Label generation method, device, equipment and product based on large model and configuration

Abstract

The invention discloses a label generation method, device, equipment and product based on a large model and configuration, and relates to the technical field of large models and computers, and the label generation method comprises the steps: obtaining the label demand information of a label required by a business scene; generating a label on the basis of the label demand information through at least one of the following modes: under the condition that the label demand information comprises a preset keyword, performing semantic understanding on the preset keyword through a large model, and generating a similar keyword which is semantic similar to the preset keyword; obtaining a first label according to the similar keywords; and under the condition that the label demand information comprises the label aperture information, a second label is generated according to a label generation rule corresponding to the label aperture information, and the label generation rule is determined in response to a first configuration operation based on the label aperture information in the first configuration page. The development efficiency and iteration efficiency of the label are improved, the satisfaction rate of the label to the service is also improved, and the increasing label demand problem of the service is effectively solved.

Description

Technical Field

[0001] The present disclosure relates to the fields of big models and computer technology, and in particular, to a label generation method, apparatus, device, and product based on big models and configuration. Background Art

[0002] Tags are keywords or identifiers used to classify, mark, and retrieve data, helping users quickly locate, manage, and understand data. Tags can include rule-based tags and indicator-based tags. Rule-based tags are generated based on predefined rules or conditions. For example, the category tag for product A is "electronic products." This tag can help merchants quickly categorize products or facilitate users to search and browse products by category on the website. Indicator-based tags are generated based on statistical or calculated data, such as "Product A's sales in the past month." This tag can help merchants understand product sales and, in turn, adjust inventory and promotion strategies.

[0003] With the widespread adoption of tags in real-world applications, business demand for tags continues to rise. However, the existing manual tag development methods by developers are inefficient and often require updates late, making them unable to meet the growing demand. Summary of the Invention

[0004] This summary is provided to briefly introduce concepts that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a label generation method based on a large model and configuration, the label generation method comprising: Obtain label requirement information for labels required by business scenarios; Generate a label based on the label requirement information in at least one of the following ways: In the case where the tag requirement information includes preset keywords, semantic understanding of the preset keywords is performed using a large model to generate similar keywords with similar semantics to the preset keywords; and a first tag is obtained based on the similar keywords; In a case where the label requirement information includes label caliber information, a second label is generated according to a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

[0006] In a second aspect, the present disclosure provides a label generation device based on a large model and configuration, the label generation device comprising: The acquisition module is used to obtain the label requirement information of the labels required by the business scenario; A generation module is configured to generate a label based on the label requirement information by at least one of the following methods: In the case where the tag requirement information includes preset keywords, semantic understanding of the preset keywords is performed using a large model to generate similar keywords with similar semantics to the preset keywords; and a first tag is obtained based on the similar keywords; In a case where the label requirement information includes label caliber information, a second label is generated according to a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

[0007] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when executed by a processing device.

[0008] In a fourth aspect, the present disclosure provides an electronic device, comprising: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the method in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0010] Through the above technical solution, when the label requirement information includes preset keywords, the preset keywords can be semantically understood by the large model to generate similar keywords with similar semantics to the preset keywords, and then the first label can be obtained based on the similar keywords. When the label requirement information includes label caliber information, the second label can be generated based on the label generation rules configured based on the label caliber information. Using this method, the text processing capabilities of the large model can be used to automatically expand labels with similar semantics to the preset keywords. Label generation rules can also be configured based on the label caliber information to automatically generate labels that comply with the label generation rules. This not only improves the development efficiency and iteration efficiency of labels, but also improves the satisfaction rate of labels for businesses, effectively solving the problem of the growing label demand of businesses.

