Multi-user interaction calendar management method based on artificial intelligence, medium and equipment

Abstract

The invention discloses a multi-user interaction calendar management method based on artificial intelligence, a medium and equipment, and the method comprises the steps: inputting user demand information and user preference information corresponding to each user into a trained first neural network model, and outputting first calendar travel information corresponding to each user; and inputting the first calendar itinerary information corresponding to each user, the constraint condition information and the user association relationship into a trained second neural network model, and outputting second calendar itinerary information corresponding to each user, third calendar itinerary information of other users having the association relationship with each user and total calendar itinerary information. According to the scheme, the personalized requirements of all the users can be considered, and the rationality of travel arrangement of all the associated users is considered, so that the collaborative requirements among the multiple users can be met.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation, and particularly to a multi-user interactive calendar management method, medium and device based on artificial intelligence. Background Art

[0002] In the rapid development of current information technology and artificial intelligence, the demand for multi-user schedule management is increasing day by day. However, most traditional schedule management tools are single and limited to personal use, unable to efficiently meet the collaborative needs among multiple users, and lacking the ability of personalized recommendation, unable to provide intelligent support according to users' behavior habits and events dynamically. Summary of the Invention

[0003] In view of the above problems, the present invention provides a multi-user interactive calendar management method, medium and device based on artificial intelligence to solve the problems that existing schedule management tools cannot meet the collaborative needs among multiple users and lack the ability of personalized recommendation.

[0004] To achieve the above object, in the first aspect, the present application provides a multi-user interactive calendar management method based on artificial intelligence, and the method includes the following steps:

[0005] Receiving historical schedule data of multiple users, respectively analyzing each piece of the historical schedule data to generate a calendar portrait corresponding to each user, where the calendar portrait includes user identification information, user preference information, user association relationship and user permission information;

[0006] Receiving user requirement information, inputting the user requirement information and the user preference information corresponding to each user into a trained first neural network model, and outputting first calendar schedule information corresponding to each user;

[0007] Receiving constraint condition information, inputting the first calendar schedule information corresponding to each user, the constraint condition information and the user association relationship into a trained second neural network model, and outputting second calendar schedule information corresponding to each user, third calendar schedule information of other users having an association relationship with each user, and calendar total schedule information, where the calendar total schedule information includes the second calendar schedule information and the third calendar schedule information;

[0008] Displaying any one or more of the second calendar schedule information, the third calendar schedule information or the calendar total schedule information on the user side according to the user permission information corresponding to each user.

[0009] Optionally, receiving constraint condition information, and inputting the first calendar schedule information corresponding to each user, the constraint condition information and the user association relationship into a trained second neural network model includes:

[0010] When the second neural network model after training detects that there are conflicts between the first calendar schedule information of multiple mutually related users and the constraint condition information, determine the first user group and the first schedule adjustment information according to the conflict content, send the first schedule adjustment information to the first user group, and receive the feedback information of the first user group regarding the constraint condition information or the first schedule adjustment information. Based on the feedback information, adjust the constraint condition information or the first calendar schedule information of at least one user in the first user group, and after the adjustment is completed, determine again whether there are conflicts between the first calendar schedule information of all users and the constraint condition information;

[0011] Repeat the above steps until there are no conflicts between the first calendar schedule information of all users and the constraint condition information or all users in the first user group have been traversed.

[0012] Optionally, determining the first user group and the first schedule adjustment information according to the conflict content, and sending the first schedule adjustment information to the first user group includes:

[0013] Determine the first schedule optimization problem according to the conflict content, analyze the first schedule optimization problem, and determine the first user group according to the schedule adjustment amplitude. The first user group is several users with the smallest schedule adjustment amplitude;

[0014] Generate schedule replacement options according to the user preference information of the users in the first user group, and generate the first schedule adjustment information based on the schedule replacement options and send it to the first user group.

[0015] Optionally, the method includes:

[0016] If all users in the first user group have been traversed, but there are still conflicts between the first calendar schedule information of all users and the constraint condition information, record the current conflict content;

[0017] Add the user identification information of all users associated with the current conflict content to the discussion group, and display the current conflict content and the proposed adjustment strategy for the current conflict content during the discussion.

[0018] Optionally, the user permission information includes the first permission, the second permission, or the third permission. The priority of the third permission is greater than that of the second permission, and the priority of the second permission is greater than that of the first permission;

[0019] Displaying any one or more of the second calendar schedule information, the third calendar schedule information, or the total calendar schedule information on the user side according to the user permission information corresponding to each user includes:

[0020] When the user permission information is the first permission, display the second calendar itinerary information corresponding to the user on the user side;

[0021] When the user permission information is the second permission, display the second calendar itinerary information or the third calendar itinerary information corresponding to the user on the user side according to the received first itinerary switching instruction;

[0022] When the user permission information is the third permission, display the second calendar itinerary information, the third calendar itinerary information, or the total calendar itinerary information corresponding to the user on the user side according to the received second itinerary switching instruction. When displaying the total calendar itinerary information on the user side, highlight the calendar itinerary information corresponding to the current user in the total calendar itinerary information.

