Schedule creation methods and electronic devices

Abstract

This disclosure provides a schedule creation method and electronic device, which can be applied to the field of artificial intelligence technology. The method includes: in response to detecting an order interface that meets target conditions, obtaining target trip information corresponding to the order interface; the trip information includes at least trip time information and trip content information; creating a schedule reminder corresponding to the target trip information; the schedule reminder is used to display the trip content information before the time represented by the trip time information.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and more specifically to a schedule creation method and electronic device. Background Technology

[0002] Schedule reminders can help users plan their trips, but they are usually built based on trip information. If the trip information is not obtained in a timely or accurate manner, the creation of the schedule reminder may fail. Summary of the Invention

[0003] According to a first aspect of this disclosure, a schedule creation method is provided, comprising: in response to detecting an order interface that meets target conditions, obtaining target trip information corresponding to the order interface; the trip information includes at least trip time information and trip content information; creating a schedule reminder corresponding to the target trip information; the schedule reminder is used to display the trip content information before the time represented by the trip time information.

[0004] According to embodiments of this disclosure, the target condition is selected from one of the following combinations: the indication information in the order interface used to indicate the service type represents the service items related to the schedule; the interface identifier of the order interface is the target identifier.

[0005] According to embodiments of this disclosure, in response to detecting an order interface that meets target conditions, target travel information corresponding to the order interface is obtained, selected from one of the following combinations: inputting image information of the order interface and first prompt information into a first target model, so that the first target model infers the target travel information corresponding to the order interface from the image information based on the guidance of the first prompt information; obtaining first text information of the order interface, and inputting the first text information and second prompt information into a second target model, so that the second target model infers the target travel information corresponding to the order interface from the first text information based on the guidance of the second prompt information; wherein the number of weight parameters of the first target model and the second target model is greater than one hundred million.

[0006] According to embodiments of this disclosure, in response to detecting an order interface that meets target conditions, target trip information corresponding to the order interface is obtained, including: obtaining second text information of the order interface; inputting the second text information into an information extraction model so that the information extraction model can identify and mark the trip time information and trip content information contained in the second text information to obtain target trip information.

[0007] According to embodiments of this disclosure, obtaining second text information from an order interface includes: obtaining original text information from the order interface; and cleaning the original text information from the order interface to obtain second text information.

[0008] According to embodiments of this disclosure, obtaining text information from an order interface includes: extracting original text information from at least one target area in the order interface based on the interface area distribution characteristics of the order interface.

[0009] According to embodiments of this disclosure, the original text information of the order interface is cleaned, including at least one of the following: removing information representing nodes from the original text information; removing meaningless letters and / or special strings from the original text; and removing duplicate information from the original text information.

[0010] According to embodiments of this disclosure, the method further includes: if the first target model and / or the second target model infers a reasoning result representing no target trip information, the second text information of the order interface is input into the information extraction model so that the information extraction model can identify the trip time information and trip content information contained in the second text information to obtain the target trip information.

[0011] According to embodiments of this disclosure, obtaining target trip information corresponding to the order interface includes: if the network status meets the network connection conditions, obtaining target trip information corresponding to the order interface based on a first target model or a second target model deployed in the cloud; if the network status does not meet the network connection conditions, obtaining target trip information corresponding to the order interface based on an information extraction model deployed on the local device.

[0012] According to a second aspect of this disclosure, an electronic device is provided, comprising: a first application running on the electronic device; the first application being configured to: parse at least one task based on input, and invoke a target model to execute at least one task, at least for performing: in response to detecting an order interface that meets target conditions, invoking the target model to obtain target trip information corresponding to the order interface; the trip information includes at least trip time information and trip content information; creating a schedule reminder corresponding to the target trip information; the schedule reminder is used to prompt the trip content information before the time represented by the trip time information.

[0013] According to a third aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program or instructions are stored, which, when executed by a processor, implement the steps of the above-described method.