[0011] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a schematic flow chart of a tag generation method based on a large model and configuration according to an exemplary embodiment of the present disclosure; Figure 2 is a schematic diagram of a label generation process based on a large model according to an exemplary embodiment of the present disclosure; Figure 3 is a schematic diagram showing a first configuration page according to an exemplary embodiment of the present disclosure; Figure 4 is a schematic diagram comparing a label generation process of a related technology and this embodiment according to an exemplary embodiment of the present disclosure; Figure 5 is a schematic diagram of a label quality detection process according to an exemplary embodiment of the present disclosure; Figure 6 is a schematic diagram showing a second configuration page according to an exemplary embodiment of the present disclosure; Figure 7 This is a schematic diagram showing a process of developing tags by division of labor according to an exemplary embodiment of the present disclosure; Figure 8 is a structural block diagram of a label generation device based on a large model and configuration according to an exemplary embodiment of the present disclosure; Figure 9 The figure is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0014] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0015] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0020] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] At the same time, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] Taking e-commerce as an example, tags can be used in core scenarios such as message push, finding potential users, targeting promotional activities, searching and recommending, and advertising. As tags are increasingly used in e-commerce, the demand for tags is also increasing. This has led to a contradiction between this growing demand and the inefficiency of tag development.

[0025] Taking the iterative updating of rule-based tags as an example, some rule-based tags require listing similar keywords to implement tag updates. Related technologies primarily rely on manually organizing keywords and adding them to storage to implement tag iteration, which is time-consuming, inefficient, and results in delayed tag updates. Alternatively, a developed and deployed data processing chain processes raw data collected from various data sources to generate labels and register them with the tag management platform. While this data processing chain is visible, it requires time to develop and is inefficient.

[0026] In view of this, the present disclosure provides a label generation method, device, equipment and product based on a large model and configuration to solve the above technical problems.

[0027] The following further explains the embodiments of the present disclosure with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart of a tag generation method based on a large model and configuration according to an exemplary embodiment of the present disclosure, referring to Figure 1 , the label generation method may include the following steps: S101: Obtain label requirement information of labels required for business scenarios.

[0029] For example, the tag requirement information may be determined based on the tag requirement of a business scenario and may be specifically configured based on the requirement, which is not limited in the present disclosure.

[0030] S102: Generate a label based on the label requirement information in at least one of the following ways: when the label requirement information includes preset keywords, perform semantic understanding of the preset keywords through a large model to generate similar keywords with similar semantics to the preset keywords; obtain a first label based on the similar keywords; when the label requirement information includes label caliber information, generate a second label based on a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

[0031] For example, in real-world business scenarios, rule-based tags are typically presented in vocabulary form. Therefore, the big model can be used to semantically understand the keywords in the tags provided by business feedback and expand them to generate more semantically similar tags. For example, if a business scenario requires selecting users who purchased "baby milk powder," "baby milk powder" could be used as a pre-defined keyword. The big model can then be used to expand these keywords to generate more tags, such as "baby formula milk powder" and "infant milk powder." This is not a limitation of this disclosure.

[0032] For example, in actual business scenarios, for rule-based tags and indicator-based tags, the specific standards and ranges of the required tags can be accurately defined and described by setting tag caliber information, so that the corresponding tag generation rules can be configured based on the tag caliber information, and the required tags can be automatically generated based on the tag generation rules. Assuming that the business scenario requires adjusting inventory based on the historical sales of goods, the tag generation rules can include tag sources, algorithms, time ranges, screening conditions, etc., and then the tags generated according to the tag generation rules, such as "sales of product A in the past month", etc., are not limited in this regard.

[0033] It is worth noting that labels can be generated using a large model method or a configured method, or a combination of the large model method and the configured method. The specific selection can be made according to needs, and this disclosure does not impose any restrictions on this.

[0034] By using the above method, the text processing capabilities of the large model can be used to automatically expand tags with semantically similar preset keywords. Label generation rules can also be configured based on label caliber information to automatically generate labels that comply with the label generation rules. This not only improves the development and iteration efficiency of labels, but also increases the satisfaction rate of labels for the business, effectively solving the problem of the business's growing label demand.

