Travel email processing method and device

Abstract

The embodiment of the invention provides a travel email processing method and device, and relates to the technical field of natural language processing, and the method comprises the steps: extracting target travel feature information according to target email information, the target travel feature information comprises a target traffic mode feature, a target travel node feature and / or a target association feature of a target traffic mode and a target travel node; and generating target travel reminding information according to the target travel feature information. In this way, the automatic integration precision of travel mail information is improved, the establishment process of travel reminding is simplified, the automatic generation precision and efficiency of travel reminding are improved, the relevance of travel reminding is improved, the probability of travel delay, mutual collision of travel and missing of travel by personnel is reduced, the fusion degree and matching degree among multiple travels are improved, and the travel reminding efficiency is improved. And the integrating degree of personnel and the journey is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of natural language processing technology, and more particularly to a method and device for processing travel emails. Background Art

[0002] With the rapid development of information technology, email has become an indispensable part of people's daily life. At present, email also plays a pivotal role in the flow of itinerary information. However, in the relevant technology, the accuracy of automated integration of itinerary email information is poor, the process of establishing itinerary reminders is relatively cumbersome, and the relevance of itinerary reminders is poor, resulting in delays and contradictions in the itinerary, and a high probability of people missing the itinerary.

[0003] Therefore, a new technical solution is urgently needed to solve the above technical problems. Summary of the invention

[0004] According to the embodiments of the present application, a method and device for processing itinerary emails are provided, which are conducive to improving the accuracy of automated integration of itinerary email information, simplifying the process of establishing itinerary reminders, improving the accuracy and efficiency of automated generation of itinerary reminders, improving the relevance of itinerary reminders, reducing the probability of itinerary delays, itinerary conflicts, and people missing their itineraries, improving the integration and matching between multiple itineraries, and improving the fit between people and itineraries.

[0005] In a first aspect of the present application, a method for processing itinerary emails is proposed, comprising: Extracting target trip feature information according to the target email information, wherein the target trip feature information includes: target transportation mode features, target trip node features and / or target association features between the target transportation mode and the target trip node; Generate target trip reminder information based on target trip characteristic information.

[0006] In some feasible implementations, before extracting the travel feature information according to the target email information, the method further includes: Determine the target emails based on the target keywords and / or target domain names; A target cleaning operation is performed on a target email to generate target email information.

[0007] In some feasible implementations, extracting the itinerary feature information according to the target email information includes: Identify target mail information to determine target transportation characteristics; Among them, the target transportation mode characteristics include: The class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and ending node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode.

[0008] In some feasible implementations, extracting the itinerary feature information according to the target email information further includes: Identify target email information to determine target trip node characteristics; Among them, the target trip node features include: Target itinerary node features, target itinerary node pointing features, and / or time node features corresponding to the target itinerary node.

[0009] In some feasible implementations, the above-mentioned association features between the target transportation mode and the target trip node include: Spatial series correlation features, and / or, time series correlation features.

[0010] In some feasible implementations, generating target trip reminder information according to target trip characteristic information includes: Schedule reminder information is generated according to target traffic mode characteristics, target travel node characteristics, and time series correlation characteristics, wherein the time series correlation characteristics correspond one-to-one to the target traffic mode characteristics and the target travel node characteristics.

[0011] In some feasible implementations, generating target trip reminder information according to the target trip characteristic information further includes: A target prompt card is generated according to target transportation mode characteristics, target travel node characteristics, spatial sequence association characteristics, and / or time series association characteristics.

[0012] In some feasible implementations, the method as described in any of the above items further includes: When it is determined that there are multiple persons associated with the target trip, Generate auxiliary reminder cards based on the target itinerary characteristic information corresponding to other personnel.

[0013] In a second aspect of the present application, a device for processing travel mail is provided, comprising: An extraction unit is used to extract target trip feature information according to the target email information, wherein the target trip feature information includes: target transportation mode features, target trip node features, and / or target association features of the target transportation mode and the target trip node; The generating unit is used to generate target trip reminder information according to the target trip characteristic information.

