Data processing method and device for project management, equipment and storage medium

Abstract

The invention provides a data processing method and device for project management, equipment and a storage medium, and relates to the field of computers. The method comprises the steps that generation description information for a target field in a work item is obtained, the work item comprises a plurality of fields, and the generation description information describes a generation requirement of a field value of the target field; selecting a target system cue word from the plurality of system cue words based on the type of the target field; on the basis of the generated description information and the target system cue word, cue word information used for field value generation of the target field is determined, the cue word information comprises description information for a structured computer language, and the structured computer language is used for describing the content of the rich text type; and based on the cue word information, utilizing a machine learning model to determine a field value of the target field. There may be fields of rich text type in project management. By utilizing the embodiment of the invention, the generation of the field value related to the rich text content can be efficiently processed, so that the project management efficiency is improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a data processing method, apparatus, device, computer-readable storage medium, and computer program product for project management. Background Art

[0002] With the development of information technology, various terminal devices can provide a variety of services to people in their work and daily lives. Applications that provide these services can be deployed on these devices. These devices present content and interact with users through the application's user interface, meeting their needs. For example, in a project management scenario, a terminal device or application can process project-related data based on user requests to achieve project management objectives. Summary of the Invention

[0003] In a first aspect of the present disclosure, a data processing method for project management is provided. The method includes: obtaining generation description information for a target field in a work item, the work item includes multiple fields, the target field is one of the multiple fields, and the generation description information describes generation requirements for a field value of the target field; based on the type of the target field, selecting a target system prompt word from multiple system prompt words; based on the generation description information and the target system prompt word, determining prompt word information for generating a field value of the target field, wherein the generation description information indicates that the field value of the target field is generated based on content of a rich text type or the type of the target field is a rich text type, and the prompt word information includes description information for a structured computer language, the structured computer language is used to describe content of the rich text type; and based on the prompt word information, using a machine learning model, determining the field value of the target field.

[0004] In a second aspect of the present disclosure, a data processing device for project management is provided. The device includes: an acquisition module configured to acquire generation description information for a target field in a work item, the work item includes multiple fields, the target field is one of the multiple fields, and the generation description information describes the generation requirements of the field value of the target field; a selection module configured to select a target system prompt word from multiple system prompt words based on the type of the target field; a first determination module configured to determine prompt word information for generating the field value of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value of the target field is generated based on rich text type content or the type of the target field is rich text type, and the prompt word information includes description information for a structured computer language, the structured computer language is used to describe the content of the rich text type; and a second determination module configured to determine the field value of the target field using a machine learning model based on the prompt word information.

[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 coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform 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] In a fifth aspect of the present disclosure, a computer program product is provided. The program product includes a computer program, and the computer program can be executed by a processor to implement the method of the first aspect.

[0008] It should be understood that the content described in this summary 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

[0009] 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: Figure 1 A schematic diagram illustrating an example environment in which embodiments of the present disclosure can be implemented; Figure 2 A schematic diagram illustrating an example interface for presenting basic information of a work item according to some embodiments of the present disclosure is shown; Figure 3 A schematic block diagram showing an example flow of a data processing method according to some embodiments of the present disclosure; Figure 4 A schematic diagram illustrating a dialog interface for fields in a work item according to some embodiments of the present disclosure is shown; Figure 5 A schematic diagram illustrating an example interface for initiating a configuration request according to some embodiments of the present disclosure is shown; Figure 6 A schematic diagram illustrating an example of a configuration request according to some embodiments of the present disclosure; Figure 7 A schematic diagram illustrating an example architecture for processing rich text content according to some embodiments of the present disclosure is shown; Figure 8 A diagram illustrating an example architecture for field value generation when a referenced field includes rich text content according to some embodiments of the present disclosure; Figure 9 A schematic diagram showing an example architecture for generating a field value of a rich text type according to some embodiments of the present disclosure is shown; Figure 10 A flowchart illustrating an example process of a data processing method for project management according to some embodiments of the present disclosure is shown; Figure 11 A schematic structural block diagram of a data processing device for project management according to some embodiments of the present disclosure is shown; and Figure 12 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0010] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0011] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, 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 in different sections / subsections.

[0012] 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.

[0013] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects shall comply with the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms them. Accordingly, when implementing the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method may vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0014] Where this specification and the solutions in the examples involve the processing of personal information, such processing will be conducted with a legitimate basis (e.g., with the consent of the personal information subject or as necessary for the performance of a contract) and only within the prescribed or agreed scope. A user's refusal to process personal information other than that required for basic functions will not affect their use of these functions.

[0015] Sample Environment Figure 1 1 is a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented. In environment 100 , component execution platform 110 can support the execution of business components 125 . User 140 can interact with business components 125 via a client of component execution platform 110 .

[0016] In some embodiments, the business component 125 can be downloaded and installed on the terminal device of the user 140. In some embodiments, the business 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 .

