A method, apparatus, device, medium, and product for generating schedule information.

Abstract

This invention discloses a method, apparatus, device, medium, and product for generating schedule information. It relates to the field of artificial intelligence and can be used in the fintech field. The method includes: acquiring a target image set; performing character recognition on each target image in the target image set based on an optical character recognition model to obtain target schedules that match each target image; and processing each target schedule using a pre-trained artificial intelligence model to obtain a target schedule matching the target image set. Through the technical solution of this invention, the automatic generation of office schedules can be achieved, improving the efficiency of office schedule generation and thus enhancing the efficiency of office work processing. It avoids various repetitive tasks and the introduction of human error during manual operation, and to a certain extent, reduces redundant consumption of computer resources.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence and can be used in the field of financial technology, particularly to a method, apparatus, device, medium, and product for generating schedule information. Background Technology

[0002] In the course of continuous social development, artificial intelligence (AI) has deeply integrated into various fields. The fusion of office automation and AI is leading a disruptive transformation of traditional office models, significantly impacting office efficiency. Traditional office automation systems primarily focus on process standardization and mechanized task processing. However, with the intervention of AI technology, office automation systems are being upgraded to "intelligent office hubs." Leveraging natural language processing technology, AI can automatically extract key points from meetings and generate meeting minutes; simultaneously, based on machine learning, AI can also generate personalized work schedules according to different office scenarios, acting as an intelligent assistant.

[0003] However, traditional scheduling methods rely heavily on manual processes, which exposes several pain points. First, information fragmentation is a serious problem; transaction data is scattered across different systems such as office automation systems, email, and meetings, requiring employees to manually check each platform, easily leading to the omission of critical matters. Second, reminders are delayed; for important milestones such as meeting starts and project milestones, manual reminder settings fail to automatically link with transaction data, potentially causing missed crucial moments. Third, operational efficiency is low; employees must frequently switch between different systems to record schedules, significantly impacting work efficiency. Existing calendar reminder tools only support manual input of schedule information and cannot automatically link all office operation data, failing to meet actual needs. Furthermore, single-system notification functions like email reminders lack integration of global information and cannot achieve intelligent alerts for cross-platform transactions.

[0004] In summary, existing methods for generating office schedules have limitations, including the inability to generate them automatically, the introduction of excessive manpower costs leading to low efficiency and long generation times. Summary of the Invention

[0005] This invention provides a method, apparatus, device, medium, and product for generating schedule information, which can solve the problems of existing methods for generating office schedules, such as the inability to automatically generate office schedules, low efficiency in generating office schedules, and long generation time.

[0006] In a first aspect, embodiments of the present invention provide a method for generating schedule information, the method comprising:

[0007] Obtain the target image set;

[0008] Based on the optical character recognition model, character recognition is performed on each target image in the target image set to obtain the target schedule that matches each target image respectively;

[0009] Each target schedule is processed by a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0010] Secondly, embodiments of the present invention provide a schedule information generation apparatus, the apparatus comprising:

[0011] The image acquisition module is used to acquire the target image set;

[0012] The character recognition module is used to perform character recognition on each target image in the target image set based on the optical character recognition model, and obtain the target schedule that matches each target image respectively.

[0013] The schedule generation module is used to process each target schedule using a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0014] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for generating schedule information according to any embodiment of the present invention.

[0018] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute a method for generating schedule information as described in any embodiment of the present invention.

[0019] Fifthly, embodiments of the present invention provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements a method for generating schedule information as described in any embodiment of the present invention.

[0020] The technical solution of this invention acquires a target image set, then performs character recognition on each target image in the target image set based on an optical character recognition model to obtain a target schedule that matches each target image. Finally, a pre-trained artificial intelligence model processes each target schedule to obtain a target schedule that matches the target image set. This solves the problems of existing office schedule generation methods, such as the inability to automatically generate office schedules, low efficiency in generating office schedules, and long processing time. It realizes the automatic generation of office schedules, improves the efficiency of office schedule generation, avoids various repetitive tasks and human errors introduced by manual operation, and also reduces the redundant consumption of computer resources to a certain extent.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a method for generating schedule information according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of a method for generating schedule information according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of a schedule information generation device according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a method for generating schedule information according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, any variations of the terms "comprising" and "having" are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a method for generating schedule information according to Embodiment 1 of the present invention. This embodiment is applicable to the automatic generation of office schedules. The method can be executed by a schedule information generation device, which can be implemented in hardware and / or software. The schedule information generation device can be configured in a terminal or server with schedule information generation function.

