Automatic capacity expansion method, device, equipment and readable medium based on business prediction

Abstract

The present disclosure is about an automatic capacity expansion method, device, equipment and readable medium based on business prediction, and relates to the field of computer technology. The method can construct a business question for inquiring whether there is business for the object to be expanded, and obtain the business answer output by the prediction question and answer big model based on the business question. When the business answer is that there is business, the automatic capacity expansion task of the object to be expanded can be constructed based on the business information; wherein, the business prediction question and answer big model is obtained by fine-tuning the business page information captured periodically, and when there is business for the object to be expanded, the business answer can include the corresponding business information. The method can enable the business prediction question and answer big model to have a certain business monitoring capability by periodically capturing business page information, and then automatically create the corresponding automatic capacity expansion task through the question and answer task, without offline communication and manual intervention, and can flexibly respond to traffic bursts during business at low cost and high efficiency.

Description

Background Art

[0002] In business operations, the platform can expand its user base by launching marketing, promotions or other user-oriented activities. At this time, a large number of users usually visit, browse or take other actions in a short period of time, resulting in a sudden increase in traffic, which may further lead to traffic restrictions, thereby affecting the dissemination effect of the platform activities among the user group.

[0003] Currently, the platform can notify in advance of possible traffic surges, and expand capacity through manual intervention. This solution requires offline communication, relies on the efficiency of multi-party communication, and has a high degree of manual intervention, making the expansion cost high and the efficiency low. Summary of the invention

[0004] The purpose of the present disclosure is to provide an automatic capacity expansion method based on business prediction, an automatic capacity expansion device based on business prediction, an electronic device and a computer-readable medium. The method can periodically monitor business initiation, automatically create corresponding capacity expansion tasks, and achieve low-cost and high-efficiency automatic capacity expansion without manual intervention.

[0005] According to a first aspect of the present disclosure, an automatic capacity expansion method based on business prediction is provided, which may include: constructing a business question, where the business question is used to inquire whether there is any business for an object to be expanded; obtaining a business answer output by a business prediction question and answer big model based on the business question; the business prediction question and answer big model is fine-tuned based on periodically captured business page information; in the case that there is business for the object to be expanded, the business answer includes business information; in the case that the business answer is that there is business, constructing an automatic capacity expansion task corresponding to the object to be expanded based on the business information.

[0006] Optionally, the business information includes business time information, and constructing an automatic capacity expansion task corresponding to the object to be expanded based on the business information includes: determining the automatic capacity expansion time based on the business time information; and creating a scheduled automatic capacity expansion task based on the automatic capacity expansion time.

[0007] Optionally, after creating the scheduled automatic capacity expansion task based on the automatic capacity expansion time, the method further includes: when the automatic capacity expansion time corresponds to multiple automatic capacity expansion tasks, accumulating and merging the multiple automatic capacity expansion tasks.

[0008] Optionally, the business information includes business type information, and constructing an automatic expansion task corresponding to the object to be expanded based on the business information includes: determining the number of machine expansions based on the business type information; and creating a quantitative automatic expansion task based on the number of machine expansions.

[0009] Optionally, constructing an automatic expansion task corresponding to the object to be expanded based on the business information includes: when the object to be expanded includes a root object, determining that the expansion ratio corresponding to the root object is a full ratio; and constructing a full-ratio automatic expansion task corresponding to the object to be expanded based on the business information.

[0010] Optionally, an automatic expansion task corresponding to the object to be expanded is constructed based on the business information, including: when the object to be expanded includes multiple sub-objects, obtaining historical traffic corresponding to each sub-object; wherein the multiple sub-objects belong to the same root object; determining the expansion ratio of each sub-object as a sub-ratio based on the historical traffic; and constructing a sub-ratio automatic expansion task corresponding to each sub-object based on the business information.

[0011] Optionally, the periodic training steps of the business prediction question and answer big model are as follows: crawling business page information in the business page based on business keywords, the business keywords include at least one of business type keywords and business time keywords; building a sequence-to-sequence question and answer training set based on the business page information; and fine-tuning the business prediction question and answer big model on the question and answer training set.

