Information processing method and device, equipment and storage medium
By identifying and storing event records, aggregating information to determine actions, the problem of low information processing efficiency in the instant messaging automation workflow is solved, and efficient utilization of resources and intelligent processing is achieved.
Patent Information
- Application Number
- CN202411047920.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-31
AI Technical Summary
In the automated workflow of instant messaging, it is difficult to effectively extract and process message content, resulting in waste of information transmission resources and low processing efficiency, and machine learning models have poor results when short messages or small files, and are costly.
By identifying events related to workflow, storing event records and updating event record information, indicating event occurrence information from multiple dimensions, aggregating event records to determine actions, avoiding waste of single transmissions, and improving information processing efficiency.
Ensure that the event information provided to subsequent nodes is sufficient and useful, reduce the waste of information transmission resources, improve the efficiency of intelligent processing workflows, and avoid unbalanced resource occupation.
Smart Images

Figure CN118939384A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for information processing. Background Art
[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. How to use terminal devices or applications to provide users with more convenient services is a technical issue that needs to be explored at present. Summary of the invention
[0003] In a first aspect of the present disclosure, a method for information processing is provided. The method includes: for a workflow in at least one workflow, in response to identifying at least one event related to the workflow, storing a corresponding event record for the at least one event; in response to the storage of the corresponding event record, updating event record information for the workflow, the event record information indicating event occurrence information or event record usage information of the workflow from at least one dimension; and based on the corresponding event record information for the at least one workflow, using the event record stored for the at least one workflow to determine an action for the at least one workflow.
[0004] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: an event record storage module configured to store a corresponding event record for at least one event in response to identifying at least one event related to the workflow in at least one workflow; a record information update module configured to update event record information for the workflow in response to the storage of the corresponding event record, wherein the event record information indicates event occurrence information or event record usage information of the workflow from at least one dimension; and an event record usage module configured to use the event record stored for at least one workflow based on the corresponding event record information for at least one workflow to determine an action for a target workflow.
[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.
[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.
[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:
[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0010] Figure 2 A schematic diagram showing an example architecture of information processing according to some embodiments of the present disclosure;
[0011] Figure 3 A flowchart illustrating an example process for information processing according to some embodiments of the present disclosure;
[0012] Figure 4 A schematic diagram showing an example of determining whether to store an event record based on a water level according to some embodiments of the present disclosure;
[0013] Figure 5 A flowchart showing a process of information processing according to some embodiments of the present disclosure;
[0014] Figure 6 A block diagram showing an apparatus for information processing according to some embodiments of the present disclosure; and
[0015] Figure 7 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION
[0016] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of user information involved in the present 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.
[0017] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's information. Thus, the user can autonomously choose whether to provide the user information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the technical solution of the present disclosure according to the prompt message.
[0018] As an optional but non-limiting implementation, in response to receiving an active request from the user, 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. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide the user information to the electronic device.
[0019] The activation of relevant functions of the embodiments of the present disclosure, the data obtained, the processing and storage methods of the data, etc., shall all be authorized in advance by the user and other rights holders associated with the user, and shall comply with the provisions of relevant laws and regulations and agreement rules between rights holders.
[0020] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.
[0021] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.
[0022] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.
[0023] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0024] It is understandable that when adopting this technical solution, the data involved (including but not limited to the data itself, data acquisition, use, storage, and transmission) shall comply with the requirements of relevant laws, regulations and relevant provisions.
[0025] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0026] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments set forth herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0027] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.
[0028] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
[0029] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.
[0030] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", which are used interchangeably in this article. A model may also include different types of processing units or networks.
[0031] In some scenarios, such as in automated workflows based on instant messaging (IM) messages, some content is difficult to extract through simple keywords. It is understandable that in the automated workflow of IM messages, a simple workflow can be abstracted as: a real-time or near-real-time message as a trigger that can trigger multiple actions. It is usually necessary to provide the message to a subsequent node (e.g., a machine learning model) in order to determine the subsequent triggered action. The introduction of machine learning models can greatly improve the coverage of scenarios. Users can enter very simple message texts or just make simple configurations to obtain the content they care about. For example, configure action trigger condition information, which is used to trigger the action in the automated workflow when the condition is met. When the information content related to the action trigger condition information is the content that the user cares about, the action set by the user before can be triggered, wherein the content that the user cares about can be determined based on the message text entered by the user, such as the subject, category, example, sentence, paragraph, etc. expressed in natural language, or it can be a multimedia file such as a picture or video.
[0032] Subsequent nodes (e.g., machine learning models) rely on contextual information for classification / summarization. In this case, providing the content of user relationships (e.g., a single message, a text snippet, an audio or video clip, etc.) to subsequent nodes will have a poor effect. In addition, if subsequent nodes utilize machine learning models, considering the performance limitations of current machine learning models such as the amount of data transmitted in a single time, when a single message is very short, the token provided to the machine learning model is wasted on the transmission of the prompt word, which can easily cause additional costs. Similar to messages, when the text snippet or the audio or video clip is too small, the machine learning model has a poor effect and wastes transmission resources.