[0031] like Figure 1 As shown, the method includes:

[0032] S110. Obtain the target image set.

[0033] The target images include: an office system interface, an email system interface, a conference system interface, and an office document interface.

[0034] Specifically, the office system interface refers to the user interface of the system used within an enterprise to handle standardized office processes and manage office affairs. These systems typically have functions such as form submission, workflow approval, and task assignment, and the interface includes key information such as task type, processing status, time requirements, and operation buttons. The email system interface refers to the interface displayed by the client or web-based system used by employees to send, receive, and manage emails, including key data related to email transactions such as email subject, sender, recipient, email content, attachment information, and email status (e.g., read, unread, urgent). The meeting system interface refers to the user interface of the software system used to organize, convene, and participate in online meetings, including information related to meeting transactions such as meeting topic, meeting time, participant list, meeting agenda, and meeting control buttons. The office document interface refers to the file content interface displayed by the software used by employees to create, edit, and view various office documents, including information related to document processing such as document title, file content, editing status, and save time.

[0035] S120. Based on the optical character recognition model, character recognition is performed on each target image in the target image set to obtain the target schedule that matches each target image.

[0036] S130. Process each target schedule using a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0037] The target schedule includes the transaction category and key parameter information, which includes time information and keyword information.

[0038] The process involves processing each target schedule using a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set. This includes: sorting each target schedule according to the time information in the key parameter information of each target schedule to obtain a target schedule sequence; processing the keyword information in the key parameter information of each target schedule using a pre-trained artificial intelligence model to obtain schedule suggestions that match each target schedule; and obtaining a target schedule that matches the target image set based on the target schedule sequence and the schedule suggestions.

[0039] Furthermore, the pre-trained artificial intelligence model is a model trained on a large amount of transaction data in office scenarios, which has the ability to extract key information of transactions, analyze the relationship between transactions, and generate personalized schedule-related content. In this embodiment, the artificial intelligence model can be specifically a self-attention model. With its self-attention mechanism, the model can deeply explore the implicit relationship between transaction data and provide accurate algorithmic support for schedule processing.

[0040] In one specific implementation of this embodiment, a pre-trained artificial intelligence model processes each target schedule to obtain a target schedule that matches the target image set. For example, firstly, the system extracts accurate time information from the key parameter information of each target schedule. If it is a specific time point such as "June 15, 14:00", it is directly used as the sorting basis; if it is a time period such as "June 15, 14:00-16:00", the start time is used as the main basis, and then all target schedules are arranged in chronological order. For example, "Project Milestone Node Attention" on June 10 is arranged first, followed by "XX Project Discussion Meeting" at 14:00 on June 15, and finally "Email Feedback" before the end of the workday on June 30, forming a target schedule sequence arranged linearly along the timeline, which makes it convenient for employees to intuitively understand the tasks that need to be handled at different times. Subsequently, leveraging a pre-trained AI model, the system performs in-depth analysis of keyword information in key parameters of each target schedule. Combining historical office data with a pre-defined task association rule base, it generates schedule suggestions. For example, for emails containing keywords such as "urgent" and "email feedback before the end of the workday on June 30th," it generates a suggestion to "reply before 10:00 AM on June 30th to avoid being late." For meetings such as "XX project discussion meeting" and "participants: Zhang San, Wang Wu," it generates a suggestion to "test equipment and prepare presentation materials 15 minutes in advance." For "leave application" and "3 days of leave," based on the rule of "leave form → work handover required," it generates a suggestion to "hand over to colleagues 1 day in advance." Finally, the system uses the target schedule sequence sorted by time as the basic framework, supplements the specific schedule suggestions under the corresponding time nodes of each target schedule, and integrates the task category and complete key parameter information to form the target schedule table. For example, the entry "June 15, 14:00-16:00" will display the task category - meeting, key parameter information (time: June 15, 14:00-16:00, keywords: XX project discussion meeting, participants: Zhang San, Wang Wu), and schedule suggestions (test equipment 15 minutes in advance, prepare report materials), ensuring that employees can clearly understand the basic information of the task and obtain processing guidance when viewing it.

[0041] Optionally, after obtaining the target schedule that matches the target image set, the method further includes: in response to a user's trigger operation on the target interface, obtaining a screenshot of the target interface as the image to be updated; performing character recognition on the image to be updated based on an optical character recognition model to obtain the schedule to be updated that matches the image to be updated; and updating the target schedule based on the schedule to be updated using a pre-trained artificial intelligence model.

