Task processing method and device, equipment and storage medium
By associating entity attribute information with the identification in the task processing system and only passing the entity identification, the high resource consumption and information security problems in the distributed task processing system are solved, and task processing of resource conservation and information security is realized.
Patent Information
- Application Number
- CN202311111431.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-30
- Publication Date
- 2024-11-22
AI Technical Summary
In a distributed task processing system, there are high resource consumption and information security problems when passing entity attribute information between processing units, and different processing units do not fully understand the other party's needs, resulting in the risk of resource waste and information leakage.
By associating the attribute information of an entity with the entity identification in the task processing system, the entity identification is only transmitted within the scope of the task topic. The next processing unit obtains the required attribute information based on the identification to perform the task, avoiding the direct transmission of entity attribute information, ensuring that Information security.
Reduces the consumption of communication and storage resources, improves information security, and allows the processing unit to decide to read part or all of the attribute information according to needs, avoiding resource waste and information leakage.
Smart Images

Figure CN119003104A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for task processing. Background Art
[0002] In a task processing system, multiple distributed processing units work together to complete a specific task. At different nodes of the task, different processing units perform their respective functions. During the task processing process, different processing entities may need to operate and process the same entity. In order for the processing unit to better understand the entity and successfully complete the task, the processing entity needs to know certain attribute information of the entity. Summary of the invention
[0003] In the first aspect of the present disclosure, a method for task processing is provided, which is applied to a task processing system composed of multiple processing units. The method includes: when the first task request or the first task processing result contains information of the first entity, the first processing unit stores the attribute information of the first entity in association with the first entity identifier, and the first entity is mentioned for the first time within the scope of the first task subject of the task processing system; the first processing unit replaces the information of the first entity contained in the first task request or the first task processing result with the first entity identifier, so that the first task request or the first task processing result is passed to the second processing unit; the second processing unit obtains at least a part of the stored attribute information of the first entity based on the first entity identifier in the first task request or the first task processing result; and the second processing unit executes the task related to the first task request or the first task processing result according to at least a part of the acquired attribute information of the first entity.
[0004] In the second aspect of the present disclosure, a task processing system is provided. The system includes: a first processing unit, configured to: when the information of the first entity is included in the first task request or the first task processing result, store the attribute information of the first entity in association with the first entity identifier, and the first entity is mentioned for the first time within the first task subject of the task processing system; use the first entity identifier to replace the information of the first entity included in the first task request or the first task processing result, so that the first task request or the first task processing result is passed to the second processing unit; the second processing unit, configured to: based on the first entity identifier in the first task request or the first task processing result, obtain at least a part of the stored attribute information of the first entity; and perform tasks related to the first task request or the first task processing result according to at least a part of the acquired attribute information of the first entity.
[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 content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it 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 a processing flow of a task processing system in task processing involving an entity according to some embodiments of the present disclosure;
[0011] Figure 3 A block diagram showing an apparatus for task processing according to some embodiments of the present disclosure; and
[0012] Figure 4 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure can be implemented. DETAILED DESCRIPTION
[0013] 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.
[0014] 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 also be included below.
[0015] 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.
[0016] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.
[0017] 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.
[0018] 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.
[0019] 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.
[0020] 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.
[0021] As mentioned above, in order for the processing units in the task processing system to better understand the entity and thus better complete the task, the processing entity needs to know certain attribute information of the entity. In a task processing system with distributed processing units, in order for the next processing unit to understand and operate the entity, it is usually necessary to transfer the attribute information of the entity between processing units, and different processing units may need to allocate their own storage space to cache the attribute information.
[0022] Such a task processing process consumes a lot of communication resources and storage resources, which is not conducive to the effectiveness of task processing. Moreover, the previous processing unit may not fully understand whether the next processing unit needs to use entity attribute information in task execution and what specific entity attribute information is needed. Therefore, the previous processing unit often passes all attribute information of the entity to the next processing unit. This will further cause greater resource consumption. On the other hand, if a processing unit needs to call an external processing unit, such as an external model to assist in task processing, providing entity attribute information to the external processing unit will also involve information security issues.