[0033] In view of this, an embodiment of the present disclosure proposes an improved scheme for information processing. According to various embodiments of the present disclosure, for a workflow in at least one workflow, if at least one event related to the workflow is identified, a corresponding event record for the at least one event is stored. Further, in response to the storage of the corresponding event record, the event record information for the workflow is updated, and the event record information indicates the event occurrence information or event record usage information of the workflow from at least one dimension. Then, based on the corresponding event record information for at least one workflow, the event record stored for at least one workflow is used to determine the action for the target workflow.
[0034] According to an embodiment of the present disclosure, when an event related to a workflow is identified, event records are stored so as to aggregate event records generated over a period of time, rather than processing a single event record. The aggregated event records are then provided to subsequent nodes to facilitate determination of the actions to be performed. For example, prompt information is generated based on the information of the aggregated event records and provided to a machine learning model to determine subsequent actions. Thus, it is possible to ensure that the event information provided to subsequent nodes (e.g., machine learning models) is sufficient and useful, thereby avoiding waste of information transmission resources. In this way, the efficiency of intelligent processing of workflows can be improved.
[0035] Example Environment
[0036] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100 , a component execution platform 110 can support the execution of a business component 125 . A user 140 can interact with the business component 125 via a client of the component execution platform 110 .
[0037] In some embodiments, the service component 125 can be downloaded and installed on the terminal device of the user 140. In some embodiments, the service component 125 can also be accessed through other means, such as through a web page. Figure 1 In the environment 100 , in response to the business component 125 being started, the client of the component execution platform 110 may present the interface 150 of the business component 125 .
[0038] The business component 125 includes but is not limited to one or more of the following: a chat business component (also known as an instant messaging business IM component), a document business component, an audio and video conference business component, an email business component, a task business component, a calendar business component, an objective and key result (OKR) business component, etc. It can be understood that although Figure 1A single business component is shown in FIG. 1 , but in fact, multiple business components can be installed on the component operation platform 110. Multiple business components can be integrated on the component operation platform 110, and such a component operation platform 110 can be regarded as a multifunctional collaboration platform. In the case where multiple business components are installed in the terminal device, these multiple business components can be integrated on one or more component operation platforms 110. In the component operation platform 110, people can start different business components as needed to complete corresponding information processing, sharing, communication, etc. The business component 125 can provide a content entity 126. The content entity 126 can be a content instance created by the user 140 or other users on the business component 125. For example, depending on the type of the business component 125, the content entity 126 can be a document (e.g., a word document, a pdf document, a presentation, a spreadsheet document, etc.), an email, a message (e.g., a conversation message on an instant messaging business component), a calendar, a schedule, a task, an audio, a video, an image, etc.
[0039] An interaction window between user 140 and other users may be presented in the client interface. In the interaction window, user 140 can communicate with other users by inputting natural language, pictures, audio files, video files, web page files, etc. The interaction window may include a conversation window, such as a conversation window in an instant messaging service component or an instant messaging module of a target service component. In the conversation window, the interaction between user 140 and other users may be presented in the form of conversation messages. Alternatively or additionally, the interaction window may also include other types of windows, such as a window in a floating window mode, in which user 140 may trigger the client to perform corresponding operations by inputting instructions, selecting shortcut instructions, etc.
[0040] The component operation platform 110 may be deployed locally on the terminal device of each user 140, and / or may be supported by a server-side device. For example, the terminal device of the user 140 may run a client of the component operation platform 110, which may support the interaction between the user 140 and the component operation platform 110 provided by the server. In the case where the component operation platform 110 runs locally on the user's terminal device, the user 145 may directly interact with the local component operation platform 110 using the terminal device. In the case where the component operation platform 110 runs on the server-side device, the server-side device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The component operation platform 110 may present a corresponding interface 150 to the user 140 based on the operation of the user 140, so as to output to the user 140 and / or receive from the user 140 information related to the use of the component.
[0041] In some embodiments, at least some of the functions of business component 125 and / or at least some of the functions of digital assistant 120 may be implemented based on a target model. During the operation of business component 125, one or more target models 155 may be called. Target models 155 may be used to understand user input and provide services based on the output of target models 155, such as providing a response to the user.
[0042] Although shown as being independent of the component runtime platform 110, one or more target models 155 may be run on the component runtime platform 110, or other remote servers. In some embodiments, the target model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The target model 155 may also be based on other appropriate models.
[0043] The component operation platform 110 can be run on appropriate electronic devices. The electronic device here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the component operation platform 110 can be implemented based on cloud services.
[0044] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.
[0045] Some example embodiments of the present disclosure will continue to be described with reference to the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and various page designs may actually exist. The various graphic elements in the page may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect. In addition, hereinafter, the example embodiments will be described primarily with respect to the component runtime platform 110. It should be understood that the actions described with respect to the component runtime platform 110 may be performed by an application, component, or suite (e.g., business component 125) on the component runtime platform 110, or may be performed by an application, component, or suite in collaboration with its service end (e.g., server).
[0046] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.
[0047] Some example embodiments of the present disclosure will be described below with reference to the accompanying drawings. In the following, the example embodiments will be described mainly with respect to the component runtime platform 110. It should be understood that the actions described with respect to the component runtime platform 110 can be performed by an application on the component runtime platform 110, or can be performed by the application in collaboration with its service end (e.g., server 130).
[0048] The following references Figure 2 and Figure 3 The present disclosure is described for information processing schemes. Figure 2 A schematic diagram of an example framework 200 for performing information processing according to some embodiments of the present disclosure is shown. Figure 3 A flow chart is shown of an example process 300 for performing information processing according to some embodiments of the present disclosure.
