Data processing method and device

Abstract

The present application discloses a data processing method, which can obtain a first parameter input by a user, determine whether the first parameter is included in a parameter library, and if the first parameter is included in the parameter library, output a prompt message, which is used to prompt that the first parameter is a parameter created historically, so that the user can determine that the first parameter has been created based on the prompt message, thereby avoiding the user from creating duplicate parameters. If the first parameter is not included in the parameter library, at least one parameter in the parameter library whose similarity with the first parameter is higher than a first threshold value can be determined and output. In this way, the user can determine whether it is necessary to continue to create the first parameter based on the at least one parameter, or determine the modification method of the first parameter. Compared with the manual method, the adoption of this solution can quickly determine whether the first parameter meets the requirements.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data processing method and device. Background Art

[0002] To facilitate data management, data management products have emerged. These products manage user-entered parameters. Data management can span multiple business lines, managing a large number of parameters. Therefore, to facilitate data management, user-created parameters are often required to meet certain requirements.

[0003] Currently, when creating parameters, users can manually determine whether the parameters meet requirements. For example, when a user needs to create a parameter, they can first ask an administrator to confirm whether the parameters meet requirements. However, this method is inefficient in determining whether the parameters meet requirements.

[0004] Therefore, a solution is urgently needed to solve the above problems. Summary of the Invention

[0005] The technical problem to be solved by this application is how to improve the efficiency of determining whether the parameters to be created meet the requirements, and to provide a data processing method and device.

[0006] In a first aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0007] Get the first parameter input by the user;

[0008] Determining whether the parameter library includes the first parameter;

[0009] If the parameter library includes the first parameter, output a prompt message, where the prompt message is used to indicate that the first parameter is a parameter created historically;

[0010] If the parameter library does not include the first parameter, determine and output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold.

[0011] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words constitute each parameter according to a preset specification; and determining at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold includes:

[0012] In a case where the first parameter meets the preset specification, at least one parameter in the parameter library having a similarity with the first parameter higher than the first threshold is determined.

[0013] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words constitute each parameter according to a preset specification; and determining at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold includes:

[0014] When the first parameter does not meet the preset specification, determine at least one parameter in the parameter library whose similarity with the second parameter is higher than a first threshold, wherein the second parameter is a parameter that meets the preset specification and is obtained based on each word segmentation in the first parameter and the preset specification.

[0015] Optionally, the method further includes:

[0016] Output the second parameter.

[0017] Optionally, the similarity between the first parameter and the third parameter in the parameter library is determined based on the similarity between each participle in the first parameter and the participle corresponding to each participle in the third parameter.

[0018] Optionally, determining whether the first parameter meets the preset specification is performed in the following manner:

[0019] Determining the category to which each word in the first parameter belongs;

[0020] Based on the category to which each word segment in the first parameter belongs, it is determined whether the first parameter meets the preset specification.

[0021] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0022] Determining, based on the similarity between the first participle and each participle in the parameter library, a second participle in the parameter library that matches the first participle, where the second participle is the same as or different from the first participle;

[0023] The category of the second participle is determined to be the category to which the first participle belongs.

[0024] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0025] If, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle matching the first participle;

[0026] The preset category is determined as the category to which the first participle belongs.

[0027] Optionally, the method further includes:

[0028] The second participle different from the first participle is output.

[0029] Optionally, the similarity between the first word segmentation and each word segmentation in the parameter library is obtained based on the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library, and the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library are obtained based on a pre-trained machine learning model, and the machine learning model is trained based on the word segmentations included in the parameter library.

[0030] Optionally, the machine learning model includes:

[0031] Character-level based fasttext model.

[0032] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0033] an acquiring unit, configured to acquire a first parameter input by a user;

[0034] a first determining unit, configured to determine whether the parameter library includes the first parameter;

[0035] a first output unit, configured to output prompt information if the parameter library includes the first parameter, wherein the prompt information is used to indicate that the first parameter is a parameter created historically;

[0036] a second determining unit, configured to determine, if the parameter library does not include the first parameter, at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold;

[0037] The second output unit is configured to output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold.