[0023] In an embodiment of the present disclosure, an improved scheme for task processing is provided. In this scheme, in a task processing system including multiple processing units, if the information of a first entity is included in a task request or a task processing result, and the first entity is mentioned for the first time within the scope of a first task subject of the task processing system, then the processing unit stores the attribute information of the first entity and the first entity identifier in association, and replaces the information of the first entity included in the task request or the task processing result with the first entity identifier. When the task request or the task processing result is passed to the next processing unit, the next processing unit obtains at least a portion of the stored attribute information of the first entity based on the first entity identifier in the task request or the task processing result, and performs a task related to the task request or the task processing result according to at least a portion of the acquired attribute information of the first entity. According to this scheme, between processing units, the information of the entity is simplified into the form of an entity identifier, and the entity identifier is effective within a certain task subject scope. In this way, compared with directly transmitting the entity attribute information between processing units, identifying the entity involved in the task with the help of the entity identifier can avoid excessive consumption of communication resources and storage resources in task processing, and different processing units can decide whether to read part or all of the attribute information of the entity according to their respective task processing requirements. In addition, when it comes to calling external processing units or models, the use of entity identifiers can also avoid information leakage and improve information security.
[0024] Figure 1A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In the example environment 100, a task processing system 110 is configured to complete a task in response to a task request. The task processing system 110 includes a plurality of processing units 112-1, 112-2, ... 112-N (collectively or individually referred to as processing units 112). Different processing units 112 may be configured with corresponding task processing functions. The task processing system 110 may execute a corresponding task in response to a user input from a user 120 or a task request from other sources.
[0025] In some embodiments, a processing unit 112 in the task processing system 110 may receive an initial task request. The processing unit 112 may execute the task related to the task request to obtain the corresponding task processing result. The processing unit 112 may pass the task processing result to the next processing unit 112 for the next processing unit 112 to use in its own task processing, or may send a task request (which may be an original task request or a task request generated by the processing unit 112) to the next processing unit 112 to request the next processing unit 112 to process the corresponding task. In other words, each processing unit 112 may receive a task request from a user or other processing unit, or a task processing result from other processing units. Each processing unit 112 may pass a task request or a task processing result to other processing units. Multiple processing units 112 in the task processing system 110 cooperate to ultimately complete the task requested by the task processing system 110, such as a task request from a user 120.
[0026] In some application scenarios, the processing unit 112 in the task processing system 110 may include a digital assistant, which is configured to interact with the user 120 to receive user input and feedback output to the user. The digital assistant can support dialogue with the user 120 in a natural language, determine the task processing requirements of the user 120 from the natural language input by the user, and call other processing units in the task processing system 110 to complete the task processing requirements of the user 120. In some embodiments, one or more other processing units 112 in the task processing system 110 may include plug-ins that can be called by the digital assistant, and each plug-in may be configured to perform a corresponding function. Examples of plug-ins may include, but are not limited to, search plug-ins, contact plug-ins, message plug-ins, document plug-ins, table plug-ins, mail plug-ins, calendar plug-ins, schedule plug-ins, task plug-ins, and the like. When completing a specific task requested by a user, one or more plug-ins may need to be called.
[0027] In some embodiments, each plug-in may correspond to one or more functional components in an application. A plug-in may be understood as a collection of functions, and a "tool" in a plug-in may be understood as a unit function or atomic function in a plug-in. With the aid of multiple tools, a plug-in can ultimately be used to process a class of tasks desired by the user. For example, a plug-in for processing documents may include: a document creation tool for creating new documents; a search tool for performing searches in documents; a formula generation tool for generating and inserting formulas in documents, and so on.
[0028] In some embodiments, the task processing system 110 is also connected to the target model 130 to complete the task with the help of the target model 130. In some embodiments, the task processing system 110 can understand the user input with the help of the target model 130 to determine the user's task processing requirements, arrange and call the processing unit to complete the task processing requirements. In some embodiments, the target model 130 can be a model configured to perform other processing. The task processing system 110 (for example, one or more processing units 112 therein) can interact with the target model 130 to provide model input to the target model 130 and obtain corresponding model output from the target model 130. The target model 130 can run locally on the task processing system 110 or on a remote server. In some embodiments, the target model 130 can be a model with question-and-answer capabilities. The target model 130 can of course also be based on other appropriate models.