[0035] In a possible manner, semantic understanding of preset keywords is performed through a large model to generate similar keywords with similar semantics to the preset keywords, including: semantic understanding of the preset keywords is performed through a large model, target long-tail words whose semantic similarity with the preset keywords is greater than a preset similarity are obtained from a target data source, and the target long-tail words are determined as similar keywords.

[0036] It should be understood that because the same label may have different meanings in different business scenarios, to generate labels that better meet labeling requirements, the labeling requirements can be limited to business scenarios, such as e-commerce business scenarios. This allows the large model to mine labels from the corresponding data sources, improving the accuracy of label generation. Furthermore, the large model can be fed with a corpus corresponding to the business scenario to help it more accurately understand semantics and further improve the accuracy of label generation.

[0037] For example, Figure 2 Preset keywords can be determined based on rule-based tags from business feedback. For example, in an e-commerce business scenario, the large model leverages its text processing capabilities and pre-set keywords for semantic understanding. It then detects similar keywords from the business data generated by the e-commerce business scenario. The large model can periodically detect similar keywords in the business data generated by the business scenario to iteratively update tags and avoid update lags.

[0038] It should be understood that the keywords perceived by the large model that are semantically similar to the preset keywords can be long-tail words. Long-tail words refer to those keywords that are relatively specific, detailed, and have relatively small search volumes. Tags determined based on long-tail words can improve the accuracy of tags and better meet the business needs of tags.

[0039] For example, using "baby milk powder" as the pre-set keyword, if the keyword is directly sensed, the "milk powder" tag might be expanded, thereby selecting users who purchase "adult milk powder" and "middle-aged and elderly milk powder," which does not meet the actual business needs. However, by sensing long-tail words with similar semantics to the pre-set keyword, tags that better meet business needs can be discovered, such as "baby stage 1 milk powder" and "baby stage 2 milk powder," thereby accurately selecting users who meet business needs.

[0040] To further ensure the accuracy of the labels, a similarity algorithm can be built into the large model to filter long-tail words and output similar keywords. For example, the semantic similarity between the preset keyword and each long-tail word can be calculated based on cosine similarity, and then the target long-tail word with a semantic similarity greater than the preset similarity can be selected as the similar keyword, thereby further improving the accuracy of the label, improving the efficiency of label development and the satisfaction rate of the label for the business. The preset similarity can be set according to needs and is not limited in this disclosure.

[0041] It should be noted that the above-mentioned large model can be fine-tuned based on the general large model, combined with the corpus and similarity algorithm of the business scenario, to meet the business needs of automatically expanding tags.

[0042] In a possible manner, the tag generation method further includes: when the preset keyword does not include the target long-tail word, storing the preset keyword in a candidate tag pool, wherein the target data source includes the candidate tag pool.

[0043] For example, continue to refer to Figure 2 If the large model cannot detect semantically similar long-tail words based on the preset keywords, it means that no more tags can be expanded based on the preset keywords. In this case, the preset keywords can be stored in the candidate tag pool as one of the data sources for subsequent tag expansion, thereby increasing the richness of the tag source. At the same time, the tag expansion process is stopped.

[0044] In a possible manner, obtaining a first label based on similar keywords includes: obtaining a verification result of the similar keywords, the verification result is used to characterize whether the similar keywords match the business scenario; when the verification result characterizes that the similar keywords match the business scenario, using the similar keywords as the first label.

[0045] For example, continue to refer to Figure 2 , similar keywords can be verified, for example, by inputting similar keywords and business scenario information into a verification model, and judging whether similar keywords match the business scenario through the verification model. Manual verification can also be performed, and this disclosure does not impose any restrictions on this. When the verification result indicates that similar keywords match the business scenario, similar keywords are determined as tags and stored in a tag extension queue or registered with a tag management platform so that downstream tag consumption platforms can consume the tags. The specific settings can be based on demand, and this disclosure does not impose any restrictions on this.

