Plann management method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a plan management method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a demand text and user personalized information; generating a current plan by applying the demand text and the user personalized information on the basis of an expert rule model, performing feasibility reasoning on the current plan on the basis of a logical reasoning model and the user personalized information, and adjusting the current plan on the basis of a reasoning result of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on large language model training; and managing the stage plan based on the execution condition of the stage plan. According to the plan management method and device, the electronic equipment and the storage medium provided by the invention, unreasonable parts in the plan can be found and corrected in time, smooth execution of the plan is ensured, and thus feasibility and reliability of the plan are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a planning management method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of natural language processing technology, especially the emergence of large language models (big models), artificial intelligence has significantly improved its ability to assist humans in managing complex tasks. These technological breakthroughs enable machines to understand and generate natural language texts, and use them to help users efficiently complete planning work.

[0003] The related technologies for plan making can be roughly divided into two categories: the first type of solution relies on manual operation by the user, that is, the user needs to input the specific execution steps and details of each plan on the software interface. Although this method directly reflects the user's intention, it requires the user to have a rich knowledge reserve and lacks intelligent assistance, making it difficult to adapt to rapidly changing plan needs. The second type of solution uses the understanding function of a large language model to automatically generate a plan based on the user's natural language description and generate corresponding record files for the user to review. This solution improves the efficiency of plan making to a certain extent, but it cannot meet the user's personalized customization needs, resulting in the plan being easily abandoned during execution due to unreasonableness. Summary of the invention

[0004] The present invention provides a plan management method, device, electronic device and storage medium, which are used to solve the defect in the prior art that plan formulation does not match the personalized customization needs of users, resulting in unreasonable plans that are easily abandoned.

[0005] The present invention provides a plan management method, comprising: Determine the required text and user personalized information; Based on the expert rule model, the demand text and the user personalized information are applied to generate the current plan, and based on the logical reasoning model and the user personalized information, the feasibility reasoning of the current plan is performed, and the current plan is adjusted based on the reasoning result of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on the training of a large language model; The phase plan is managed based on the execution status of the phase plan.

[0006] According to the plan management method provided by the present invention, the current plan is adjusted based on the reasoning result of the current plan until a stage plan is obtained, including: If the inference result indicates that the current plan does not match the user personalized information, the current plan is adjusted until the adjusted current plan matches the user personalized information, and the adjusted current plan is determined to be the stage plan.

[0007] According to the plan management method provided by the present invention, if the inference result indicates that the current plan does not match the user personalized information, adjusting the current plan includes: If the inference result indicates that the current plan does not match the user personalized information, sending the inference result to the expert rule model so that the expert rule model adjusts the current plan based on the inference result; and / or, Receive user feedback on the inference result, and adjust the current plan based on the user feedback.

[0008] According to the plan management method provided by the present invention, managing the stage plan based on the execution status of the stage plan includes: Analyze the execution status and deviation status of the plan for the stage respectively to obtain the execution status and deviation status; Based on the deviation status, updating the user personalized information; The phase plan is adjusted based on the execution status and the updated user personalized information.

[0009] According to the plan management method provided by the present invention, the execution status and plan deviation status of the stage plan are analyzed respectively to obtain the execution status and the deviation status, including: Analyze the execution status of the phase plan based on at least one of user interaction behavior, behavior monitoring data, and knowledge question and answer results to obtain the execution status; Based on the changes in the user status monitoring indicators corresponding to the type of the phase plan, the plan deviations are analyzed respectively to obtain the deviation status.

[0010] According to the plan management method provided by the present invention, managing the stage plan based on the execution status of the stage plan includes: In the case where it is determined that a virtual coach is needed based on the execution of the stage plan, or in response to user input, a virtual coach model is called to perform encouraging interaction, and the virtual coach model is trained based on a large language model.

[0011] According to the plan management method provided by the present invention, calling the virtual coach model for encouraging interaction includes: Determining virtual coach prompt information based on the execution status of the stage plan and / or the user input; Based on the virtual coach prompt information and the demand characteristics corresponding to the type of the stage plan, the virtual coach model is called to generate an interactive text, and encouraging interaction is performed based on the interactive text.

[0012] The present invention also provides a plan management device, comprising: A determination unit, used to determine the requirement text and user personalized information; A plan generating unit, for generating a current plan based on an expert rule model, applying the demand text and user personalized information, performing feasibility reasoning on the current plan based on a logical reasoning model and the user personalized information, and adjusting the current plan based on the reasoning result of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on training of a large language model; The plan management unit is used to manage the stage plan based on the execution status of the stage plan.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the planning management method described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described planning management methods.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned planning management methods.