[0038] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words constitute each parameter according to a preset specification; the second determining unit is used to:

[0039] In a case where the first parameter meets the preset specification, at least one parameter in the parameter library having a similarity with the first parameter higher than the first threshold is determined.

[0040] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words constitute each parameter according to a preset specification; the second determining unit is used to:

[0041] When the first parameter does not meet the preset specification, determine at least one parameter in the parameter library whose similarity with the second parameter is higher than a first threshold, wherein the second parameter is a parameter that meets the preset specification and is obtained based on each word segmentation in the first parameter and the preset specification.

[0042] Optionally, the device further includes:

[0043] The third output unit is configured to output the second parameter.

[0044] Optionally, the similarity between the first parameter and the third parameter in the parameter library is determined based on the similarity between each participle in the first parameter and the participle corresponding to each participle in the third parameter.

[0045] Optionally, determining whether the first parameter meets the preset specification is performed in the following manner:

[0046] Determining the category to which each word in the first parameter belongs;

[0047] Based on the category to which each word segment in the first parameter belongs, it is determined whether the first parameter meets the preset specification.

[0048] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0049] Determining, based on the similarity between the first participle and each participle in the parameter library, a second participle in the parameter library that matches the first participle, where the second participle is the same as or different from the first participle;

[0050] The category of the second participle is determined to be the category to which the first participle belongs.

[0051] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0052] If, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle matching the first participle;

[0053] The preset category is determined as the category to which the first participle belongs.

[0054] Optionally, the device further includes:

[0055] The fourth output unit is configured to output the second participle that is different from the first participle.

[0056] Optionally, the similarity between the first word segmentation and each word segmentation in the parameter library is obtained based on the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library, and the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library are obtained based on a pre-trained machine learning model, and the machine learning model is trained based on the word segmentations included in the parameter library.

[0057] Optionally, the machine learning model includes:

[0058] Character-level based fasttext model.

[0059] In a third aspect, an embodiment of the present application provides a device, comprising a processor and a memory;

[0060] The processor is configured to execute instructions stored in the memory, so that the device executes the method described in any one of the first aspects above.

[0061] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that it includes instructions, and the instructions instruct a device to execute any method described in the first aspect above.

[0062] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a computer, enables the computer to execute any of the methods described in the first aspect above.

[0063] Compared with the prior art, the embodiments of the present application have the following advantages:

[0064] The embodiment of the present application provides a data processing method, which can be executed by a server, for example. In one example, the server can obtain a first parameter input by a user, and then determine whether the first parameter is included in a parameter library. If the first parameter is included in the parameter library, the server can output a prompt message, which is used to prompt that the first parameter is a parameter created in the past, so that the user can determine that the first parameter has been created based on the prompt message, thereby avoiding the user from creating a duplicate parameter. If the parameter library does not include the first parameter, the server can determine and output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold. In this way, the user can determine whether to continue to create the first parameter or determine how to modify the first parameter based on the at least one parameter. Compared with the manual method, the present solution can quickly determine whether the first parameter meets the requirements, that is, it can quickly determine whether the first parameter is a parameter created in the past, and output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold to assist the user in determining whether to continue to create the first parameter or to assist the user in determining how to modify the first parameter. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0067] Figure 2 A flowchart of a method for determining whether a first parameter meets a preset specification provided in an embodiment of the present application;

[0068] Figure 3 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0070] After research, the inventors of this application discovered that, currently, when creating parameters, users can manually determine whether the parameters to be created meet the requirements. For example, when a user needs to create a parameter, they can first ask an administrator to determine whether the parameter to be created has already been created. If the parameter to be created has already been created, the user does not need to recreate the parameter. For another example, an administrator can determine whether the parameter to be created complies with parameter naming specifications. If the parameter to be created does not comply with parameter naming specifications, the administrator can provide corresponding modification suggestions.

[0071] However, in this way, it is inefficient to determine whether the parameters to be created meet the requirements.

[0072] In order to solve the above problems, the embodiments of the present application provide a data processing method and device.