[0046] Alternatively, if the verification result indicates that the similar keyword does not match the business scenario, the similar keyword is discarded.

[0047] By screening similar keywords, the accuracy of extended tags is further guaranteed, the mismatch between extended tags and business scenarios is avoided, and the tag requirements of business scenarios are met.

[0048] In a possible manner, the label generation rule is configured in the following manner: a rule creation page is displayed, wherein the rule creation page displays options corresponding to a preset rule template, the preset rule template is pre-set for different label generation scenarios, and the preset rule template is associated with and displays descriptive information of the corresponding label generation scenario; in response to a triggering operation on a corresponding option of a target rule template in the preset rule template based on label caliber information, a first configuration page corresponding to the target rule template is displayed; in response to a first configuration operation in the first configuration page based on label caliber information, the label generation rule is determined according to the configuration information corresponding to the first configuration operation.

[0049] For example, Figure 3 As shown, the rule creation page displays options corresponding to preset rule templates. Each preset rule template is associated with a description of the corresponding label generation scenario. For example, Template 1 is used to aggregate offline detailed data as label values, and so on. The specific settings can be customized based on the needs and are not limited by this disclosure. This allows users to select the desired template based on the template description, improve the understandability of the configuration operation, and enhance the efficiency of label generation rule configuration.

[0050] For example, you can select a template that meets your needs from the preset rule templates based on the label caliber information, and continue to refer to Figure 3Select Template 1 to display the corresponding rule configuration page. You can configure configuration items such as the tag type and tag generation algorithm. This can be configured based on tag caliber information, which is not limited in this disclosure. This allows you to configure and produce tags based on the tagging requirements of your business scenarios, improving tag development efficiency.

[0051] For example, if business needs require adjusting the advertising delivery strategy based on the sales of product A in the past month, the set label generation algorithm can aggregate the sales field according to product A, set the time range to one month, and obtain the indicator label "sales of product A in the past month". In actual applications, the sales of product A can be counted through this label. For example, if the sales are greater than the preset sales, the current advertising delivery strategy can be maintained; if the sales are lower than the preset sales, the advertising delivery strategy needs to be adjusted, and so on. The specific settings can be based on the needs, and this disclosure does not impose any restrictions on this.

[0052] It is worth noting that if Figure 4 As shown, in the related art, developers develop the calculation logic of the label by understanding the label caliber information, and then develop the corresponding data processing link and deploy the corresponding label generation task. The development cycle is long and the label development efficiency is low. However, the configurable label generation method in this embodiment, by understanding the label caliber information, can configure the label generation rules on the visual configuration page, and then automatically convert the label generation rules into the label calculation logic based on the label generation rules, automatically generate the corresponding data processing link and deploy the corresponding label generation task. The production of labels with complex calculation calibers can be achieved through the configuration rules. The operation is simple, and the configuration production of real-time and offline labels can also be achieved based on the connected data source, effectively improving the efficiency of label development.

[0053] in, Figure 4 The tag test shown can refer to the tag verification process, which can be determined specifically according to needs and is not limited by the present disclosure.

[0054] In a possible manner, the label generation method also includes: transmitting the second label and the quality detection rules corresponding to the label generation rules to the label management platform, the label management platform is used to perform quality detection on the business data obtained based on the second label according to the quality detection rules, and perform label management on the second label according to the results of the quality detection; the quality detection rules corresponding to the second label are configured in the following manner: displaying a second configuration page corresponding to the label generation rules, wherein the second configuration page is used to configure the quality detection rules corresponding to the label generation rules, and the second configuration page displays detection parameters and alarm thresholds corresponding to the detection parameters; in response to the second configuration operation on the detection parameters and / or alarm thresholds in the second configuration page, determining the quality detection rules according to the configuration information corresponding to the second configuration operation.

[0055] It should be noted that in related technologies, the quality inspection rules for tags are manually configured after the tags are registered on the tag management platform, which is inefficient.