[0016] The plan management method, device, electronic device and storage medium provided by the present invention generate the current plan through the expert rule model, ensuring that the best practices and potential risks in the industry can be taken into account during the plan formulation process. The personalized customization combined with the user's personalized information not only improves the satisfaction with the plan, but also enhances the user's participation. On this basis, the logical reasoning model can evaluate the feasibility of the plan, can promptly discover and correct the unreasonable aspects of the plan, and ensure the smooth execution of the plan, thereby enhancing the feasibility and reliability of the plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the planning management method provided by the present invention.

[0019] Figure 2 This is the second flow chart of the planning management method provided by the present invention.

[0020] Figure 3 It is one of the flowchart diagrams of step 130 in the planning management method provided by the present invention.

[0021] Figure 4 This is the second flowchart of step 130 in the planning management method provided by the present invention.

[0022] Figure 5 It is a flow chart of the virtual coaching model provided by the present invention.

[0023] Figure 6 It is a structural schematic diagram of the planning management device provided by the present invention.

[0024] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The planning techniques in the related art can be roughly divided into two categories. The first type of scheme relies on manual operation by the user, that is, the user needs to input the specific execution steps and details of each plan on the software interface. Although this method directly reflects the user's intention, it requires the user to have a rich knowledge reserve and lacks intelligent assistance, making it difficult to adapt to the rapidly changing planning needs.

[0027] The second type of solution uses the understanding function of large language models to automatically generate plans based on the user's natural language description and generate corresponding record files for the user to review. This solution improves the efficiency of plan formulation to a certain extent, but it cannot meet the user's personalized customization needs, resulting in the plan being easily abandoned during execution due to unreasonableness.

[0028] In response to the above problems, an embodiment of the present invention proposes a plan management method. In the plan formulation stage, the current plan is generated based on the expert rule model, application requirement text and user personalized information, the feasibility of the current plan is reasoned based on the logical reasoning model and user personalized information, and the current plan is adjusted based on the reasoning results of the current plan until a stage plan is obtained.

[0029] The expert rule model can make full use of the experience and knowledge of domain experts to ensure that the best practices and potential risks in the industry are taken into account during the planning process. Through expert rules, key elements that match user demand text and personalized information can be quickly identified. This personalized customization not only improves the satisfaction of the plan, but also enhances user participation.

[0030] The logical reasoning model can evaluate the feasibility of the plan and check whether there are logical loopholes or contradictions in the plan. Through logical reasoning, the unreasonable aspects of the plan can be discovered and corrected in time to ensure the smooth implementation of the plan, thereby enhancing the feasibility and reliability of the plan.

[0031] On this basis, plan management is carried out based on the execution of the formulated stage plans. Deviations and problems in the plan implementation process can be discovered in a timely manner so that the plan can be adjusted quickly. This flexibility and adaptability helps to ensure the smooth implementation of the plan.

[0032] The embodiments of the present invention can be applied to scenarios where planning and management are required, such as fitness, weight loss, learning, travel, etc. The execution subject of the method can be an electronic device such as a terminal device, a computer, a server, a server cluster, or a specially designed plan management device, or a plan management device set in the electronic device, and the plan management device can be implemented by software, hardware, or a combination of the two.

[0033] Figure 1 It is one of the flow charts of the planning management method provided by the present invention, such as Figure 1 As shown, the method comprises the following steps: Step 110, determining the demand text and user personalized information.

[0034] Specifically, the requirement text is usually proposed by the user and is usually expressed in text form to describe the specific requirements of the plan, including but not limited to functional requirements, performance requirements, time requirements, etc. The requirement text is the basis for making a plan. For example, the requirement text can be "I hope to lose 10 pounds in a month, please help me make a weight loss plan." For another example, the requirement text can be "I hope to pass the CET-4 exam this year, please help me make an English study plan."

[0035] User personalized information refers to specific information related to users, such as user behavior preferences, user portraits, demand characteristics, etc. User personalized information helps to understand user needs more accurately, thereby formulating plans that better meet user expectations.