[0049] In the example architecture 200, in the configuration scenario, user 140 (sometimes also referred to as the workflow configuration party) can configure a custom workflow through the front-end page. For example, a workflow can be defined by a work recipe. User 140 can set one or more work recipes. Each work recipe defines a workflow. In some embodiments, each workflow has its corresponding trigger, which may include one or more trigger conditions. For example, a message received by the component operation platform 110. If the message is related to the workflow, the cumulative trigger condition is met, and the event record related to the message will be stored. Then, it can be determined whether the action trigger condition is met for the message. If the action trigger condition is met, the action corresponding to the message is executed, for example, the machine learning model analyzes the message, writes the message into a table, and so on.
[0050] After the user 140 confirms the configuration state, the running state can be switched. The following will continue to describe the scheme of message processing by the component running platform 110 in the running state. In some embodiments, for a workflow in at least one workflow, if the component running platform 110 identifies at least one event related to the workflow, the corresponding event record for the at least one event is stored.
[0051] When in the running state, the component operation platform 110 will receive and detect the event source 210 from the client (for example, the client of user 140). For example, the component operation platform 110 can detect the message event 210-1 of user 140, the schedule event 210-2 of user 140, the task event of user 140, or other data source events 210-3 and other events. In some embodiments, events may include but are not limited to received messages, schedules, emails, text fragments, audio and video fragments, etc. The corresponding event record of the message can be the sending time, sender, recipient, and which session the message is in. The corresponding event record of the schedule can be the occurrence time, end time, participating members, etc. of the schedule. The corresponding event record of the email can be the occurrence time, sender, recipient, etc. of the email. For the convenience of discussion, the following will mainly use messages as examples to describe the embodiments of the present disclosure.
[0052] In some embodiments, the component operation platform 110 can use the trigger module 211 to identify at least one event related to the workflow. The trigger module 211 can perform basic verification through some parameters (for example, current limiting, parameter verification, request deduplication, etc.) to verify whether the detected event meets the pre-set trigger conditions. For example, in process 300, the component operation platform 110 delivers (311) the received message event 210-1 to the filter 212. The component operation platform 110 uses the filter 212 to perform one and / or two filtering and classification (312) of the message event 210-1 according to the rules set by the user. That is, the filter 212 can identify at least one message event 210-1 related to the workflow. Other types of events have similar processing methods to message events, so they are not repeated here.
[0053] In some embodiments, the component operation platform 110 stores corresponding event records for at least one event. Continuing with the above example, in process 300, the component operation platform 110 stores (313) the corresponding event records corresponding to at least one message event 210-1 to the accumulator module 213 according to the configuration for at least one message event 210-1 after filtering and classification. In some embodiments, the accumulator module 213 can store event record information on at least one dimension. In some embodiments, at least one dimension can include a first dimension and a second dimension. The first dimension can indicate the time information, frequency information, and time information of triggering the output of prompt information to the target model based on the event record for the event record. The second dimension can indicate the event occurrence time information, the occurrence frequency information, or the event storage time information, and the event storage number information. In some examples, the accumulator module 213 may include a storage device for storing the corresponding event records of at least one event.
[0054] In some embodiments, the component operation platform 110 updates the event record information for the workflow for the storage of the corresponding event record. In some embodiments, the event record information indicates event occurrence information or event record usage information of any workflow from at least one dimension. In some examples, the component operation platform 110 updates the event record information for the workflow based on the corresponding event record stored for at least one event related to the workflow in at least one workflow. For example, the event occurrence information or event record usage information of the workflow is updated.
[0055] In some embodiments, the component execution platform 110 determines the target workflow from at least one workflow based on the corresponding event record information for at least one workflow. In some examples, the component execution platform 110 can determine the target workflow from at least one workflow through the accumulator module 213 based on the corresponding event record information for at least one workflow. In some examples, the component execution platform 110 can also determine multiple workflows, such as X workflows, from at least one workflow through the accumulator module 213 based on the event records stored for at least one workflow.
[0056] The accumulator module 213 is configured to aggregate events (that is, store multiple event records), and after slicing the events, call subsequent nodes (for example, machine learning models) for processing. For example, the data corresponding to the streaming message is cut into n slices, and each slice may include, for example, 10 messages or 20 messages. For another example, the received email data related to the workflow is sliced into n segments, and each slice may include, for example, 10 emails, 20 emails, etc. In this way, the processing effect on events (for example, a single message) can be improved, and the additional costs caused by performance limitations such as the amount of data transmitted by the machine learning model in a single time can be reduced. The component execution platform 110 determines the target workflow from at least one workflow in detail as described below.
[0057] In some embodiments, the component execution platform 110 uses the event records stored for the target workflow to determine the action for the target workflow. In the example architecture 200, after the accumulator module 213 is executed, the component execution platform 110 uses the process scheduler 214 to schedule the events after slicing. Accordingly, the component execution platform 110 calls the action module 215 to process the sliced events to determine the action for the target workflow. For example, if the event record stored in the workflow is "XX product sales today is XXX", then the action corresponding to the workflow can be to add the record to the "Sales" table.