[0012] According to the second aspect of the present disclosure, an automatic expansion device based on business prediction is provided, which may include: a question construction module, used to construct business questions, where the business questions are used to inquire whether there is any business for the object to be expanded; an answer acquisition module, used to obtain the business answers output by the business prediction question and answer big model based on the business questions; the business prediction question and answer big model is fine-tuned based on the business page information captured periodically; when there is business for the object to be expanded, the business answer includes business information; a task creation module, used to construct an automatic expansion task corresponding to the object to be expanded based on the business information when the business answer is that there is business.

[0013] Optionally, the business information includes business time information, and the task creation module is specifically used to determine the automatic capacity expansion time based on the business time information; and create a scheduled automatic capacity expansion task based on the automatic capacity expansion time.

[0014] Optionally, the task creation module is further configured to accumulate and merge multiple automatic capacity expansion tasks when the automatic capacity expansion time corresponds to multiple automatic capacity expansion tasks.

[0015] Optionally, the business information includes business type information, and a task creation module determines the number of machine expansion based on the business type information; and creates a quantitative automatic expansion task based on the number of machine expansion.

[0016] Optionally, the task creation module is specifically used to determine that the expansion ratio corresponding to the root object is full ratio when the object to be expanded includes the root object; and construct a full ratio automatic expansion task corresponding to the object to be expanded based on the business information.

[0017] Optionally, a task creation module is specifically used to obtain the historical traffic corresponding to each sub-object when the object to be expanded includes multiple sub-objects; wherein the multiple sub-objects belong to the same root object; based on the historical traffic, the expansion ratio of each sub-object is determined as a sub-ratio; and based on the business information, a sub-ratio automatic expansion task corresponding to each sub-object is constructed.

[0018] Optionally, the device may also include a model training module, which is used to capture business page information in the business page based on business keywords, where the business keywords include at least one of business type keywords and business time keywords; construct a sequence-to-sequence question and answer training set based on the business page information; and fine-tune the business prediction question and answer large model on the question and answer training set.

[0019] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0020] Processor; and

[0021] a memory for storing a computer program for the processor;

[0022] The processor is configured to implement the automatic capacity expansion method based on business prediction as described above in the first aspect by executing a computer program.

[0023] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the automatic capacity expansion method based on business prediction as in the first aspect is implemented.

[0024] According to a fifth aspect of the present disclosure, a computer program product is provided. When the computer program product is run on an electronic device, the electronic device implements the automatic capacity expansion method based on business prediction as in the first aspect.

[0025] The present disclosure provides an automatic capacity expansion method based on business prediction, an automatic capacity expansion device based on business prediction, an electronic device and a computer-readable medium. The method includes constructing a business question for inquiring whether there is any business for the object to be expanded, obtaining a business answer output by the prediction question and answer big model based on the business question, and when the business answer is that there is business, an automatic capacity expansion task for the object to be expanded can be constructed based on the business information; wherein, the business prediction question and answer big model is fine-tuned based on the periodically captured business page information, and when there is business for the object to be expanded, the business answer may include the corresponding business information. The method can enable the business prediction question and answer big model to have a certain business monitoring capability by periodically capturing business page information, and then automatically create the corresponding automatic capacity expansion task through the question and answer task, without the need for offline communication notification and manual intervention in capacity expansion, and can flexibly respond to traffic bursts during business at low cost and high efficiency.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0028] Figure 1 A flowchart of the steps of an automatic capacity expansion method based on business prediction provided in an embodiment of the present disclosure.

[0029] Figure 2 A schematic diagram of the application process of the automatic capacity expansion method based on business prediction provided in an embodiment of the present disclosure on the k8s platform.

[0030] Figure 3 A structural block diagram of an automatic capacity expansion device based on business prediction provided in an embodiment of the present disclosure.