[0029] In some embodiments, the task processing system 110 may be partially or entirely deployed on a terminal device, and / or partially or entirely deployed on a service device. The terminal device may be, for example, any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio receiver, an e-book device, a gaming device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The service device may be, for example, any service device with computing capabilities, such as a mainframe, an edge computing node, a cloud service, etc.
[0030] In some embodiments, the modules included in the various processing units 112 in the task processing system 110 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more processing units 112 can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. For example, in some implementations, one or more processing units 112 can be implemented in the form of an application installed on a terminal device. In some implementations, in addition to or as an alternative to machine executable instructions, the processing unit 112 in the task processing system 110 can be at least partially implemented by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0031] It should be understood that the structure and function of each element in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Figure 1 The task processing scheme according to the embodiment of the present disclosure is described with reference to the environment 100 .
[0032] Figure 2 FIG. 2 is a schematic diagram showing a processing flow 200 of the task processing system 110 in task processing involving entities according to some embodiments of the present disclosure. Figure 2 In the example of FIG. 1 , it is assumed that the task processing system 110 triggers a task request according to the user input 210 of the user 120, and it is assumed that the processing unit 112-1 of the task processing system 110 receives the user input 210. From the user input 210, the processing unit 112-1 can determine the task request of the user.
[0033] When the task request or the task processing result includes the information of the first entity, the processing unit 112-1 stores the attribute information of the first entity in association with the first entity identifier. In some embodiments, the processing unit 112-1 may include a digital assistant that receives the user input 210 and determines the task request from the user from the user input 210.
[0034] In the embodiments of the present disclosure, an entity refers to an operation object in the task processing system. In some embodiments, an entity may include at least one of the following: a document, an audio, a video, an image, an email, a message, a group, a calendar, a schedule, and a task. The task processing system 110 may operate on these entities, such as processing documents, scheduling schedules, creating tasks, searching for content, and the like.
[0035] In an embodiment of the present disclosure, a simplified representation of entities is proposed, and entity identifiers are assigned to entities for use in task processing. For example, for a document entity, entity identifiers DOC_1, DOC_2, etc. may be assigned, and for a schedule entity, entity identifiers SCHEDULE_1, SCHEDULE_2, etc. may be assigned. In some embodiments, entity identifiers may also be assigned based on entity types. That is, for different entity types, the styles of entity identifiers may be different, for example, the entity identifier of a document entity includes "DOC", and the entity identifier of a schedule entity includes "SCHEDULE". In this way, at least the entity type can be identified from the entity identifier itself. Different entities under the same entity type can be further distinguished based on the entity identifier corresponding to the type, such as DOC_1, DOC_2, etc. exemplified above.
[0036] Different entities often have different attribute information. For example, for a document entity, its attribute information may include the document title, document link (for example, uniform resource locator URL), document type, author information, document body, etc. For an email entity, its attribute information may include the email title, email sender and receiver list, receipt time, email link, email body, etc. For a message entity, its attribute information may include the message title, sending time, message body, etc. For a schedule entity, its attribute information may include schedule time, participants, location, schedule content, etc. For each entity, the corresponding entity identifier and entity attribute may be stored in association. For example, Figure 2 As shown, the entity identifier 222 of each entity is stored in the entity temporary storage 220 corresponding to its attribute information.
[0037] In some embodiments, an attribute storage specification corresponding to an entity type may be configured. The attribute storage specification defines the attribute information type (also referred to as an attribute field) that needs to be stored under each entity type. Thus, when the processing unit 112-1 wants to store the attribute information of the first entity, it may obtain the attribute storage specification corresponding to the entity type based on the entity type of the first entity, and store the attribute information of the first entity in association with the first entity identifier based on the attribute storage specification. The following Table 1 shows some entity types and their attribute storage specifications:
[0038] Table 1
[0039] Entity Type Attribute fields Documentation (DOC) [token(str),title(str),extra(str),doc_type(str),url(str)] Email [token(str),title(str),extra(str),applink(str)] MESSAGE [token(str),title(str),extra(str)] ... ...