[0014] The processing and device of itinerary emails provided in the embodiments of the present application, wherein the method includes: extracting target itinerary feature information according to target email information, wherein the target itinerary feature information includes: target transportation mode features, target itinerary node features, and / or target association features between the target transportation mode and the target itinerary node; generating target itinerary reminder information according to the target itinerary feature information. The present application is conducive to improving the accuracy of automated integration of itinerary email information, simplifying the process of establishing itinerary reminders, improving the accuracy and efficiency of automated generation of itinerary reminders, improving the relevance of itinerary reminders, reducing the probability of itinerary delays, itinerary conflicts, and people missing itineraries, improving the integration and matching between multiple itineraries, and improving the fit between people and itineraries.

[0015] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A schematic diagram of a process of processing a travel email provided in an embodiment of the present application; Figure 2 A structural schematic diagram of a travel email processing device provided in an embodiment of the present application; Figure 3 A structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0018] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0019] According to a first aspect of an embodiment of the present application, a method for processing travel emails is provided. Figure 1 A schematic diagram of a process of processing a travel email 100 provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method 100 includes: Step S110: extracting target trip characteristic information according to the target email information, wherein the target trip characteristic information includes: target transportation mode characteristics, target trip node characteristics, and / or target association characteristics of the target transportation mode and the target trip node.

[0020] Exemplarily, the above-mentioned target transportation mode characteristics may include: the type of target transportation mode, the flight number of the target transportation mode, the departure time of the target transportation mode, and / or the target departure point, target destination, target airport, target station, and / or the arrival time of the target transportation mode, etc.

[0021] Exemplarily, the target itinerary node features may include: target itinerary location features, such as: target hotel and / or target tourist attraction, etc.

[0022] Exemplarily, the target association features of the target transportation mode and the target itinerary node may include: the association relationship between the target transportation mode and the target destination, the association relationship between the target departure place and the target destination, the association relationship between the departure time of the target transportation mode and the target departure place, the association relationship between the departure time of the target transportation mode and the target departure place, the association relationship between the arrival time of the target transportation mode and the target destination, the association relationship between the target departure place and the target airport, the association relationship between the target destination and the target airport, the association relationship between the target departure place and the target station, the association relationship between the target destination and the target station, the association relationship between the target destination and the target hotel, the association relationship between the target destination and the target tourist attraction, and / or the association relationship between the target hotel and the target tourist attraction, etc. It should be noted that the above association relationships include: distance association relationships, and / or time node association relationships, etc.

[0023] In some feasible implementations, the subject, sender, and body of the target email can be converted into plain text target email information based on a preset model, and a text information extraction operation can be performed on the target email to extract the target trip feature information. The preset model can include a Long Short-Term Memory - Conditional Random Field (LSTM-CRF) model.

[0024] Exemplarily, based on the LSTM-CRF model, sequence labeling can be performed on the target email information to generate named entity recognition results and part-of-speech tagging results, and target trip feature information can be generated based on the named entity recognition results and part-of-speech tagging results. The data form of the target trip feature information can include: structured JSON data.

[0025] Specifically, based on the LSTM-CRF model, an entity boundary recognition operation can be performed on the above-mentioned target email information to determine the starting position and the ending position of the target entity, and according to the category of the entity, the above-mentioned target transportation mode characteristics, the above-mentioned target itinerary node characteristics, and / or the target association characteristics of the above-mentioned target transportation mode and the target itinerary node are generated.

[0026] Step S120: Generate target trip reminder information according to the target trip characteristic information.