[0036] A user's behavioral preferences may include, for example, their daily routines, dietary preferences, commonly used hardware devices, etc.; a user portrait may include, for example, educational information, geographic location, job type, etc.; demand characteristics may include the classification of the user's current demand (fitness, weight loss, learning, travel, education, etc.), the average time to achieve the goal (1 day, 10 days, 20 days, 2 years, etc.), and external dependencies for achieving the demand (purchasing equipment, travel services, video services, etc.).

[0037] The demand text and user personalized information can be obtained through communication with the user, collected and organized, or input by the user.

[0038] Step 120, based on the expert rule model, the application requirement text and the user personalized information, the current plan is generated, the feasibility reasoning of the current plan is performed based on the logical reasoning model and the user personalized information, and the current plan is adjusted based on the reasoning result of the current plan until the stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on the training of the large language model.

[0039] In this step, the expert rule model is a model based on the knowledge and experience of domain experts, which is used to generate plans that meet industry best practices or specific requirements. The expert rule model usually contains a series of rules, which are formulated based on expert experience and are used to guide the formulation and adjustment of plans. The rule package is formulated by human experts, and the model is trained after the rule package is organized and combined with the general large language model to obtain the expert rule model. The demand text and user personalized information are input into the trained expert rule model to generate the current plan.

[0040] Considering that the relevant technologies do not take into account the matching degree between the plan and the user's personalized information, resulting in poor feasibility of the formulated plan or logical loopholes, this embodiment performs feasibility reasoning on the current plan based on the logical reasoning model and the user's personalized information.

[0041] The logical reasoning model is a model based on logical reasoning, which is used to evaluate the feasibility of a plan. The logical reasoning model can check the logical consistency and condition satisfaction in the plan, so as to ensure the rationality and feasibility of the plan. The logical reasoning model is also trained based on a large language model. The current plan and user personalized information are input into the trained logical reasoning model to obtain the reasoning result for the current plan output by the logical reasoning model.

[0042] If the reasoning result indicates that the current plan is unreasonable or not feasible, it is necessary to adjust the current plan until the adjusted plan is both consistent with the user's personalized customization information and feasible, that is, a stage plan that meets the requirements is obtained.

[0043] Step 130: managing the phase plan based on the execution status of the phase plan.

[0044] Specifically, the implementation of the phase plan refers to the actual performance of the phase plan during its implementation, including information on progress, deviations, etc. The implementation status is the basis for managing the phase plan and is used to evaluate the implementation effect of the plan and make corresponding adjustments.

[0045] Here, managing the phase plan may include real-time monitoring of the execution of the phase plan, and timely adjusting and optimizing the phase plan based on feedback from the execution.

[0046] The method provided by the embodiment of the present invention generates the current plan through an expert rule model, ensuring that the best practices and potential risks in the industry can be taken into account during the plan formulation process. The personalized customization combined with the user's personalized information not only improves the satisfaction with the plan, but also enhances the user's participation. On this basis, the logical reasoning model can evaluate the feasibility of the plan, and can promptly discover and correct the unreasonable aspects of the plan to ensure the smooth execution of the plan, thereby enhancing the feasibility and reliability of the plan.

[0047] Based on any of the above embodiments, in step 110, adjusting the current plan based on the inference result of the current plan until a stage plan is obtained includes: Step 111: if the inference result indicates that the current plan does not match the user personalized information, the current plan is adjusted until the adjusted current plan matches the user personalized information, and the adjusted current plan is determined to be a stage plan.

[0048] Specifically, the inference results output by the logical reasoning model can be interpreted and analyzed to identify and determine whether the current plan matches the user's personalized information. The logical reasoning model evaluates the fit between the current plan and the user's personalized information based on a series of rules and algorithms, and gives a score or matching index. When this index is lower than a preset threshold, it can be considered that the current plan does not match the user's personalized information.

[0049] For example, the user is a first-grade primary school student, and the current planned study time is 10 o'clock in the evening, which is obviously not in line with the student's daily routine. At this time, it can be considered that the current plan does not match the user's personalized information; for another example, the user is an adult female, and the current plan includes 100 push-ups every day. At this time, it can be preliminarily determined that the current plan does not match the user's personalized information.

[0050] Once a mismatch is identified, it means that the feasibility of the current plan is not high, and the current plan needs to be adjusted. The current plan can be adjusted based on the expert rule model. The expert rule model usually contains a series of rules based on domain knowledge and experience. These rules can help identify the problem and provide corresponding solutions. In addition to the expert rule model, user feedback is also an important basis for adjusting the plan. For example, you can set up channels such as online feedback forms and multi-round dialogues to facilitate users to provide feedback at any time and invite users to participate in the plan formulation and adjustment process.