[0017] The business component 125 includes but is not limited to one or more of the following: chat business component (also known as instant messaging business IM component), document business component, audio and video conference business component, email business component, task business component, calendar business component, objectives and key results (OKR) business component, project management component, etc. It is understandable that although Figure 1Although a single business component is shown in the figure, multiple business components can actually be installed on the component runtime platform 110. Multiple business components can be integrated on the component runtime platform 110, and such a component runtime platform 110 can be considered a multifunctional collaboration platform. When multiple business components are installed on a terminal device, these components can be integrated on one or more component runtime platforms 110. Within the component runtime platform 110, users can activate different business components as needed to perform corresponding information processing, sharing, communication, and so on. Business component 125 can provide content entities 126. Content entities 126 can be content instances created by user 140 or other users on business component 125. For example, depending on the type of business component 125, content entities 126 can include documents (e.g., Word documents, PDF documents, presentations, spreadsheets, etc.), emails, messages (e.g., conversation messages on instant messaging business components), calendars, schedules, tasks, audio, video, images, and so on.

[0018] In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly taken as an example, which is a conversation window.

[0019] The component operation platform 110 can be deployed locally on the terminal device of each user 140, and / or can be supported by a server-side device. For example, the terminal device of user 140 can run a client of the component operation platform 110, which can 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 140 can directly use the terminal device to interact with the local component operation platform 110. In the case where the component operation platform 110 runs on the server-side device, the server-side device can realize the service provision of the client running in the terminal device based on the communication connection between the terminal device and the server-side device. The component operation platform 110 can present a corresponding interface 150 to the user 140 based on the operation of the user 140, so as to output and / or receive information related to the use of the component to the user 140 and / or receive information from the user 140 from the user 140.

[0020] In some embodiments, at least some of the functionality of business component 125 can be implemented based on a target model. During the operation of business component 125, one or more target models 155 can be called. Target models 155 can be used to understand user input and provide services based on the output of target models 155, such as providing responses to users.

[0021] Although shown as being independent of the component execution platform 110, one or more target models 155 can run on the component execution platform 110 or other remote servers. In some embodiments, the target model 155 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM), such as a large language model. By learning from a large amount of corpus, the language model can have question-answering capabilities. The target model 155 can also be based on other appropriate models. In some embodiments, the model can be a multimodal model that can process input from multiple modalities, such as text and vision.

[0022] The component operation platform 110 can run on an appropriate electronic device. The electronic device here can be any type of device with computing capabilities, including a terminal device or a server device. The terminal device can be 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 positioning device, a television receiver, a radio broadcast 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 server device can, for example, include 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 a cloud service.

[0023] 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.

[0024] As mentioned above, terminal devices or applications can provide project management services to users. In one solution, the service provider can provide users with project-related information in the form of fields, enabling users to accurately and intuitively understand project status, resources, risks, and progress. In this solution, the service provider typically updates and manages the values ​​of each field through manual processing or automated instructions based on preset rules.

[0025] However, manually processing field values ​​requires administrators to manually edit and process data, resulting in low processing efficiency. When dealing with large amounts of data, this approach can easily lose key information. Using automated instruction sets to manage field values ​​can only process project information based on preset logic and cannot understand natural language instructions and contextual information, thus affecting processing efficiency. Therefore, providing a new data processing method is an urgent problem that those skilled in the art need to solve.

[0026] Embodiments of the present disclosure provide a data processing method for project management. In this method, after obtaining generated description information for a target field in a work item, a target system prompt word is determined based on the target field type. Based on the target system prompt word and the generated description information, prompt word information for a machine learning model is determined. Furthermore, the machine learning model is used to determine the field value of the target field.

[0027] In an embodiment of the present disclosure, the field value of the target field is determined by utilizing a machine learning model, thereby improving the data processing efficiency in project management. In addition, in order to enable the machine learning model to understand the rich text type content, a structured computer language that is easy for the machine learning model to understand is adopted. In the case where the field value generation involves rich text type content, for example, when the field value generation depends on rich text type content or the field value is a rich text type, the description information of the structured computer language is included in the prompt word information provided to the machine learning model, so that the machine learning model can understand the rich text type content. In this way, the machine learning model does not need to understand the complex structure of the rich text type content, but can focus on field value generation.

[0028] Unlike general data processing, project management may contain various rich text fields to better describe the project situation. Utilizing the embodiments of the present disclosure, field value generation involving rich text content can be efficiently processed, thereby improving the efficiency of project management.

[0029] Various example implementations of this solution are described in detail below in conjunction with the accompanying drawings.

[0030] Example Architecture In some embodiments, the component execution platform 110 can provide project management services for the user 140. For example, the component execution platform 110 can provide multiple forms corresponding to multiple project management tasks. Users can add work items to the forms. Project management tasks can include project requirement tasks, project defect tasks, and the like.