[0058] In some embodiments, the component operation platform 110 uses the event records stored for at least one workflow to determine the action for at least one workflow. For ease of understanding, the following description will be given by taking one workflow in at least one workflow as an example. For the target workflow in at least one workflow, the component operation platform 110 generates prompt information for the target model based on the event records stored for the target workflow. Then, the component operation platform 110 determines the target action for the target workflow based on the output of the target model. In some embodiments, the component operation platform 110 can determine the target action based on the output of the target model and the action configuration information of the target workflow. In some embodiments, the component operation platform 110 can determine the relationship between the event records stored for the target workflow and the target workflow based on the output of the target model. Then, the component operation platform 110 determines the target action based on the relationship and the action configuration information of the target workflow.
[0059] In the example architecture 200, the component operation platform 110 generates prompt information for the target model based on the event record corresponding to the target workflow. That is, the component operation platform 110 can call the machine learning model to process event slicing. Accordingly, the component operation platform 110 can also mark each event after slicing to record and store the relationship between the target workflow and its corresponding event record. For example, marking can include identifying whether the event belongs to a key node of the workflow and which key node it belongs to. Then, the component operation platform 110 determines the action for the target workflow (for example, sending a message, adding a table record, calling a model, etc.) based on the relationship between the target workflow and its corresponding event record, and the action configuration information of the target workflow (for example, current limiting, parameter verification, request deduplication, etc.).
[0060] Continuing with process 300, the component execution platform 110 stores (313) the corresponding event record corresponding to at least one message event 210-1 after filtering and classification to the accumulator module 213 according to the configuration. For each workflow, the accumulator module 213 can maintain the trigger time dimension, the event number dimension, the event time dimension, etc. In some examples, the target workflow is selected according to the trigger time dimension, the event number dimension, and the event time dimension. The component execution platform 110 can pop up the corresponding event record according to the identity identifier (ID) corresponding to the target workflow and deliver (315) to the process scheduler 214.
[0061] Subsequently, the process scheduler 214 triggers (316) the consumption of the message event 210-1, thereby starting the action module 215. In some examples, a trigger may be performed every certain period of time, when the number of messages stored in the workflow accumulates to m, when the number of received emails reaches a certain number, or when a suitable slicing time is reached. Then, the action module 215 calls (317) the model interface 216 in response to the trigger event, and the model interface 216 returns (318) the result to the action module 215. Then, the action module 215 executes the action for the target workflow.
[0062] The component execution platform 110 determines the target workflow from at least one workflow as described below. In some embodiments, the component execution platform 110 determines the corresponding score of the workflow in at least one dimension for the workflow in at least one workflow. Then, the component execution platform 110 selects the target workflow from at least one workflow according to the corresponding score of at least one dimension determined for at least one workflow.
[0063] In some examples, the component execution platform 110 determines the corresponding score of each workflow in at least one dimension for any workflow in the at least one workflow. Then, the component execution platform 110 selects a target workflow from the at least one workflow according to the corresponding score of each workflow in at least one dimension.
[0064] As described above, the accumulator module 213 can store and maintain event record information in at least one dimension. In some embodiments, the first dimension may include: a trigger time dimension, and the second dimension may include an event number dimension, and an event time dimension. In some embodiments, the trigger time dimension indicates the next trigger time of the use event record. For example, the trigger time dimension may indicate the start time of the window. In some examples, when each event record is inserted into the time window for temporary storage, the component execution platform 110 may set the corresponding score of the time window to the current time, or the time of the next trigger and the time window size.
[0065] In some embodiments, the event number dimension indicates the number of event records that have been stored and not used. For example, the event number dimension can indicate the cumulative number of event records. In some examples, when each event record is inserted into the time window for temporary storage, the component execution platform 110 can perform cumulative summation on the corresponding score of the event number dimension. In some embodiments, the event time dimension indicates the storage time or occurrence time of the most recent event record stored for the workflow. For example, the event time dimension can indicate the storage time of the last event (e.g., the last message).
[0066] In some examples, for each workflow in at least one workflow, the component execution platform 110 may obtain a corresponding score of each workflow (e.g., workflow A) in each dimension in at least one dimension. Subsequently, the component execution platform 110 weights the corresponding score of workflow A in each dimension to determine the weighted score of workflow A, and then selects a workflow or multiple workflows from the at least one workflow.
[0067] The above describes an example process for a single workflow. The following describes an example implementation of target workflow selection. In some embodiments, the component execution platform 110 may also select a target workflow from at least one workflow in the following manner.
[0068] For a dimension in at least one dimension, the component execution platform 110 selects a predetermined number of workflows from at least one workflow according to the corresponding score of at least one workflow in the dimension. In some examples, for the corresponding score of at least one workflow in the trigger time dimension, the first J workflows can be taken out from at least one workflow. For the corresponding score of at least one workflow in the event number dimension, the first K workflows can be taken out from at least one workflow. For the corresponding score of at least one workflow in the event time dimension, the first L workflows can be taken out from at least one workflow.
[0069] Subsequently, the component execution platform 110 determines one or more candidate workflows based on a predetermined number of workflows selected for at least one dimension. In some embodiments, the component execution platform 110 performs a deduplication operation on a predetermined number of workflows selected for at least one dimension to remove duplicate workflows. Then, the component execution platform 110 determines one or more candidate workflows based on the result of the deduplication operation. It should be understood that the deduplication operation is not necessary, and in some embodiments, there may be no deduplication operation.