[0023] Optionally, the user demand information includes any one or more of the number of people information, budget information, time span information, geographical location information, activity theme type information, and activity priority information;

[0024] The constraint condition information includes any one or more of time constraint conditions, resource-related constraint conditions, resource-related constraint conditions, or itinerary theme constraint conditions.

[0025] Optionally, the method further includes:

[0026] Store the generated total calendar itinerary information in the first public storage space of the server, and store the generated second calendar itinerary information or third calendar itinerary information in the second public storage space of the server;

[0027] When receiving a first modification request from the user side, after the permission verification of the current user passes, generate a second calendar itinerary copy information based on the second calendar itinerary information, or generate a third calendar itinerary copy information based on the third calendar itinerary information, send the second calendar itinerary copy information or the third calendar itinerary copy information to the user side, and receive the modified second calendar itinerary copy information or third calendar itinerary copy information uploaded by the current user side. Determine whether there are conflicts in the itinerary information of each user in the modified third calendar itinerary copy information. If not, generate a first log information according to the content of this modification and the user identification information of the initiator of the modification;

[0028] When a second modification request from the client is received, after the permission verification of the current user passes, generate a copy of the calendar total itinerary information based on the calendar total itinerary information, send the copy of the calendar total itinerary information to the client, and receive the modified second copy of the calendar total itinerary information uploaded by the current client. Determine whether there are conflicts in the itinerary information of each user in the modified second copy of the calendar total itinerary information. If not, generate a new second calendar itinerary information and a new third calendar itinerary information based on the current copy of the calendar total itinerary information, update the new second calendar itinerary information and the new third calendar itinerary information to the second public storage space of the server, and generate a second log information according to the content of this modification and the user identification information of the initiator of the modification.

[0029] Optionally, the first neural network model is trained in the following manner:

[0030] Obtain a first sample data set, where the first sample data set includes sample user demand information and sample user preference information;

[0031] Perform data augmentation on the first sample data set, and randomly permute and combine the first sample data in the augmented first sample data set to obtain multiple groups of first test cases;

[0032] Input multiple groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model.

[0033] The second neural network model is trained in the following manner:

[0034] Obtain a second sample data set, where the second sample data set includes sample user association relationships, sample constraint condition information, and the first calendar itinerary information output by the trained first neural network model;

[0035] Perform data augmentation on the second sample data set, and randomly permute and combine the second sample data in the augmented second sample data set to obtain multiple groups of second test cases;

[0036] Input multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain a trained second neural network model.

[0037] In a second aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the multi-user interactive calendar management method based on artificial intelligence as described in the first aspect of the present application.

[0038] In a third aspect, the present application provides an electronic device with a computer program stored thereon, including a processor and a storage medium. The storage medium stores a computer program, and when the computer program is executed by the processor, it implements the multi-user interactive calendar management method based on artificial intelligence as described in the first aspect of the present application.

[0039] Different from the prior art, the above technical solution provides a multi-user interactive calendar management method, medium and device based on artificial intelligence. The method includes: receiving historical schedule data of multiple users, generating a calendar portrait corresponding to each user, where the calendar portrait includes user identification information, user preference information, user association relationship, and user permission information; inputting user requirement information and the user preference information corresponding to each user into a trained first neural network model to output the first calendar schedule information corresponding to each user; inputting the first calendar schedule information corresponding to each user, constraint condition information, and user association relationship into a trained second neural network model to output the second calendar schedule information corresponding to each user, the third calendar schedule information of other users having an association relationship with each user, and a calendar total schedule information, where the calendar total schedule information includes the second calendar schedule information and the third calendar schedule information. The generated second calendar schedule information and calendar total schedule information can not only take into account the personalized needs of each user, but also consider the rationality of the schedule arrangements of each associated user, so as to meet the collaborative needs among multiple users.

[0040] The above description of the invention content is only an overview of the technical solution of the present invention. In order to enable those of ordinary skill in the art to more clearly understand the technical solution of the present invention, and then to implement it according to the content recorded in the description and the drawings, and in order to make the above objects, other objects, features, and advantages of the present invention more easily understood, the following description is made in conjunction with the specific embodiments and drawings of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings are only used to illustrate the principles, implementation methods, applications, features, and effects of the specific embodiments of the present invention and other related contents, and should not be considered as a limitation to the present invention.