[0031] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0033] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0034] It should be noted that the data obtained in this disclosure are accessed, collected, stored and used for subsequent analysis and processing with the consent and authorization of the users or the parties to whom the relevant data belong, after the users or the parties to whom the relevant data belong are clearly informed of the data collection content, data purpose, processing method and other information. The users or the parties to whom the relevant data belong may be sent the ways to access, correct and delete the data, as well as the methods to revoke consent and authorization.

[0035] Figure 1 The flowchart of the automatic capacity expansion method based on business prediction provided by the embodiment of the present disclosure is as follows: Steps 101 to 103:

[0036] Step 101: Construct a business question, which is used to inquire whether the object to be expanded has any business.

[0037] In the disclosed embodiment, the subject that can initiate the business can be taken as the object to be expanded, and the business can be an event that causes a sudden increase in traffic within a specific time during the operation process. On this basis, a business question can be constructed to ask whether the object to be expanded has a business. The business question can at least include information about the object to be expanded, question words, and business information, expressed in text, voice or other forms to adapt to the interpretation needs of the subsequent business prediction question and answer model. Among them, the question words can be keywords such as "whether", "there is" and so on to express the inquiry; the business information can be "business", or it can be a specific business name, such as "marketing", "promotion", "reward", "full reduction", "subsidy", "second kill", etc., and can further include time information of the business, such as "morning", "afternoon", "today", "tomorrow", etc.

[0038] For example, when the object to be expanded is platform A, a business question in text form can be constructed, such as "Does platform A have any business?" or "Does platform A have any flash sales today?" The present disclosed embodiment does not impose specific restrictions on this.

[0039] Step 102: Obtain the business answers output by the business prediction question and answer big model based on the business questions; the business prediction question and answer big model is obtained by fine-tuning the business page information captured periodically; when the object to be expanded has business, the business answers include business information.

[0040] In the disclosed embodiment, the business prediction question-and-answer big model is obtained by fine-tuning the business page information captured periodically. Among them, the business page can be a web page provided by the object to be expanded to a third party to introduce, enter or participate in related businesses, and the business page information includes business-related information captured from the business page. By periodically capturing business page information, continuous business monitoring can be formed. The business prediction question-and-answer big model continuously converts business page information into knowledge through fine-tuning, so that corresponding business answers can be output based on business questions.

[0041] On this basis, after inputting business questions into the business prediction question and answer model, the business prediction question and answer model can perform classification prediction tasks to determine whether the object to be expanded has business. If the prediction result is that there is no business, the business answer can be negative information such as "no", "none", "no", etc., and the question and answer process ends; if the prediction result is that there is business, the business answer can include business information related to the business, so as to subsequently build the corresponding automatic expansion task.

[0042] Step 103: When the business answer is that the business exists, an automatic capacity expansion task corresponding to the object to be expanded is constructed based on the business information.

[0043] In the embodiment of the present disclosure, when the business answer output by the business prediction question and answer big model indicates that the object to be expanded has business, an automatic expansion task corresponding to the object to be expanded can be further constructed according to the business information provided by the business prediction question and answer big model. The automatic expansion task can set a specific expansion quantity, expansion conditions, etc. The expansion conditions can be parameter conditions such as time and load, so that the expansion plan of the corresponding number of machines is automatically executed when the expansion conditions are met.

[0044] In an optional method embodiment of the present disclosure, the business information may include business time information, and the automatic capacity expansion task corresponding to the object to be expanded based on the business information in the aforementioned step 103 may include steps A1 to A2.

[0045] Step A1: Determine the automatic capacity expansion time based on the business time information.

[0046] In the disclosed embodiment, the business time information refers to the time information of the actual initiation of the business. For example, when the text information such as "Stay tuned at 20:00 on X month X day" and "Second sale at 16:00 on X month X day" is captured in the business page information, the business prediction question-answering model internalizes the knowledge from it and provides the knowledge as the business time information when receiving the corresponding business question. Based on the business time information, the actual business initiation time can be determined when the object to be expanded has a business.