[0042] The target interface includes interfaces that employees operate during subsequent work processes, which may generate new tasks or change existing tasks, including the office system interface, email system interface, meeting system interface, and office document interface, etc. Furthermore, the triggering operation refers to key operations that reflect the user's work behavior, such as modifying the leave application time in the office system, receiving and viewing new urgent emails in the email system, adjusting the meeting time in the meeting system, and marking new task deadlines in office documents, etc. When the system detects these operations, it will automatically capture a screenshot of the current target interface as the image to be updated.

[0043] Based on the above steps, for example, when it is detected that a user receives and reads a new email in the email system interface, its time information is extracted, inserted into the corresponding time position in the target schedule sequence, and a corresponding schedule suggestion is generated and added to the target schedule table; if it is detected that a user changes an existing task in the office system interface (such as modifying leave time or adjusting meeting time), the corresponding original task entry is found in the target schedule table, its key parameter information (time information, keyword information) is updated, and a new schedule suggestion is generated based on the changed content to replace the original suggestion content, ensuring that the target schedule table is always consistent with the employee's actual office tasks, and providing employees with accurate and real-time schedule management support.

[0044] The technical solution of this invention acquires a target image set, then performs character recognition on each target image in the target image set based on an optical character recognition model to obtain a target schedule that matches each target image. Finally, a pre-trained artificial intelligence model processes each target schedule to obtain a target schedule that matches the target image set. This solves the problems of existing office schedule generation methods, such as the inability to automatically generate office schedules, low efficiency in generating office schedules, and long processing time. It realizes the automatic generation of office schedules, avoids various repetitive tasks and the introduction of human error caused by manual operation, and also reduces the redundant consumption of computer resources to a certain extent.

[0045] Example 2

[0046] Figure 2 This is a flowchart of a method for generating schedule information according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. In this embodiment, the method of performing character recognition on each target image in the target image set based on the optical character recognition model to obtain the target schedule that matches each target image is refined.

[0047] like Figure 2 As shown, the method includes:

[0048] S210. Obtain the target image set.

[0049] S220. Perform image preprocessing on each target image in the target image set to obtain each image to be identified.

[0050] The process involves preprocessing each target image in the target image set to obtain an image to be identified, including: processing the target image using a preset color model to obtain a grayscale image matching the target image; binarizing the grayscale image using the maximum inter-class variance method to obtain a binarized image matching the target image; and denoising the binarized image based on a pre-configured filter to obtain an image to be identified matching the target image.

[0051] The color model can be the RGB color model, which is a color representation system based on the combination of red, green, and blue basic color components to generate various colors. All images displayed on office terminals are rendered based on the RGB model. Since the target images are mostly color images, pixels of different colors will increase the computational load of subsequent text recognition, and color differences may obscure the boundary between text and background. Therefore, grayscale processing is required to convert the color images into grayscale images containing only grayscale information. Grayscale processing uses a weighted average method, that is, according to the differences in human eye sensitivity to different color components, different channel weights are assigned to the three RGB color components, and the R, G, B values ​​of each pixel are weighted and calculated to obtain a single grayscale value. In the final grayscale image, each pixel is represented by only one grayscale value, laying the foundation for subsequent binarization processing.

[0052] Furthermore, the Otsu's method is a classic algorithm for adaptively determining image segmentation thresholds. Its core principle is to treat the grayscale values ​​of all pixels in a grayscale image as a dataset, and by calculating the inter-class variance between foreground and background pixels under different grayscale thresholds, find the threshold that maximizes the inter-class variance. In office scenarios, grayscale images still contain some grayscale gradient regions, which can cause text edges to become blurred. Therefore, binarization processing is needed to further simplify the image information, transforming the grayscale image into a binary image containing only black and white colors. This completely eliminates the interference caused by grayscale gradients and significantly improves the clarity of text outlines.

[0053] Furthermore, in this embodiment, the filter can be a signal processing tool preset to suppress noise of a specific frequency based on common noise types in office scene images, including a median filter or a Gaussian filter. It should be noted that the specific type of filter can be configured or modified by the developers according to the actual implementation scenario, and this embodiment does not impose any restrictions here.

[0054] Those skilled in the art should understand that the method of preprocessing target images using a preset color model, the maximum inter-class variance method, and filters is a mature existing technology, and the specific operation process and principle will not be described in detail in this embodiment.