[0027] Exemplarily, it can be based on the type of the above-mentioned target transportation mode, the flight number of the target transportation mode, the departure time of the target transportation mode, and / or the target departure place, the target destination, the target airport, the target station, and / or the arrival time of the target transportation mode, etc.; the characteristics of the target itinerary location, such as: the target hotel and / or the target tourist attraction, etc.; the association relationship between the target transportation mode and the target destination, the association relationship between the target departure place and the target destination, the association relationship between the departure time of the target transportation mode and the target departure place, the association relationship between the departure time of the target transportation mode and the target departure place, the association relationship between the arrival time of the target transportation mode and the target destination, the association relationship between the target departure place and the target airport, the association relationship between the target destination and the target airport, the association relationship between the target departure place and the target station, the association relationship between the target destination and the target station, the association relationship between the target destination and the target hotel, the association relationship between the target destination and the target tourist attraction, and / or the association relationship between the target hotel and the target tourist attraction, etc. It should be noted that the above-mentioned association relationship includes: distance association relationship, and / or time node association relationship, etc., to generate the target itinerary reminder information.

[0028] It should be noted that the target itinerary reminder information may include: multiple reminder forms, wherein the multiple reminder forms may include: message reminder, schedule reminder, alarm reminder, email reminder and / or schedule card reminder, etc.

[0029] Based on this, the method for processing itinerary emails provided in the embodiment of the present application includes: extracting target itinerary feature information according to the target email information, wherein the target itinerary feature information includes: target transportation mode features, target itinerary node features, and / or target association features between the target transportation mode and the target itinerary node; generating target itinerary reminder information according to the target itinerary feature information. The present application can improve the accuracy of automatic integration of target itinerary feature information, simplify the process of establishing target itinerary reminder information, improve the accuracy and efficiency of automatic generation of target itinerary reminder information, improve the relevance of target itinerary reminder information, reduce itinerary delays, itinerary conflicts, and the probability of people missing their itineraries, thereby improving the integration and matching between multiple itineraries, and improving the fit between people and itineraries.

[0030] In some feasible implementations, before extracting the travel feature information according to the target email information, the method further includes: Step S110a: Determine the target email according to the target keyword and / or the target domain name.

[0031] For example, the target keywords may include: airline names, hotel service provider names, travel service platform names, and itinerary booking related sentences composed of gerund structures, etc. The itinerary booking related sentences composed of gerund structures may include: "itinerary confirmation", "hotel reservation", "itinerary arrangement", etc.

[0032] Exemplarily, the email sender name, email title, and email body of the current email can be traversed and queried based on the above-mentioned target keywords. When it is determined that the email sender name, email title, and / or email body contain the above-mentioned target keywords, the current email is determined to be the target email.

[0033] Specifically, the plain text data of the email sender name, email title, and email body can be segmented based on the longest match algorithm and the industry-specific Chinese vocabulary, and then the segmentation results can be traversed and fuzzy compared with the target keyword dictionary. When it is determined that the plain text data of the email sender name, email title, and email body contain the target keywords in the above-mentioned target keyword dictionary, the current email is determined to be the target email.

[0034] Exemplarily, the domain name information corresponding to the above-mentioned airlines, the domain name information corresponding to the hotel service providers, and the domain name information corresponding to the travel service platform providers can be pre-stored to form a target domain name storage pool. When it is determined that the domain name of the current email belongs to the above-mentioned target domain name storage pool, the current email is determined to be the target email. It should be noted that the above-mentioned target domain name storage pool can be updated in real time according to the airline industry database, the hotel service provider industry database, and the travel service platform industry database.

[0035] Step S110b: Perform a target cleaning operation on the target email to generate target email information.

[0036] For example, after determining that the current email is a target email, a target parsing operation can be performed on the HyperText Markup Language (HTML) corresponding to the target email based on a preset regular expression to filter style data, layout data, and irrelevant noise data such as tags, symbols, and advertisements to generate structured target email information. The preset regular expression can be defined according to actual needs.

[0037] Based on this, the above method accurately determines the target email according to the target keyword and / or the target domain name, improves the accuracy of subsequent data cleaning operations and information extraction operations, avoids performance waste, and performs target cleaning operations on the target email to generate target email information, which is conducive to accurately removing redundant information and noise information in the target email information, thereby improving the extraction accuracy of itinerary feature information.