[0056] In this embodiment, the configuration process of the quality detection rules is integrated into the label generation process, such as Figure 5 As shown, after sorting out the label caliber information according to the label requirements, and configuring the label generation specifications according to the label caliber information, as shown Figure 3 The "Next" control shown in the figure triggers the control to display the following Figure 6 The configuration page of the quality detection rules shown in the figure can be used to configure the corresponding quality detection rules after configuring the label generation rules, so that the corresponding quality detection rules can be uniformly configured for the labels generated based on the label generation rules, greatly improving the configuration efficiency of the quality detection rules.

[0057] For example, Figure 6 As shown, the quality detection rules can be filled with unified quality detection rules by default to improve the configuration efficiency of the quality detection rules. It can also support on-demand modification of the default quality detection rules, such as modifying the detection parameters, the alarm thresholds corresponding to the detection parameters, adding quality detection rules, and deleting quality detection rules. The specific requirements can be determined according to the needs, and this disclosure does not impose any restrictions on this, so as to meet different quality detection needs.

[0058] It is worth noting that quality monitoring rules with different detection intensities can be used for risk labels and non-risk labels. For non-risk labels, since they have little impact on online business, conventional quality detection rules can be used to detect them. For example, fine-grained detection can be carried out around indicators such as the number of data queried through the label, data volatility, and enumeration value coverage. For risk labels, since they have a greater impact on online business, additional re-inspection detection rules can be added on top of conventional quality detection rules to strengthen the detection of risk labels. Among them, re-inspection detection rules can include bypass cross-detection (i.e., using different data sources / fields, producing the same label through different production links, and cross-validating each other) and fallback detection, etc., to meet the quality detection needs of different intensities.

[0059] The above conventional quality inspection rules and re-inspection inspection rules can be passed as follows Figure 6 The configuration page of the quality detection rules shown in the figure can be configured, or conventional quality detection rules do not need to be configured, and the re-protection detection rules can be configured for the tags that need to be re-protected. The specific configuration can be determined according to the needs, and this disclosure does not limit this. In the disclosed embodiment, after the labels are produced and put online, the labels can be continuously quality-tested using quality inspection rules. This allows quality problems in the label production chain to be discovered based on quality inspection, and improvements can be made based on the quality problems, thereby further improving the control effect of label quality.

[0060] In a possible manner, the label requirement information also includes a label type, and the label generation method also includes: in a case where the label type is a first label type, generating a first prompt information based on the label requirement information, the first prompt information being used to prompt a first developer to develop a label based on the label requirement information, the first label type representing a label type corresponding to a label whose usage frequency in a business scenario is lower than or equal to a preset threshold; in a case where the label type is a second label type, generating a second prompt information based on the label requirement information, the second prompt information being used to prompt a second developer to develop a label based on the label requirement information, the second label type representing a label type corresponding to a label whose usage frequency in a business scenario is higher than a preset threshold.

[0061] For example, Figure 7 As shown, for tags that are used less frequently in business scenarios, a first developer can develop tags, while for tags that are used more frequently in business scenarios, a second developer can develop tags. The preset threshold can be set as needed, and the prompt information can be a corresponding development task, which is not limited in this disclosure.

[0062] It should be noted that the first developers can be developers who are not business scenario developers or developers who have little understanding of business scenarios. These developers are numerous and have high development efficiency, but the label quality is lower. The second developers can be developers who are business scenario developers or developers who understand business scenarios. These developers are familiar with business scenarios, but they are few in number and have low development efficiency. However, the labels they develop are more closely aligned with the business scenarios and have higher label quality.

[0063] In related technologies, pure first developers or pure second developers are usually used for label development. Although the division of labor is clear, the labels developed by pure first developers have obvious quality problems, and pure second developers are limited by development efficiency and cannot meet the label requirements of the business.