[0031] In some embodiments, if it is detected that the user selects a certain task type (eg, a requirement type or an approval type), the component execution platform 110 may present a plurality of project management tasks corresponding to the task type to the user 140 . Figure 2 FIG. 1 shows a schematic diagram of an example interface for presenting basic information of a work item according to some embodiments of the present disclosure. Figure 2As shown, a portion of a form 210 is presented in the interface 200. The form 210 includes multiple work items, corresponding to different tasks under the task type. If a user selection for a work item in the form 210 is detected, the component operation platform 110 can present the basic information 220 of the work item to the user. For example, if a user selection for the work item "Requirement 03" is detected, the basic information 220 of "Requirement 03" is presented in the form of a window. The basic information 220 may include multiple fields, for example, a name field 221-1, a business line field 221-2, a requirement type field 221-3, and a priority field 221-4. The field value of a certain field can be a system default value or a value entered by the user, or it can be determined based on the field values ​​of other fields, which is not limited here. In some embodiments, the component operation platform 110 can present other information of the work item selected by the user 140, such as the requirement target, the requirement value, and the requirement-related documents.

[0032] In some embodiments, the component execution platform 110 may obtain a processing request input by a user and process data in a work item according to the processing request. For example, the component execution platform 110 may obtain the processing request through a digital assistant. Figure 3 Schematic block diagram showing an example process of a data processing method according to some embodiments of the present disclosure. Figure 3 As shown, after obtaining the processing request 310, the component execution platform 110 determines the historical conversation 320 corresponding to the processing request 310. Exemplarily, the component execution platform 110 may determine the corresponding historical conversation 320 from the historical conversation record based on the type of the processing request 310 or fields related to the processing request 310.

[0033] The component execution platform 110 determines the model input 330 based on the processing request 310 and the historical conversation 320. For example, the component execution platform 110 may determine the model input 330 by concatenating the model inputs. Subsequently, the component execution platform 110 provides the model input 330 to the intent determination unit 340, which uses the intent determination unit 340 to determine the user intent indicated by the processing request 310. In some embodiments, the intent determination unit 340 may determine the user intent indicated by the processing request 310 based on a machine learning model (e.g., a large language model).

[0034] In some embodiments, if the user intention determined by the intention determination unit 340 is “field value generation”, the processing request 310 is provided to the field value generation unit 350 .

[0035] The field value generation unit 350 is used to generate a field value for a target field based on the processing request 310 and may be implemented or included in the component execution platform 110. Exemplarily, the field value generation unit 350 may determine generation description information for the target field in the work item based on the processing request 310. The generation description information is used to describe the generation requirements (e.g., generation rules, etc.) for the field value of the target field. In some embodiments, the field value generation unit 350 may determine the processing request 310 as generation description information, or process (e.g., rewrite or supplement) the processing request 310 using a machine learning model and use the generated description information as the generated description information.

[0036] return Figure 2 In some embodiments, if a trigger is received for a certain field (eg, selection, click, etc.), the component execution platform 110 presents a dialogue interface with the digital assistant. Figure 4 FIG. 1 shows a schematic diagram of a dialog interface for fields in a work item according to some embodiments of the present disclosure. Figure 4 As shown, the component execution platform 110 detects the user 140's selection of the priority field 221-4 and presents a dialogue interface 410 of the digital assistant in the interface 400. The dialogue interface 410 includes guidance information related to the target field provided by the digital assistant, for example, "What can I do for you regarding the priority field?" Figure 4 As shown, the processing request 310 provided by the user may include “return priority according to name content.” In this case, the component execution platform 110 may provide the processing request 310 to the field value generation unit 350 to determine the generation description information corresponding to the processing request 310 .

[0037] The user can start the digital assistant by triggering one of the multiple fields (for example, selecting, clicking, etc.) to provide the digital assistant with generated description information. In some embodiments, the target field can be the field triggered by the user. Exemplarily, if the user selects the "priority" field, the dialogue interface of the digital assistant for the priority field is presented. The target fields of the processing request 310 provided by the user through the dialogue interface are all "priority" fields. In some embodiments, the component operation platform 110 can determine the target field based on the processing request 310. For example, if the processing request 310 input by the user is "Set the requirement type to technical requirement", the component operation platform 110 can determine the target field as the "requirement type" field based on the processing request 310.

[0038] In some embodiments, the component execution platform 110 selects a target system prompt word from a plurality of system prompt words based on the type of the target field. In some embodiments, the type of the target field can be text type, single choice type, multiple choice type, or rich text type, etc. Exemplarily, if the type of the target field is text type, a system prompt word of text type is determined. If the type of the target field is single choice type, a prompt word of unit type is determined. The system prompt word can be a prompt word predetermined for different types of fields, used to generate field values ​​for fields of corresponding types. The system prompt word includes information such as role description, workflow description, and output format.

[0039] The following describes examples of system prompt words with reference to Tables 1 to 3. Table 1 is an example of system prompt words for a single-select field, Table 2 is an example of system prompt words for a multiple-select field, and Table 3 is an example of system prompt words for a text field.