[0042] In the accompanying drawings of the specification:

[0043] Figure 1 It is the first flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific embodiment;

[0044] Figure 2 It is the second flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific embodiment;

[0045] Figure 3It is the third flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0046] Figure 4 It is the fourth flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0047] Figure 5 It is the fifth flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0048] Figure 6 It is the sixth flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0049] Figure 7 It is the seventh flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0050] Figure 8 It is the eighth flowchart of the multi-user interactive calendar management method based on artificial intelligence involved in the specific implementation manner;

[0051] Figure 9 It is the module schematic diagram of the electronic device described in the specific implementation manner;

[0052] The descriptions of the reference numerals involved in the above-mentioned various drawings are as follows:

[0053] 10. Electronic device;

[0054] 101. Processor;

[0055] 102. Storage medium. Specific implementation manner

[0056] To describe in detail the possible application scenarios, technical principles, specific implementable solutions, achievable purposes and effects of the present invention, etc., the following is described in detail in conjunction with the listed specific examples and with reference to the drawings. The examples recorded in this article are only used to more clearly illustrate the technical solutions of the present invention, so they are only used as examples and cannot be used to limit the protection scope of the present invention.

[0057] Referring to "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present invention. The term "embodiment" appearing in various positions in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in the present invention, as long as there is no technical contradiction or conflict, the technical features mentioned in each embodiment can be combined in any way to form the corresponding implementable technical solutions.

[0058] Unless otherwise defined, the meanings of the technical terms used herein are the same as those commonly understood by those skilled in the technical field to which the present invention pertains; the use of the relevant terms herein is only for describing specific embodiments and is not intended to limit the present invention.

[0059] In the description of the present invention, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that there can be three relationships. For example, A and / or B means: there is A, there is B, and there is both A and B at the same time. In addition, the character " / " herein generally represents an "or" logical relationship between the associated objects before and after.

[0060] In the present invention, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantitative, primary-secondary, or sequential relationship between these entities or operations.

[0061] Without further limitation, in the present invention, the expressions such as "comprising", "including", "having", or other similar expressions used in a statement are intended to cover non-exclusive inclusion. These expressions do not exclude that there may be additional elements in the process, method, or product including the said elements, so that a process, method, or product including a series of elements may not only include those defined elements, but also include other elements not explicitly listed, or also include elements inherent to such a process, method, or product.

[0062] In the present invention, expressions such as "greater than", "less than", "exceeding", etc. are understood not to include the number itself; expressions such as "above", "below", "within", etc. are understood to include the number itself. In addition, in the description of the embodiments of the present invention, the meaning of "multiple" is two or more (including two), and similar expressions related to "many", such as "multiple groups", "multiple times", etc., are understood in the same way, unless otherwise specifically defined.

[0063] In the description of the embodiments of the present invention, the spatially related expressions used, such as "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "perpendicular", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiment or the drawing. It is only for the convenience of describing the specific embodiments of the present invention or facilitating the understanding of the reader, and does not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, it cannot be understood as a limitation to the embodiments of the present invention.

[0064] Unless otherwise clearly specified or limited, in the description of the embodiments of the present invention, the terms "installed", "connected", "linked", "fixed", "set", etc. shall be understood in a broad sense. For example, the "connection" may be a fixed connection, a detachable connection, or an integral setting; it may be a mechanical connection, an electrical connection, or a communication connection; it may be directly connected, or indirectly connected through an intermediate medium; it may be the communication between two components or the interaction relationship between two components. For those skilled in the art to which the present invention pertains, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0065] As Figure 1 shown, in a first aspect, the present application provides a multi-user interaction calendar management method based on artificial intelligence, and the method includes the following steps:

[0066] Step S101: Receive historical schedule data of multiple users, analyze each piece of the historical schedule data respectively, and generate a calendar portrait corresponding to each user, where the calendar portrait includes user identification information, user preference information, user association relationship, and user permission information.

[0067] In step S101, the historical schedule data usually includes time information and event information, and the event information refers to the tasks that the user needs to perform at a certain time point or time period.

[0068] Step S102: Receive user demand information, input the user demand information and the user preference information corresponding to each user into the trained first neural network model, and output the first calendar schedule information corresponding to each user.

[0069] In step S102, the user's demand information can be input in ways such as text, voice, imported template, etc. For example, the user's demand information can be a piece of text, such as "Learning arrangements for next week, referring to past historical data". After receiving this piece of text, the first neural network model will generate the corresponding learning plan arrangement for the user next week, that is, the first calendar schedule information, based on the user's historical preference information (such as the proportion of past learning plans and rest, the distribution of time periods, etc.).