[0070] In some examples, the component execution platform 110 performs a deduplication operation on J workflows selected for the trigger time dimension, K workflows selected for the event number dimension, and L workflows selected for the event time dimension. It can be understood that the component execution platform 110 performs a deduplication operation on J+K+L workflows. Then, the component execution platform 110 determines one or more candidate workflows based on the result of the deduplication operation.
[0071] Then, the component operation platform 110 selects a target workflow from one or more candidate workflows. For example, a certain number of workflows, such as N workflows, may be selected from the candidate workflows. For another example, the candidate workflows may be divided into multiple batches (e.g., M batches) and used as target workflows in batches. In some embodiments, the component operation platform 110 may select a target workflow from one or more candidate workflows in the following manner.
[0072] In some embodiments, a priority strategy may be used to select a target workflow from candidate workflows. Specifically, the component execution platform 110 determines a weighted score of each candidate workflow in one or more candidate workflows based on the corresponding weight of at least one dimension and the corresponding score of the candidate workflow in at least one dimension. Then, the component execution platform 110 selects a target workflow from one or more candidate workflows based on the weighted scores respectively determined for the one or more candidate workflows.
[0073] In some embodiments, determining the target workflow from at least one workflow is based on the corresponding weight of at least one dimension. In some examples, for each candidate workflow in one or more candidate workflows, the component operation platform 110 is weighted and ranked based on the priority strategy. In some embodiments, the weight of the dimension indicating the use of event records is greater than the weight of the dimension indicating the occurrence of event information. In some examples, the dimension indicating the use of event records, that is, the trigger time dimension, is at a high priority, thereby preventing the proportion of certain content in the content that the user cares about from being higher than the threshold. For example, if a group chat session is in an active state, if the score is calculated only according to the dimension of the number of events, the group chat session will frequently trigger the corresponding action, which will cause the session content of the group to occupy too much resources. In order to solve the problem of uneven resource occupation, when the number of processed events reaches a predetermined number, the trigger time dimension can also be referred to to avoid the active session occupying too many resources, resulting in other events not being processed in time. Therefore, to solve this situation, the dimensions such as trigger time, number of events, and event time can be weighted according to their corresponding priorities to calculate the final weighted score, and then select the target workflow from one or more candidate workflows.
[0074] In some embodiments, after each window is triggered, the component operation platform 110 can reset the event records corresponding to the time, number, and session window respectively until the next event comes again. Therefore, by adopting a priority strategy, the resource preemption problem can be solved and the demand for horizontal expansion can be met. For example, as the number of users increases, the number of workflows and the number of events also increase. The embodiments of the present disclosure can flexibly cope with the increase in the number of workflows and the number of events.
[0075] The above describes an example embodiment of selecting a target workflow from at least one workflow based on the stored event records to perform event record slicing. Such at least one workflow can be regarded as a group of workflows. In some embodiments, if the component operation platform 110 needs to manage multiple workflows, these workflows can be divided into multiple groups of workflows. Each group of workflows can be regarded as the above-mentioned at least one workflow to be managed and maintained separately.
[0076] In some embodiments, at least one workflow can be determined in the following manner: the component operation platform 110 divides the multiple workflows into multiple groups of workflows according to the corresponding workflow attributes (e.g., identification, name, occurrence time, etc.) of the configured multiple workflows. In some embodiments, the component operation platform 110 performs a hash operation on the workflow attributes of each workflow in the multiple workflows to obtain the attribute hash value of each workflow. Accordingly, the component operation platform 110 divides the workflows whose attribute hash values match into one group of workflows in the multiple groups of workflows. Then, the component operation platform 110 determines the multiple groups of workflows as at least one workflow respectively.
[0077] In some examples, the component operation platform 110 can use a hash function to hash each of the multiple workflows to obtain a hash value for each workflow. Subsequently, the component operation platform 110 divides at least one workflow with the same hash value or a hash value difference less than a threshold into a group of workflows. Based on this approach, the component operation platform 110 can divide multiple workflows into P groups of workflows, and each group of workflows can include an indefinite number or a predetermined number of workflows, such as 5000. Therefore, the number of workflows that the component operation platform 110 supports the machine learning model to execute can be 5000*P. In this way, the performance degradation caused by the long window can be avoided. Accordingly, the problem of server downtime (also known as "hot key") caused by excessive concentration of traffic and reaching the upper limit of the physical network card can also be avoided.
[0078] In some cases, because messages are not in order and there is a problem of delayed arrival, messages that should belong to the previous time window may be stored in the current window. Therefore, for this situation, in some embodiments, a watermark of the time dimension of the workflow instance can be maintained based on the reference time to be used for comparison with the message sending time, so as to determine the difference between the message sending time and the watermark. That is, in this way, the watermark can be used to specify the allowed data delay to determine whether the message is stored.
[0079] Specifically, the component operation platform 110 may store the corresponding event record for at least one event in the following manner. For any one of the at least one workflows, if the component operation platform 110 identifies a first event related to the workflow, it determines whether the first time difference between the occurrence time of the first event and the reference time is less than a threshold. If the first time difference is less than the threshold, the event record of the first event is stored for the workflow. In some embodiments, the reference time includes the current time.