[0051] Perform feasibility reasoning on the adjusted current plan. If the adjusted current plan still does not match the user's personalized information, continue to adjust the current plan to form an iterative loop until the adjusted current plan completely matches the user's personalized information. At this time, the adjusted current plan that completely matches the user's personalized information can be determined as the stage plan.

[0052] The method provided by the embodiment of the present invention can further enhance the executability and reliability of the plan by performing multiple rounds of adjustments through iterative cycles when the current plan does not match the user's personalized information until a stage plan matching the user's personalized information is obtained.

[0053] Based on any of the above embodiments, if the inference result in step 111 indicates that the current plan does not match the user personalized information, adjusting the current plan includes: Step 111-1, if the inference result indicates that the current plan does not match the user personalized information, the inference result is sent to the expert rule model so that the expert rule model adjusts the current plan based on the inference result; and / or, Step 111 - 2 , receiving user feedback based on the inference result, and adjusting the current plan based on the user feedback.

[0054] Specifically, when the logic reasoning model concludes that the current plan does not match the user's personalized information, the plan needs to be adjusted. The plan adjustment can be based on the expert rule model and / or based on user feedback.

[0055] This inference result is passed as input data to the expert rule model. After receiving the inference result, the expert rule model will analyze the current plan based on the built-in rule set and algorithm. The rules may involve multiple aspects such as the logic, feasibility, and user acceptance of the plan. Based on the analysis results, the expert rule model will put forward specific adjustment suggestions, such as modifying certain functions in the plan, optimizing the process, adjusting the timeline, etc., to form a new version of the plan.

[0056] In addition, the plan can be adjusted based on user feedback. After the logical reasoning model reaches a mismatch conclusion, the result is notified to the user in an appropriate manner (such as email, SMS, in-app notification, etc.). At the same time, users are encouraged to provide feedback based on the reasoning results, including whether the user can accept the current plan, improvement suggestions, etc., and user feedback is received. Then, the current plan is adjusted in a targeted manner based on user feedback.

[0057] For example, the logical reasoning model determines that it is not reasonable for an adult woman to do 100 push-ups a day. Through user feedback, it is learned that users can accept 50 push-ups a day, so the plan can be adjusted based on user feedback.

[0058] The method provided in the embodiment of the present invention adjusts the current plan based on the expert rule model and / or user feedback, which can further improve the matching degree between the plan and the user's personalized information, thereby enhancing the executability of the plan.

[0059] Based on any of the above embodiments, Figure 2 This is the second flow chart of the planning management method provided by the present invention, such as Figure 2 As shown in the figure, the plan generation is realized by the expert rule model, the large model reasoning generation model, and multiple dialogues with the user. The user only participates when personalized information needs to be input. The expert rule model formulates the rule package through artificial experts, organizes the rule package and then trains the model, merges it with the general large model and generates a plan based on personalized information. The logical reasoning model performs logical reasoning on the feasibility of the plan generated by the rule model in combination with personalized information. Feedback can be provided for plans that the user cannot achieve and submitted to the expert rule model for correction and adjustment. For plans that require user confirmation, the user is guided to make a choice. After multiple adjustments, a plan that meets the user's current conditions and is highly feasible is obtained, that is, a stage plan.

[0060] Based on any of the above embodiments, Figure 3 is one of the flow charts of step 130 in the planning management method provided by the present invention, such as Figure 3 As shown, based on the execution of the phase plan, manage the phase plan, including: Step 131, analyzing the execution status and deviation status of the stage plan respectively to obtain the execution status and deviation status; Step 132, updating the user personalized information based on the deviation from the current status; Step 133: Adjust the phase plan based on the execution status and the updated user personalized information.

[0061] Specifically, considering the relevant technologies, during the execution of the plan, it is impossible to fine-tune it according to the user's personalized characteristics and progress. There are many new problems that the user did not think of when making the plan, resulting in the plan not being in line with the user's current situation.

[0062] The execution status of the stage plan refers to the actual completion of the stage plan during the execution process. For example, it includes completed tasks, ongoing tasks, uncompleted tasks, and any factors that may affect the progress of the plan. For example, the push-up task has been completed on the day, and the running task is in progress.

[0063] Analyzing the execution of the phase plan can identify which tasks have been successfully completed and which tasks are delayed or incomplete. The execution status obtained helps to understand the current status, such as completed tasks, progress percentage, resource usage, etc.