[0038] It should be noted that, before executing the following step S111, the target email may be further classified into a primary category according to the target keyword and / or the target domain name, and a primary category identifier may be generated for the target email.

[0039] Exemplarily, when the target email is determined to be a traffic email based on the target keywords and / or the target domain name corresponding to the traffic category, the following step S111 is performed on the target email. The target keywords corresponding to the traffic category may include: train schedule, station name, airline name, flight schedule, etc. The target domain name may include: official railway domain name, official airline domain name, etc.

[0040] It should be noted that the target emails can also be classified into secondary categories according to the target keywords corresponding to the above-mentioned transportation categories and / or the target domain names, and secondary category identifiers can be generated for the target emails to determine whether the target emails belong to train-related travel emails or airplane-related travel emails, etc., thereby improving the accuracy of determining the characteristics of the target transportation mode. Among them, for the target emails belonging to the transportation category, a transportation-specific email list view can be aggregated to improve the query efficiency of transportation-related emails.

[0041] In some feasible implementations, step S110: extracting itinerary feature information according to the target email information includes: Step S111: Identify the target email information to determine the characteristics of the target transportation mode; wherein the characteristics of the target transportation mode include: the class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and ending node characteristics corresponding to the target transportation mode, and / or, the safety assessment characteristics corresponding to the target transportation mode.

[0042] Exemplarily, the flight number characteristics corresponding to the above-mentioned target transportation mode may include: flight number characteristics, train number characteristics, etc.

[0043] Exemplarily, the time node features associated with the above-mentioned target transportation mode may include: flight departure date, flight arrival date, flight departure time, flight arrival time, train departure date, train departure time, train arrival date, train arrival time, etc.

[0044] Exemplarily, the starting and ending node features corresponding to the above-mentioned target transportation mode may include: flight boarding gate, flight boarding position, flight departure airport, flight arrival airport, flight departure city, flight arrival city, train departure platform, train arrival platform, train departure city, train arrival city, etc.

[0045] Exemplarily, the safety assessment features corresponding to the above-mentioned target transportation mode may include: the airline to which the flight belongs, the flight status, the flight model, the years of service of the aircraft, the locomotive depot to which the train belongs, the train status, the train model, the years of service of the train, etc.

[0046] Specifically, when it is determined that the target email belongs to the category of transportation email, the class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and ending node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode are extracted according to the target email information. Among them, the class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and ending node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode can be stored as structured JSON data. It should be noted that when the target email has been marked as a transportation email, and the target transportation mode characteristics have an extraction exception or extraction failure, and the target transportation mode characteristics cannot be determined, the mark is removed and the target email is restored to an ordinary email.

[0047] Based on this, the above method can accurately determine the class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and docking node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode according to the target email information, and provide a data basis for accurately generating target trip reminder information based on the above-mentioned class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and docking node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode, thereby improving the comprehensiveness and precision of the target trip reminder information and improving the exploitable value of the target trip reminder information.

[0048] It should be noted that, before executing the following step S112, the target email may be further classified into a primary category according to the target keyword and / or the target domain name, and a primary category identifier may be generated for the target email.

[0049] Exemplarily, when it is determined that the target email belongs to the itinerary node email according to the target keyword corresponding to the itinerary node email and / or the target domain name, step S112 is performed on the target email. The target keywords corresponding to the itinerary node email may include: "hotel", "check-in", "ticket", etc. The target domain name may include: the domain name corresponding to the hotel service provider, etc.

[0050] It should be noted that the target emails can also be classified into secondary categories according to the target keywords corresponding to the above-mentioned itinerary node emails, and secondary classification marks can be generated for the target emails to determine whether the target emails belong to hotel check-in emails or tourist attraction emails, etc., so as to finely determine the target itinerary node characteristics. Among them, the target emails belonging to itinerary node emails can be aggregated to generate a list view of itinerary node-specific emails to improve the query efficiency of itinerary node emails.