[0047] Furthermore, the automatic expansion time is the execution time of the automatic expansion task. The automatic expansion time may be at the time point indicated by the business time information, or may be appropriately earlier than the time point indicated by the business time information. The embodiments of the present disclosure do not impose specific restrictions on this.

[0048] For example, when the business time information is 20:00, the automatic expansion time can be 20:00, 19:55, 19:50, and so on.

[0049] Step A2: Create a scheduled automatic capacity expansion task based on the automatic capacity expansion time.

[0050] In the embodiment of the present disclosure, based on the determination of the automatic capacity expansion time, the automatic capacity expansion time can be used as the task automatic triggering time to create a scheduled automatic capacity expansion task.

[0051] For example, you can create an automatic expansion task with the automatic expansion time of 19:50 and schedule it to start at 19:50.

[0052] In an optional method embodiment of the present disclosure, step A2 may further include the following step A3.

[0053] Step A3: When the automatic capacity expansion time corresponds to multiple automatic capacity expansion tasks, the multiple automatic capacity expansion tasks are accumulated and merged.

[0054] In the disclosed embodiment, multiple automatic capacity expansion tasks correspond to the capacity expansion requirements of different objects to be expanded. On this basis, in order to meet the capacity expansion requirements of multiple objects to be expanded, when the same automatic capacity expansion time corresponds to multiple automatic capacity expansion tasks, the multiple capacity expansion tasks can be accumulated and merged. At this time, an automatic capacity expansion task is triggered, and the capacity expansion requirements of multiple objects to be expanded can be executed.

[0055] For example, the automatic expansion tasks started at 19:50 include automatic expansion task A of object A to be expanded, corresponding to the expansion demand of object A to be expanded, and automatic expansion task B of object B to be expanded, corresponding to the expansion demand of object B to be expanded. Multiple automatic expansion tasks can be executed in parallel to improve efficiency, or they can be combined into automatic expansion task AB. When automatic expansion task AB is executed, it corresponds to the cumulative expansion demand of object A and object B to be expanded.

[0056] In an optional method embodiment of the present disclosure, the business information includes business type information, and constructing the automatic capacity expansion task corresponding to the object to be expanded based on the business information in the aforementioned step 103 may include steps B1 to B2.

[0057] Step B1: Determine the number of machines to be expanded based on the business type information.

[0058] In the embodiments of the present disclosure, the business type information refers to the type information of the business content initiated by the object to be expanded, and the number of machines required for different business type information may be different. For example, when serving different customer groups such as paying members, ordinary registered users, and non-registered users, or when providing different platform resources such as single-category platform resources, multi-category platform resources, full-category platform resources, and multi-platform resources, the number of machines required is also different. Specifically, the correspondence between the business type information and the number of machines required can be determined based on historical traffic or can be set based on experience, and the embodiments of the present disclosure do not impose specific restrictions on this.

[0059] On this basis, based on the number of running machines, determine the corresponding number of machine expansion when the number of machines required for business type information is met. For example, if the number of running machines is 10 and the number of machines required for business type information is 20, then the number of machine expansion is 10.

[0060] Step B2: Create a quantitative automatic capacity expansion task based on the number of machine capacity expansion.

[0061] In the embodiment of the present disclosure, based on the determination of the number of machines to be expanded, a quantitative automatic expansion task can be created based on the number of machines to expand the corresponding number of machines when the automatic expansion task is triggered to meet the number of machines required by the business type information.

[0062] In the disclosed embodiment, referring to the aforementioned step A3, when the same automatic expansion time corresponds to multiple automatic expansion tasks, the multiple automatic expansion tasks are merged into a new automatic expansion task, and the number of machines to be expanded is the number of machines to be expanded by accumulating the number of machines to be expanded by the multiple automatic expansion tasks. For example, the automatic expansion task scheduled to be started at 19:50 includes automatic expansion task A of object A to be expanded, corresponding to 10 machines to be expanded, and automatic expansion task B of object B to be expanded, corresponding to 20 machines to be expanded, which can be merged into automatic expansion task AB, corresponding to 30 machines to be expanded.