[0064] Deviation from the plan refers to the difference between the actual implementation of the stage plan and the original plan. For example, according to the stage plan, you need to lose 5 catties at the current time node, but you actually lose 3 catties at the current time node, which means there is a deviation from the plan. For another example, the stage plan is to learn Chapter 3 at the current time node, but the actual chapter you have learned at the current time node is Chapter 4, which means there is a deviation from the plan and there is a situation of advanced learning.

[0065] Compare the stage plan with the actual implementation status, and analyze the current status of plan deviation, such as the cause, degree, and impact of the deviation.

[0066] Then, based on the deviation from the current situation, the user's personalized information is updated. User needs, user preferences, user expectations, etc. can be adjusted. For example, the behavior preference in the user's personalized information shows that the user has time in the morning, but through the deviation from the current situation, it is found that the user actually has more time in the evening, so the user's personalized information can be updated.

[0067] On this basis, the stage plan is adjusted based on the execution status and the updated user personalized information. The specific adjustment can be achieved through the expert rule model and the logical reasoning model until the adjusted stage plan conforms to the updated user personalized information.

[0068] Figure 4 This is the second flow chart of step 130 in the planning management method provided by the present invention, such as Figure 4 As shown, during the plan execution process, the best personalized customized plan that best meets the user's personalized information can be achieved through multiple analyses of the execution status and deviations, and multiple adjustments.

[0069] Based on any of the above embodiments, the execution status and plan deviation status of the stage plan are analyzed respectively to obtain the execution status and the deviation status, that is, step 131 specifically includes: Step 131-1, analyzing the execution status of the phase plan based on at least one of the user interaction behavior, the behavior monitoring data, and the knowledge question and answer result to obtain the execution status; Step 131 - 2 , based on the changes in the user status monitoring indicators corresponding to the type of the phase plan, analyze the plan deviations respectively to obtain the deviation status.

[0070] Specifically, the execution status can be obtained by analyzing the execution status of the phase plan based on at least one of user interaction behavior, behavior monitoring data, and knowledge question and answer results.

[0071] User interaction behavior refers to the user's interaction with the system during the use of the product or service, such as clicking, sliding, inputting, browsing, etc. These behaviors can reflect the user's feedback and attitude towards the execution of the stage plan. If the user clicks on or views the recommended content, it can be determined that the user has performed the planned task on that day.

[0072] Behavior monitoring data is data about user interaction collected through hardware. Behavior monitoring data can quantify user activity, engagement, and usage habits, providing an objective basis for the execution of the plan in the analysis phase. For example, through the movement trajectory and number of steps monitored by hardware, it can be determined whether the user has performed the planned tasks on that day.

[0073] The results of the knowledge quiz refer to the knowledge points required for the task mentioned in the casual conversation between the virtual person and the user through knowledge questions. The results of the knowledge quiz can reflect the user's understanding of the stage plan, the satisfaction of needs, and possible problems and confusions. If the user answers correctly, it is determined that the user has performed the planned task on that day.

[0074] In view of the deviation status, the plan deviation can be analyzed and implemented separately based on the changes in the user status monitoring indicators corresponding to the type of the stage plan.

[0075] The types of stage plans may include, for example, fitness services, learning and improvement services, health management services, etc. For different types of stage plans, there are corresponding user status monitoring indicators. User status monitoring indicators are quantitative indicators used to measure the changes in the user's status during the execution of the stage plan. For example, for weight and fitness plans, user status monitoring indicators may include weight, body fat percentage, etc., and the user's weight and body fat percentage changes are monitored through weight scales, body fat scales, video cameras, etc. Based on the changes, it is concluded whether the plan is completed ahead of schedule or delayed. For learning and improvement plans, user status monitoring indicators may include the mastery of each learning unit, and small tests can be used to verify the user's mastery. For health management plans, user status monitoring indicators may include blood pressure, blood sugar, facial complexion, emotions, etc., and the changes in the user's blood pressure, blood sugar, facial complexion, emotions, etc. can be analyzed through cameras and health instruments.

[0076] Based on any of the above embodiments, managing the stage plan based on the execution status of the stage plan, that is, step 130 specifically includes: Step 134, when it is determined that a virtual coach is needed based on the execution of the stage plan, or in response to user input, a virtual coach model is called to perform encouraging interaction, and the virtual coach model is trained based on a large language model.

