponding to the at least one similar object; Alternatively, at least one similar object corresponding to the at least one image-similar object and the image similarities respectively corresponding to the at least one image-similar object are determined as the similarities respectively corresponding to the at least one similar object.

11. The method according to claim 10, characterized in that The objects to be detected include: text information to be detected and image information to be detected; Inputting the object to be detected into the similar object detection sub-model to obtain at least one similar object matching the object to be detected and the similarity between the at least one similar object and the object to be detected includes: Inputting the to-be-detected text information into the text detection unit, detecting and obtaining at least one text-similar object and the text similarity corresponding to each of the at least one text-similar object; and inputting the image information to be detected into the image detection unit to detect and obtain at least one image-similar object and the image similarity corresponding to the at least one image-similar object; determining an object identifier of the at least one text-similar object and an object identifier of the at least one image-similar object; performing object deduplication processing based on the object identifier of the at least one text-similar object and the object identifier of the at least one image-similar object to obtain at least one similar object; Determining the similarity of similar objects with the same object identifier based on the text similarity of similar text objects and the image similarity of similar image objects; The text similarity of text-similar objects with non-overlapping object identifiers is used as the similarity of the corresponding similar objects, and the image similarity of image-similar objects with non-overlapping object identifiers is used as the similarity of the corresponding similar objects to obtain the object similarity of the at least one similar object.

12. The method according to claim 2, characterized in that Also includes: generating optimization prompt information based on the at least one similar object; Output the optimization prompt information for the object to be detected.

13. The method according to claim 12, characterized in that The generating optimization prompt information based on the at least one similar object includes: Sending the at least one similar object and the object to be detected to an optimization user, so that the optimization user generates an optimization suggestion for the object to be detected based on the at least one similar object and feeds back the optimization suggestion; Receiving the optimization suggestions fed back by the optimization users; Generate optimization prompt information corresponding to the optimization suggestion.

14. The method according to claim 1, wherein The step of obtaining the object to be detected provided by the target user includes: Obtaining the object to be detected provided by the target user and sent by the target client; Outputting the target passing level for the target user includes: Generating level prompt information based on the target passing level; The level prompt information is sent to the target client, so that the target client displays the level prompt information, so that the target user can know the target passing level.

15. The method according to claim 14, characterized in that The generating of level prompt information based on the target passing level includes: determining at least one passing grade in the grade prediction model; Generate a level bar control and a scale control corresponding to the level bar control; Based on the at least one passing level, dividing the level bar control into at least one sub-control in an order of the at least one passing level from low to high or from high to low; The control position of the scale control is adjusted to the sub-control corresponding to the target passing level in the level bar control to obtain the level prompt information.

16. The method according to claim 1, wherein Outputting the target passing levels corresponding to the plurality of third categories for the target user includes: sorting the target pass levels corresponding to the plurality of third categories in descending order of pass levels; The target passing levels corresponding to the plurality of third categories are outputted in descending order.

17. The method according to claim 1, wherein Outputting the target passing levels corresponding to the plurality of third categories for the target user includes: sorting the targets corresponding to the plurality of third categories according to their levels in the order of the corresponding third categories; The target passing levels respectively corresponding to the plurality of third categories are outputted in order from high to low categories.

18. The method according to claim 11, characterized in that Also includes: detecting a monitoring category selected by the target user from the plurality of third categories; Outputting the target passing levels corresponding to the plurality of third categories for the target user includes: determining a first display mode for the monitoring category and a second display mode for each of the third categories other than the monitoring category in the plurality of third categories; Displaying the target passing level corresponding to the monitoring category in a preset first display mode; The target passing levels of the third categories other than the monitoring category in the plurality of third categories are displayed in a preset second display manner.

19. The method according to claim 18, characterized in that The first display mode includes: a first display shape, a first display position corresponding to a center of the first display shape, and a first display color; The second display manner includes: a second display shape, a second display position corresponding to the center of the second display shape, and a second display color.

20. The method according to claim 1, wherein Also includes: Generating category prompt information for each of the plurality of third categories based on the target passing levels of the object to be detected corresponding to the plurality of third categories respectively; Output category prompt information corresponding to the multiple third categories respectively.

21. The method according to claim 20, characterized in that Outputting the category prompt information corresponding to the plurality of third categories includes: Displaying the category prompt information corresponding to the plurality of third categories to generate comprehensive prompt information; detecting a movement operation of the target user with respect to the comprehensive prompt information; In response to the move operation, performing corresponding move control processing on the plurality of third categories in the comprehensive prompt information to obtain the comprehensive prompt information after the move; The comprehensive prompt information after the movement is displayed.