[0073] Various non-limiting embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0074] Exemplary Methods

[0075] See also Figure 1 , which is a flow chart of a data processing method provided by an embodiment of the present application. In one example, Figure 1 The method shown can be executed by the server. In another example, the method can be executed by the client, which is not specifically limited in the embodiments of the present application.

[0076] Figure 1 The method shown may, for example, include the following steps: S101 - S104 .

[0077] S101: Obtain a first parameter input by a user.

[0078] In the embodiment of the present application, the first parameter may be a parameter to be created and input by a user. The user may input the first parameter in a corresponding parameter input area.

[0079] S102: Determine whether the parameter library includes the first parameter.

[0080] In an embodiment of the present application, the parameter library includes multiple parameters, all of which are already created parameters. The parameter library can be a parameter library based on Hive. Hive is a data warehouse tool based on Hadoop and will not be described in detail here.

[0081] In one example, during specific implementation of S102 , the first parameter may be compared with each parameter in the parameter library to determine whether the parameter library includes the first parameter.

[0082] S103: If the parameter library includes the first parameter, output prompt information, where the prompt information is used to prompt that the first parameter is a parameter created historically.

[0083] In an embodiment of the present application, to prevent the user from creating duplicate parameters, when the parameter library includes the first parameter, a prompt message may be output, the prompt message being used to indicate that the first parameter is a parameter that has been created historically. The embodiment of the present application does not specifically limit the specific implementation method of outputting the prompt message. In one example, the prompt message may be displayed on a screen, for example, displaying "This parameter has been created" on the screen.

[0084] S104: If the parameter library does not include the first parameter, determine and output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold.

[0085] In an embodiment of the present application, if the parameter library does not include the first parameter, it means that the first parameter has not been created. However, this does not mean that the first parameter can be created. For example, the first parameter includes multiple participles, and the first parameter is similar to a parameter in the indicator library (such as parameter 1). The difference is that the participle 1 in the first parameter is different from the participle 2 in parameter 1. However, the participle 1 in the first parameter and the participle 2 in parameter 1 are synonyms. At this time, the meaning actually expressed by the first parameter is the same as that of parameter 1, so the first parameter cannot be created either.

[0086] Therefore, in one example, when the parameter library does not include the first parameter, at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold value may be determined and output, so that the user can determine whether to continue creating the first parameter based on the at least one parameter.

[0087] In addition, in some examples, the created parameters need to meet certain conditions. Outputting the at least one parameter can enable the user to determine the conditions that the created parameters need to meet, and can also assist the user in determining how to modify the first parameter.

[0088] In one example, when outputting the at least one parameter, each parameter in the at least one parameter and the similarity between each parameter and the first parameter may be output separately. For example, (parameter 2, similarity 1) and (parameter 3, similarity 2) may be output.

[0089] In one example, each parameter included in the parameter library includes segmentations of multiple categories (for example, M categories), and the segmentations of the multiple categories constitute each parameter according to a preset specification. With respect to the preset specification, it may refer to the order in which the segmentations of the multiple categories appear in the parameter. For example: for segmentation 3 of the first category, segmentation 4 of the second category, segmentation 5 of the third category, and segmentation 6 of the fourth category, the preset specification indicates that the segmentations of the multiple categories appear in the parameter in the order of the first category, the second category, the fourth category, and the third category. Then, based on segmentation 3, segmentation 4, segmentation 5, and segmentation 6, the parameters that meet the preset specification can be obtained: segmentation 3-segmentation 4-segmentation 6-segmentation 5.

[0090] Regarding the category to which the word segmentation belongs, the embodiment of the present application does not make any specific restrictions. In one example, the category may include: business category, statistical category, dimension category, and measurement category, etc. Among them:

[0091] Business category is used to indicate a business, for example, to indicate a business of a certain company;

[0092] The statistical category is used to indicate the category of the statistical parameter. For example, the category of the statistical parameter can be the average value, the sum, the maximum value, the minimum value, etc.