[0055] S230. Based on the optical character recognition model, perform character recognition on each image to be recognized to obtain each target schedule that matches each target image.

[0056] The process involves recognizing characters in each image to be recognized based on an optical character recognition model to obtain target schedules that match each target image. This includes: processing the image to be recognized based on the optical character recognition model to obtain at least one valid region that matches the image to be recognized and text information of the region that matches the valid region; matching the text information of the region with a preset office affairs keyword library to obtain a transaction category that matches the image to be recognized; processing the text information of each region based on a pre-trained language model to obtain key parameter information that matches the image to be recognized, wherein the key parameter information includes time information and keyword information of the image to be recognized; and obtaining target schedules that match the image to be recognized based on the transaction category and the key parameter information.

[0057] The preset office affairs keyword library is a set of keywords pre-constructed based on common office scenarios. Each affairs category corresponds to a set of exclusive keywords. In this embodiment, the overlap or semantic similarity between text information and keywords of each category is calculated. If the overlap exceeds a preset threshold, it is determined to be the corresponding affairs category.

[0058] In this embodiment, the pre-trained language model refers to a language understanding model pre-trained on large-scale general text data. Such models possess powerful semantic understanding and key information extraction capabilities, automatically identifying and extracting specific dimensional information that meets the needs of office tasks from unstructured regional text information. Time information refers to specific time points or time periods related to the commencement, deadline, or attention required for a task. The pre-trained language model can recognize common time expression formats and can even convert ambiguous times into specific times by combining the current date. For example, the time information "June 15th, 14:00-16:00" can be extracted from the regional text information "XX Project Discussion Meeting June 15th, 14:00-16:00". Furthermore, the keyword information is core information that supplements task details and clarifies the associated objects or requirements of the task, covering dimensions such as task topic, associated personnel, task priority, and associated projects. The pre-trained language model will extract this information based on semantic logic and office scenario characteristics. For example, the keyword information "3 days of personal leave" and "Approver: Zhao Liu" can be extracted from the regional text information "Leave application: 3 days of personal leave, approver: Zhao Liu".

[0059] Furthermore, the target log is a structured unit of office transaction information. It integrates the transaction categories and key parameter information extracted in the previous steps to form a transaction record in a preset format. For example, if the transaction category is "Meeting Held," the time information is "June 15th, 14:00-16:00," and the keyword information is "XX Project Discussion Meeting, Participants: Zhang San, Wang Wu," then the integrated target schedule would be "Meeting Held, Time - June 15th, 14:00-16:00, XX Project Discussion Meeting, Participants: Zhang San, Wang Wu." It should be noted that the above target log is only an example provided in this embodiment. In actual implementation scenarios, the preset format of the target log can be set and modified by the user according to the actual implementation scenario. This embodiment does not impose any restrictions here.

[0060] Furthermore, the image to be recognized is processed based on the optical character recognition model to obtain at least one effective region matching the image to be recognized and regional text information matching the effective region, including: scanning the image to be recognized using a contour analysis algorithm to obtain at least one effective region matching the image to be recognized; and segmenting the text in each effective region using the shortest path word segmentation method to obtain regional text information matching each effective region.

[0061] Specifically, the effective region refers to a specific area containing key information about office affairs; the contour analysis algorithm is specifically used to scan the boundaries of abrupt changes in pixel grayscale values ​​in the image, identify regions with closed or continuous contours, and filter the effective region by combining the layout features of the office interface. Furthermore, the shortest path word segmentation method treats a continuous text sequence as a directed graph, and finds the optimal splitting path based on the probability of word combinations to obtain the text information of the region.

[0062] S240. Process each target schedule using a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0063] Based on the above embodiments, after obtaining the target schedule matching the target image set, the method may further include:

[0064] In response to the adjustment instruction for the target schedule, an updated schedule is generated;

[0065] Based on the target schedule and the updated schedule, new training samples are constructed, and the model parameters of the artificial intelligence model are updated using the new training samples.

[0066] With the above settings, when there is a discrepancy between the target schedule automatically generated by the AI ​​model and the actual ideal schedule, a manual or specially trained schedule calibration model can generate adjustment instructions for the target schedule. Based on these adjustment instructions, an updated schedule (i.e., the ideal schedule) is generated. Furthermore, based on the difference between the updated schedule and the target schedule, the model parameters of the AI ​​model can be dynamically updated, allowing the AI ​​model to continuously optimize and update itself during the actual inference process.