[0064] Because quality issues with frequently used tags can impact a wider range of businesses, a primary developer can develop less frequently used tags, while a secondary developer can develop more frequently used tags. This reduces the risk of business anomalies caused by tag quality issues. By having primary and secondary developers work together on tag development, we can ensure tag quality while effectively improving tag development efficiency and meeting the tagging needs of businesses.

[0065] In a possible manner, the label generation method further includes: obtaining a target label developed by the first developer and / or the second developer; determining business object information corresponding to the target label based on label requirement information, and the business object information is used to perform quality management on the target label.

[0066] For example, continue to refer to Figure 7 , a corresponding quality management personnel can be assigned to each label entity. For example, a corresponding quality management personnel can be assigned to the product label entity. In this way, when the business object information corresponding to the label developed by the first developer and the second developer determines that the label belongs to the product label entity, the corresponding quality management personnel will perform unified quality management on the label. In this way, regardless of whether the label is developed by the first developer or the second developer, unified quality management can be achieved to ensure the uniformity of label quality.

[0067] By dividing the development of labels by frequency of use and then implementing unified quality management, we can ensure label quality while achieving rapid label rollout and meeting business labeling needs. Subsequent label consumption platforms can produce data based on labels, which will not be discussed in detail in this disclosure.

[0068] The above method significantly improves label development efficiency through automatic expansion of rule labels, configurable label production, division of labor development based on usage frequency, and unified quality management. This not only increases the label satisfaction rate of the business, but also reduces the difficulty and cycle of label development and launch. Through overall efficiency improvement, it resolves the contradiction between the growing business demand for labels and the low efficiency of label development, and better supports business growth.

[0069] Based on the same concept, the embodiment of the present disclosure also provides a label generation device based on a large model and configuration, such as Figure 8 As shown, the label generating device 800 may include: The acquisition module 801 is used to obtain label requirement information of labels required by the business scenario; The generation module 802 is configured to generate a label based on the label requirement information by at least one of the following methods: In the case where the tag requirement information includes preset keywords, semantic understanding of the preset keywords is performed using a large model to generate similar keywords with similar semantics to the preset keywords; and a first tag is obtained based on the similar keywords; In a case where the label requirement information includes label caliber information, a second label is generated according to a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

[0070] Optionally, the generating module 802 is configured to: The preset keywords are semantically understood through the large model, and target long-tail words whose semantic similarity with the preset keywords is greater than the preset similarity are obtained from the target data source, and the target long-tail words are determined as the similar keywords, wherein the target data source is determined based on the scenario information representing the business scenario in the label requirement information.

[0071] Optionally, the label generating device 800 further includes a storage module, and the storage module is configured to: In a case where the preset keyword does not include the target long-tail word, the preset keyword is stored in a candidate tag pool, wherein the target data source includes the candidate tag pool.

[0072] Optionally, the generating module 802 is configured to: Obtaining a verification result of the similar keyword, where the verification result is used to indicate whether the similar keyword matches the business scenario; If the verification result indicates that the similar keyword matches the business scenario, the similar keyword is used as the first tag.

[0073] Optionally, the label generation rule is configured as follows: Displaying a rule creation page, wherein the rule creation page displays options corresponding to preset rule templates, wherein the preset rule templates are pre-set for different label generation scenarios, and the preset rule templates are associated with description information of the corresponding label generation scenarios; In response to a triggering operation on an option corresponding to a target rule template in the preset rule template based on the tag caliber information, displaying a first configuration page corresponding to the target rule template; In response to a first configuration operation based on the tag caliber information in the first configuration page, the tag generation rule is determined according to configuration information corresponding to the first configuration operation.