[0063] In an optional method embodiment of the present disclosure, step 103 may include the following steps C1 to C2.

[0064] Step C1: When the object to be expanded includes a root object, determine that the expansion ratio corresponding to the root object is a full ratio.

[0065] Step C2: construct a full-proportional automatic capacity expansion task corresponding to the object to be expanded based on the business information.

[0066] In the disclosed embodiment, the object to be expanded may be a root object, which can initiate business and also bear the traffic of sub-objects. For example, the root object may be a trading platform, and the sub-object may be a store on the trading platform; the root object may be an information platform, and the sub-object may be a self-media account on the information platform. In the case where the object to be expanded includes a root object, the expansion ratio of the root object may be a full ratio, that is, the number of running machines is expanded by 100%, and then a full ratio expansion task corresponding to the root object is created according to the expansion ratio.

[0067] In an optional method embodiment of the present disclosure, step 103 may include the following steps D1 to D3.

[0068] Step D1: When the object to be expanded includes multiple sub-objects, obtain the historical traffic corresponding to each sub-object; wherein the multiple sub-objects belong to the same root object.

[0069] In the embodiment of the present disclosure, when the object to be expanded includes multiple sub-objects and the multiple sub-objects belong to the same root object, the historical traffic of each sub-object can be obtained. The historical traffic can characterize the expansion demand of the sub-object. The historical traffic can be characterized by selecting corresponding indicators according to different sub-objects. For example, on the trading platform, it can be the number of views, orders, and transactions completed of different stores, etc. On the information platform, it can be the number of followers, forwardings, and comments of different accounts, etc. The embodiment of the present disclosure does not impose specific restrictions on this.

[0070] For example, the objects to be expanded include store 1, store 2, store 3, ..., store 10, etc. on the trading platform. Taking the transaction completion volume as an example, referring to the historical initiation time of the business, such as the historical initiation time is 20:00, the transaction completion volume of each sub-object is obtained between 20:00 and 20:10 every day within a period of time, and the peak value is taken as the historical traffic of each sub-object.

[0071] Step D2: Determine the expansion ratio of each sub-object as a sub-ratio based on the historical traffic.

[0072] In the embodiment of the present disclosure, the expansion ratios corresponding to the multiple sub-objects can be determined based on the historical traffic corresponding to the sub-objects, and the sub-ratios corresponding to each sub-object can be obtained.

[0073] In an optional method embodiment of the present disclosure, manual configuration of the sub-proportions corresponding to the sub-objects may also be allowed, and the present disclosure embodiment does not impose any specific limitation on this.

[0074] For example, among store 1, store 2, store 3, ..., store 10, the sub-proportion of store 1 is determined to be 10% based on the historical traffic.

[0075] Step D3: construct a sub-proportion automatic expansion task corresponding to each sub-object based on the business information.

[0076] In the embodiment of the present disclosure, when the sub-proportions corresponding to each sub-object are obtained, the sub-proportion automatic expansion tasks corresponding to the objects can be constructed based on the business information. The business information of multiple sub-objects can be the same or different. The sub-proportion automatic expansion tasks can be triggered at the same time or at different times. When the triggering time of the sub-proportion automatic expansion tasks is the same, the sub-proportions can be accumulated.

[0077] In an embodiment of the present disclosure, there may be multiple sub-objects belonging to the same root object, and other root objects may be mixed, so that the full-proportional automatic expansion task and the sub-proportional automatic expansion task with the same trigger time are mixed. In this case, the full-proportional and sub-proportional can be accumulated and merged into a new automatic expansion task.

[0078] For example, if the execution time of a 10% sub-ratio automatic expansion task is the same as that of a 100% full-ratio automatic expansion task, they will be combined into a 110% automatic expansion task. If there are 10 machines in operation, 11 more will be added based on the 10 machines according to the expansion ratio; if there are 2 machines in operation, the machines that are less than 1 can be counted as 1, and 3 more will be added based on the 2 machines according to the expansion ratio.