[0014] According to a fourth aspect of this disclosure, a computer program product is also provided, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method. Attached Figure Description

[0015] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0016] Figure 1 This illustration schematically depicts an application scenario of the display method according to an embodiment of the present disclosure;

[0017] Figure 2 A flowchart illustrating a schedule creation method according to an embodiment of the present disclosure is shown schematically;

[0018] Figure 3 This schematic diagram illustrates one of the principle diagrams for obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure;

[0019] Figure 4 This schematically illustrates a second diagram of the principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure;

[0020] Figure 5 This schematic diagram illustrates the third principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure;

[0021] Figure 6 This schematic diagram illustrates the fourth principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure;

[0022] Figure 7 This schematic diagram illustrates the fifth principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure;

[0023] Figure 8 A schematic block diagram of a schedule creation apparatus according to an embodiment of the present disclosure is shown. Detailed Implementation

[0024] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0027] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0028] In the technical solution disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0029] This disclosure provides a schedule creation method and an electronic device. Before introducing the technical solutions provided by this disclosure, the relevant technologies involved in this disclosure will be described first.

[0030] Currently, users typically create schedule reminders in the following ways:

[0031] Manual creation: Users manually enter information such as trip time, location, and event name, and save the settings after the system is configured.

[0032] Copy and paste to create: Users copy trip information from the order interface, switch to the calendar application, and create the schedule using the paste or clipboard recognition function.

[0033] SMS parsing and creation: After a user completes an order, the merchant sends a confirmation SMS. By listening to and parsing the SMS content, the merchant can extract the trip information and create a schedule reminder.

[0034] However, the above method has the following problems:

[0035] First, the process is cumbersome and inefficient. Manually creating or copying and pasting requires users to switch between multiple applications, involving many steps and taking a long time.

[0036] Secondly, it's easy to miss. Users may forget to create a schedule reminder after placing an order, causing them to miss their trip.

[0037] Third, the information coverage is incomplete. The SMS parsing method relies on SMS messages sent by merchants, but not all trips will send SMS messages (such as some movie tickets and restaurant reservations). Furthermore, the SMS content may be incomplete or contain marketing information, making it difficult to extract accurate information.

[0038] Fourth, information is not received in a timely manner. SMS messages may be delayed (e.g., due to network issues), and users may receive the message only after leaving the order page, making it impossible to create a schedule reminder immediately.

[0039] The aforementioned issues result in existing schedule creation methods being cumbersome, prone to omissions, lacking complete information, and untimely access, thus affecting the timeliness and accuracy of schedule reminders.

[0040] Figure 1 The illustration depicts an application scenario of the schedule creation method according to embodiments of the present disclosure. For example... Figure 1 As shown, application scenario 100 according to an embodiment of this disclosure may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables. For example, a user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send information, etc.

[0041] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be electronic devices such as smartphones, wearable devices, personal computers, intelligent voice interaction devices, smart home appliances, intelligent vehicles, in-vehicle terminals, aircraft, unmanned vending terminals, and extended reality devices. Extended reality devices can include virtual reality devices, augmented reality devices, and mixed reality devices. A client application for the target application can be installed and run on the terminal device. This target application can include, but is not limited to, shopping applications, web browser applications, search applications, instant messaging tools, email clients, and social media platform software (these are just examples). Furthermore, this embodiment does not limit the form of the target application, and it can include, but is not limited to, applications, mini-programs, etc., installed on the terminal device, and can also be in the form of a webpage.

[0042] The first terminal device 101, the second terminal device 102, and the third terminal device 103 are all equipped with corresponding display modules, which can present various types of information to meet users' needs for information visualization.

[0043] Server 105 can be a server providing various services, such as a backend management server supporting websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process received user requests and other data, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services such as cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and basic cloud computing services such as big data. The server can be the backend server of the aforementioned target application, used to provide backend services to the clients of the target application.

[0044] It should be noted that the schedule creation method provided in this disclosure embodiment can generally be executed by server 105 and / or terminal devices 101-103. Accordingly, the schedule creation device provided in this disclosure embodiment can generally be set in server 105 and / or terminal devices 101-103.

[0045] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0046] Figure 2 A flowchart illustrating a schedule creation method according to an embodiment of this disclosure is shown schematically. Figure 2 As shown, the process creation method according to the embodiments of this disclosure may include operations S210 to S220.

[0047] In operation S210, in response to detecting an order interface that meets the target conditions, the target trip information corresponding to the order interface is obtained; the trip information includes at least trip time information and trip content information.

[0048] In operation S220, a schedule reminder corresponding to the target itinerary information is created; the schedule reminder is used to display the itinerary content information before the time represented by the itinerary time information.