[0040] In Table 1, "str" indicates that the attribute information is of string type, "token" indicates the unique identifier in the URL of the corresponding entity, "title" indicates the title of the corresponding entity, "doc_type" indicates the document type, "url" indicates the URL of the corresponding entity, and "extra" indicates the additional information of the corresponding entity. It should be understood that Table 1 only gives some examples of entity types and attribute storage specifications. In a specific implementation, different attribute storage specifications can be configured for more entity types and different entity types according to actual needs.
[0041] In some embodiments, the assignment of entity identifiers may be performed according to the task subject scope of the task processing system 110. In the task processing system 110, the task subject scope may be divided at any appropriate granularity. In some embodiments, a task subject scope may correspond to a task triggering of the task processing system 110 by the user 120. In some embodiments, if the user 120 interacts through a digital assistant in the task processing system 110, a task subject scope may correspond to a topic between the user 120 and the digital assistant. In the interaction with the digital assistant, a "topic" may be defined as corresponding to a specific context of the interaction between the user and the digital assistant. During the interaction process of each topic, the interaction information between the user and the digital assistant will be regarded as contextual information to assist the digital assistant in determining subsequent conversation messages. During the interaction process between the user and the digital assistant, the user can end the current topic and create a new topic as needed.
[0042] When receiving a task request or a task processing result, each processing unit 112 in the task processing system 110 can determine the task subject scope corresponding to the task request or the task processing result. For example, each task subject scope can be assigned a corresponding scope identifier, and the task request or task processing result within the task subject scope can include the scope identifier corresponding to the task subject scope. In this way, each processing unit 112 can determine the corresponding task subject scope through the scope identifier.
[0043] Specifically, if the processing unit 112-1 determines in the user input 210 that the first entity is mentioned for the first time within the task subject scope of the task processing system 110, then the processing unit 112-1 assigns a first entity identifier to the first entity and stores the attribute information of the first entity in association with the first entity identifier. In some embodiments, the processing unit 112 (e.g., the processing unit 112-1) may first load the entity identifiers stored within the task subject scope to determine whether the entity mentioned in the current task request or task processing result is mentioned for the first time within the task subject scope. The entity mentioned for the first time in the task request may be an existing entity that needs to be processed, and the entity mentioned for the first time in the task processing result may be an entity newly introduced or newly created after the task processing of the previous processing unit is completed.
[0044] In some embodiments, the first entity identification of the first entity is stored in the corresponding task theme scope. In this way, the entity identification of the same entity will not be reused between different task theme scopes. If the first entity is mentioned in another task theme scope, the entity identification can be allocated again for use in the corresponding task theme scope.
[0045] In some embodiments, the processing unit 112-1 may store the attribute information of the first entity and the first entity identifier in the entity temporary storage 220 in association with each other. In some embodiments, the entity temporary storage 220 may temporarily store the entity identifier and its attribute information required by the task processing system 110 at a certain granularity. The granularity may be the granularity of the task subject scope, such as the granularity of the topic between the user and the digital assistant, or may be a granularity smaller than the granularity of the task subject scope, such as a round of conversation in the topic between the user and the digital assistant. In some embodiments, alternatively, the entity identifier 222 and its attribute information 224 stored in the entity temporary storage 220 may be stored in batches (e.g., at a specific granularity in the task subject scope, such as the session granularity) in the entity persistent storage 230. It should be understood that Figure 2 The separate storage method of temporary storage of entity identification and its attribute information and persistent storage of entity is only an example. In actual application, an appropriate storage system can be configured as needed, as long as storage and reading can be achieved according to the scope of task subject.
[0046] The above discussion discusses the assignment of entity identifiers and the storage of entity attribute information for entities mentioned for the first time in the task subject area. Figure 2 For the first entity, after the first entity identifier is assigned, the processing unit 112-1 replaces the information of the first entity contained in the task request or task processing result with the first entity identifier. The task request or task processing result here can be, for example, a task request or task processing result generated in response to the user input 210. Figure 2 In the example, it is assumed that processing unit 112-1 transmits the task request or task processing result replaced with the first entity identifier to processing unit 112-2. The user inputs "Help me summarize this document {document title} {document link}". After the entity identifier is replaced, the user's actual input becomes "Help me summarize <<DOC_1> >".