[0070] In some embodiments, the user requirement information includes any one or more of the number of people information, budget information, time span information, geographical location information, activity theme type information, and activity priority information. For example, a certain user can input by voice "Arrange a travel plan for XX City for 2 - 3 days, with at least 2 hours of meeting time per day during the itinerary", then the first neural network model will take into account the user preference information of each user (such as favorite snacks, favorite items to play, etc.), and combine the characteristics of the city to generate a preliminary calendar itinerary arrangement for each user, that is, the first calendar itinerary information.

[0071] Step S103: Receive the constraint condition information, input the first calendar itinerary information, constraint condition information, and user association relationship corresponding to each user into the trained second neural network model, and output the second calendar itinerary information corresponding to each user, the third calendar itinerary information of other users associated with each user, and the calendar total itinerary information, where the calendar total itinerary information includes the second calendar itinerary information and the third calendar itinerary information.

[0072] In some embodiments, the constraint condition information includes any one or more of time constraint conditions, resource - related constraint conditions, or itinerary theme constraint conditions.

[0073] For example, for a meeting itinerary that requires multiple people to participate, and the budgets and preference information of different users are different. This leads to some users wanting to rest more, some users wanting to visit more scenic spots, some users wanting to visit more cultural landscapes, and some users wanting to visit more natural landscapes. As a result, it is necessary to integrate the first calendar itinerary information of multiple users to ensure that there are no time conflicts when multiple users complete some public itineraries, and at the same time, as much as possible, take into account the personal preferences of each user. Therefore, the second neural network model will generate corresponding adjustment factors based on the constraint condition information and the first calendar itinerary information. The adjustment factors can adjust the time sequence and itinerary content (preferably the replacement of the same itinerary theme) of some of the users' itineraries. Then, based on the adjustment factors, the first calendar itinerary information of each user is adjusted to obtain the second calendar itinerary information, the third calendar itinerary information, and the calendar total itinerary information corresponding to each user.

[0074] Step S104: Display any one or more of the second calendar itinerary information, the third calendar itinerary information, or the calendar total itinerary information on the user side according to the user permission information corresponding to each user.

[0075] The above solution first generates user portraits for each user based on their historical schedule data, then generates preliminary itinerary arrangements for each user based on the user's demand information and preferences, and then selects a part of the users based on the correlation relationships of each user's actions (such as corporate team building, family outings, etc.) and constraint conditions (considering the different budgets and preferences of each user), and adjusts the first calendar itinerary information of this part of the users to obtain the adjusted calendar itinerary information. Specifically, it includes the second calendar itinerary information, the third calendar itinerary information, and the total calendar itinerary information. For example, if the users with correlation relationships include User A, User B, and User C, then for User A, if User A has sufficient permissions, then in addition to being able to obtain and view its own second calendar itinerary information, it can also view the third calendar itinerary information (including the second calendar itinerary information of User B or User C) and the total calendar itinerary information (including the calendar itinerary information of User A, User B, and User C). The total calendar itinerary information generated by the method of the present application can not only take into account the personalized needs of each user, but also consider the rationality of the itinerary arrangements of each associated user, so that it can meet the collaborative needs among multiple users.

[0076] Historical schedule data, and analyze each of the historical schedule data to generate a calendar portrait corresponding to each user

[0077] In some embodiments, such as Figure 2 shown, receiving constraint condition information, and inputting the first calendar itinerary information, constraint condition information, and user correlation relationship corresponding to each user into the trained second neural network model includes:

[0078] Step S201: When the trained second neural network model detects that there is a conflict between the first calendar itinerary information of multiple mutually associated users and the constraint condition information, determine the first user group and the first itinerary adjustment information according to the conflict content, send the first itinerary adjustment information to the first user group, and receive the feedback information of the first user group regarding the constraint condition information or the first itinerary adjustment information, adjust the constraint condition information or the first calendar itinerary information of at least one user in the first user group based on the feedback information, and after the adjustment is completed, determine again whether there is a conflict between the first calendar itinerary information of all users and the constraint condition information;

[0079] Step S202: Repeat the above steps until there is no conflict between the first calendar itinerary information of all users and the constraint condition information or all the users in the first user group have been traversed.

[0080] Further, such as Figure 3As shown in the figure, determining the first user group and the first trip adjustment information according to the conflict content, and sending the first trip adjustment information to the first user group includes:

[0081] Step S301: Determine the first trip optimization problem according to the conflict content, analyze the first trip optimization problem, and determine the first user group according to the trip adjustment range. The first user group is several users with the smallest trip adjustment range.

[0082] Step S302: Generate trip replacement options according to the user preference information of the users in the first user group, generate the first trip adjustment information based on the trip replacement options, and send it to the first user group.