[0051] In some feasible implementations, step S110: extracting the itinerary characteristic information according to the target email information further includes: Step S112: Identify the target email information to determine the target itinerary node characteristics; wherein the target itinerary node characteristics include: target itinerary destination node characteristics, target itinerary destination node pointing characteristics, and / or, time node characteristics corresponding to the target itinerary destination node.

[0052] Exemplarily, the above-mentioned target itinerary node features may include: hotel name, hotel address, hotel phone number, attraction name, attraction address, attraction phone number, hotel city, attraction city, etc.

[0053] Exemplarily, the above-mentioned target itinerary node pointing feature may include: the pointing feature from the hotel to the scenic spot. For example: when the hotel is a Beijing AAA hotel and the scenic spot is the Beijing Forbidden City, the above-mentioned target itinerary node pointing feature may include pointing from the Beijing AAA hotel to the Beijing Forbidden City, and / or, from the Beijing Forbidden City to the Beijing AAA hotel. And / or, the pointing feature from the first itinerary city to the second itinerary city. For example: the first itinerary city may be an itinerary city earlier in the time series, and the second itinerary city may be an itinerary city later in the time series. For example: when the first itinerary city is Beijing and the second itinerary city is Seattle, the target itinerary node pointing feature is from Beijing to Seattle.

[0054] Specifically, the embodiment of the target itinerary node pointing feature may include: a three-dimensional map pointing form, or a two-dimensional map pointing form.

[0055] Exemplarily, the time node features corresponding to the above-mentioned target itinerary node may include: hotel check-in time, scenic spot visiting time.

[0056] Specifically, when it is determined that the target email belongs to the itinerary node type email, the target itinerary node features, the target itinerary node pointing features, and / or the time node features corresponding to the target itinerary node are extracted according to the target email information. Among them, the above-mentioned target itinerary node features, the above-mentioned target itinerary node pointing features, and / or the above-mentioned time node features corresponding to the target itinerary node can be stored as structured JSON data. It should be noted that when the target email has been marked as a itinerary node type email, and the target itinerary node feature extraction exception or extraction failure occurs, and the target itinerary node feature cannot be determined, the mark is removed and the above-mentioned target email is restored to an ordinary email.

[0057] Based on this, the above method can accurately determine the target itinerary node characteristics, the target itinerary node pointing characteristics, and / or the time node characteristics corresponding to the target itinerary node according to the target email information, and provide a data basis for accurately generating target itinerary reminder information based on the above target itinerary node characteristics, the target itinerary node pointing characteristics, and / or the time node characteristics corresponding to the target itinerary node, thereby improving the comprehensiveness and precision of the target itinerary reminder information and improving the exploitable value of the target itinerary reminder information.

[0058] In some feasible implementations, the above-mentioned association features between the target transportation mode and the target travel node include: spatial sequence association features and / or time series association features.

[0059] Exemplarily, the spatial sequence association features may include: spatial sequence association pointing features of departure cities and arrival cities corresponding to multiple itineraries, spatial sequence association pointing features of transportation methods corresponding to multiple itineraries, spatial sequence association pointing features of hotels corresponding to multiple itineraries, and spatial sequence association pointing features of tourist attractions in multiple itineraries. The spatial sequence association pointing features may include: geographic coordinate features, distance features, direction features, etc.

[0060] Exemplarily, the time series association features may include: time sequence features of departure and arrival times corresponding to multiple itineraries, time sequence features of hotel check-in and check-out times corresponding to multiple itineraries, time sequence features of departure and arrival times of transportation methods corresponding to multiple itineraries, and time sequence features of sightseeing times corresponding to tourist attractions in multiple itineraries. The time sequence features are used to arrange the order of specific behaviors of users, wherein the specific behaviors include: taking the target transportation, leaving the target city, going to the target city, checking into the target hotel, leaving the target hotel, going to the target attraction, etc.

[0061] There may be a one-to-one correspondence between the time nodes in the time series association feature and the travel nodes in the space series association feature, so as to improve the orderliness of the schedule reminder information.