[0079] In an optional method embodiment of the present disclosure, the steps of periodically training the aforementioned business prediction question-answering large model are shown in the following E1 to E3:

[0080] Step E1: crawling business page information from a business page based on business keywords, where the business keywords include at least one of a business type keyword and a business time keyword.

[0081] In the disclosed embodiment, page information can be periodically captured based on business keywords in business pages through a scheduled crawler task. The page keywords may include business type keywords, such as flash sales, Black Friday, Black Friday, Double Eleven, and about to start, etc., and the business time keywords may include different time units such as hours, minutes, seconds, years, months, and days. By setting page keywords, the required information can be selectively captured to avoid obtaining other meaningless page content that interferes with source data.

[0082] For example, taking the flash sale page https: / / miaosha.a.com / of platform A as an example, the business page information "A flash sale event will start at 12:00 on November 15th" is captured through business keywords.

[0083] Step E2: construct a sequence-to-sequence question-answering training set based on the business page information.

[0084] Furthermore, the question-answering training set includes question samples and answer annotations corresponding to the question samples. Taking the business page information "A flash sale event will start at 12:00 on November 15th" as an example, an example of constructing a question-answering training set is as follows:

[0085]

[0086]

[0087] On this basis, the question-answering task of the business prediction question-answering model is designed as a business classification task and a time extraction task. When judging whether a business exists, the output is yes if the business exists, and no if the business does not exist. Furthermore, if the business exists, the business time information is extracted, and if the business does not exist, the output is no for the business time information.

[0088] Step E3: Fine-tune the business prediction question-answering model on the question-answering training set.

[0089] In the disclosed embodiment, the business prediction question and answer large model can be trained and fine-tuned using an open source LLM (Large Language Model) generation model such as GPT-3. On the aforementioned question and answer training set, the input and output pairs are formatted as sequence-to-sequence generation tasks. At this time, if the input "Does A have a flash sale?" and the output "There is a flash sale, the time is 12:00 on November 15, 2024" are paired, the question is input into the model to be trained, and the model is adjusted to output the aforementioned answer to obtain a business prediction question and answer large model.

[0090] In the embodiments of the present disclosure, the application of k8s (Kubernetes) is taken as an example. K8s is an open source container orchestration platform for automatically deploying, expanding and managing containerized applications. At this time, the capacity can be expanded by increasing the number of pods (hosts) in the platform.

[0091] Figure 2 The following is a schematic diagram of the application process of the automatic capacity expansion method based on business prediction provided by the embodiment of the present disclosure on the k8s platform, as shown in FIG. Figure 2 As shown, the process may include the following steps 201 to 207.

[0092] Step 201: Construct a business question "Does A have any promotional activities recently?" for the object A to be expanded.

[0093] Step 202: Obtain the business answer "Yes, 2024 X month X day X hour 30" output by the business prediction question and answer model for the business question. If there is no automatic capacity expansion task at the time point indicated by the business time information, execute step 203; otherwise, execute step 204.

[0094] Step 203: Based on “Xh:30, Xh:X, 2024”, create an automatic capacity expansion task with an automatic capacity expansion time of “Xh:20, Xh:X, 2024”.

[0095] Step 204: When reaching "2024 X month X day X hour 20 minutes", determine whether there are multiple automatic capacity expansion tasks. If yes, execute step 205; otherwise, execute step 206.

[0096] Step 205: Accumulate and merge multiple automatic capacity expansion tasks.

[0097] Step 206: Send a pod node expansion command to the k8s api server to execute the expansion.

[0098] Step 207: Obtain the business answer "No, None" output by the business prediction question and answer big model for the business question, end the question and answer process, and continue to capture business page information to train the business prediction question and answer big model.