[0047] The processing unit 112-2 obtains at least a portion of the stored attribute information of the first entity based on the first entity identifier in the task request or the task processing result. For example, the processing unit 112-2 uses the first entity identifier to read at least a portion of the attribute information of the first entity from the entity temporary storage 220. In other words, for the received task request or task processing result, the attribute information corresponding to the entity can be obtained simply by using the entity identifier contained therein. In this way, the processing unit 112-2 can read the required attribute information from all the stored entity information according to the needs of the task part to be executed. The processing unit 112-2 executes the task related to the task request or the task processing result according to at least a portion of the acquired attribute information of the first entity.
[0048] In some embodiments, if the processing unit 112-2 modifies the first entity during the execution of the task, the processing unit 112-2 may also update the attribute information of the first entity stored in the entity temporary storage 220 and the entity persistent storage 230. In this way, the first entity identifier of the first entity will be associated with the updated attribute information. Of course, if the processing unit 112-2 modifies other existing entities except the first entity during the execution of the task, the attribute information stored in the other existing entities may also be similarly updated.
[0049] In some embodiments, in addition to reading the attribute information of the entity, the processing unit 112 may also store the entities generated during the task execution (for example, searching for documents by a search plug-in). In some embodiments, the processing unit 112-2 may determine that a new second entity is to be introduced during the execution of the task. The second entity may be an already created entity or an entity created by the processing unit 112-2 during the task execution, but the second entity is mentioned for the first time within the scope of the current task topic. Similar to the method described above for the first entity, a second entity identifier may also be assigned to the second entity, and the second entity identifier may be stored in the entity temporary storage 220 and the entity persistent storage 230 in association with the attribute information of the second entity.
[0050] In some embodiments, after executing a task related to a task request or task processing result from processing unit 112-1, processing unit 112-2 may continue to generate a new task request or task processing result to pass to the next processing unit, such as processing unit 112-3. If the task request or task processing result passed downward also contains information of the first entity, processing unit 112-2 may also use the first entity identifier to replace the information of the first entity contained in the task request or task processing result. Similarly, if the task request or task processing result passed downward also contains information of the second entity, processing unit 112-2 may also use the second entity identifier to replace the information of the second entity contained in the task request or task processing result, and so on.
[0051] At processing unit 112-3, if the received task request or task processing result contains one or more entity identifiers, such as a first entity identifier and / or a second entity identifier, processing unit 112-3 can use the entity identifiers to read at least a portion of the attribute information of the corresponding entity from the entity temporary storage 220 for executing tasks related to the received task request or task processing result.
[0052] Similarly, if the processing unit 112-3 modifies the attribute information of an existing entity, the attribute information of the corresponding entity stored in the entity temporary storage 220 and the entity persistent storage 230 may be updated. If a new entity, such as a third entity, is introduced at the processing unit 112-3, the processing unit 112-3 may also add a third entity identifier of the third entity and its attribute information in the entity temporary storage 220.
[0053] In some embodiments, the task processing system 110 is also connected to the target model 130. During the task processing process, the task processing system 110 needs the assistance of the target model 130, for example, requesting the target model 130 to determine the user's task processing requirements from the user input 210, and arranging one or more processing units 112 to complete the task processing requirements (for example, which processing units 112 need to be called to perform a specific task processing). In the interaction with the target model 130, one or more processing units 112 of the task processing system 110 also need to send a task request to the target model 130. In some embodiments, if the task request sent to the target model 130 contains information about a certain entity, the processing unit sending the task request also uses the entity identifier of the entity to replace the information of the first entity contained in the task request. For example, for the processing unit 112-1, if it needs to call the target model 130 to identify the task processing requirements of the user input 210 and the specific execution of the task processing requirements, the processing unit 112-1 can replace the information related to the first entity in the task request sent to the target model 130 with the first entity identifier. For other processing units 112 , in the interaction with the target model 130 , the entity identifier of the corresponding entity is similarly used to replace the entity information in the task request.