[0040] Table 1:

[0041] Table 2:

[0042] Table 3:

[0043] In some embodiments, the component execution platform 110 determines prompt word information for generating a field value of a target field based on the generated description information and the determined target system prompt word. For example, a user prompt word can be generated based on the generated description information (which is also referred to as a "task description" in some examples) and other information. Examples of other information may include, but are not limited to, information about the fields required to generate the target field, information about the target field, a list of options for the field value of the target field, and additional reference information. The component execution platform 110 provides the prompt word information to the machine learning model to obtain the output of the machine learning model. Subsequently, based on the output of the machine learning model, the component execution platform 110 determines the field value 360 ​​of the target field. For example, the machine learning model can be a large language model.

[0044] The following describes an example embodiment for generating prompt word information. In some embodiments, the component execution platform 110 can determine a user prompt word corresponding to the generated description information based on the generated description information and a prompt word template. The user prompt word is then combined (e.g., concatenated) with the target system prompt word to determine prompt word information for generating the field value of the target field.

[0045] In some embodiments, the component operation platform 110 may determine, based on the generated description information, at least one field that the generated field value of the target field needs to rely on or be referenced. Exemplarily, if the generated description information includes "generating priority based on the name field", the "priority" field is the target field, and the "name" field is the referenced field. Subsequently, the component operation platform 110 may determine the context information for generating the field value of the target field based on the determined at least one field. For example, the field name, field type, and field value of the at least one field may be used as context information. The component operation platform 110 generates prompt word information based on the generated description information, the context information, and the target system prompt word. Exemplarily, the component operation platform 110 may use the generated description information and the context information as at least a part of the user prompt word, and splice the user prompt word and the target system prompt word as the prompt word information.

[0046] The following describes user prompt words with reference to Table 4 and Table 5. Table 4 is an example of a user prompt word template.

[0047] Table 4:

[0048] In the example in Table 4, Used to add build description information, such as user input. Used to add information about at least one referenced field (ie, context information), such as name, type, field value, etc. The name of the target field to add. Candidate field values ​​for adding target fields; Used to add additional information related to field value generation.

[0049] Table 5:

[0050] Table 5 shows an example of a user prompt word generated based on the template in Table 4. Table 5 shows a portion of the user prompt word. Table 5 includes generated description information (which corresponds to the "task description" part) and corresponding context information (which corresponds to the JSON {...} part in Table 5), and the context information is included in the prompt word information in the form of a reference. Specifically, the task description includes a reference to the context information (for example, This prevents the prompt word from being too long, which can cause the machine learning model to be unable to understand the user's true intention.

[0051] One or some fields in a work item may be of rich text type. Since the rich text content style is complex and the data structure is a linear tile structure, the machine learning model may not be able to directly understand its content. In some embodiments, the generated description information may indicate that the field value of the target field generates content based on the rich text type or the type of the target field is a rich text type. Accordingly, the prompt word information determined based on the generated description information may include description information for a structured computer language. The structured computer language is used to describe the content of the rich text type. In this way, the machine learning model does not need to understand the complex structure of the rich text type content, but can focus on field value generation.

[0052] If the target field includes rich text content or the field value of the target field generates content based on the rich text type, the performance of the model may be affected. Therefore, in some embodiments, a rich text conversion tool (e.g., a rich text software development kit) can be used to convert the rich text content to a structured computer language, such as JavaScript Object Notation (JSON) format or Markdown format.

[0053] Figure 7 Schematic diagram of an example architecture for processing rich text content according to some embodiments of the present disclosure is shown. Figure 7 As shown, a rich text conversion tool 740 is deployed on both the front end (e.g., browser 710) and the back end (e.g., server 750) of the component runtime platform 110. The rich text conversion tool 740 is used to convert the browser product 720 of the browser 710 into a structured computer language 730, and to convert the runtime product 760 of the server 750 into rich text content 770, so as to achieve conversion between rich text content and computer language. The structured computer language can include any suitable form of computer language, such as a domain-specific language (DSL). In this way, the machine learning model can focus on understanding and outputting the computer language without having to understand the complex data structure of the rich text content. In this way, interference with the machine learning model can be reduced, thereby improving generation quality.

[0054] In some embodiments, the component runtime platform 110 can implement a common runtime code based on the browser engine, enabling the rich text conversion tool used by the front-end to run within the back-end service. This allows the rich text conversion tool to run across platforms (i.e., across the server and browser), ensuring data consistency and reducing maintenance costs.