[0080] In some examples, if the component execution platform 110 identifies an event related to the workflow, it determines whether the time difference between the occurrence time of the event and the watermark is less than the preset time configuration for allowing data delay. If the time difference between the two is less than the preset time configuration for allowing data delay, the event record corresponding to the event is stored.
[0081] In some embodiments, for at least one workflow in the workflow, if the component execution platform 110 identifies a second event related to the workflow, it determines whether a second time difference between the occurrence time of the second event and the reference time is less than a threshold. If the second time difference is greater than the threshold, the event record of the second event is abandoned.
[0082] In some examples, if the component execution platform 110 identifies an event related to the workflow, it determines whether the time difference between the occurrence time of the event and the watermark is less than the preset time configuration for allowing data delay. If the time difference between the two is greater than the preset time configuration for allowing data delay, the event record corresponding to the event is abandoned.
[0083] Figure 4 A schematic diagram of an example architecture 400 for determining whether to store an event record based on a watermark according to some embodiments of the present disclosure is shown. In the example architecture 400, when the threshold is set to 1, whether to store an event record may be determined in the following manner. Figure 4 In the example of , when event 411 with a time identifier of 5 (e.g., time identifier of 5) arrives, it can be known from the example architecture 200 that watermark 412 is 6, and the difference between event 411 with a time identifier of 5 and watermark 412 is 1. This difference is less than or equal to the preset threshold value 1. Accordingly, the event record corresponding to event 411 with a time identifier of 5 can be stored, such as Figure 4 shown.
[0084] If the threshold is set to 0.5, the following method can be used to determine whether to store the event record. When event 411 with an identifier of 5 (for example, a time identifier of 5) arrives, it can be seen from the example architecture 200 that the watermark 412 is 6, and the difference between event 411 with a time identifier of 5 and watermark 412 is 1. This difference is greater than the preset difference of 0.5. Accordingly, the event record corresponding to event 411 with a time identifier of 5 is not stored. However, this is merely exemplary and the present disclosure does not limit this. It is understandable that an event that is delayed in reception due to certain factors (for example, network connection) may no longer be relevant to the current message. In this way, the problem of delayed event reception can be solved, and delayed events (for example, messages) can be prevented from interfering with the judgment of the current context in the workflow.
[0085] In summary, the present disclosure can achieve near real-time aggregation of streaming messages based on instant messaging. Accordingly, the embodiments of the present disclosure can ensure that there is no stability impact on the downstream (e.g., messages, information flows, etc.). For example, since the quota that a machine learning model can accept is limited, the present disclosure uses a frequency control strategy, that is, setting the number of requests processed per second (QPS) to be less than or equal to the quota that the machine learning model can accept, to reduce the additional costs.
[0086] Example Process
[0087] Figure 5 FIG. 5 is a flowchart of a process 500 for information processing according to some embodiments of the present disclosure. The process 500 may be implemented at the component execution platform 110. Figure 1 Process 500 is described.
[0088] In block 510 , the component execution platform 110 stores a corresponding event record for at least one event in response to identifying at least one event related to the workflow in at least one workflow.
[0089] In block 520 , the component execution platform 110 updates the event record information or event record usage information for the workflow in response to the storage of the corresponding event record.
[0090] In block 530 , the component execution platform 110 uses the event records stored for at least one workflow to determine an action for the target workflow based on the corresponding event record information for the at least one workflow.
[0091] In some embodiments, at least one dimension includes at least one of the following: a first dimension, indicating event record usage time information, usage frequency information, and event information that triggers output of prompt information to the target model based on the event record, or a second dimension, indicating event occurrence time information, occurrence frequency information, or event storage time information, event storage number information.
[0092] In some embodiments, the first dimension includes a trigger time dimension, which indicates the next trigger time of using the event record, and the second dimension includes at least one of the following: an event number dimension, which indicates the number of stored and unused event records, or an event time dimension, which indicates the storage time or occurrence time of the most recent event record stored for the workflow.
[0093] In some embodiments, using event records stored separately for at least one workflow to determine an action for at least one workflow includes: determining a target workflow from at least one workflow based on corresponding event record information for at least one workflow; and determining an action for the target workflow using event records stored for the target workflow.
[0094] In some embodiments, determining a target workflow from at least one workflow includes: determining a corresponding score of a workflow in at least one workflow on at least one dimension; and selecting a target workflow from at least one workflow based on the corresponding score of at least one dimension determined respectively for at least one workflow.
[0095] In some embodiments, selecting a target workflow from at least one workflow includes: for a dimension in at least one dimension, selecting a predetermined number of workflows from at least one workflow according to the corresponding score of at least one workflow on the dimension; determining one or more candidate workflows based on the predetermined number of workflows respectively selected for at least one dimension; and selecting the target workflow from the one or more candidate workflows.
[0096] In some embodiments, selecting a target workflow from one or more candidate workflows includes: for each candidate workflow in the one or more candidate workflows, determining a weighted score of the candidate workflow based on a corresponding weight of at least one dimension and a corresponding score of the candidate workflow on at least one dimension; and selecting a target workflow from the one or more candidate workflows based on the weighted scores respectively determined for the one or more candidate workflows.
[0097] In some embodiments, determining the target workflow from the at least one workflow is determined based on the corresponding weight of at least one dimension, and the weight of the dimension indicating event record usage information is greater than the weight of the dimension indicating event occurrence information.