[0054] In some embodiments, unlike the processing unit 112 in the task processing system 110, the target model 130 does not read the attribute information of the stored entity in the processing of the task request. In this way, when processing a task, the target model 130 only needs to pay attention to the fact that it operates on a specific entity, without paying attention to the specific entity attributes. For example, if the task request sent by the task processing system 110 (for example, the processing unit 112-1) to the target model 130 is to request the target model 130 to determine the user's task processing requirements for a certain document from the user input 210. The target model 130 may only need to pay attention to how to operate the document to meet the user's task processing requirements, such as searching for paragraphs with a certain keyword from the document. The model output returned by the target model 130 may indicate that the processing unit 112-1 is to call another processing unit (for example, a document search plug-in) to search the document, and inform the processing unit 112-2 to search for specific keywords. In this process, the target model 130 does not need to pay attention to the specific attribute information of the document. Based on such model output, the processing unit 112 - 1 may request another processing unit (eg, a document search plug-in) in the task processing system 110 to perform a specific search task.
[0055] The above discussion discusses the task processing process for the involved entities in the task processing system 110. Figure 2FIG. 1 shows the processing of processing units 112 - 1 to 112 - 3 , but depending on the specific task processing requirements, more or fewer processing units may be required to complete the entire task processing process. Figure 2 In the example of , for the task processing process triggered by the user input 210, the task processing system 110 may provide the output 212 to the user after completing the task processing. For example, the output 212 may be presented to the user by a digital assistant in the task processing system 110.
[0056] Figure 3 FIG. 3 is a flowchart of a process 300 for task processing according to some embodiments of the present disclosure. The process 300 may be implemented at the task processing system 110. For ease of discussion, reference will be made to FIG. Figure 1 The process 300 is described in the environment 100.
[0057] In box 310, when the first task request or the first task processing result includes information of the first entity, the first processing unit of the task processing system 110 stores the attribute information of the first entity in association with the first entity identifier, and the first entity is mentioned for the first time within the first task topic scope of the task processing system.
[0058] In block 320 , the first processing unit of the task processing system 110 replaces the information of the first entity contained in the first task request or the first task processing result with the first entity identifier, so that the first task request or the first task processing result is transferred to the second processing unit.
[0059] In block 330 , the second processing unit of the task processing system 110 obtains at least a portion of the stored attribute information of the first entity based on the first entity identifier in the first task request or the first task processing result.
[0060] In block 340 , the second processing unit of the task processing system 110 executes a task related to the first task request or the first task processing result according to at least a portion of the acquired attribute information of the first entity.
[0061] In some embodiments, when the first entity is modified during the execution of the task, the second processing unit of the task processing system 110 updates the attribute information of the first entity.
[0062] In some embodiments, the task processing system 110 is further connected to the target model. When the second task request sent by the task processing system 110 to the target model includes the information of the first entity, the first entity identifier is used to replace the information of the first entity included in the second task request.
[0063] In some embodiments, the target model does not read the stored attribute information of the first entity during processing of the second task request.
[0064] In some embodiments, storing the attribute information of the first entity and the first entity identifier in association with each other includes: based on the entity type of the first entity, obtaining the attribute storage specification corresponding to the entity type; and based on the attribute storage specification, storing the attribute information of the first entity and the first entity identifier in association with each other.
[0065] In some embodiments, a first entity identification of a first entity is stored within the scope of a first task subject matter.
[0066] In some embodiments, the first entity includes at least one of the following: a document, an audio, a video, an image, an email, a message, a calendar, a schedule, and a task.
[0067] Figure 4 FIG. 4 is a block diagram of an electronic device 400 suitable for implementing an embodiment of the present disclosure. It should be understood that Figure 4 The electronic device 400 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 4 The electronic device 400 shown can be used to implement Figure 1 task processing system 110 in part or in whole.
[0068] like Figure 4 As shown, the electronic device 400 is in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to, one or more processors or processing units 410, a memory 420, a storage device 430, one or more communication units 440, one or more input devices 450, and one or more output devices 460. The processing unit 410 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 420. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capabilities of the electronic device 400.