[0055] In some embodiments, if the generated description information indicates that the field value of the target field is generated based on rich text content (for example, the type of the referenced field is a rich text type), the component running platform 110 can convert the rich text content (for example, the field value of the referenced field) into field description information expressed in a structured computer language based on predetermined conversion rules. Figure 8 A schematic diagram illustrating an example architecture for generating field values ​​when a referenced field includes rich text content according to some embodiments of the present disclosure is shown. Figure 8 As shown, the component execution platform 110 converts rich text content 810 (e.g., the field value of the referenced field) into field description information expressed in a structured computer language via a computer language conversion unit 820 (e.g., a rich text conversion tool 740). Subsequently, the component execution platform 110 determines first prompt word information 830 based on the field description information, the generated description information, and the target system prompt word. In some embodiments, the component execution platform 110 may add descriptive information for the structured computer language to the first prompt word information 830 to facilitate the machine learning model's understanding of the structure of the rich text content. The descriptive information may, for example, include a definition of the structured computer language, such as a DSL definition. The first prompt word information 830 is then provided to the machine learning model 840 to obtain the field value 360 ​​of the target field.

[0056] Table 6 is an example of prompt words related to a rich text type field.

[0057] Table 6:

[0058] As shown in Table 6, based on the rich text content in the referenced field, field description information expressed in a structured computer language is determined. This field description information can be added to the system prompt word to generate prompt word information for providing to the machine learning model.

[0059] In some embodiments, the type of the target field may be a rich text type, that is, the field value 360 ​​of the target field may include rich text content. Figure 9 A schematic diagram showing an example architecture for generating a field value of a rich text type according to some embodiments of the present disclosure is shown. Figure 9As shown, if the target field for which the description information is generated is a rich text type, the component execution platform 110 provides a processing request 910 for the rich text content to the reference field parsing unit to determine the information of the referenced field. Subsequently, the component execution platform 110 combines the referenced field information, the generated description information, and the target system prompt word to obtain second prompt word information 920. In some embodiments, the system prompt word corresponding to the rich text type may include descriptive information for a structured computer language, such as a DSL definition. In this case, since the target field is a rich text field, the selected target system prompt word includes descriptive information. Thus, the second prompt word information generated based on the target prompt word also includes descriptive information. The model can return a result in a structured computer language. Subsequently, the second prompt word information 920 and the rich text content are provided to the machine learning model 840 to obtain a model output from the machine learning model 840 expressed in a structured computer language. The model output can be provided to the rich text conversion unit 930. The rich text conversion unit 930 can then convert the model output of the machine learning model 840 into rich text content based on predetermined conversion rules, which serves as the field value 360 ​​of the target field.

[0060] In the above, an embodiment in which the referenced field is of rich text type and an embodiment in which the target field is of rich text type are described respectively. In some embodiments, these two cases can be combined, that is, the field value of the target field of rich text type can be generated based on the referenced field of rich text type.

[0061] Continue to refer Figure 2 After obtaining the field value 360 ​​of the target field, the component operation platform 110 may present the field value 360 ​​of the target field and operation information related to the field value 360 ​​of the target field to the user 140. For example, the operation information may indicate an update operation for the target field, that is, updating the target field using the obtained field value. In some embodiments, the field value 360 ​​of the target field and the operable items corresponding to the corresponding operation information may be presented to the user through the dialog information 380 presented in the session. Figure 4 As shown, dialog information 380 may include conversation text "The field value of the priority is XXX," a first actionable item for updating the target field, and a second actionable item for regenerating the field value of the target field. If a user selection of the first actionable item is detected, the determined field value is filled into the target field in the work item.

[0062] The above describes an example embodiment of an example interaction between the component execution platform 110 and the user 140. In the above embodiment, the component execution platform 110 presents information related to the project management task to the user 140 through work items and fields, and based on the processing request 310 provided by the user 140, uses a machine learning model to generate field values ​​of the target field, thereby enabling the update and management of the field value. In some embodiments, the fields and work items provided by the component execution platform 110 may include configuration information provided by the administrator. The component execution platform 110 can determine the corresponding field value based on the configuration information of the field to achieve automatic update and management of the field value. In the following embodiment, the process of the administrator determining the configuration information is described.

[0063] Figure 5 A schematic diagram of an example interface for initiating a configuration request according to some embodiments of the present disclosure is shown. If a configuration request for a form from the management party is detected, the component execution platform 110 presents corresponding configuration items for multiple fields in the form. Figure 5 As shown, if a configuration request for requirement form A is received, the component operation platform 110 presents an interface 500 for obtaining the configuration information of the requirement form A to the administrator. The interface 500 includes a first area 510 for presenting information related to the field and a second area 520 for presenting field configuration items. The interface 500 includes multiple fields, such as proposal time, completion time, followers, and business lines. If the administrator's selection of a field is detected, the component operation platform 110 can present the configuration items corresponding to the field in the second area 520. Exemplarily, if the component operation platform 110 detects that the administrator selects the "follower" field, the configuration items presented in the second area 520 include a first configuration item 530 for providing editing instructions, a second configuration item 540 for determining whether to update the field value based on the AI ​​instruction, and a third configuration item 550 for configuring the basic information of the field.