[0067] The technical solution of this invention involves acquiring a target image set, preprocessing each target image in the target image set to obtain each image to be recognized, and performing character recognition on each image to be recognized based on an optical character recognition model to obtain each target schedule that matches each target image. Finally, a pre-trained artificial intelligence model is used to process each target schedule to obtain a target schedule that matches the target image set. This solves the problems of existing office schedule generation methods, such as the inability to automatically generate office schedules, low efficiency in generating office schedules, and long processing time. It realizes the automatic generation of office schedules, improves the efficiency of office schedule generation, avoids various repetitive tasks and human errors introduced by manual operation, and to a certain extent reduces the redundant consumption of computer resources.

[0068] Example 3

[0069] Figure 3 This is a schematic diagram of a schedule information generation device provided in Embodiment 3 of the present invention.

[0070] like Figure 3 As shown, the device includes:

[0071] Image acquisition module 310 is used to acquire a target image set;

[0072] The character recognition module 320 is used to perform character recognition on each target image in the target image set based on the optical character recognition model, and obtain the target schedule that matches each target image respectively.

[0073] The schedule generation module 330 is used to process each target schedule through a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0074] The technical solution of this invention acquires a target image set, then performs character recognition on each target image in the target image set based on an optical character recognition model to obtain a target schedule that matches each target image. Finally, a pre-trained artificial intelligence model processes each target schedule to obtain a target schedule that matches the target image set. This solves the problems of existing office schedule generation methods, such as the inability to automatically generate office schedules, low efficiency in generating office schedules, and long processing time. It realizes the automatic generation of office schedules, improves the efficiency of office schedule generation, avoids various repetitive tasks and human errors introduced by manual operation, and also reduces the redundant consumption of computer resources to a certain extent.

[0075] Based on the above embodiments, the character recognition module 320 includes:

[0076] The image preprocessing unit is used to perform image preprocessing on each target image in the target image set to obtain each image to be recognized.

[0077] An optical recognition unit is used to perform character recognition on each image to be recognized based on an optical character recognition model, so as to obtain each target image that matches each target image.

[0078] Based on the above embodiments, the image preprocessing unit includes:

[0079] The grayscale processing unit is used to process the target image using a preset color model to obtain a grayscale image that matches the target image.

[0080] The binarization unit is used to perform binarization processing on the grayscale image using the maximum inter-class variance method to obtain a binarized image that matches the target image.

[0081] The denoising unit is used to denoise the binarized image based on a pre-configured filter to obtain a recognition image that matches the target image.

[0082] Based on the above embodiments, the optical recognition unit further includes:

[0083] The region recognition unit is used to process the image to be recognized based on the optical character recognition model to obtain at least one effective region that matches the image to be recognized and the region text information that matches the effective region.

[0084] The transaction category matching unit is used to match the text information of the region with a preset office transaction keyword library to obtain the transaction category that matches the image to be identified;

[0085] The key parameter acquisition unit is used to process the text information of each region based on the pre-trained language model to obtain key parameter information that matches the image to be identified. The key parameter information includes the time information and keyword information of the image to be identified.

[0086] The target schedule generation unit is used to obtain a target schedule that matches the image to be identified based on the transaction category and key parameter information.

[0087] Based on the above embodiments, the region identification unit includes:

[0088] A contour analysis unit is used to scan the image to be identified using a contour analysis algorithm to obtain at least one effective region that matches the image to be identified.

[0089] The word segmentation unit is used to segment the text in each effective region using the shortest path word segmentation method to obtain the regional text information that matches each effective region.

[0090] Based on the above embodiments, the schedule generation module 330 is further configured to: after obtaining a target schedule that matches the target image set, in response to a user's trigger operation on the target interface, obtain a screenshot of the target interface as an image to be updated; and perform character recognition on the image to be updated based on an optical character recognition model to obtain a schedule to be updated that matches the image to be updated.

[0091] The target schedule is updated using a pre-trained artificial intelligence model based on the schedule to be updated.

[0092] Based on the above embodiments, the schedule generation module 330 includes:

[0093] The sorting unit is used to sort the target schedules according to the time information in the key parameter information of each target schedule, so as to obtain the target schedule sequence;

[0094] The suggestion acquisition unit is used to process the keyword information in the key parameter information of each target schedule through a pre-trained artificial intelligence model to obtain schedule suggestions that match each target schedule respectively.

[0095] A schedule generation unit is used to obtain a target schedule that matches the target image set based on the target schedule sequence and each schedule suggestion.