[0062] Based on this, the above method can accurately determine the spatial sequence association characteristics and / or time series association characteristics of the target transportation mode and the target travel node according to the characteristics of the target transportation mode and the target travel node, which is conducive to providing accurate data support for the accurate generation of spatial dimension and / or time dimension schedule reminder information.

[0063] In some feasible implementations, step S120: generating target trip reminder information according to the target trip characteristic information includes: Step S121: Generate schedule reminder information according to the target traffic mode characteristics, the target trip node characteristics, and the time series association characteristics, wherein the time series association characteristics correspond one-to-one with the target traffic mode characteristics and the target trip node characteristics.

[0064] Exemplarily, the target traffic mode features and target trip node features can be sorted according to the time series association features to generate a target sorting result. According to the target sorting results, schedule reminders are automatically added to the target trip APP of the target electronic device of the target user in sequence. Among them, the target electronic device can include: computers, PADs, mobile phones, and vehicle terminals, etc. Specifically, the target trip APP can include: calendar software, or a user-specified schedule APP, etc.

[0065] For example, the target trip APP can be triggered once per second to detect whether the time displayed by the current system clock reaches the reminder time corresponding to the target trip. The reminder time can be determined based on the time corresponding to the target trip and the preset advance reminder time threshold. The preset advance reminder time threshold can be customized according to user needs.

[0066] Specifically, when the departure time of the target user's train ticket is 12:00 on October 1st, and the preset advance reminder period threshold is 2 hours, the reminder service corresponding to the target itinerary is triggered at 10:00 on October 1st. When the current system clock is detected to show 10:00 on October 1st, the itinerary reminder of the target user is added to the queue to be sent. When the target user sets the target itinerary reminder method to SMS, the mobile phone number bound to the target user is queried, and the SMS gateway is called to send SMS to the electronic device corresponding to the target user. When the target user sets the target itinerary reminder method to email, the email address bound to the target user is queried, and the email is sent to the email address corresponding to the target user.

[0067] It should be noted that, if the reminder corresponding to the target trip has been sent successfully, the task of sending the reminder corresponding to the target trip in the waiting queue will be deleted. If the reminder corresponding to the target trip fails to be sent or the sending queue is full, the task of sending the reminder corresponding to the target trip will be re-executed in the next preset polling cycle. The above preset polling cycle can be defined according to the needs of the target user.

[0068] Based on this, the above method can accurately generate schedule reminder information according to the target transportation mode characteristics, target trip node characteristics, and time series correlation characteristics, which is conducive to improving the accuracy and efficiency of automatic generation of target trip reminder information, improving the relevance of target trip reminder information, reducing trip delays, trip conflicts, and the probability of people missing their trips, improving the integration and matching between multiple trips, and improving the fit between people and trips. The above time series correlation characteristics correspond one-to-one with the target transportation mode characteristics and the target trip node characteristics, which is conducive to improving the orderliness of schedule reminder information.

[0069] In some feasible implementations, step S120: generating target trip reminder information according to the target trip characteristic information further includes: Step S122: Generate a target reminder card based on target transportation mode characteristics, target trip node characteristics, spatial sequence association characteristics, and / or time series association characteristics.

[0070] Exemplarily, the above-mentioned target transportation mode features, target trip node features, spatial sequence association features, and / or time series association features may be aggregated to generate a primary target prompt card.

[0071] Exemplarily, a secondary target reminder card can also be generated based on the target transportation mode characteristics, target trip node characteristics, spatial sequence association characteristics, or time series association characteristics. For example, based on the target trip node characteristics, a target trip node secondary target reminder card is generated, wherein the target trip node secondary target reminder card may include: company logo, company name, arrival time, company location, company contact number, etc. It should be noted that, if the target email information does not contain the above information, the above information can be retrieved from channels such as the company database or official account to generate the target trip node secondary target reminder card.