[0077] Specifically, considering that users may encounter various difficulties during the plan execution stage, they may easily feel discouraged, resulting in unsuccessful plan execution. This embodiment can autonomously determine whether a virtual coach needs to intervene based on the execution of the stage plan. If the user has not executed the plan for many consecutive days, or the user's recent execution is not optimistic, it can be determined that a virtual coach needs to intervene.

[0078] A virtual coach is a simulated coach that uses artificial intelligence technology to simulate the behavior and thinking of a real coach. It can interact with users through software or applications to provide guidance, advice and encouragement. For example, in fitness program management, a virtual coach can provide voice guidance or feedback during training based on the user's execution, comforting the user and helping him or her to boost confidence.

[0079] In another embodiment, the user may actively initiate a virtual coaching service during the execution of the plan, that is, the user actively requests to interact with the virtual coach.

[0080] At this time, the trained virtual coach model can be called to provide personalized encouragement and guidance based on the user's actual situation (such as plan execution progress, physical condition, psychological state, etc.). For example, if the user feels tired or frustrated during fitness, the virtual coach can motivate the user with positive and encouraging words; if the user needs to improve a certain action or skill, the virtual coach can provide detailed guidance and suggestions.

[0081] The virtual coach model is trained based on a large language model. A large amount of text data from related fields is used to train the large language model. During the training process, the model learns how to understand and generate natural language text related to the planned field, and learns how to provide appropriate guidance and suggestions based on the user's situation. After the training is completed, the model can be used as a virtual coach in the application to interact with the user in real time. Preferably, in order to further improve the experience, a virtual image can be generated to interact with the user.

[0082] The method provided by the embodiment of the present invention uses a virtual coach trained by a large language model to assist users in completing stage plans and provide encouragement and guidance when necessary, thereby improving user participation and satisfaction.

[0083] Based on any of the above embodiments, calling a virtual coach model for encouraging interaction includes: Determine virtual coach prompt information based on the execution of the phase plan and / or user input; Based on the virtual coach prompt information and the demand characteristics corresponding to the type of stage plan, the virtual coach model is called to generate interactive text, and encouraging interaction is carried out based on the interactive text.

[0084] Specifically, the virtual coach prompt information is information generated by the system to guide the virtual coach to interact with the user. The virtual coach prompt information may include the execution status of the stage plan, that is, the user's execution status, and may also include the questions and confusions input by the user, or may include both the execution status and the user input.

[0085] Demand characteristics refer to specific needs or features related to the type of phase plan (such as fitness, learning, games, etc.). Demand characteristics determine what aspects the virtual coach should focus on when interacting with the user and how to provide personalized guidance and suggestions. The demand characteristics corresponding to the type of phase plan can be shown as shown in Table 1. For example, for a phase plan of oral English, the demand characteristics are usually that the user cannot persist from the 10th day onwards. At this time, the virtual coach can directly guide the user to have oral conversations in daily life. For example, for a phase plan of learning, the demand characteristics are usually manifested as the existence of a learning sedimentation curve. The virtual coach can encourage the user to continue after taking a break for 2-3 days.

[0086] Table 1

[0087] Input text can be generated based on the virtual coach prompt information and the demand characteristics corresponding to the type of stage plan, and the input text is input into the virtual coach model to generate interactive text, which may include an explanation of the reason why the user has the problem and specific suggestions. The virtual coach can interact with the user in an encouraging manner based on the interactive text to ensure the smooth completion of the plan.

[0088] Figure 5 It is a flow chart of the virtual coaching model provided by the present invention, such as Figure 5 As shown in the figure, when the user inputs "Is there no way to improve my writing skills? Am I stupid?", the user actively initiates the virtual coach encouragement service. The system automatically determines that the user has not written for 4 consecutive days, and automatically supplements the relevant information based on the user input and the current status of the plan execution, and obtains the virtual coach prompt information. Then, based on the demand characteristics of the type of writing that is prone to regression in the early stage of the plan, the model outputs interactive text. The interactive text can illustrate how historical writers honed their writing skills, and enhance the user's writing confidence through specific examples.

[0089] Based on any of the above embodiments, a plan management method is provided, including: S1, determine the demand text and user personalized information.

[0090] S2, based on the expert rule model, application requirement text and user personalized information, generates the current plan, and based on the logical reasoning model and user personalized information, performs feasibility reasoning on the current plan.