[0093] Dimension categories correspond to businesses and are used to describe different dimensions of a business. For example, for an advertising business, dimension categories may include: impressions, clicks, conversions, etc.

[0094] The measurement category is used to indicate the measurement method of the statistical parameter. The measurement category can be, for example, quantity or percentage.

[0095] In the embodiment of the present application, the step of "determining at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold value" in S104 can be implemented in a variety of ways. Two implementation ways are described below.

[0096] A first implementation manner: when the first parameter meets the aforementioned preset specification, determining at least one parameter in the parameter library whose similarity with the first parameter is higher than a first threshold.

[0097] In the embodiment of the present application, it is possible to first determine whether the first parameter meets the preset specification. In the specific implementation, it is possible to determine whether the first parameter meets the preset specification by Figure 2 The S201-S202 shown is implemented, Figure 2 A flowchart of a method for determining whether a first parameter meets a preset specification is provided in an embodiment of the present application.

[0098] S201: Determine the category to which each word in the first parameter belongs.

[0099] In an embodiment of the present application, the first parameter may be firstly segmented to obtain each segmented word included in the first parameter, and then the category to which each segmented word in the first parameter belongs may be determined.

[0100] In one example, during specific implementation of S201 , semantic analysis may be performed on each of the segmented words to obtain the category to which each segmented word in the first parameter belongs.

[0101] In another example, S201 can be implemented with the aid of a parameter library. The parameter library includes multiple participles and the categories to which the multiple participles belong. For each participle included in the first parameter, the specific implementation method for determining the category to which each participle belongs is the same. Next, taking the first participle included in the first parameter as an example, the specific implementation method for determining the category to which the first participle belongs is described.

[0102] In the embodiment of the present application, the category to which the first word segment belongs can be determined through the following steps A1-A2.

[0103] Step A1: Based on the similarity between the first segmentation and each segmentation in the parameter library, determine a second segmentation in the parameter library that matches the first segmentation, where the second segmentation is the same as or different from the first segmentation.

[0104] In one example, the similarity between the first word segmentation and each word segmentation in the parameter library may be determined first, and then, based on the similarity between the first word segmentation and each word segmentation in the parameter library, a second word segmentation in the parameter library that matches the first word segmentation may be determined.

[0105] The second participle mentioned here that matches the first participle refers to a participle whose similarity with the first participle exceeds a certain threshold, that is, the second participle is semantically close to the first participle. The second participle and the first participle can be the same, that is, they are the same participle, or they can be different, that is, they are synonyms.

[0106] Among them, in the specific implementation, the similarity between the first participle and each participle in the parameter library can be obtained with the help of a pre-trained machine learning model, and the machine learning model is used to determine the word embedding vectors of the first participle and each participle in the parameter library. Accordingly, the similarity between the first participle and each participle in the parameter library can be determined based on the word embedding vector of the first participle and the word embedding vector of each participle in the parameter library. For example, the similarity between the first participle and a participle in the parameter library can be obtained based on the word embedding vector of the first participle and the word embedding vector of the participle.

[0107] Regarding the machine learning model, it should be noted that, in one example, considering that for the parameter library, the segmentations included therein may not be complete segmentations, for example, they may be part of a complete segmentation. Accordingly, the first segmentation included in the first parameter input by the user may also be part of a complete segmentation. In order to accurately calculate the word embedding vector of the first segmentation and the word embedding vector of the segmentations in the parameter library, the machine learning model can be trained based on the segmentations included in the parameter library.

[0108] The embodiments of the present application do not specifically limit the machine learning model.

[0109] In one example, the machine learning model may be, for example, a Convolutional Neural Networks (CNN) model.

[0110] In another example, considering that the word vector generated by the fasttext model based on character level for low-frequency word segmentation (such as part of the aforementioned complete word segmentation) will be better. Moreover, for word segmentation not included in the parameter library input by the user, the fasttext model based on character level can still construct the corresponding word embedding vector. In addition, the fasttext model based on character level has a faster calculation speed. Therefore, the machine learning model can be a fasttext model based on character level.