[0083] In this embodiment, when it is detected that there is a conflict between the calendar trip information of a certain user and the constraint condition information, the first trip adjustment information can be generated, feedback can be sent to the users in a specific group, asking whether these users are willing to adjust their trip arrangements, and after adjusting the first calendar trip information of the users according to the feedback information, the judgment of whether there is a conflict is made again. Preferably, in order to save computing power and improve the adjustment speed, an equation is established based on the constraint problem, and the first trip adjustment information is preferentially sent to the users with the smallest adjustment range. If the feedback result shows that the user does not accept the adjustment arrangement of the first trip adjustment information, the first trip adjustment information will be sent to the users with the next smallest adjustment range, and so on, until there is no conflict between the first calendar trip information of all users and the constraint condition information or all the users in the first user group are traversed.

[0084] Of course, in some other embodiments, priority levels can also be marked for each user. Then, every time the first user group needs to be determined, a score can be given to each user, and the score depends on the user's priority level and the adjustment range. The higher the user's priority level, the greater the impact of the user on a certain trip arrangement, and the lower the probability of being adjusted. The smaller the user's adjustment range, the smaller the correction amount that can make the first calendar trip information of all users conflict-free with the constraint condition information if the user's trip is adjusted. This solution considers the importance of each user to a certain trip event and the adjustment range, and comprehensively determines the first user group, which can make the adjustment of the trip information more targeted and meet the diverse application scenario requirements.

[0085] In some embodiments, as Figure 4 shown, the method includes:

[0086] Step S401: If all the users in the first user group have been traversed, but there is still a conflict between the first calendar trip information of all users and the constraint condition information, record the current conflict content.

[0087] Step S402: Add all user identification information associated with the current conflict content to the discussion group, and display the current conflict content and the proposed adjustment strategy for the current conflict content in the discussion.

[0088] In short, if all users in the first user group have been traversed, but there are still conflicts between all users' first calendar schedule information and the constraint condition information, it means that there are unreasonable aspects in this schedule arrangement. The reason may be that there are significant differences and distinctions in the preference information or choices of at least two users, and the schedule arrangement cannot take into account the needs of all users in every aspect. Therefore, in response to this situation, the system will automatically establish a discussion group and add all users related to resolving the current conflict content to the discussion group so that multiple parties can discuss solutions in the discussion group. The conflict content refers to conflicting time points or schedule arrangements, as well as the schedule tendencies of each user at this time point.

[0089] In some embodiments, the method further includes: receiving feedback content from each user in the discussion group regarding the proposed adjustment strategy, generating adjustment strategy confirmation information based on this feedback content, and after all relevant users in the discussion group have confirmed without error, adjusting and updating the first calendar schedule information of the relevant users based on the confirmed adjustment strategy confirmation information, so as to output second calendar schedule information that conforms to the constraint condition information through the second neural network model.

[0090] In some embodiments, the user permission information includes a first permission, a second permission, or a third permission, the priority of the third permission is greater than that of the second permission, and the priority of the second permission is greater than that of the first permission;

[0091] Displaying any one or more of the second calendar schedule information, the third calendar schedule information, or the total calendar schedule information on the user side according to the user permission information corresponding to each user includes:

[0092] When the user permission information is the first permission, display the second calendar schedule information corresponding to the user on the user side;

[0093] When the user permission information is the second permission, display the second calendar schedule information or the third calendar schedule information corresponding to the user on the user side according to the received first schedule switching instruction;

[0094] When the user permission information is the third permission, display the second calendar schedule information, the third calendar schedule information, or the total calendar schedule information corresponding to the user on the user side according to the received second schedule switching instruction. When displaying the total calendar schedule information on the user side, highlight the calendar schedule information corresponding to the current user in the total calendar schedule information.

[0095] In short, for the overall calendar itinerary information of individuals, relevant users, and all users, different user permissions can be attached to different users, and users with different permissions can view different types of calendar itinerary information on their own user terminals. For example, during a family gathering, all family members can view each other's calendar itinerary information and the overall calendar itinerary information. In the enterprise business field, each grass-roots employee of the enterprise is only given the permission to view the second calendar itinerary information corresponding to the individual, while the third calendar itinerary information or the overall calendar itinerary information needs to be viewed by the middle and senior employees of the enterprise.