[0074] Optionally, the label generating apparatus 800 further includes a transmission module, and the transmission module is configured to: Transmitting the second tag and the quality detection rules corresponding to the tag generation rule to a tag management platform, wherein the tag management platform is configured to perform a quality detection on the business data obtained based on the second tag according to the quality detection rules, and perform tag management on the second tag according to the result of the quality detection; The quality detection rule corresponding to the second tag is configured as follows: Displaying a second configuration page corresponding to the label generation rule, wherein the second configuration page is used to configure a quality detection rule corresponding to the label generation rule, and the second configuration page displays detection parameters and alarm thresholds corresponding to the detection parameters; In response to a second configuration operation on the detection parameter and / or the alarm threshold in the second configuration page, the quality detection rule is determined according to configuration information corresponding to the second configuration operation.

[0075] Optionally, the label requirement information further includes a label type, and the label generating apparatus 800 further includes a development module, wherein the development module is configured to: In a case where the tag type is a first tag type, first prompt information is generated based on the tag requirement information, the first prompt information being used to prompt a first developer to develop a tag based on the tag requirement information, the first tag type representing a tag type corresponding to a tag whose usage frequency in the business scenario is less than or equal to a preset threshold; In the case where the tag type is the second tag type, a second prompt information is generated based on the tag requirement information, and the second prompt information is used to prompt a second developer to develop a tag based on the tag requirement information. The second tag type represents the tag type corresponding to the tag whose usage frequency in the business scenario is higher than a preset threshold.

[0076] Optionally, the label generating apparatus 800 further includes a determining module, wherein the determining module is configured to: Obtaining target tags developed by the first developer and / or the second developer; According to the tag requirement information, the business object information corresponding to the target tag is determined, and the business object information is used to perform quality management on the target tag.

[0077] Based on the same concept, an embodiment of the present disclosure further provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of any of the above-mentioned label generation methods based on large models and configurations.

[0078] Based on the same concept, an embodiment of the present disclosure further provides an electronic device, which may include: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of any of the above-mentioned label generation methods based on large models and configurations.

[0079] Based on the same concept, an embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the steps of any of the above-mentioned label generation methods based on large models and configurations when executed by a processor.

[0080] Reference below Figure 9 , which shows a schematic structural diagram of an electronic device 900 suitable for implementing an embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0081] like Figure 9 As shown, electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 902 or programs loaded from a storage device 908 into a random access memory (RAM) 903. RAM 903 also stores various programs and data required for the operation of electronic device 900. Processing device 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to bus 904.

[0082] Typically, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Figure 9 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0083] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0084] It should be noted that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0085] In some embodiments, communications may be conducted using any currently known or later developed network protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0086] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0087] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device is enabled to: obtain label requirement information of the label required for the business scenario; generate labels based on the label requirement information in at least one of the following ways: when the label requirement information includes preset keywords, the preset keywords are semantically understood by a large model to generate similar keywords that are semantically similar to the preset keywords; a first label is obtained based on the similar keywords; when the label requirement information includes label caliber information, a second label is generated according to the label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

[0088] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0090] The modules described in the embodiments of the present disclosure may be implemented in software or hardware, wherein the name of a module does not necessarily limit the module itself.

[0091] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0092] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0093] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the scope of the above disclosure. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0094] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0095] Although the subject matter has been described using language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims. Regarding the apparatus in the above-described embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method and will not be elaborated upon here.

Claims

1. A label generation method based on a large model and configuration, characterized in that: The label generation method comprises: Obtain label requirement information for labels required by business scenarios; Generate a label based on the label requirement information in at least one of the following ways: In the case where the tag requirement information includes preset keywords, semantic understanding of the preset keywords is performed using a large model to generate similar keywords with similar semantics to the preset keywords; and a first tag is obtained based on the similar keywords; In a case where the label requirement information includes label caliber information, a second label is generated according to a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

2. The label generation method based on large model and configuration according to claim 1 is characterized in that: The method of performing semantic understanding on the preset keywords by using a large model to generate similar keywords with similar semantics to the preset keywords includes: The preset keywords are semantically understood through the large model, and target long-tail words whose semantic similarity with the preset keywords is greater than the preset similarity are obtained from the target data source, and the target long-tail words are determined as the similar keywords, wherein the target data source is determined based on the scenario information representing the business scenario in the label requirement information.