[0111] In one example, considering that a certain meaning can be expressed by multiple participles, for example, the participles "show" and "display" can both express the meaning of "display". In order to standardize the management of data, for a specific meaning, a specific participle is used to express its meaning. For example, for the meaning of "display", "show" is uniformly used to express it. In view of this, in some embodiments, when the second participle is different from the first participle, the second participle can be output, so that the user can modify the first parameter with the help of the second participle, for example, so that the user can modify the first participle in the first parameter to the second participle.

[0112] In an embodiment of the present application, when outputting the second participle, for example, the second participle can be displayed on the screen. In one example, the first participle, the second participle, and the meaning of the first participle can be output accordingly. For example, if the first participle is "display" and the second participle is "show", the content displayed on the screen can be ("display", "show", "display").

[0113] Step A2: Determine the category of the second participle as the category to which the first participle belongs.

[0114] After determining the second participle, since the second participle is either the same as the first participle or a synonym of the first participle, the category to which the first participle belongs is the same as the category to which the second participle belongs. Therefore, in an embodiment of the present application, the category to which the second participle belongs can be determined to be the category to which the first participle belongs. For example: if the category of the second participle is the first category, then the category of the first participle can be determined to be the first category.

[0115] In another example, if, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle that matches the first participle, then the parameter library does not include a participle that is semantically close to the first participle. In this case, the preset category can be determined as the category to which the first participle belongs. The present embodiment does not specifically limit the preset category, and the preset category can be determined based on actual circumstances. As an example, the preset category can be the aforementioned dimension category.

[0116] S202: Based on the category to which each word segment in the first parameter belongs, determine whether the first parameter meets a preset specification.

[0117] After determining the category to which each segmentation in the first parameter belongs, whether the first parameter conforms to a preset specification can be determined based on the category to which each segmentation in the first parameter belongs. For example, whether the order in which each segmentation appears in the first parameter conforms to the preset specification can be determined based on the category to which each segmentation in the first parameter belongs.

[0118] For example: the preset specification indicates that the order in which the segment words of each category appear in the parameter is: segment words corresponding to the first category - segment words corresponding to the second category - segment words corresponding to the fourth category - segment words corresponding to the third category, and the order in which the segment words in the first parameter appear in the first parameter is: segment words corresponding to the first category - segment words corresponding to the second category - segment words corresponding to the fourth category - segment words corresponding to the third category, then it can be determined that the first parameter meets the preset specification. If the order in which the segment words in the first parameter appear in the first parameter is: segment words corresponding to the first category - segment words corresponding to the second category - segment words corresponding to the third category - segment words corresponding to the fourth category, then it can be determined that the first parameter does not meet the preset specification.

[0119] After determining that the first parameter meets the preset specification, at least one parameter having a similarity with the first parameter greater than a first threshold value can be determined from the parameter library. In a specific implementation, "determining at least one parameter having a similarity with the first parameter greater than the first threshold value from the parameter library" can be implemented by calculating the similarity between the first parameter and each parameter in the parameter library, and sorting the similarities between the first parameter and each parameter in the parameter library in descending order to obtain at least one parameter having a similarity with the first parameter greater than the first threshold value.

[0120] In one example, when calculating the similarity between the first parameter and each parameter in the parameter library, for example, the word embedding vector of the first parameter and the word embedding vector of each parameter in the parameter library can be calculated respectively, so as to obtain the similarity between the first parameter and each parameter in the parameter library based on the word embedding vector of the first parameter and the word embedding vector of each parameter in the parameter library.

[0121] In another example, considering that each parameter includes multiple participles (e.g., M participles) for the first parameter and the parameters included in the parameter library, the similarity between each participle in the first parameter and the corresponding participle in the parameter library can be determined. The following describes the example of determining the similarity between the first parameter and the third parameter in the parameter library.