22. The method according to claim 20, characterized in that Outputting the category prompt information corresponding to the plurality of third categories includes: Outputting a category prompt page corresponding to the category prompt information respectively corresponding to the plurality of third categories; detecting a selection operation triggered by the target user on any third category among the plurality of third categories to obtain an attention category; Generate a level prompt subpage based on the target passing level corresponding to the concerned category input by the target user; The level prompt subpage is displayed for the target user.

23. The method according to claim 1, wherein Also includes: Determine multiple third categories corresponding to the first category level; Obtaining a target category selected by the target user from multiple third categories; Inputting the object to be detected into a grade prediction model to obtain an initial passing grade of the object to be detected includes: Inputting the object to be detected into a grade prediction model corresponding to the target category to obtain an initial passing grade of the object to be detected in the target category; Outputting the target passing level for the target user includes: Output the target passing level corresponding to the target category for the target user.

24. The method according to claim 23, wherein The acquiring of the target category selected by the target user from the plurality of third categories includes: generating category input prompt information for the plurality of third categories; Displaying the category input prompt information for the target user; The target category is obtained by selecting or inputting the prompt information of the category input by the target user.

25. An information processing method, characterized in that: include: Obtain the trademark to be tested provided by the target user; Inputting the trademark to be tested into a grade prediction model to obtain an initial passing grade of the trademark to be tested; Performing grade optimization processing on the initial pass grade using a grade optimization model to obtain a target pass grade for the trademark to be inspected; outputting the target passing grade for the target user; Inputting the trademark to be detected into a grade prediction model to obtain an initial passing grade of the trademark to be detected includes: Determine multiple third categories corresponding to the first category level; Inputting the trademark to be tested into a grade prediction model corresponding to any third category to obtain an initial passing grade of the trademark to be tested corresponding to the third category, thereby obtaining initial passing grades of the trademark to be tested corresponding to multiple third categories respectively; The performing grade optimization processing on the initial pass grade by using the grade optimization model to obtain the target pass grade of the trademark to be inspected comprises: Using a grade optimization model, respectively optimizing the initial pass grades corresponding to the plurality of third categories to obtain target pass grades corresponding to the trademark to be inspected in the plurality of third categories; Outputting the target passing level for the target user includes: Outputting target passing levels corresponding to the plurality of third categories respectively to the target user.

26. A computing device, characterized in that The system comprises: a storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component; The processing component is used to: Obtaining an object to be detected provided by a target user; inputting the object to be detected into a grade prediction model to obtain an initial pass grade of the object to be detected; performing grade optimization processing on the initial pass grade using a grade optimization model to obtain a target pass grade of the object to be detected; Outputting the target pass grade for the target user; inputting the object to be detected into the grade prediction model to obtain the initial pass grade of the object to be detected includes: determining multiple third categories corresponding to the first category level; inputting the object to be detected into the grade prediction model corresponding to any third category to obtain the initial pass grade of the object to be detected corresponding to the third category, so as to obtain the initial pass grades corresponding to the multiple third categories of the object to be detected; using the grade optimization model to perform grade optimization processing on the initial pass grade to obtain the target pass grade of the object to be detected includes: using the grade optimization model to perform grade optimization processing on the initial pass grades corresponding to the multiple third categories respectively, to obtain the target pass grades corresponding to the multiple third categories of the object to be detected respectively; Outputting the target passing level to the target user includes outputting the target passing levels corresponding to the plurality of third categories to the target user.

27. A computing device, characterized in that It includes a storage component and a processing component; the storage component is used to store one or more computer instructions; the one or more computer instructions are called and executed by the processing component; The processing component is used to: Obtaining a trademark to be tested provided by a target user; inputting the trademark to be tested into a grade prediction model to obtain an initial passing grade of the trademark to be tested; performing grade optimization processing on the initial passing grade using a grade optimization model to obtain a target passing grade of the trademark to be tested; Outputting the target pass grade for the target user; inputting the trademark to be detected into the grade prediction model to obtain the initial pass grade of the trademark to be detected includes: determining multiple third categories corresponding to the first category level; inputting the trademark to be detected into the grade prediction model corresponding to any third category to obtain the initial pass grade of the trademark to be detected corresponding to the third category, so as to obtain the initial pass grades corresponding to the trademark to be detected in the multiple third categories respectively; performing grade optimization processing on the initial pass grade using the grade optimization model to obtain the target pass grade of the trademark to be detected includes: performing grade optimization processing on the initial pass grades corresponding to the multiple third categories respectively using the grade optimization model to obtain the target pass grades corresponding to the trademark to be detected in the multiple third categories respectively; Outputting the target passing level to the target user includes outputting the target passing levels corresponding to the plurality of third categories to the target user.

Images