[0049] In some embodiments, the target conditions can be a series of conditions that can be flexibly configured according to different business needs. Target conditions may include at least one of order type, order status conditions, or user behavior conditions. For example, the order type is an order with a clear time attribute, such as an airline ticket, hotel ticket, movie ticket, or restaurant reservation. The order status condition is "ticket issued" or "reservation successful." Other conditions include the user staying on the order completion page for more than a set time, taking a screenshot, etc.

[0050] When an order interface is detected to meet the preset target conditions, it is determined that the order interface meets the requirements for subsequent processing, and the corresponding target trip information is extracted from the current order interface or related data.

[0051] Related data can be data that is relevant to the current order page but may not be fully displayed on the current page. For example, some applications' order success pages only display the words "Booking Successful" and the order number, while detailed trip information is displayed on other pages (such as the confirmation page of the previous page).

[0052] The target itinerary information should include at least the itinerary time information and itinerary content information. The itinerary time information can include the specific start and end times or time periods of the itinerary, such as flight departure times, hotel check-in and check-out times, etc. The itinerary content information can include specific details of the itinerary, such as flight numbers, destinations, hotel names, activity names, etc.

[0053] Based on the obtained target itinerary information, corresponding schedule reminders can be created in a schedule management application. Schedule management applications can include, for example, the phone's built-in calendar app or third-party schedule management software. During schedule creation, the itinerary time information can be used as the basis for the schedule reminder, setting the reminder to depart at an appropriate time before the itinerary begins. The advance time can be flexibly adjusted according to the nature of the itinerary and user preferences. Simultaneously, the itinerary content will be included as the specific content of the reminder, allowing users to understand the itinerary details upon receiving the reminder.

[0054] This embodiment of the disclosure retrieves target schedule information from the order interface and creates schedule reminders when target conditions are met, achieving automatic retrieval of target itinerary information and automatic creation of schedule reminders, effectively simplifying user operation processes and schedule management processes. Directly retrieving itinerary information from the order interface and creating schedule reminders avoids errors that may occur from manually entering itinerary information, improves the accuracy of information retrieval, ensures the completeness and standardization of itinerary information, and thus improves the accuracy of subsequent schedule reminders.

[0055] According to one embodiment of this disclosure, the target condition is selected from one of the following combinations: the indication information in the order interface used to indicate the business type represents the service items related to the schedule; the interface identifier of the order interface is the target identifier.

[0056] In some embodiments, it can be determined whether the order interface meets the target conditions based on the interface content. When the interface type is detected as an order interface, text, icons, or labels indicating the business type are extracted from the current interface. The indicating information may include, for example, page title text (such as order details, booking successful, etc.), service type keywords (such as "flight", "movie ticket", "hotel", etc.), page icons (such as airplane, cinema icon, etc.).

[0057] The extracted instruction information can be matched with services related to the preset schedule. If a match is successful, the current order interface is deemed to meet the target conditions, and the subsequent "Get Trip Information" and "Create Schedule" processes are executed. Services related to the schedule can include at least one of the following: transportation booking (such as air tickets, train tickets, car rentals, etc.), accommodation booking (such as hotel reservations, restaurant reservations, etc.), or entertainment ticket booking (such as movie tickets, performance tickets, beauty appointments, etc.).

[0058] In some embodiments, it can be determined whether the current order interface meets the target conditions based on the interface identifier of the current order interface.

[0059] The order interface refers to the user interface in a client application used to display order information or order operation results. In Android systems, this user interface is implemented through Activities, where an Activity is the execution unit on the client side used to host one or more user interface views. The interface identifier is the unique identification information used to identify the order interface. In Android systems, this interface identifier can be the name or address of the Activity. It should be noted that the above description using Activity as an example is only illustrative; the specific form of the interface identifier can be flexibly determined according to the characteristics of different operating systems or application frameworks. For example, in iOS systems, it is represented by a ViewController and its class name, while in web applications, it is represented by a page window and its URL address.

[0060] For example, the current interface identifier can be matched with a preset target identifier. If the match is successful, it is determined that the order interface meets the preset conditions. The preset target identifier may include the interface identifiers in each application that need to trigger the creation of the schedule.