[0122] The similarity between the first parameter and the third parameter can be determined based on the similarity between each participle in the first parameter and the participle in the third parameter corresponding to each participle. The participle in the third parameter corresponding to the first participle in the first parameter refers to a participle belonging to the same category as the first participle. When the first parameter meets the preset specification, the relative position of the participle in the third parameter corresponding to the first participle in the first parameter in the third parameter is the same as the relative position of the first participle in the first parameter. For example:

[0123] Assuming that the first parameter is abcd and the third parameter is efgh, the similarity between the first parameter and the third parameter can be obtained based on the similarity between a and e, the similarity between b and f, the similarity between c and g, and the similarity between d and h.

[0124] In one example, the similarity between a and e, the similarity between b and f, the similarity between c and g, and the similarity between d and h can first be normalized to obtain four normalized similarities, and then the average of the four normalized similarities is calculated to obtain the similarity between the first parameter and the third parameter.

[0125] The second implementation method: when the first parameter does not meet the preset specification, determine at least one parameter in the parameter library whose similarity with the second parameter is higher than a first threshold, wherein the second parameter is a parameter that meets the preset specification and is obtained based on each word segmentation in the first parameter and the preset specification.

[0126] Regarding the specific implementation of determining whether the first parameter meets the preset specification, please refer to the relevant description part above, which will not be repeated here.

[0127] After determining that the first parameter does not meet the preset specification, a second parameter that meets the preset specification can be obtained based on the individual segmented words in the first parameter and the preset specification. As an example, the second parameter that meets the preset specification can be obtained based on the categories to which the individual segmented words in the first parameter belong and the preset specification. For example, the order in which at least one segmented word in the first parameter appears can be adjusted based on the categories to which the individual segmented words belong and the preset specification to obtain the second parameter.

[0128] For example:

[0129] The preset specification indicates that the order in which the segmentation words of each category appear in the parameter is: segmentation words corresponding to the first category - segmentation words corresponding to the second category - segmentation words corresponding to the fourth category - segmentation words corresponding to the third category, and the order in which the segmentation words in the first parameter appear in the first parameter is: segmentation words corresponding to the first category - segmentation words corresponding to the second category - segmentation words corresponding to the third category - segmentation words corresponding to the fourth category. The order in which the third and fourth segmentation words in the first parameter appear in the first parameter can be interchanged to obtain the second parameter.

[0130] After the second parameter is obtained, at least one parameter in the parameter library having a similarity with the second parameter higher than a first threshold value can be obtained based on the similarity between the second parameter and each parameter in the parameter library.

[0131] Regarding the specific implementation of "obtaining, based on the similarity between the second parameter and each parameter in the parameter library, at least one parameter in the parameter library having a similarity with the second parameter higher than a first threshold value", the principle is the same as the principle of "obtaining, based on the similarity between the first parameter and each parameter in the parameter library, at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold value", so the specific implementation of "obtaining, based on the similarity between the second parameter and each parameter in the parameter library, at least one parameter in the parameter library having a similarity with the second parameter higher than a first threshold value" can be referred to the above specific implementation part of "obtaining, based on the similarity between the first parameter and each parameter in the parameter library, at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold value", and will not be repeated here.

[0132] In one example, when the first parameter does not meet the preset specifications, the server can also output the second parameter so that the user can determine the specifications that the creation parameter needs to meet based on the output second parameter, so that the user can modify the first parameter.

[0133] In a specific implementation, the server outputs the second parameter, for example, by displaying the second parameter on a screen. In one example, the server may output the first parameter, the second parameter, and the meaning of the second parameter respectively. For example, the content displayed on the screen may be: {abcd, abdc, meaning 1}, where "abcd" is the first participle, "abdc" is the second participle, and meaning 1 is the meaning of the second participle "abdc".

[0134] From the above description, it can be seen that, by utilizing the solution of the embodiment of the present application, compared with the manual method, it is possible to quickly determine whether the first parameter meets the requirements, that is, it is possible to quickly determine whether the first parameter is a historically created parameter, and output at least one parameter in the parameter library whose similarity with the first parameter is higher than the first threshold value, so as to assist the user in determining whether it is necessary to continue to create the first parameter, or to assist the user in determining how to modify the first parameter.