[0099] The automatic capacity expansion method based on business prediction provided by the present disclosure includes constructing a business question for inquiring whether there is business for the object to be expanded, obtaining the business answer output by the prediction question and answer big model based on the business question, and when the business answer is that there is business, the automatic capacity expansion task of the object to be expanded can be constructed based on the business information; wherein, the business prediction question and answer big model is obtained by fine-tuning based on the periodically captured business page information, and when there is business for the object to be expanded, the business answer can include the corresponding business information. This method can enable the business prediction question and answer big model to have a certain business monitoring capability by periodically capturing business page information, and then automatically create the corresponding automatic capacity expansion task through the question and answer task, without the need for offline communication notification and manual intervention in capacity expansion, and can flexibly respond to traffic bursts during business at low cost and high efficiency.

[0100] Figure 3 A structural block diagram of an automatic capacity expansion device 300 based on business prediction is also provided. Figure 3 As shown, the device 300 may include: a question construction module 301, used to construct a business question, the business question is used to inquire whether there is any business for the object to be expanded; an answer acquisition module 302, used to obtain the business answer output by the business prediction question and answer big model based on the business question; the business prediction question and answer big model is fine-tuned based on the periodically captured business page information; in the case that the object to be expanded has business, the business answer includes business information; a task creation module 303, used to construct an automatic expansion task corresponding to the object to be expanded based on the business information when the business answer is that there is business.

[0101] In an optional device embodiment of the present disclosure, the business information includes business time information, and the task creation module 303 is specifically used to determine the automatic capacity expansion time based on the business time information; and create a scheduled automatic capacity expansion task based on the automatic capacity expansion time.

[0102] In an optional device embodiment of the present disclosure, the task creation module 303 is further configured to accumulate and merge multiple automatic capacity expansion tasks when the automatic capacity expansion time corresponds to multiple automatic capacity expansion tasks.

[0103] In an optional device embodiment of the present disclosure, the business information includes business type information, and the task creation module 303 determines the number of machine expansion based on the business type information; and creates a quantitative automatic expansion task based on the number of machine expansion.

[0104] In an optional device embodiment of the present disclosure, the task creation module 303 is specifically used to determine that the expansion ratio corresponding to the root object is a full ratio when the object to be expanded includes a root object; and to construct a full-ratio automatic expansion task corresponding to the object to be expanded based on business information.

[0105] In an optional device embodiment of the present disclosure, the task creation module 303 is specifically used to obtain the historical traffic corresponding to each sub-object when the object to be expanded includes multiple sub-objects; wherein the multiple sub-objects belong to the same root object; based on the historical traffic, the expansion ratio of each sub-object is determined as a sub-ratio; and based on the business information, a sub-ratio automatic expansion task corresponding to each sub-object is constructed.

[0106] In an optional device embodiment of the present disclosure, the device may also include a model training module, which is used to capture business page information in the business page based on business keywords, where the business keywords include at least one of business type keywords and business time keywords; construct a sequence-to-sequence question and answer training set based on the business page information; and fine-tune the business prediction question and answer large model on the question and answer training set.

[0107] The automatic capacity expansion device based on business prediction provided by the present disclosure can construct a business question for inquiring whether there is business for the object to be expanded, obtain the business answer output by the prediction question and answer big model based on the business question, and when the business answer is that there is business, the automatic capacity expansion task of the object to be expanded can be constructed based on the business information; wherein, the business prediction question and answer big model is obtained by fine-tuning based on the periodically captured business page information, and when there is business for the object to be expanded, the business answer can include the corresponding business information. This method can enable the business prediction question and answer big model to have a certain business monitoring capability by periodically capturing business page information, and then automatically create the corresponding automatic capacity expansion task through the question and answer task, without the need for offline communication notification and manual intervention in capacity expansion, and can flexibly respond to traffic bursts during business at low cost and high efficiency.

[0108] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0109] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0110] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0111] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0112] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0113] Refer to the following Figure 4 The electronic device 400 according to this embodiment of the present disclosure is described. Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0114] like Figure 4 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410).