[0061] This disclosure achieves accurate judgment of the actual situation of automatically created schedules by setting two optional trigger conditions, so as to obtain the target trip information corresponding to the order interface in a timely manner and create corresponding schedule reminders, thereby improving the timeliness and accuracy of schedule creation, eliminating the need for manual operation by the user and effectively improving the user experience.

[0062] Figure 3 The diagram illustrates one of the schematic diagrams of the target trip information corresponding to the order acquisition interface according to an embodiment of the present disclosure.

[0063] like Figure 3 As shown, according to one embodiment of this disclosure, obtaining target trip information corresponding to the order interface includes: if the network status meets the network connection conditions, obtaining target trip information corresponding to the order interface based on a first target model or a second target model deployed in the cloud; if the network status does not meet the network connection conditions, obtaining target trip information corresponding to the order interface based on an information extraction model deployed on the local device.

[0064] In some embodiments, before obtaining the target trip information corresponding to the order interface, the current network status can be checked to determine whether the network status meets preset network connection conditions. These network connection conditions can be flexibly set according to actual application scenarios and needs, and may include factors such as network availability, network type (WiFi or mobile data), network quality (signal strength, latency, packet loss rate, etc.), and network connection stability. For example, if the network connection conditions are WiFi connection, strong signal, low latency, and stable network connection, then the current network status is determined to meet the network connection conditions.

[0065] Provided the network connection conditions are met, a model for obtaining the target itinerary information can be further selected from the first and second target models deployed in the cloud. For example, the first and second target models can be models for processing different types of order interfaces (such as transportation orders and entertainment ticket orders), or models for processing different information types (such as image information and text information). After selecting a model, the relevant information from the order interface is sent as input data to the cloud model. The cloud model analyzes and processes the received input data to generate the corresponding target itinerary information.

[0066] If network connectivity is unavailable, the system switches to local execution mode and invokes the local information extraction model to retrieve the target trip information. This local information extraction model can be pre-trained and stored on the local device, possessing certain trip information extraction and processing capabilities. Relevant data from the order interface is input into the local information extraction model, which processes this data according to its internal rules and algorithms to generate the target trip information.

[0067] This disclosure employs different models to acquire target trip information based on network conditions, fully considering the uncertainty of network status and avoiding situations where trip information cannot be obtained due to network problems, thus effectively improving the reliability and availability of trip information acquisition. Automatically adjusting the trip information acquisition method according to different network environments also effectively improves the flexibility and adaptability of information acquisition.

[0068] Figure 4 The diagram illustrates a second schematic of the principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure.

[0069] like Figure 4 As shown, according to an embodiment of this disclosure, in response to detecting an order interface that meets the target conditions, target travel information corresponding to the order interface is obtained, selected from one of the following combinations: inputting image information of the order interface and first prompt information into a first target model, so that the first target model infers the target travel information corresponding to the order interface from the image information based on the guidance of the first prompt information; obtaining first text information of the order interface, and inputting the first text information and second prompt information into a second target model, so that the second target model infers the target travel information corresponding to the order interface from the first text information based on the guidance of the second prompt information; wherein, the number of weight parameters of the first target model and the second target model is greater than one hundred million.

[0070] See Figure 4 In some embodiments, part A of the above can obtain target travel information based on image information.

[0071] When an order interface that meets the target criteria is detected, a screenshot can be taken using the device's screenshot function or a dedicated image capture module to obtain the image information of the order interface. For example, in a mobile application scenario, when a user opens a flight booking order page that meets the target criteria, the system automatically takes a screenshot of the page and saves it.

[0072] The initial prompt message can be designed based on the characteristics of the order page and the type of target trip information to be obtained. This initial prompt message guides the initial target model, clarifying what the model needs to identify and infer from the image. For example, the initial prompt message could be, "Identify the flight number, departure time, arrival time, departure point, and destination from this order page image."

[0073] The collected order interface image and the prepared initial prompt information are input into the first target model. The first target model can be a deep learning model with a large number of weight parameters (more than 100 million). The first target model is trained on a large amount of image data and has the ability to extract and infer information from images.

[0074] After receiving the image information and the first prompt information, the first target model analyzes and processes the image, locates and extracts content related to the target trip information in the image, and performs reasoning and organization according to the requirements of the first prompt information, and outputs the target trip information corresponding to the current order interface.