[0096] In some embodiments, as Figure 5 shown, the method further includes:

[0097] Step S501: Store the generated overall calendar itinerary information in the first public storage space of the server, and store the generated second calendar itinerary information or third calendar itinerary information in the second public storage space of the server;

[0098] After step S501, step S502 can be entered: When a first modification request from the user terminal is received, after the permission verification of the current user passes, generate a second calendar itinerary copy information based on the second calendar itinerary information, or generate a third calendar itinerary copy information based on the third calendar itinerary information, send the second calendar itinerary copy information or the third calendar itinerary copy information to the user terminal, and receive the modified second calendar itinerary copy information or third calendar itinerary copy information uploaded by the current user terminal, and determine whether there are conflicts in the itinerary information of each user in the modified third calendar itinerary copy information. If not, generate a first log information according to the content of this modification and the user identification information of the user who initiated the modification;

[0099] After step S501, step S503 can also be entered: When a second modification request from the user terminal is received, after the permission verification of the current user passes, generate an overall calendar itinerary copy information based on the overall calendar itinerary information, send the overall calendar itinerary copy information to the user terminal, and receive the modified second overall calendar itinerary copy information uploaded by the current user terminal, and determine whether there are conflicts in the itinerary information of each user in the modified overall calendar itinerary copy information. If not, generate new second calendar itinerary information and new third calendar itinerary information according to the current overall calendar itinerary copy information, update the new second calendar itinerary information and the new third calendar itinerary information to the second public storage space of the server, and generate a second log information according to the content of this modification and the user identification information of the user who initiated the modification.

[0100] In this embodiment, the total calendar itinerary information is stored in the public storage space of the server as the calendar itinerary information of all associated users, and specific permissions are required for access. The second calendar itinerary information or the third calendar itinerary information is separately stored in another public storage space of the server. Generally, users can only obtain the second calendar itinerary information related to themselves, and users with higher permissions can further access the third calendar itinerary information or even the total calendar itinerary information.

[0101] For the convenience of traceability, when the calendar itinerary information is accessed each time, the server sends it to the user terminal in the form of generating a corresponding copy. And if a user has a very high permission level, they can also modify the calendar itinerary information of other users. Specifically, they can directly retrieve the calendar itinerary information or the total calendar itinerary information of a certain user for modification. Of course, the second neural network model will real-time verify whether the modified itinerary arrangement meets the current constraint condition information to remind the user exercising the modification permission whether they need to further adjust the itinerary information or modify the current constraint condition information so that the adjusted itinerary information meets the requirements of the constraint condition information. And for each modification of each user, corresponding log information will be generated for recording. The log information will not only record the modified content but also record the identification information of the modifier, thus facilitating traceability. The original calendar itinerary information is still stored in the first public storage space or the second public storage space of the server, which is convenient for recovery in case of user misoperation.

[0102] In some embodiments, as Figure 6 shown, the first neural network model is trained according to the following method:

[0103] Step S601: Obtain a first sample data set, where the first sample data set includes sample user demand information and sample user preference information;

[0104] Step S602: Perform data augmentation on the first sample data set, and randomly arrange and combine the first sample data in the augmented first sample data set to obtain multiple groups of first test cases;

[0105] Step S603: Input multiple groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model;

[0106] As Figure 7 shown, the second neural network model is trained according to the following method:

[0107] Step S701: Obtain a second sample data set, where the second sample data set includes sample user association relationships, sample constraint condition information, and first calendar schedule information output by the trained first neural network model;

[0108] Step S702: Perform data augmentation on the second sample data set, and randomly permute and combine the second sample data in the augmented second sample data set to obtain multiple groups of second test cases;

[0109] Step S703: Input multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain the trained second neural network model.

[0110] In this embodiment, the first neural network model or the second neural network model can be a convolutional neural network (CNN) or a recurrent neural network (RNN) and its variants (such as LSTM, GRU).

[0111] As Figure 8 shown, in some embodiments, the present application also realizes personalized schedule recommendation and conflict optimization by introducing an AI algorithm: constructing a dynamic user portrait through the fusion of multi-modal data (such as historical schedules, user preferences, context data), and adopting deep reinforcement learning (PPO) to realize personalized schedule recommendation, specifically including: defining a state space (user schedule state), an action space (event insertion, adjustment), and a reward function (time utilization rate, user satisfaction).

[0112] For conflict optimization, the present application models schedule conflicts as a dynamic multi-objective optimization problem, and combines reinforcement learning with meta-heuristic algorithms (such as adaptive genetic algorithms) to dynamically adjust the schedule arrangement. Introduce federated learning to protect user privacy, and synergistically optimize performance through edge-side inference and cloud training to achieve an efficient and intelligent solution for personalized recommendation and conflict optimization.

[0113] In addition, when the present application also collects user demand information or constraint condition information, it also integrates multi-modal interaction methods, including voice input or image input. Specifically, multi-modal deep learning technology can be used to construct an integrated interaction model for voice and image input. Voice input data parses semantic information through a pre-trained Transformer model (such as Whisper) to extract time, location, and event descriptions; image input data is jointly processed by an OCR and a vision Transformer (ViT) model to identify handwritten, printed text, or scene features and match the schedule context. The present application innovatively introduces cross-modal alignment technology (such as CLIP) to generate a unified semantic embedding space to achieve high-precision fusion and consistency verification of multi-modal data. Combine reinforcement learning to dynamically optimize the input parsing strategy, and deploy an edge-cloud collaborative architecture to achieve low-latency and high-reliability personalized schedule event creation.