[0115] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 executes the steps described in the above “exemplary method” section of this specification according to various exemplary embodiments of the present disclosure.

[0116] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 4201 and / or a cache storage unit 4202 , and may further include a read-only storage unit (ROM) 4203 .

[0117] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0118] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0119] The electronic device 400 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 400, and / or communicate with any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through a display unit 440 and an input / output (I / O) interface 450 connected to the display unit 440. In addition, the electronic device 400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 through a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0120] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0121] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0122] In the embodiments of the present disclosure, a program product for implementing the above method is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0123] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0124] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0125] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0126] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0127] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0128] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. An automatic capacity expansion method based on business prediction, characterized in that: The method comprises: Construct a business question, where the business question is used to inquire whether the object to be expanded has any business; Obtaining a business answer output by the business prediction question and answer big model based on the business question; the business prediction question and answer big model is obtained by fine-tuning the business page information captured periodically; when the object to be expanded has a business, the business answer includes business information; When the business answer is that the business exists, an automatic capacity expansion task corresponding to the object to be expanded is constructed based on the business information.

2. The method according to claim 1, characterized in that The business information includes business time information, and the step of constructing the automatic capacity expansion task corresponding to the object to be expanded based on the business information includes: Determine the automatic capacity expansion time based on the business time information; A scheduled automatic capacity expansion task is created based on the automatic capacity expansion time.

3. The method according to claim 2, characterized in that After creating a scheduled automatic capacity expansion task based on the automatic capacity expansion time, the method further includes: In the case where the automatic capacity expansion time corresponds to a plurality of automatic capacity expansion tasks, the plurality of automatic capacity expansion tasks are cumulatively merged.

4. The method according to claim 1, characterized in that The business information includes business type information, and the step of constructing the automatic capacity expansion task corresponding to the object to be expanded based on the business information includes: Determine the number of machines to be expanded based on the business type information; Create a quantitative automatic expansion task based on the number of machine expansions.

5. The method according to claim 1, characterized in that The constructing the automatic capacity expansion task corresponding to the object to be expanded based on the business information includes: In a case where the object to be expanded includes a root object, determining that the expansion ratio corresponding to the root object is a full ratio; A full-proportional automatic capacity expansion task corresponding to the object to be expanded is constructed based on the business information.

6. The method according to claim 1, characterized in that The step of constructing the automatic capacity expansion task corresponding to the object to be expanded based on the business information includes: In the case where the object to be expanded includes multiple sub-objects, obtaining the historical traffic corresponding to each of the sub-objects; wherein the multiple sub-objects belong to the same root object; Determine, based on the historical traffic, an expansion ratio of each of the sub-objects as a sub-ratio; A sub-proportion automatic expansion task corresponding to each of the sub-objects is constructed based on the business information.

7. The method according to claim 1, characterized in that The periodic training steps of the business prediction question answering model are as follows: crawling business page information from the business page based on business keywords, where the business keywords include at least one of a business type keyword and a business time keyword; Building a sequence-to-sequence question-answering training set based on the business page information; The business prediction question and answer model is fine-tuned on the question and answer training set.

8. An automatic capacity expansion device based on business prediction, characterized in that: The device comprises: A question building module is used to build a business question, wherein the business question is used to inquire whether the object to be expanded has a business; An answer acquisition module is used to obtain a business answer output by the business prediction question and answer model based on the business question; the business prediction question and answer model is obtained by fine-tuning the business page information captured periodically; when the object to be expanded has a business, the business answer includes business information; The task creation module is used to construct an automatic capacity expansion task corresponding to the object to be expanded based on the business information when the business answer is that the business exists.

9. An electronic device, characterized in that: include: Processor; and a memory for storing a computer program for the processor; The processor is configured to execute the automatic capacity expansion method based on business prediction according to any one of claims 1 to 7 by executing a computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the automatic capacity expansion method based on business prediction as described in any one of claims 1 to 7 is implemented.

Images