[0075] See Figure 4In part B of the document, in some embodiments, target trip information can be obtained based on text information.

[0076] After detecting an order interface that meets the target conditions, character recognition technology or application programming interfaces (APIs) can be used to directly extract the initial text information from the order interface. For example, for a web-based hotel booking order, the HTML code of the webpage can be parsed to extract text content containing information such as the hotel name, check-in time, and check-out time.

[0077] Similar to the design of the first prompt, a second prompt can be specified based on the characteristics of the first text information and the target travel information to be obtained. The second prompt is used to guide the second target model to infer the target travel information from the text information.

[0078] The extracted first text information and second prompt information are input into the second target model. The second target model can be a deep learning model with a large number of weight parameters (more than 100 million). The second target model is trained on a large amount of text data and is used to process natural language understanding and information extraction tasks.

[0079] After receiving the text information and the second prompt information, the second target model uses natural language processing technology to perform operations such as word segmentation, part-of-speech tagging, and semantic analysis on the text. Based on the requirements of the prompt information, the second target model can locate key information in the text, perform reasoning and integration, and finally output the target itinerary information corresponding to the order interface, such as hotel name, check-in and check-out times, etc.

[0080] In some embodiments, the first target model and the second target model may be models deployed in the cloud. The first target model and the second target model are machine learning models that can recognize natural language and / or other inputs (such as images) input to the target model, and perform comprehensive language processing tasks such as semantic analysis and question answering, thereby generating input-related outputs and / or responses to the input.

[0081] The first-objective and second-objective models learn the features and patterns of natural language by training on large amounts of diverse data, thereby enabling them to understand and generate natural language. They typically have hundreds of millions to trillions of model parameters and are able to capture complex relationships and patterns in natural language.

[0082] The first and second target models can be generative models or generative language models (GLMs). Specifically, they can include large language models (LLMs), GPT (Generative Pre-trained Transformer), large visual models, multimodal large models, etc. The models involved in the embodiments of this application can be general-purpose large models or expert large models obtained by fine-tuning based on requirements; the embodiments of this application do not limit this.

[0083] In some embodiments, the first and second prompt words may be constructed based on a pre-stored prompt word template or may be pre-designed.

[0084] For example, different prompt templates can be pre-designed for different types of order interfaces. When a specific order interface is detected, the appropriate template is selected from the template library based on the order type. Then, the template is fine-tuned based on the specific characteristics of the order interface (such as special formats, newly added information items, etc.) to generate suitable prompt information. For example, the prompt for a flight ticket order template might include "Please extract information such as flight number, departure time, arrival time, departure point, and destination from the image / text." If the flight ticket order has special service identifiers, "If there are special services, please extract the relevant information as well" can be added to the template.

[0085] Alternatively, a comprehensive and universal set of prompts can be designed for common order types and business needs. When a specific order interface is detected, the preset prompt information matching that order type can be used as the first or second prompt information.

[0086] The first and second prompt messages can be obtained after optimization based on cases that did not meet expectations during testing. During testing, the first or second target model can be tested using the initial prompt words to process order interface information, collecting cases where the output is inaccurate, incomplete, or does not meet expectations—i.e., bad cases. For example, for orders formed across multiple days, the target model may not correctly identify the cross-day situation, only extracting partial time information or extracting the time information incorrectly.

[0087] By conducting in-depth analysis of the collected bad cases, the root cause of the problem can be identified: The prompt may be unclear or inaccurate, failing to explicitly specify the requirements for recognizing cross-day situations; or the large model may have a misunderstanding of certain special formats or semantics. Based on the cause, the prompt should be adjusted accordingly. If the problem lies in the wording of the prompt, optimize its phrasing to make it more explicit and specific. For example, for cross-day situations, the prompt could be revised to "If the itinerary spans multiple days, please accurately identify and extract the date and time information of the departure and arrival days respectively, and indicate the cross-day indicator." The revised prompt should then be retested until satisfactory itinerary information extraction results are achieved.

[0088] The first and second target models possess strong capabilities for processing complex information, effectively improving the accuracy of acquiring target itinerary information. By acquiring information through both image and text methods and processing it using corresponding models, they can adapt to different types of order interfaces, enhancing the versatility and flexibility of target itinerary information extraction. By automatically capturing images or extracting text from order interfaces that meet the target conditions and inputting this data into the target model for inference, information acquisition time can be effectively shortened, and processing efficiency improved.