[0072] In some feasible implementations, the target reminder card can be generated based on the timeline. Specifically, the target transportation mode characteristics, target itinerary node characteristics, and spatial sequence association characteristics can be combined with time series association characteristics to form a target timeline. Among them, each target itinerary node and each target transportation mode can be marked on the target reminder card in the form of an icon, and each target itinerary node and each target transportation mode can generate a corresponding short text introduction to improve the target user's grasp of itinerary-related information. Among them, the above short text introduction can include: the time, address, activity content and precautions of each target itinerary point.

[0073] It should be noted that the key feature information such as departure time node features, flight features, hotel check-in features, etc. can be bolded, highlighted with different colors, and / or highlighted with different special marks to intuitively highlight the above key feature information. It should be noted that the above key feature information can be selected or set by the target user, and is not specifically limited here.

[0074] It should be noted that, when multiple target trips are involved or the target trip involves multiple target trip nodes, the above-mentioned target prompt card can also display the above-mentioned target transportation mode characteristics, target trip node characteristics, spatial sequence association characteristics, and / or, time series association characteristics in the form of a map, so as to intuitively display the relative position, relative distance, relative direction, etc. between the target trip nodes.

[0075] It should be noted that the above-mentioned destination reminder card can also be provided with interactive controls to facilitate information retrieval. Among them, the above-mentioned interactive space can be used to facilitate jumping from the current destination reminder card interface to the official website of the airline, the official website of the hotel, and / or map navigation.

[0076] Based on this, the above method can accurately generate target prompt cards according to the target transportation mode characteristics, target travel node characteristics, spatial sequence association characteristics, and / or time series association characteristics, which is conducive to providing convenience for target users to quickly and efficiently grasp the target travel characteristic information.

[0077] In some feasible implementations, the method 100 further includes: Step S130: Determine target conflict characteristics based on target transportation mode characteristics, target travel node characteristics, and / or association characteristics between the target transportation mode and the target travel node.

[0078] Step S140: Generate an abnormal reminder based on the above-mentioned target conflict characteristics.

[0079] Exemplarily, when there is an overlapping period between the time node feature corresponding to the first target travel node and the time node feature corresponding to the second target travel node, and / or when the time difference between the time node feature corresponding to the first target travel node and the time node feature corresponding to the second target travel node is less than a preset time threshold, it is judged that there is a target conflict feature, and an abnormal reminder is generated based on the target conflict feature, wherein the abnormal reminder includes: the target travel node corresponding to the target conflict feature and the time node corresponding to the target travel node. The abnormal reminder can generate a pop-up window in the target electronic device in the form of an abnormal message prompt card. The abnormal reminder can also be transmitted to the target user in the form of a voice broadcast.

[0080] It should be noted that the above-mentioned preset time threshold can be determined based on the distance difference between the above-mentioned first target journey node and the above-mentioned second target journey node, the congestion of the traffic sections between the first target journey node and the above-mentioned second target journey node, and the minimum value of the travel time required for the corresponding multiple transportation modes between the first target journey node and the above-mentioned second target journey node.

[0081] Specifically, the above preset time threshold can be determined according to the following formula: (1); in, is the preset time threshold, is the distance difference between the first target trip node and the second target trip node, is the minimum value of the travel time required for the corresponding multiple transportation modes between a target trip node and the second target trip node, is the congestion degree of the traffic section between the first target trip node and the second target trip node, is the first weight, is the second weight, The third weight.

[0082] It should be noted that the first weight , the second weight , the third weight The sum of is 1, where the first weight , the second weight , the third weight Decrease in sequence.

[0083] Based on this, the above method can be implemented to determine the existence of target conflict characteristics based on the target transportation mode characteristics, the target itinerary node characteristics, and / or the associated characteristics between the target transportation mode and the target itinerary node, and accurately generate abnormal reminders based on the above target conflict characteristics, which is conducive to timely reminding the target user to verify the target itinerary, and is conducive to preventing the target user from proposing multiple target itineraries against each other based on the feedforward mechanism, thereby improving the integration and matching between multiple target itineraries, and improving the smoothness and accuracy of the target user's itinerary flow.