[0069] The electronic device 400 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 400, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 420 can 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 430 can be a removable or non-removable medium, and can include a machine-readable medium, such as a flash drive, a disk, or any other medium, which can be used to store information and / or data and can be accessed within the electronic device 400.
[0070] The electronic device 400 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 4 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 420 may include a computer program product 425 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0071] The communication unit 440 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 400 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 400 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.
[0072] The input device 450 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 460 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 400 may also communicate with one or more external devices (not shown) through the communication unit 440 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 400, or communicate with any device that allows the electronic device 400 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).
[0073] 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.
[0074] 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.
[0075] 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.
[0076] 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.
[0077] 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.
[0078] 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. A method for task processing, applied to a task processing system composed of multiple processing units, the method include: When the first task request or the first task processing result includes information of the first entity, the first processing unit stores the attribute information of the first entity in association with the first entity identifier, and the first entity is mentioned for the first time within the scope of the first task subject of the task processing system; The first processing unit uses the first entity identifier to replace the information of the first entity contained in the first task request or the first task processing result, so that the first task request or the first task processing result is transmitted to the second processing unit; The second processing unit acquires at least a portion of the stored attribute information of the first entity based on the first entity identifier in the first task request or the first task processing result; as well as The second processing unit executes a task related to the first task request or the first task processing result according to at least a portion of the acquired attribute information of the first entity.
2. The method according to claim 1, further comprising: include: When the first entity is modified during the execution of the task, the second processing unit updates the attribute information of the first entity.
3. The method according to claim 1, wherein the task processing system is further connected to a target model, and the method further include: When the second task request sent by the task processing system to the target model includes the information of the first entity, the information of the first entity included in the second task request is replaced by the first entity identifier. 4 . The method according to claim 3 , wherein the target model does not read the stored attribute information of the first entity in processing the second task request.
5. The method according to claim 1, wherein the attribute information of the first entity and the first entity identifier are stored in association with each other. include: Based on the entity type of the first entity, obtaining a property storage specification corresponding to the entity type; as well as Based on the attribute storage specification, the attribute information of the first entity and the first entity identifier are stored in association with each other. The method of claim 1 , wherein the first entity identification of the first entity is stored within the scope of the first task subject matter.
7. The method according to claim 1, wherein the first entity comprises at least one of the following: a document, an audio, a video, an image, an email, a message, a calendar, a schedule, and a task.
8. A task processing system, include: The first processing unit is configured as follows: When the first task request or the first task processing result includes information of a first entity, storing the attribute information of the first entity in association with the first entity identifier, the first entity being mentioned for the first time within the scope of the first task subject of the task processing system; Using the first entity identifier to replace the information of the first entity contained in the first task request or the first task processing result, so that the first task request or the first task processing result is transmitted to the second processing unit; The second processing unit is configured as follows: Based on the first entity identifier in the first task request or the first task processing result, acquiring at least a portion of the stored attribute information of the first entity; as well as A task related to the first task request or the first task processing result is executed according to at least a portion of the acquired attribute information of the first entity. 9 . The system according to claim 8 , wherein the second processing unit is further configured to: update the attribute information of the first entity when the first entity is modified during the execution of the task.
10. The system according to claim 8, wherein the task processing system is also connected to a target model, wherein when the second task request sent by the task processing system to the target model contains information about the first entity, the first entity identifier is used to replace the information about the first entity contained in the second task request. 11 . The system according to claim 10 , wherein the target model does not use the first entity representation to read the stored attribute information of the first entity in processing the second task request.
12. The system according to claim 8, wherein the first processing unit is configured to: Based on the entity type of the first entity, obtaining a property storage specification corresponding to the entity type; and Based on the attribute storage specification, the attribute information of the first entity and the first entity identifier are stored in association with each other.
13. The system of claim 8, wherein the first entity identification of the first entity is stored within the scope of the first task subject matter.
14. The system according to claim 8, wherein the first entity comprises at least one of the following: a document, an audio, a video, an image, an email, a message, a calendar, a schedule, and a task.
15. An electronic device, include: 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 7 when executed by the at least one processing unit.
16. 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 7.
Citation Information
Patent Citations
Data processing method, apparatus and system
CN108027801A
Providing optimization in micro-service architecture
CN114402292A