[0098] In some embodiments, determining one or more candidate workflows includes: performing a deduplication operation on a predetermined number of workflows respectively selected for at least one dimension to remove duplicate workflows; and determining one or more candidate workflows based on a result of the deduplication operation.
[0099] In some embodiments, storing a corresponding event record for at least one event includes: for a workflow in at least one workflow, in response to identifying a first event related to the workflow, determining whether a first time difference between an occurrence time of the first event and a reference time is less than a threshold; and in response to the first time difference being less than the threshold, storing an event record of the first event for the workflow.
[0100] In some embodiments, process 500 also includes: for at least one workflow in the workflow, in response to identifying a second event related to the workflow, determining whether a second time difference between the occurrence time of the second event and the reference time is less than a threshold; and in response to the second time difference being greater than the threshold, abandoning storing the event record of the second event.
[0101] In some embodiments, the reference time comprises the current time.
[0102] In some embodiments, at least one workflow is determined by: dividing the multiple workflows into multiple groups of workflows based on corresponding workflow attributes of the multiple configured workflows; and determining each of the multiple groups of workflows as at least one workflow.
[0103] In some embodiments, dividing the multiple workflows into multiple groups of workflows includes: performing a hash operation on the workflow attributes of each workflow in the multiple workflows to obtain an attribute hash value of each workflow; and dividing the workflows with matching attribute hash values into one group of workflows in the multiple groups of workflows.
[0104] In some embodiments, using event records stored separately for at least one workflow to determine an action for at least one workflow includes: for a target workflow in at least one workflow, based on the event records stored for the target workflow, generating prompt information for a target model; and determining a target action for the target workflow based on an output of the target model.
[0105] In some embodiments, determining a target action of a target workflow includes: determining the target action based on an output of a target model and action configuration information of the target workflow.
[0106] In some embodiments, determining a target action for a target workflow includes: determining a relationship between an event record stored for the target workflow and the target workflow based on an output of a target model; and determining the target action based on the relationship and action configuration information of the target workflow.
[0107] Example devices and equipment
[0108] Figure 6 A schematic structural block diagram of an apparatus 600 for information processing according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented as or included in the component execution platform 110. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware or any combination thereof.
[0109] As shown in the figure, the device 600 includes an event record storage module 610, which is configured to store a corresponding event record for at least one event in response to identifying at least one event related to the workflow for the workflow in at least one workflow. The device 600 also includes a record information update module 620, which is configured to update the event record information or event record usage information for the workflow in response to the storage of the corresponding event record. The device 600 also includes an event record usage module 630, which is configured to use the event record stored for at least one workflow to determine an action for the target workflow based on the corresponding event record information for at least one workflow.
[0110] In some embodiments, at least one dimension includes at least one of the following: a first dimension, indicating event record usage time information, usage frequency information, and time information that triggers output of prompt information to the target model based on the event record; or a second dimension, indicating event occurrence time information, occurrence frequency information, or event storage time information, event storage number information.
[0111] In some embodiments, the first dimension includes a trigger time dimension, which indicates the next trigger time of using the event record, and the second dimension includes at least one of the following: an event number dimension, which indicates the number of event records that have been stored and not used, or an event time dimension, which indicates the storage time or occurrence time of the most recent event record stored for the workflow.
[0112] In some embodiments, the event record using module 630 is further configured to determine a target workflow from at least one workflow based on corresponding event record information for at least one workflow; and determine an action for the target workflow using the event record stored for the target workflow.
[0113] In some embodiments, the event record usage module 630 is also configured to determine, for a workflow in at least one workflow, a corresponding score of the workflow in at least one dimension; and select a target workflow from at least one workflow based on the corresponding score of at least one dimension determined respectively for at least one workflow.
[0114] In some embodiments, the event record usage module 630 is also configured to select a predetermined number of workflows from at least one workflow for a dimension in at least one dimension according to the corresponding score of at least one workflow on the dimension; determine one or more candidate workflows based on the predetermined number of workflows selected respectively for at least one dimension; and select a target workflow from the one or more candidate workflows.
[0115] In some embodiments, the event record usage module 630 is also configured to determine, for each candidate workflow in one or more candidate workflows, a weighted score of the candidate workflow based on the corresponding weight of at least one dimension and the corresponding score of the candidate workflow on at least one dimension; and select a target workflow from the one or more candidate workflows based on the weighted scores determined respectively for the one or more candidate workflows.
[0116] In some embodiments, determining the target workflow from the at least one workflow is determined based on the corresponding weight of at least one dimension, and the weight of the dimension indicating event record usage information is greater than the weight of the dimension indicating event occurrence information.
[0117] In some embodiments, the event record usage module 630 is further configured to perform a deduplication operation on a predetermined number of workflows respectively selected for at least one dimension to remove duplicate workflows; and determine one or more candidate workflows based on the result of the deduplication operation.
[0118] In some embodiments, the device 600 also includes a record storage module configured to, for a workflow in at least one workflow, determine whether a first time difference between the occurrence time of the first event and a reference time is less than a threshold in response to identifying a first event related to the workflow; and in response to the first time difference being less than the threshold, store an event record of the first event for the workflow.
[0119] In some embodiments, the device 600 also includes an abandonment storage module configured to, for a workflow in at least one workflow, determine whether a second time difference between the occurrence time of the second event and a reference time is less than a threshold in response to identifying a second event related to the workflow; and abandonment of storing the event record of the second event in response to the second time difference being greater than the threshold.