[0089] Figure 5 The diagram illustrates the principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure.

[0090] like Figure 5 As shown, according to an embodiment of this disclosure, the method further includes: if the first target model and / or the second target model infers a reasoning result representing no target trip information, inputting the second text information of the order interface into the information extraction model, so that the information extraction model can identify the trip time information and trip content information contained in the second text information to obtain the target trip information.

[0091] In some embodiments, in response to detecting an order interface that meets the target conditions, a first target model and / or a second target model deployed in the cloud are invoked to perform reasoning on the order interface. After the first target model and / or the second target model complete the reasoning, the reasoning result is judged to check whether the reasoning result represents no target trip information.

[0092] For example, the inference results can be tested by setting specific conditions or thresholds. If the inference result is a null value, the inference result is a preset specific identifier such as "unrecognizable", the inference result lacks necessary fields such as travel time or content, the inference time exceeds a preset threshold, or the confidence level of the inference result is lower than a preset threshold, it can be determined that the first target model and / or the second target model cannot infer valid travel information from the order interface.

[0093] If the first target model and / or the second target model are unable to infer valid travel information from the order interface, the information extraction model is used to process the order interface in order to extract travel information from the order interface.

[0094] In some embodiments, cleaned text information can be extracted from the order interface as second text information. The cleaned second text information is then input into the information extraction model, which marks and identifies the second text information to extract structured target trip information.

[0095] In cases where the first and second target models fail to make inferences or cannot accurately extract information, this disclosure utilizes an information extraction model to further obtain trip-related information. This can effectively improve the completeness and accuracy of information acquisition, avoid missing trip information due to the limitations of the target model's inference, effectively improve the robustness and availability of the system, and meet the trip information extraction needs in different scenarios.

[0096] The following section provides further explanation of the scheme of obtaining target trip information using an information extraction model.

[0097] Figure 6 The fourth schematic diagram illustrates the principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure.

[0098] According to one embodiment of this disclosure, in response to detecting an order interface that meets the target conditions, target trip information corresponding to the order interface is obtained, including: obtaining second text information of the order interface; inputting the second text information into an information extraction model so that the information extraction model can identify and mark the trip time information and trip content information contained in the second text information to obtain the target trip information.

[0099] In some embodiments, a suitable text extraction method can be selected based on the type and format of the order interface. For example, if the order interface is a webpage, a webpage parsing tool can be used to extract the text content from the page. If the order interface is an image, Optical Character Recognition (OCR) technology can be used to convert the text in the image into editable text.

[0100] The second text information is input into a trained information extraction model. The model then uses pre-trained patterns and rules to reason and analyze the input text, identifying and labeling the travel time and content information contained within it. For example, the model can identify a time format like "2024-08-15 14:00" as travel time information and text like "flying from Beijing Capital Airport to Shanghai Pudong Airport" as travel content information.

[0101] After the information extraction model outputs labeled results, these results are integrated and processed to obtain complete target itinerary information. The itinerary time information and itinerary content information labeled by the information extraction model can be associated and combined to form structured target itinerary information.

[0102] This embodiment of the disclosure accurately identifies and marks the trip time information and trip content information in the order interface text through an information extraction model, effectively improving the accuracy and efficiency of information acquisition.

[0103] Figure 7 The fifth schematic diagram illustrates the principle of obtaining target trip information corresponding to an order interface according to an embodiment of the present disclosure.

[0104] According to one embodiment of this disclosure, obtaining second text information from an order interface includes: obtaining original text information from the order interface; and cleaning the original text information from the order interface to obtain second text information.

[0105] The appropriate text information acquisition method can be selected based on the characteristics of the order interface to obtain the original text information corresponding to the order interface. For example, the original text information can be obtained from the application's order interface using appropriate tools or interfaces, or the image information of the order interface can be obtained by taking a screenshot of the device screen, and the original text information can be extracted using optical character recognition technology.

[0106] In some embodiments, obtaining second text information of the order interface includes: extracting original text information from at least one target area in the order interface based on the interface area distribution characteristics of the order interface.