[0114] The computational complexity of the above embodiments is as follows:

[0115] (1) Date and time parsing: Complexity formula: O(n), where n is the length of the string to be parsed;

[0116] (2) Time zone conversion: Complexity formula: O(1), constant-time operation;

[0117] (3) Repeated rule calculation: Complexity formula O(m), where n is the number of rule matches;

[0118] (4) Comparison complexity: Complexity formula O(y), where n is the number of comparisons;

[0119] Overall complexity: T = O(n) + O(1) + O(m) + O(y).

[0120] Example: Calculate the events of a year, looping through each day;

[0121] Time complexity: O(n);

[0122] 1. Among them, n is the total number of days in a year including leap years;

[0123] 2. The operations in each loop are constant-time operations, so the complexity is linearly proportional to the number of days;

[0124] 3. The overall loop process can be expressed as:

[0125] Number of loops n (number of days in a year);

[0126] The computational operation for each loop is O(1);

[0127] The complexity of the entire loop can be comprehensively expressed as:

[0128] T = O(n) × O(1) = O(n) T = O(n) × O(1) = O(n).

[0129] In a second aspect, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the multi-user interactive calendar management method based on artificial intelligence as described in the first aspect of the present invention.

[0130] Among them, the computer-readable storage medium can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0131] The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD ROM); the magnetic surface memory may be a disk memory or a tape memory.

[0132] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as a static random access memory (SRAM), a synchronous static random access memory (SSRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a sync link dynamic random access memory (SLDRAM), a direct rambus random access memory (DRRAM). The computer-readable storage medium described in embodiments of the present invention is intended to include these and any other suitable types of memory.

[0133] As Figure 9 shown, in a third aspect, the present invention provides an electronic device 10, including a processor 101 and a storage medium 102, where a computer program is stored on the storage medium, and when the computer program is executed by the processor, it implements the artificial intelligence-based multi-user interactive calendar management method as described in the first aspect of the present invention.

[0134] In some embodiments, the processor can be implemented by software, hardware, firmware, or a combination thereof, and can use a circuit, one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), central processing units (CPUs), controllers, microcontrollers, microprocessors, etc., so that the processor can execute some steps, all steps, or any combination of the steps in the artificial intelligence-based multi-user interactive calendar management method described in the various embodiments of the present application.

[0135] Finally, it should be noted that although the above embodiments have been described in the text of the specification and drawings of the present application, the patent protection scope of the present application cannot be limited thereby. Any technical solutions obtained by equivalent structure or equivalent process substitution or modification based on the substantial concept of the present application and using the content recorded in the text of the specification and drawings of the present application, as well as those directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are all included in the patent protection scope of the present application.

Claims

1. A multi-user interactive calendar management method based on artificial intelligence, characterized in that: The method comprises the following steps: Receive historical schedule data of multiple users, analyze each of the historical schedule data respectively, and generate a calendar portrait corresponding to each user, wherein the calendar portrait includes user identification information, user preference information, user association relationship and user authority information; Receive user demand information, input the user demand information and user preference information corresponding to each user into a trained first neural network model, and output first calendar itinerary information corresponding to each user; receiving constraint information, inputting first calendar itinerary information corresponding to each user, constraint information, and user association relationship into a trained second neural network model, and outputting second calendar itinerary information corresponding to each user, third calendar itinerary information of other users who have an association relationship with each user, and total calendar itinerary information, wherein the total calendar itinerary information includes the second calendar itinerary information and the third calendar itinerary information; Any one or more of the second calendar itinerary information, the third calendar itinerary information or the total calendar itinerary information is displayed on the user terminal according to the user authority information corresponding to each user.

2. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 1, characterized in that: Receiving constraint information and inputting the first calendar itinerary information, constraint information, and user association relationship corresponding to each user into the trained second neural network model includes: When the trained second neural network model detects that the first calendar itinerary information of multiple mutually related users conflicts with the constraint information, the first user group and the first itinerary adjustment information are determined according to the conflict content, the first itinerary adjustment information is sent to the first user group, and feedback information from the first user group regarding the constraint information or the first itinerary adjustment information is received, the constraint information or the first calendar itinerary information of at least one user in the first user group is adjusted based on the feedback information, and after the adjustment is completed, it is determined again whether the first calendar itinerary information of all users conflicts with the constraint information; The above steps are repeated until there is no conflict between the first calendar itinerary information of all users and the constraint condition information or all users in the first user group are traversed.

3. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 2, characterized in that: Determining a first user group and first itinerary adjustment information according to the conflict content, and sending the first itinerary adjustment information to the first user group includes: Determine a first itinerary optimization problem according to the conflict content, analyze the first itinerary optimization problem, and determine a first user group according to the itinerary adjustment range, wherein the first user group is a number of users with the smallest itinerary adjustment range; Generate itinerary replacement options according to user preference information of users in the first user group, generate first itinerary adjustment information based on the itinerary replacement options, and send the information to the first user group.

4. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 2, characterized in that: The method comprises: If all users in the first user group have been traversed, but the first calendar itinerary information of all users still conflicts with the constraint information, then the current conflicting content is recorded; All user identification information associated with the current conflicting content is added to the discussion group, and the current conflicting content and the suggested adjustment strategy for the current conflicting content are displayed in the discussion.

5. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 1, characterized in that: The user authority information includes a first authority, a second authority or a third authority, the third authority has a higher priority than the second authority, and the second authority has a higher priority than the first authority; Displaying any one or more of the second calendar itinerary information, the third calendar itinerary information or the total calendar itinerary information on the user terminal according to the user authority information corresponding to each user includes: When the user authority information is the first authority, displaying the second calendar itinerary information corresponding to the user on the user terminal; When the user authority information is the second authority, displaying the second calendar itinerary information or the third calendar itinerary information corresponding to the user on the user terminal according to the received first itinerary switching instruction; When the user authority information is the third authority, the second calendar itinerary information or the third calendar itinerary information or the total calendar itinerary information corresponding to the user is displayed on the user end according to the received second itinerary switching instruction. When the total calendar itinerary information is displayed on the user end, the calendar itinerary information corresponding to the current user is highlighted in the total calendar itinerary information.

6. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 1, characterized in that: The user demand information includes any one or more of personnel quantity information, budget information, time span information, geographic location information, activity theme type information, and activity priority information; The constraint information includes any one or more of time constraints, resource-related constraints, resource-related constraints or itinerary theme constraints.

7. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 1, characterized in that: The method further comprises: The generated calendar total travel information is stored in a first public storage space of the server, and the generated second calendar travel information or third calendar travel information is stored in a second public storage space of the server; When receiving a first modification request from the user terminal, after the authority check of the current user is passed, generating second calendar itinerary copy information based on the second calendar itinerary information, or generating third calendar itinerary copy information based on the third calendar itinerary information, sending the second calendar itinerary copy information or the third calendar itinerary copy information to the user terminal, and receiving the modified second calendar itinerary copy information or the third calendar itinerary copy information uploaded by the current user terminal, determining whether there is a conflict in itinerary information of each user in the modified third calendar itinerary copy information, and if not, generating first log information according to the content of this modification and the user identification information initiating the modification; When a second modification request is received from the user end, after the permission check of the current user is passed, a calendar total itinerary copy information is generated based on the calendar total itinerary information, the calendar total itinerary copy information is sent to the user end, and the modified second calendar total itinerary copy information uploaded by the current user end is received, and it is determined whether there is a conflict in the itinerary information of each user in the modified calendar total itinerary copy information. If not, new second calendar itinerary information and new third calendar itinerary information are generated according to the current calendar total itinerary copy information, the new second calendar itinerary information and new third calendar itinerary information are updated to the second public storage space of the server end, and second log information is generated according to the content of this modification and the user identification information that initiated the modification.

8. The multi-user interactive calendar management method based on artificial intelligence as claimed in claim 1, characterized in that: The first neural network model is trained according to the following method: Acquire a first sample data set, where the first sample data set includes sample user demand information and sample user preference information; Performing data expansion on the first sample data set, and randomly arranging and combining the first sample data in the expanded first sample data set to obtain multiple groups of first test cases; Inputting multiple groups of the first test cases into the first neural network model to be trained for iterative training to obtain a trained first neural network model; The second neural network model is trained according to the following method: Acquire a second sample data set, where the second sample data set includes sample user association relationships, sample constraint information, and first calendar itinerary information output by the trained first neural network model; Performing data expansion on the second sample data set, and randomly arranging and combining the second sample data in the expanded second sample data set to obtain multiple groups of second test cases; Input multiple groups of the second test cases into the second neural network model to be trained for iterative training to obtain a trained second neural network model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the artificial intelligence-based multi-user interactive calendar management method as described in any one of claims 1 to 8 is implemented.

10. An electronic device having a computer program stored thereon, characterized in that: It comprises a processor and a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by the processor, the multi-user interactive calendar management method based on artificial intelligence as described in any one of claims 1 to 8 is implemented.

Images