3. The label generation method based on large model and configuration according to claim 2 is characterized in that: The label generation method further includes: In a case where the preset keyword does not include the target long-tail word, the preset keyword is stored in a candidate tag pool, wherein the target data source includes the candidate tag pool.

4. The label generation method based on large model and configuration according to claim 2 is characterized in that: The obtaining of a first tag according to the similar keywords includes: Obtaining a verification result of the similar keyword, where the verification result is used to indicate whether the similar keyword matches the business scenario; If the verification result indicates that the similar keyword matches the business scenario, the similar keyword is used as the first tag.

5. The label generation method based on large model and configuration according to claim 1 is characterized in that: The label generation rules are configured as follows: Displaying a rule creation page, wherein the rule creation page displays options corresponding to preset rule templates, wherein the preset rule templates are pre-set for different label generation scenarios, and the preset rule templates are associated with description information of the corresponding label generation scenarios; In response to a triggering operation on an option corresponding to a target rule template in the preset rule template based on the tag caliber information, displaying a first configuration page corresponding to the target rule template; In response to a first configuration operation based on the tag caliber information in the first configuration page, the tag generation rule is determined according to configuration information corresponding to the first configuration operation.

6. The label generation method based on large model and configuration according to claim 1 is characterized in that: The label generation method further includes: Transmitting the second tag and the quality detection rules corresponding to the tag generation rule to a tag management platform, wherein the tag management platform is configured to perform a quality detection on the business data obtained based on the second tag according to the quality detection rules, and perform tag management on the second tag according to the result of the quality detection; The quality detection rule corresponding to the second tag is configured as follows: Displaying a second configuration page corresponding to the label generation rule, wherein the second configuration page is used to configure a quality detection rule corresponding to the label generation rule, and the second configuration page displays detection parameters and alarm thresholds corresponding to the detection parameters; In response to a second configuration operation on the detection parameter and / or the alarm threshold in the second configuration page, the quality detection rule is determined according to configuration information corresponding to the second configuration operation.

7. The label generation method based on a large model and configuration according to any one of claims 1 to 6, characterized in that: The label requirement information also includes a label type, and the label generation method further includes: In a case where the tag type is a first tag type, first prompt information is generated based on the tag requirement information, the first prompt information being used to prompt a first developer to develop a tag based on the tag requirement information, the first tag type representing a tag type corresponding to a tag whose usage frequency in the business scenario is less than or equal to a preset threshold; In the case where the tag type is the second tag type, a second prompt information is generated based on the tag requirement information, and the second prompt information is used to prompt a second developer to develop a tag based on the tag requirement information. The second tag type represents the tag type corresponding to the tag whose usage frequency in the business scenario is higher than a preset threshold.

8. The label generation method based on large model and configuration according to claim 7 is characterized in that: The label generation method further includes: Obtaining target tags developed by the first developer and / or the second developer; According to the tag requirement information, the business object information corresponding to the target tag is determined, and the business object information is used to perform quality management on the target tag.

9. A label generation device based on a large model and configuration, characterized in that: The label generating device comprises: The acquisition module is used to obtain the label requirement information of the labels required by the business scenario; A generation module is configured to generate a label based on the label requirement information by at least one of the following methods: In the case where the tag requirement information includes preset keywords, semantic understanding of the preset keywords is performed using a large model to generate similar keywords with similar semantics to the preset keywords; and a first tag is obtained based on the similar keywords; In a case where the label requirement information includes label caliber information, a second label is generated according to a label generation rule corresponding to the label caliber information, wherein the label generation rule is determined in response to a first configuration operation based on the label caliber information in a first configuration page, and the first configuration page is used to configure the label generation rule.

10. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 8 are implemented.

11. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images