[0120] In some embodiments, the reference time comprises the current time.
[0121] In some embodiments, the event record using module 630 is further configured to divide the multiple workflows into multiple groups of workflows based on corresponding workflow attributes of the multiple configured workflows; and determine each of the multiple groups of workflows as at least one workflow.
[0122] In some embodiments, the device 600 also includes a workflow partitioning module configured to perform a hash operation on the workflow attributes of each workflow in multiple workflows to obtain an attribute hash value of each workflow; and partition workflows with matching attribute hash values into one group of workflows in multiple groups of workflows.
[0123] In some embodiments, the event record usage module 630 is also configured to generate prompt information for a target model for a target workflow in at least one workflow based on the event records stored for the target workflow; and determine a target action for the target workflow based on the output of the target model.
[0124] In some embodiments, the record usage module 630 is further configured to determine a target action based on an output of the target model and action configuration information of the target workflow.
[0125] In some embodiments, the event record usage module 630 is further configured to determine the relationship between the event records stored for the target workflow and the target workflow based on the output of the target model; and determine the target action based on the relationship and the action configuration information of the target workflow.
[0126] Figure 7 A block diagram of an electronic device 700 is shown in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The electronic device 700 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown can be used to implement Figure 1 The component operation platform 110.
[0127] like Figure 7 As shown, the electronic device 700 is in the form of a general electronic device. The components of the electronic device 700 may include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 720. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 700.
[0128] The electronic device 700 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 700.
[0129] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0130] The communication unit 740 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.
[0131] The input device 750 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 760 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 may also communicate with one or more external devices (not shown) through the communication unit 740 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 700, or communicate with any device that allows the electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).
[0132] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.
[0133] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0134] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0135] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0136] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.
[0137] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.
Claims
1. An information processing method, comprising: For at least one workflow in the workflow, in response to identifying at least one event related to the workflow, storing a corresponding event record for the at least one event; In response to the storage of the corresponding event record, updating event record information for the workflow, wherein the event record information indicates event occurrence information or event record usage information of the workflow from at least one dimension; as well as Event records stored for the at least one workflow are used to determine actions for the at least one workflow based on corresponding event record information for the at least one workflow.
2. The method according to claim 1, wherein the at least one dimension comprises at least one of the following: The first dimension indicates the time information, frequency information, and time information of the event record usage, and triggers the output of prompt information to the target model based on the event record; or The second dimension indicates the event occurrence time information, the event occurrence frequency information, or the event storage time information, the event storage number information.
3. The method of claim 1 , wherein using the event records stored separately for the at least one workflow to determine an action for the at least one workflow comprises: Determining a target workflow from the at least one workflow based on corresponding event record information for the at least one workflow; as well as Using the event records stored for the target workflow, an action for the target workflow is determined.
4. The method according to claim 3, wherein determining a target workflow from the at least one workflow comprises: For a workflow in the at least one workflow, determining a corresponding score of the workflow on the at least one dimension; as well as The target workflow is selected from the at least one workflow based on the corresponding score of the at least one dimension respectively determined for the at least one workflow.
5. The method of claim 1 , wherein storing a corresponding event record for the at least one event comprises: For at least one workflow, in response to identifying a first event related to the workflow, determining whether a first time difference between an occurrence time of the first event and a reference time is less than a threshold; as well as In response to the first time difference being less than the threshold, an event record of the first event is stored for the workflow.
6. The method according to claim 1, wherein the at least one workflow is determined by: Based on corresponding workflow attributes of the configured multiple workflows, dividing the multiple workflows into multiple groups of workflows; and The multiple groups of workflows are respectively determined as the at least one workflow.
7. The method according to claim 6, wherein dividing the plurality of workflows into a plurality of groups of workflows comprises: Performing a hash operation on the workflow attribute of each workflow in the plurality of workflows to obtain an attribute hash value of each workflow; as well as The workflows having matching attribute hash values are divided into a group of workflows among the multiple groups of workflows.
8. The method of claim 1, wherein using the event records stored separately for the at least one workflow to determine an action for the at least one workflow comprises: For a target workflow in the at least one workflow, based on an event record stored for the target workflow, generating prompt information provided to a target model; as well as Based on the output of the target model, a target action for the target workflow is determined.
9. An apparatus for information processing, comprising: an event record storage module configured to, for at least one workflow in the workflow, store a corresponding event record for the at least one event in response to identifying at least one event related to the workflow; A record information updating module, configured to update event record information for the workflow in response to the storage of the corresponding event record, wherein the event record information indicates event occurrence information or event record usage information of the workflow from at least one dimension; as well as The event record using module is configured to use the event records respectively stored for the at least one workflow to determine an action for the at least one workflow based on the corresponding event record information for the at least one workflow.
10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.
11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Automatic operation and maintenance method, system and equipment for cloud platform and storage medium
CN107368365A
Data processing method and device and storage medium
CN110245110A
Business processing method and device, storage medium and electronic equipment
CN116089048A
Event processing method and device, electronic equipment and medium
CN116502841A
Capture and execution of provider network tasks
US10951540B1
Cited By
Method and apparatus for determining event information, and device and storage medium
WO2026129112A1