[0135] Exemplary devices

[0136] Based on the method provided in the above embodiment, the embodiment of the present application further provides a device, which is described below in conjunction with the accompanying drawings.

[0137] See also Figure 3 , Figure 3 The structure diagram of a data processing device provided in an embodiment of the present application is as follows: the device 300 may specifically include: an acquisition unit 301, a first determination unit 302, a first output unit 303, a second determination unit 304 and a second output unit 305.

[0138] An acquisition unit 301 is configured to acquire a first parameter input by a user;

[0139] A first determining unit 302 is configured to determine whether the parameter library includes the first parameter;

[0140] A first output unit 303 is configured to output a prompt message if the parameter library includes the first parameter, where the prompt message is used to indicate that the first parameter is a parameter created historically;

[0141] A second determining unit 304 is configured to determine, if the parameter library does not include the first parameter, at least one parameter in the parameter library having a similarity with the first parameter higher than a first threshold;

[0142] The second output unit 305 is configured to output at least one parameter in the parameter library whose similarity to the first parameter is higher than a first threshold.

[0143] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words form each parameter according to a preset specification; the second determining unit 304 is used to:

[0144] In a case where the first parameter meets the preset specification, at least one parameter in the parameter library having a similarity with the first parameter higher than the first threshold is determined.

[0145] Optionally, each parameter included in the parameter library includes multiple categories of segmented words, and the multiple categories of segmented words form each parameter according to a preset specification; the second determining unit 304 is used to:

[0146] When the first parameter does not meet the preset specification, determine at least one parameter in the parameter library whose similarity with the second parameter is higher than a first threshold, wherein the second parameter is a parameter that meets the preset specification and is obtained based on each word segmentation in the first parameter and the preset specification.

[0147] Optionally, the device further includes:

[0148] The third output unit is configured to output the second parameter.

[0149] Optionally, the similarity between the first parameter and the third parameter in the parameter library is determined based on the similarity between each participle in the first parameter and the participle corresponding to each participle in the third parameter.

[0150] Optionally, determining whether the first parameter meets the preset specification is performed in the following manner:

[0151] Determining the category to which each word in the first parameter belongs;

[0152] Based on the category to which each word segment in the first parameter belongs, it is determined whether the first parameter meets the preset specification.

[0153] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0154] Determining, based on the similarity between the first participle and each participle in the parameter library, a second participle in the parameter library that matches the first participle, where the second participle is the same as or different from the first participle;

[0155] The category of the second participle is determined to be the category to which the first participle belongs.

[0156] Optionally, the parameter library includes multiple segmented words and categories to which the multiple segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes:

[0157] If, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle matching the first participle;

[0158] The preset category is determined as the category to which the first participle belongs.

[0159] Optionally, the device further includes:

[0160] The fourth output unit is configured to output the second participle that is different from the first participle.

[0161] Optionally, the similarity between the first word segmentation and each word segmentation in the parameter library is obtained based on the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library, and the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library are obtained based on a pre-trained machine learning model, and the machine learning model is trained based on the word segmentations included in the parameter library.

[0162] Optionally, the machine learning model includes:

[0163] Character-level based fasttext model.

[0164] Since the device 300 is a device corresponding to the data processing method provided in the above method embodiment, the specific implementation of each unit of the device 300 is based on the same concept as the data processing method described in the above method embodiment. Therefore, regarding the specific implementation of each unit of the device 300, please refer to the relevant description part of the above method embodiment, which will not be repeated here.

[0165] An embodiment of the present application further provides a device, the device comprising a processor and a memory;

[0166] The processor is used to execute instructions stored in the memory, so that the device executes the data processing method provided by the above method embodiment.

[0167] An embodiment of the present application provides a computer-readable storage medium, including instructions, wherein the instructions instruct a device to execute the data processing method provided in the above method embodiment.

[0168] An embodiment of the present application further provides a computer program product, which, when executed on a computer, enables the computer to execute the data processing method provided in the above method embodiment.