[0091] If the inference result indicates that the current plan does not match the user's personalized information, the inference result is sent to the expert rule model so that the expert rule model adjusts the current plan based on the inference result; and / or, user feedback on the inference result is received, the current plan is adjusted based on the user feedback and the inference result of the current plan is adjusted until the adjusted current plan matches the user's personalized information, and the adjusted current plan is determined to be a stage plan. The expert rule model and the logical reasoning model are trained based on a large language model.

[0092] S3, manage the stage plan based on the execution of the stage plan. Specifically include: S31, based on at least one of the user interaction behavior, behavior monitoring data, and knowledge question and answer results, analyze the execution status of the stage plan to obtain the execution status; based on the changes in the user status monitoring indicators corresponding to the type of the stage plan, analyze the plan deviations separately to obtain the deviation status; based on the deviation status, update the user personalized information; based on the execution status and the updated user personalized information, adjust the stage plan.

[0093] S32, when it is determined that a virtual coach is needed based on the execution of the stage plan, or in response to user input, calling a virtual coach model for encouraging interaction, where the virtual coach model is trained based on a large language model. Calling the virtual coach model for encouraging interaction includes: Based on the execution status of the stage plan and / or user input, the virtual coach prompt information is determined; based on the virtual coach prompt information and the demand characteristics corresponding to the type of the stage plan, the virtual coach model is called to generate interactive text, and encouraging interaction is performed based on the interactive text.

[0094] The plan management device provided by the present invention is described below. The plan management device described below and the plan management method described above can be referenced to each other.

[0095] Based on any of the above embodiments, Figure 6 It is a schematic diagram of the structure of the plan management device provided by the present invention. Figure 6 As shown, the device comprises: A determination unit 610, configured to determine a demand text and user personalized information; A plan generating unit 620 is used to generate a current plan based on an expert rule model, apply the demand text and the user personalized information, perform feasibility reasoning on the current plan based on a logical reasoning model and the user personalized information, and adjust the current plan based on the reasoning result of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on the training of a large language model; The plan management unit 630 is used to manage the stage plan based on the execution status of the stage plan.

[0096] The device provided by the embodiment of the present invention generates the current plan through an expert rule model, ensuring that the best practices and potential risks in the industry can be taken into account during the plan formulation process. The personalized customization combined with the user's personalized information not only improves the satisfaction with the plan, but also enhances the user's participation. On this basis, the logical reasoning model can evaluate the feasibility of the plan, and can promptly discover and correct the unreasonable aspects of the plan to ensure the smooth execution of the plan, thereby enhancing the feasibility and reliability of the plan.

[0097] Based on any of the above embodiments, the plan generating unit is specifically used for: If the inference result indicates that the current plan does not match the user personalized information, the current plan is adjusted until the adjusted current plan matches the user personalized information, and the adjusted current plan is determined to be the stage plan.

[0098] Based on any of the above embodiments, the plan generating unit is specifically used for: If the inference result indicates that the current plan does not match the user personalized information, sending the inference result to the expert rule model so that the expert rule model adjusts the current plan based on the inference result; and / or, Receive user feedback on the inference result, and adjust the current plan based on the user feedback.

[0099] Based on any of the above embodiments, the planning management unit is specifically used for: Analyze the execution status and deviation status of the plan for the stage respectively to obtain the execution status and deviation status; Based on the deviation status, updating the user personalized information; The phase plan is adjusted based on the execution status and the updated user personalized information.

[0100] Based on any of the above embodiments, the planning management unit is specifically used for: Analyze the execution status of the phase plan based on at least one of user interaction behavior, behavior monitoring data, and knowledge question and answer results to obtain the execution status; Based on the changes in the user status monitoring indicators corresponding to the type of the phase plan, the plan deviations are analyzed respectively to obtain the deviation status.

[0101] Based on any of the above embodiments, the planning management unit is specifically used for: In the case where it is determined that a virtual coach is needed based on the execution of the stage plan, or in response to user input, a virtual coach model is called to perform encouraging interaction, and the virtual coach model is trained based on a large language model.

[0102] Based on any of the above embodiments, the planning management unit is specifically used for: Determining virtual coach prompt information based on the execution status of the stage plan and / or the user input; Based on the virtual coach prompt information and the demand characteristics corresponding to the type of the stage plan, the virtual coach model is called to generate an interactive text, and encouraging interaction is performed based on the interactive text.