[0064] In some embodiments, if interaction information is received via a configuration item for a field, the component execution platform 110 may determine to generate description information based on the interaction information. For example, if an interaction operation is detected for the first configuration item 530, the component execution platform 110 presents an interface for obtaining generated description information for the field. Figure 6 A schematic diagram illustrating an example of a configuration request according to some embodiments of the present disclosure. Figure 6An editing instruction acquisition interface 610 is shown, which includes an entry 620 for acquiring generated description information, a control 630 for selecting a debugging instance, and a presentation area 640 for presenting debugging results. If the component execution platform 110 detects the content input by the administrator in the entry 620, the input content can be directly used as the generated description information for the target field. In some embodiments, the component execution platform 110 can process the input content to determine the generated description information. The exemplary content input by the administrator in the entry 620 can be a natural language instruction that references other fields, for example, "Generate a title based on @feedback record". After obtaining the user input, the component execution platform 110 can parse the field reference relationship expressed in natural language in the user input to determine the generated description information.

[0065] After determining the generation description information, the component execution platform 110 may provide the determined generation description information to the debugging instance selected by the administrator in the control 630. Subsequently, the component execution platform 110 executes the debugging instance to obtain debugging output of the debugging instance and presents the debugging output in the presentation area 640 for the administrator to view. If the debugging output does not meet the administrator's expectations, the administrator may update the generation description information.

[0066] In some embodiments, if the component execution platform 110 detects that the information of a certain field in the work item is updated, then based on the updated information of the field, an update operation is performed on the corresponding information of other fields that reference the field in the generated description information. For example, the generated description information "update priority based on multi-line text field" for the priority field includes a reference to the "multi-line text" field. After the generated description information for the priority field is applied, if the component execution platform 110 detects that the content of the "multi-line text" field is updated, then based on the updated content of the "multi-line text" field, the field value of the "priority" field is updated. In this way, the purpose of automatically updating field values ​​can be achieved.

[0067] Figure 6 Control 650 is shown as being used to set the generation description information corresponding to the input content of entry 620 as the commonly used generation description information for the corresponding administrator. If component execution platform 110 detects that control 650 has been selected, the generation description information determined based on the user input of entry 620 is set as the commonly used generation description information for the administrator initiating the configuration request. For example, if generation description information a for field A is set as the commonly used generation description information for the administrator, in subsequent editing operations, the default generation description information for all fields A created by the administrator can be set to a.

[0068] Continue to refer Figure 3. If the user intention determined by the intention judgment unit is "dialogue", the processing request 310 is provided to the machine learning model 370. The machine learning model 370 generates dialogue information 380 based on the obtained processing request 310 to provide conversation services for the user. In some embodiments, the machine learning model 370 can provide the user with information related to the current form. For example, if the processing request 310 is "summarize the content of the name field", the machine learning model 370 can generate summary content for the "name" field based on information related to the "name" field.

[0069] Table 7 is an example of system prompt words used for dialogue.

[0070] Table 7:

[0071] As shown in Table 7, if the user's intent is a normal conversation, the component execution platform 110 can generate corresponding prompt word information based on the processing request 310 input by the user and the prompt word template. The prompt word information is then provided to the machine learning model 370, which then provides the user with conversation information 380 based on the output of the machine learning model 370.

[0072] In summary, in an embodiment of the present disclosure, for a processing request provided by a user to a digital assistant, a target system prompt word is determined according to the field type, and prompt word information for a machine learning model is generated based on the generated description information and the target system prompt word, thereby using the machine learning model to determine the field value of the target field. In this way, field value updates based on conversational interaction are implemented. In some embodiments, contextual information is introduced into the prompt word information by referencing other fields in the generated description information. Thus, accurate contextual information is provided to the machine learning model to improve the understanding ability of the machine learning model. In some embodiments, the conversion between rich text content and structured computer language is implemented through a rich text conversion tool, which improves the large model's ability to understand rich text content, and at the same time, field values ​​of rich text type can be generated. For the management party, by configuring the generation of description information for each field in the form, the field value of the corresponding field can be automatically generated and updated.

[0073] Example Process Figure 10 FIG1 is a flowchart showing an example process of a data processing method for project management according to some embodiments of the present disclosure. The process 1000 can be implemented at the component execution platform 110. Figure 1 The process 1000 is described below with respect to the component execution platform 110 by way of example only.

[0074] like Figure 10As shown, in step 1010, generation description information for a target field in a work item is obtained, the work item includes multiple fields, the target field is one of the multiple fields, and the generation description information describes generation requirements for the field value of the target field.

[0075] In some embodiments, the work item is included in a form having multiple fields, and obtaining generated description information includes: presenting corresponding configuration items for the multiple fields in response to receiving a configuration request for the form; and determining the generated description information based on interaction information received via the configuration items for the target fields.

[0076] In some embodiments, obtaining generated description information includes: presenting basic information of the work item, the basic information including multiple fields; in response to receiving a selection for a target field, presenting a dialogue interface with the digital assistant; and in response to receiving a processing request for the target field via the dialogue interface, determining to generate description information based on the processing request.