[0107] Based on the distribution characteristics of the order interface, at least one target area that may contain trip information can be identified. Interface area characteristics can include structural features, visual features, etc., such as key information having a special background color. The target area can be determined based on the application's design features, or areas matching the characteristics of a "key information area," such as areas with special background colors, can be dynamically identified through feature recognition.

[0108] It can directly read the text content within the target area as the original text information, or it can perform image recognition on the target area to extract the text as the original text information.

[0109] For example, the system analyzes and determines the order type of the order interface. Based on the determined order type, it loads the corresponding JSON rule file from the local machine or the cloud, uses the definitions in the JSON rules to locate and extract the text from a specified area of ​​the order interface as the raw text information.

[0110] In order texts from different sources (such as different platforms or different business types), there are certain patterns in the distribution of important information. Important information will appear between fixed fields. For example, important information in high-speed rail orders will appear between "ticket number" and "trip service". Therefore, the area between the starting text and the ending text can be defined as a specified area, and text can be extracted from the specified area as the original text information.

[0111] For example, OCR technology can be used to extract text and its coordinates from an order interface image. Then, predefined JSON rules are used to determine whether each text region extracted by the OCR falls within a valid area, thereby filtering out important information. The JSON rules can define the range of areas containing key information.

[0112] This embodiment of the disclosure utilizes the regional distribution features of the order interface to extract the original text information within the target area. This can effectively improve the accuracy of information extraction, avoid interference from irrelevant information, reduce the processing scope, reduce computational load and response time, reduce noise in the extracted original text information, reduce the complexity of subsequent processing, and effectively improve processing efficiency.

[0113] In some embodiments, the original text information of the order interface is cleaned, including at least one of the following: removing information representing nodes from the original text information; removing meaningless letters and / or special strings from the original text; and removing duplicate information from the original text information.

[0114] For example, information representing nodes may include XML / HTML tags, control identifiers, etc. Meaningless representations of letters and / or special strings may include special symbols, meaningless letters, placeholder text, redundant punctuation, etc. Duplicate information may include identical content, similar content with slight differences in expression, or content extracted repeatedly due to page structure.

[0115] By removing interfering information from the original text, subsequent itinerary information extraction can be based on clean, structured second text information, reducing the computational load of subsequent processing, effectively minimizing errors in information extraction, and improving the accuracy of information extraction. Furthermore, cleaning the extracted original text information effectively removes structured node information, ensuring a consistent format for second text information across different page structures. This maintains consistency in subsequent processing logic and enhances adaptability to different page structures.

[0116] In some embodiments, the second text information can be segmented into substrings of a specific size without affecting its content, structure, or meaning, to adapt to the text processing requirements of the information extraction model, thus facilitating the model's processing of the input data. For example, a long text can be segmented into multiple substrings of size 512 and input into the information extraction model. The model can process these substrings in parallel, further improving processing speed and enabling rapid acquisition of target travel information.

[0117] Based on the above-described schedule creation method, embodiments of this disclosure also provide a schedule creation apparatus. The following will be combined with... Figure 8 The device is described in detail.

[0118] Figure 8 A schematic block diagram of a schedule creation apparatus according to an embodiment of the present disclosure is shown.

[0119] like Figure 8 As shown, the schedule creation device 800 of this embodiment includes an acquisition module 810 and a creation module 820.

[0120] The acquisition module 810 is used to acquire target trip information corresponding to the order interface in response to detecting an order interface that meets the target conditions; the trip information includes at least trip time information and trip content information. In one embodiment, the acquisition module 810 can be used to execute step S210 described above, which will not be repeated here.

[0121] The creation module 820 is used to create a schedule reminder corresponding to the target itinerary information; the schedule reminder is used to display the itinerary content information before the time represented by the itinerary time information. In one embodiment, the creation module 820 can be used to perform step S220 described above, which will not be repeated here.

[0122] According to embodiments of this disclosure, any plurality of modules in the acquisition module 810 and the creation module 820 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the acquisition module 810 and the creation module 820 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array, a programmable logic array, a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit, or any other reasonable means of integrating or packaging circuitry, or implemented in any one of software, hardware, and firmware methods, or in a suitable combination of any of these. Alternatively, at least one of the acquisition module 810 and the creation module 820 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0123] Based on the above-described schedule creation method, embodiments of this disclosure also provide an electronic device suitable for implementing the schedule creation method.