[0169] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0170] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

[0171] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Get the first parameter input by the user; Determining whether the parameter library includes the first parameter; If the parameter library includes the first parameter, output a prompt message, where the prompt message is used to indicate that the first parameter is a parameter created historically; If the first parameter is not included in the parameter library, and if the first parameter meets the preset specification, determine at least one parameter in the parameter library whose similarity to the first parameter is higher than the first threshold; if the first parameter does not meet the preset specification, determine at least one parameter in the parameter library whose similarity to a second parameter is higher than the first threshold, wherein the second parameter is a parameter meeting the preset specification obtained based on each segmentation word in the first parameter and the preset specification, and each parameter included in the parameter library includes segmentations of multiple categories, and the segmentations of the multiple categories constitute each parameter according to the preset specification; outputting the at least one parameter; Wherein: determining whether the first parameter meets the preset specification is performed in the following manner: Determining the category to which each word in the first parameter belongs; Determining whether the first parameter meets the preset specification based on the category to which each word segment in the first parameter belongs; The parameter library includes a plurality of segmented words and categories to which the plurality of segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes: Based on the similarity between the first participle and each participle in the parameter library, determining a second participle in the parameter library that matches the first participle, wherein the second participle is the same as or different from the first participle; determining the category of the second participle as the category to which the first participle belongs; or If, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle matching the first participle, the preset category is determined as the category to which the first participle belongs.

2. The method according to claim 1, characterized in that When the first parameter does not meet the preset specification, the method further includes: Output the second parameter.

3. The method according to claim 1, characterized in that The similarity between the first parameter and the third parameter in the parameter library is determined based on the similarity between each participle in the first parameter and the participle corresponding to each participle in the third parameter.

4. The method according to claim 1, wherein If the parameter library includes a second participle that matches the first participle, the method further includes: The second participle different from the first participle is output.

5. The method according to claim 1, wherein The similarity between the first word segmentation and each word segmentation in the parameter library is obtained based on the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library, and the word embedding vector of the first word segmentation and the word embedding vector of each word segmentation in the parameter library are obtained based on a pre-trained machine learning model, and the machine learning model is trained based on the word segmentations included in the parameter library.

6. The method according to claim 5, characterized in that The machine learning model includes: Character-level based fasttext model.

7. A data processing device, characterized in that: The device comprises: an acquiring unit, configured to acquire a first parameter input by a user; a first determining unit, configured to determine whether the parameter library includes the first parameter; a first output unit, configured to output prompt information if the parameter library includes the first parameter, wherein the prompt information is used to indicate that the first parameter is a parameter created historically; a second determining unit, configured to, if the first parameter is not included in the parameter library, determine at least one parameter in the parameter library having a similarity with the first parameter higher than the first threshold value if the first parameter meets a preset specification, and, if the first parameter does not meet the preset specification, determine at least one parameter in the parameter library having a similarity with a second parameter higher than the first threshold value, wherein the second parameter is a parameter meeting the preset specification obtained based on each segmentation word in the first parameter and the preset specification, and each parameter included in the parameter library includes segmentations of multiple categories, and the segmentations of the multiple categories constitute each parameter according to the preset specification; a second output unit, configured to output the at least one parameter; in: Determine whether the first parameter meets the preset specification by: Determining the category to which each word in the first parameter belongs; Determining whether the first parameter meets the preset specification based on the category to which each word segment in the first parameter belongs; The parameter library includes a plurality of segmented words and categories to which the plurality of segmented words belong, the first parameter includes a first segmented word, and determining the category to which the first segmented word belongs includes: Based on the similarity between the first participle and each participle in the parameter library, determining a second participle in the parameter library that matches the first participle, wherein the second participle is the same as or different from the first participle; determining the category of the second participle as the category to which the first participle belongs; or If, based on the similarity between the first participle and each participle in the parameter library, it is determined that the parameter library does not include a second participle matching the first participle, the preset category is determined as the category to which the first participle belongs.

8. A data processing device, characterized in that: The device includes a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the device performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The method comprises instructions for instructing a device to execute the method according to any one of claims 1 to 6.

Images