[0077] In some embodiments, process 1000 also includes: in response to determining the field value of the target field, presenting the field value and operation information related to the field value of the target field, the operation information indicating an update operation for the target field; and in response to receiving a selection for the update operation, filling the determined field value into the target field in the work item.

[0078] In step 1020 , a target system prompt word is selected from a plurality of system prompt words based on the type of the target field.

[0079] In some embodiments, the type of the target field includes at least one of the following: single-select type, multiple-select type, text type, and rich text type.

[0080] In step 1030, based on the generated description information and the target system prompt word, prompt word information for generating the field value of the target field is determined, wherein the generated description information indicates that the field value of the target field is generated based on rich text type content or the type of the target field is rich text type, and the prompt word information includes description information for a structured computer language, and the structured computer language is used to describe the rich text type content.

[0081] In some embodiments, determining prompt word information includes: based on generated description information, determining at least one field among multiple fields, generating description information indicating that a field value of a target field is generated based on the at least one field; based on the at least one field, determining context information for character value generation of the target field; and generating prompt word information based on the generated description information, the context information and the target system prompt word, the context information being included in the prompt word information in a reference form.

[0082] In some embodiments, generating description information indicates generating a field value of a target field based on a referenced field in multiple fields, and determining prompt word information includes: in response to determining that the type of the referenced field is a rich text type, based on a predetermined conversion rule, converting the field value of the referenced field into field description information expressed in a structured computer language; and determining prompt word information based on the field description information, the description information, the generated description information and the target system prompt word.

[0083] In step 1040 , based on the prompt word information, a machine learning model is used to determine the field value of the target field.

[0084] In some embodiments, the type of the target field is a rich text type, the target system prompt word includes description information for a structured computer language, and determining the field value of the target field includes: obtaining a model output expressed in a structured computer language from a machine learning model; and based on predetermined conversion rules, converting the model output expressed in a structured computer language into target rich text content as the field value of the target field.

[0085] Example devices and equipment The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 11 A schematic block diagram of a data processing device for project management according to some embodiments of the present disclosure is shown. The data processing device 1100 may be implemented as or included in the component execution platform 110. Each module / component in the data processing device 1100 may be implemented by hardware, software, firmware, or any combination thereof.

[0086] like Figure 11 As shown, data processing device 1100 includes an acquisition module 1110 configured to acquire generation description information for a target field in a work item, the work item including multiple fields, the target field being one of the multiple fields, and the generation description information describing requirements for generating a field value for the target field. Data processing device 1100 also includes a selection module 1120 configured to select a target system prompt word from multiple system prompt words based on the type of the target field. Data processing device 1100 also includes a first determination module 1130 configured to determine prompt word information for generating a field value for the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value of the target field is generated based on rich text content or that the target field is of rich text type, and the prompt word information includes description information for a structured computer language used to describe rich text content. Data processing device 1100 also includes a second determination module 1140 configured to determine the field value of the target field using a machine learning model based on the prompt word information.

[0087] In some embodiments, the work item is included in a form having multiple fields, and the acquisition module 1110 is also configured to present corresponding configuration items for the multiple fields in response to receiving a configuration request for the form; and determine to generate description information based on the interaction information received via the configuration items for the target fields.

[0088] In some embodiments, the acquisition module 1110 is also configured to present basic information of the work item, the basic information including multiple fields; in response to receiving a selection for a target field, present a dialogue interface with the digital assistant; and in response to receiving a processing request for the target field via the dialogue interface, determine to generate descriptive information based on the processing request.

[0089] In some embodiments, the data processing device 1100 also includes an update module, which is further configured to, in response to determining the field value of the target field, present the field value and operation information related to the field value of the target field, wherein the operation information indicates an update operation on the target field; and in response to receiving a selection for the update operation, fill the determined field value into the target field in the work item.

[0090] In some embodiments, the type of the target field includes at least one of the following: single-select type, multiple-select type, text type, and rich text type.

[0091] In some embodiments, the first determination module 1130 is further configured to determine at least one field among multiple fields based on generated description information, generate description information indicating that the field value of the target field is generated based on the at least one field; determine context information for character value generation of the target field based on the at least one field; and generate prompt word information based on the generated description information, the context information and the target system prompt word, the context information being included in the prompt word information in a reference form.

[0092] In some embodiments, the generated description information indicates that a field value of a target field is generated based on a referenced field in multiple fields, and the first determination module 1130 is also configured to, in response to determining that the type of the referenced field is a rich text type, convert the field value of the referenced field into field description information expressed in a structured computer language based on a predetermined conversion rule; and determine prompt word information based on the field description information, the description information, the generated description information and the target system prompt word.