[0124] The electronic device of this embodiment includes: at least one processor and a memory storing computer program instructions. The processor is used to execute instructions and process data, and the memory is used to store computer program instructions and data. The memory stores computer program instructions for a first application program, which, when executed by the processor, cause the electronic device to perform the function of the first application program.

[0125] The electronic device in this embodiment runs a first application, which is configured to: parse at least one task based on input, and call a target model to execute at least one task, at least for performing: in response to detecting an order interface that meets the target conditions, calling the target model to obtain target trip information corresponding to the order interface; the trip information includes at least trip time information and trip content information; creating a schedule reminder corresponding to the target trip information; the schedule reminder is used to prompt the trip content information before the time represented by the trip time information.

[0126] Embodiments of this disclosure also provide a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0127] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include read-only memory, and / or random access memory, and / or one or more memories other than read-only memory and random access memory.

[0128] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this disclosure.

[0129] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices or magnetic storage devices. In another embodiment, the computer program may also be transmitted and distributed as signals over a network medium, and downloaded and installed via a communication component, and / or installed from a removable medium. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0130] In embodiments of this disclosure, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a processor, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0131] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The program code can execute entirely on a user computing device, partially on a user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0133] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

Claims

1. A method for creating a schedule, comprising: In response to detecting an order interface that meets the target conditions, obtain the target trip information corresponding to the order interface; The itinerary information includes at least itinerary time information and itinerary content information; Create a schedule reminder corresponding to the target itinerary information; the schedule reminder is used to display the itinerary content information before the time represented by the itinerary time information.

2. The method according to claim 1, wherein the target condition is selected from one of the following combinations: The indication information in the order interface that indicates the service type represents the service items related to the schedule; The interface identifier of the order interface is the target identifier.

3. The method according to claim 1, wherein the step of obtaining the target trip information corresponding to the order interface in response to detecting an order interface that meets the target conditions is selected from one of the following combinations: The image information of the order interface and the first prompt information are input into the first target model, so that the first target model can infer the target trip information corresponding to the order interface from the image information based on the guidance of the first prompt information. The first text information of the order interface is obtained, and the first text information and the second prompt information are input into the second target model, so that the second target model can infer the target trip information corresponding to the order interface based on the guidance of the second prompt information from the first text information. in, The number of weight parameters in the first target model and the second target model is greater than 100 million.

4. The method according to claim 1, wherein obtaining the target trip information corresponding to the order interface in response to detecting an order interface that meets the target conditions includes: Obtain the second text information from the order interface; The second text information is input into the information extraction model so that the information extraction model can identify and mark the trip time information and trip content information contained in the second text information to obtain the target trip information.

5. The method according to claim 4, wherein obtaining the second text information of the order interface includes: Obtain the original text information of the order interface; The original text information of the order interface is cleaned to obtain the second text information.

6. The method according to claim 5, wherein obtaining the text information of the order interface includes: Based on the interface area distribution characteristics of the order interface, the original text information is extracted from at least one target area in the order interface.

7. The method according to claim 5, wherein cleaning the original text information of the order interface includes at least one of the following: Remove the information representing nodes from the original text information; Remove meaningless letters and / or special strings from the original text; Remove duplicate information from the original text information.

8. The method according to claim 3, further comprising: If the first target model and / or the second target model infer a reasoning result representing no target trip information, the second text information of the order interface is input into the information extraction model so that the information extraction model can identify and mark the trip time information and trip content information contained in the second text information to obtain the target trip information.

9. The method according to claim 1, wherein obtaining the target trip information corresponding to the order interface includes: If the network status meets the network connectivity requirements, obtain the target trip information corresponding to the order interface based on the first target model or the second target model deployed in the cloud; If the network status does not meet the network connection conditions, the target trip information corresponding to the order interface is obtained based on the information extraction model deployed on this terminal.

10. An electronic device, comprising: A first application running on the electronic device; The first application is configured to: parse at least one task based on input, and invoke a target model to execute the at least one task, for at least the following purposes: In response to the detection of an order interface that meets the target conditions, the target model is invoked to obtain the target trip information corresponding to the order interface; the trip information includes at least trip time information and trip content information; Create a schedule reminder corresponding to the target itinerary information; the schedule reminder is used to display the itinerary content information before the time represented by the itinerary time information.

Images