[0103] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the plan management method, which includes: determining the demand text and the user personalized information; based on the expert rule model, applying the demand text and the user personalized information to generate the current plan; based on the logic reasoning model and the user personalized information, performing feasibility reasoning on the current plan, and adjusting the current plan based on the reasoning result of the current plan until a stage plan is obtained; the expert rule model and the logic reasoning model are obtained based on the training of the large language model; and managing the stage plan based on the execution of the stage plan.

[0104] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0105] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the plan management method provided by the above-mentioned methods, and the method includes: determining the demand text and user personalized information; based on the expert rule model, applying the demand text and user personalized information to generate a current plan, based on the logical reasoning model and the user personalized information, performing feasibility reasoning on the current plan, and adjusting the current plan based on the reasoning results of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on training of a large language model; and managing the stage plan based on the execution of the stage plan.

[0106] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the plan management method provided by the above-mentioned methods, the method comprising: determining a demand text and user personalized information; based on an expert rule model, applying the demand text and user personalized information to generate a current plan, based on a logical reasoning model and the user personalized information, performing feasibility reasoning on the current plan, and adjusting the current plan based on the reasoning results of the current plan until a stage plan is obtained; the expert rule model and the logical reasoning model are obtained based on training of a large language model; and managing the stage plan based on the execution of the stage plan.

[0107] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A planning management method, characterized in that: include: Determine the required text and user personalized information; Based on the expert rule model, the demand text and the user personalized information are applied to generate a current plan, based on the logical reasoning model and the user personalized information, the feasibility reasoning of the current plan is performed, and the current plan is adjusted based on the reasoning result of the current plan until a stage plan is obtained; The expert rule model and the logical reasoning model are obtained by training based on a large language model; The phase plan is managed based on the execution status of the phase plan.

2. The planning management method according to claim 1, characterized in that: The adjusting the current plan based on the inference result of the current plan until a stage plan is obtained includes: If the inference result indicates that the current plan does not match the user personalized information, the current plan is adjusted until the adjusted current plan matches the user personalized information, and the adjusted current plan is determined to be the stage plan.

3. The planning management method according to claim 2, characterized in that: If the inference result indicates that the current plan does not match the user personalized information, adjusting the current plan includes: If the inference result indicates that the current plan does not match the user personalized information, sending the inference result to the expert rule model so that the expert rule model adjusts the current plan based on the inference result; and / or, Receive user feedback on the inference result, and adjust the current plan based on the user feedback.

4. The planning management method according to any one of claims 1 to 3, characterized in that: The managing the phase plan based on the execution status of the phase plan includes: Analyze the execution status and deviation status of the plan for the stage respectively to obtain the execution status and deviation status; Based on the deviation status, updating the user personalized information; The phase plan is adjusted based on the execution status and the updated user personalized information.

5. The planning management method according to claim 4, characterized in that: The execution status and deviation status of the stage plan are analyzed respectively to obtain the execution status and deviation status, including: Analyze the execution status of the phase plan based on at least one of user interaction behavior, behavior monitoring data, and knowledge question and answer results to obtain the execution status; Based on the changes in the user status monitoring indicators corresponding to the type of the phase plan, the plan deviations are analyzed respectively to obtain the deviation status.

6. The planning management method according to any one of claims 1 to 3, characterized in that: The managing the phase plan based on the execution status of the phase plan includes: In the case where it is determined that a virtual coach is needed based on the execution of the stage plan, or in response to user input, a virtual coach model is called to perform encouraging interaction, and the virtual coach model is trained based on a large language model.

7. The planning management method according to claim 6, characterized in that: The calling of the virtual coach model for encouraging interaction includes: Determining virtual coach prompt information based on the execution status of the stage plan and / or the user input; Based on the virtual coach prompt information and the demand characteristics corresponding to the type of the stage plan, the virtual coach model is called to generate an interactive text, and encouraging interaction is performed based on the interactive text.

8. A planning management device, characterized in that: include: A determination unit, used to determine the requirement text and user personalized information; A plan generating unit, for generating a current plan based on an expert rule model, applying the demand text and the user personalized information, performing feasibility reasoning on the current plan based on a logical reasoning model and the user personalized information, and adjusting the current plan based on the reasoning result of the current plan until a stage plan is obtained; The expert rule model and the logical reasoning model are obtained by training based on a large language model; The plan management unit is used to manage the stage plan based on the execution status of the stage plan.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the planning management method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the planning management method according to any one of claims 1 to 7 is implemented.

Images