[0093] In some embodiments, the type of the target field is a rich text type, the target system prompt word includes description information for a structured computer language, and the second determination module 1140 is further configured to obtain a model output expressed in a structured computer language from a machine learning model; and based on predetermined conversion rules, convert the model output expressed in a structured computer language into target rich text content as the field value of the target field.

[0094] like Figure 12 As shown, electronic device 1200 is in the form of a general electronic device. Components of electronic device 1200 may include, but are not limited to, one or more processors or processing units 1210, memory 1220, storage device 1230, one or more communication units 1240, one or more input devices 1250, and one or more output devices 1260. Processing unit 1210 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 1220. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 1200.

[0095] The electronic device 1200 typically includes a plurality of computer storage media. Such media can be any retrievable media accessible to the electronic device 1200, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 1220 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 1230 can be a removable or non-removable medium and can include machine-readable media such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 1200.

[0096] The electronic device 1200 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 12 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to 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. Memory 1220 may include a computer program product 1225 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0097] Communication unit 1240 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of electronic device 1200 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, electronic device 1200 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or other network nodes.

[0098] Input device 1250 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 1260 may be one or more output devices, such as a display, speaker, or printer. Electronic device 1200 may also communicate with one or more external devices (not shown) via communication unit 1240 as needed, such as storage devices, display devices, or other devices that allow a user to interact with electronic device 1200, or any device that allows electronic device 1200 to communicate with one or more other electronic devices (e.g., a network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0099] 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.

[0100] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0101] 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, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0102] 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, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0103] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the 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.

[0104] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A data processing method for project management, characterized in that: include: Obtaining generation description information for a target field in a work item, the work item including multiple fields, the target field being one of the multiple fields, and the generation description information describing generation requirements for a field value of the target field; Selecting a target system prompt word from a plurality of system prompt words based on the type of the target field; Determining prompt word information for generating a field value of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value of the target field generates content based on a rich text type or that the type of the target field is a rich text type, and the prompt word information includes description information for a structured computer language, wherein the structured computer language is used to describe the content of the rich text type; as well as Based on the prompt word information, a machine learning model is used to determine the field value of the target field.

2. The method according to claim 1, wherein The work item is included in a form having the plurality of fields, and obtaining the generation description information includes: In response to receiving a configuration request for the form, presenting corresponding configuration items for the plurality of fields; and The generation of description information is determined based on interaction information received via a configuration item for the target field.

3. The method according to claim 1, characterized in that Determining the prompt word information includes: Determining at least one field among the plurality of fields based on the generation description information, wherein the generation description information indicates that a field value of the target field is generated based on the at least one field; Determining context information for field value generation of the target field based on the at least one field; and The prompt word information is generated based on the generation description information, the context information and the target system prompt word, and the context information is included in the prompt word information in a reference form.

4. The method according to claim 1, wherein Obtaining the generation description information includes: Presenting basic information of the work item, where the basic information includes the multiple fields; In response to receiving a selection for the target field, presenting a conversation interface with the digital assistant; and In response to receiving a processing request for the target field via the dialogue interface, the generation description information is determined based on the processing request.

5. The method according to claim 4, wherein Also includes: In response to determining a field value of the target field, presenting the field value and operation information related to the field value of the target field, wherein the operation information indicates an update operation for the target field; as well as In response to receiving a selection for the update operation, the target field is filled with the determined field value in the work item.

6. The method according to claim 1, wherein The generating description information indicates generating a field value of the target field based on a referenced field in the plurality of fields, and determining the prompt word information includes: In response to determining that the type of the referenced field is the rich text type, based on a predetermined conversion rule, converting the field value of the referenced field into field description information represented in the structured computer language; and The prompt word information is determined based on the field description information, the explanation information, the generated description information and the target system prompt word.

7. The method according to claim 1, wherein The type of the target field is the rich text type, the target system prompt word includes the description information for the structured computer language, and determining the field value of the target field includes: Obtaining a model output from the machine learning model expressed in the structured computer language; and Based on a predetermined conversion rule, the model output represented in the structured computer language is converted into target rich text content as the field value of the target field.

8. The method according to claim 1, characterized in that The type of the target field includes at least one of the following: Single choice type, Multiple selection type, Text type, Rich text type.

9. A data processing device for project management, characterized in that: include: an acquisition module configured to acquire generation description information for a target field in a work item, the work item including a plurality of fields, the target field being one of the plurality of fields, and the generation description information describing generation requirements for a field value of the target field; A selection module is configured to select a target system prompt word from a plurality of system prompt words based on the type of the target field; a first determining module configured to determine prompt word information for generating a field value of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value of the target field generates content based on a rich text type or the type of the target field is a rich text type, and the prompt word information includes description information for a structured computer language, wherein the structured computer language is used to describe the content of the rich text type; as well as The second determination module is configured to determine the field value of the target field based on the prompt word information using a machine learning model.

10. An electronic device, characterized in that: include: at least one processing unit; as well as At least one memory 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, characterized in that A computer program is stored thereon, which can be executed by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The method comprises a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images