[0096] Based on the above embodiments, the device may further include a model parameter update module, used for:

[0097] After obtaining the target schedule that matches the target image set, an updated schedule is generated in response to the adjustment instructions for the target schedule;

[0098] Based on the target schedule and the updated schedule, new training samples are constructed, and the model parameters of the artificial intelligence model are updated using the new training samples.

[0099] The schedule information generation device provided in this embodiment of the invention can execute the schedule information generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0100] Example 4

[0101] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0102] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 and an access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from the storage unit 18 into the access memory 13. The access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0103] Multiple components in electronic device 10 are connected to input / output interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0104] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a method for generating schedule information.

[0105] Accordingly, the method includes:

[0106] Obtain the target image set;

[0107] Based on the optical character recognition model, character recognition is performed on each target image in the target image set to obtain the target schedule that matches each target image respectively;

[0108] Each target schedule is processed by a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

[0109] In some embodiments, a method for generating schedule information may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into access memory 13 and executed by processor 11, one or more steps of the method for generating schedule information described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a method for generating schedule information by any other suitable means (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0114] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0115] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts, such as high management difficulty and weak business scalability.

[0116] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

Claims

1. A method for generating schedule information, characterized in that, include: Obtain the target image set; Based on the optical character recognition model, character recognition is performed on each target image in the target image set to obtain the target schedule that matches each target image respectively; Each target schedule is processed by a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set.

2. The method according to claim 1, characterized in that, Based on the optical character recognition model, character recognition is performed on each target image in the target image set to obtain the target schedule that matches each target image, including: Image preprocessing is performed on each target image in the target image set to obtain each image to be identified; Based on the optical character recognition model, character recognition is performed on each image to be recognized to obtain each target schedule that matches each target image.

3. The method according to claim 2, characterized in that, Image preprocessing is performed on each target image in the target image set to obtain each image to be identified, including: The target image is processed using a preset color model to obtain a grayscale image that matches the target image; The grayscale image is binarized using the maximum inter-class variance method to obtain a binarized image that matches the target image. The binarized image is denoised based on a pre-configured filter to obtain a recognition image that matches the target image.

4. The method according to claim 2, characterized in that, Based on the optical character recognition model, character recognition is performed on each image to be recognized, and each target image is matched with a target character, including: The image to be recognized is processed based on the optical character recognition model to obtain at least one effective region that matches the image to be recognized and the text information of the region that matches the effective region. The text information in the region is matched with a preset database of office affairs keywords to obtain the category of affairs that matches the image to be identified; The text information of each region is processed based on a pre-trained language model to obtain key parameter information that matches the image to be identified. The key parameter information includes the time information and keyword information of the image to be identified. Based on the transaction category and key parameter information, a target schedule matching the image to be identified is obtained.

5. The method according to claim 4, characterized in that, The image to be recognized is processed based on the optical character recognition model to obtain at least one valid region matching the image to be recognized and text information of the region matching the valid region, including: The image to be identified is scanned using a contour analysis algorithm to obtain at least one valid region that matches the image to be identified; The shortest path word segmentation method is used to segment the text in each effective region to obtain the regional text information that matches each effective region.

6. The method according to any one of claims 1-4, characterized in that, After obtaining the target schedule that matches the target image set, the process further includes: In response to a user's trigger action on the target interface, a screenshot of the target interface is obtained as the image to be updated; Based on the optical character recognition model, character recognition is performed on the image to be updated to obtain the update schedule that matches the image to be updated; The target schedule is updated using a pre-trained artificial intelligence model based on the schedule to be updated.

7. The method according to claim 1, characterized in that, Each target schedule is processed by a pre-trained artificial intelligence model to obtain a target schedule that matches the target image set, including: The target schedules are sorted according to the time information in the key parameter information of each target schedule to obtain the target schedule sequence; By processing the keyword information in the key parameter information of each target schedule through a pre-trained artificial intelligence model, schedule suggestions that match each target schedule are obtained. Based on the target schedule sequence and each schedule suggestion, a target schedule matching the target image set is obtained.

8. The method according to any one of claims 1-4, characterized in that, After obtaining the target schedule that matches the target image set, the method further includes: In response to the adjustment instruction for the target schedule, an updated schedule is generated; Based on the target schedule and the updated schedule, new training samples are constructed, and the model parameters of the artificial intelligence model are updated using the new training samples.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for generating schedule information according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute a method for generating schedule information according to any one of claims 1-8.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements a method for generating schedule information according to any one of claims 1-8.

Images