[0084] In some feasible implementations, the method as described in any of the above items further includes: Step S150: When it is determined that there are multiple persons associated with the target itinerary, an auxiliary reminder card is generated according to the target itinerary feature information corresponding to other persons.

[0085] It should be noted that, when it is determined that there are multiple people associated with the target itinerary based on traffic target emails and / or target itinerary node emails, an auxiliary reminder card can be generated based on the target itinerary characteristic information corresponding to other people to inform the target user of the itinerary information of other accompanying persons, thereby improving the interoperability of the itinerary information between the target user and other accompanying persons, and improving the coordination of the target user's itinerary with the itineraries of other accompanying persons.

[0086] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0087] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.

[0088] According to a second aspect of an embodiment of the present application, a device for processing travel emails is provided. Figure 2 A structural schematic diagram of a travel email processing device 200 provided in an embodiment of the present application. Figure 2 The device 200 shown includes: an extraction unit 210 and a generation unit 220.

[0089] The extraction unit 210 is used to extract target trip feature information according to the target email information, wherein the target trip feature information includes: target transportation mode features, target trip node features, and / or target association features between the target transportation mode and the target trip node; The generating unit 220 is used to generate target trip reminder information according to the target trip characteristic information.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described method can refer to the corresponding process in the aforementioned system embodiment, and will not be repeated here.

[0091] According to a third aspect of the present invention, an electronic device is also provided. Figure 3 A structural schematic diagram of an electronic device 300 provided in an embodiment of the present application.

[0092] like Figure 3 As shown, the electronic device 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the terminal device or the server are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0093] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.

[0094] In particular, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0095] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0096] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0097] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves.

[0098] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A method for processing travel emails, characterized in that: include: Extracting target trip feature information according to the target email information, wherein the target trip feature information includes: target transportation mode features, target trip node features and / or target association features between the target transportation mode and the target trip node; Generate target trip reminder information according to the target trip characteristic information.

2. The method for processing itinerary emails according to claim 1, characterized in that: Before extracting the travel feature information according to the target email information, the method further includes: Determine the target emails based on the target keywords and / or target domain names; A target cleaning operation is performed on the target mail to generate the target mail information.

3. The method for processing travel emails according to claim 2, characterized in that: The extracting of itinerary characteristic information according to the target email information includes: Identify the target mail information to determine the target transportation mode characteristics; The target transportation mode characteristics include: The class number characteristics corresponding to the target transportation mode, the time node characteristics associated with the target transportation mode, the starting and ending node characteristics corresponding to the target transportation mode, and / or the safety assessment characteristics corresponding to the target transportation mode.

4. The method for processing travel emails according to claim 3, characterized in that: The step of extracting the itinerary characteristic information according to the target email information further includes: Identify the target email information to determine the target trip node characteristics; The target trip node features include: Target itinerary node characteristics, target itinerary node pointing characteristics, and / or, time node characteristics corresponding to the target itinerary node.

5. The method for processing travel emails according to claim 4, characterized in that: The association features between the target transportation mode and the target trip node include: Spatial series correlation features, and / or, time series correlation features.

6. The method for processing travel emails according to claim 5, characterized in that: The generating target trip reminder information according to the target trip characteristic information includes: Schedule reminder information is generated according to the target traffic mode characteristics, the target trip node characteristics, and the time series association characteristics, wherein the time series association characteristics correspond one-to-one to the target traffic mode characteristics and the target trip node characteristics.

7. The method for processing travel emails according to claim 6, characterized in that: The generating target trip reminder information according to the target trip characteristic information further comprises: A target prompt card is generated according to the target transportation mode characteristics, the target trip node characteristics, the spatial sequence association characteristics, and / or the time series association characteristics.

8. The method for processing travel mail according to any one of claims 1 to 7, characterized in that: The method further comprises: When it is determined that there are multiple persons associated with the target trip, An auxiliary reminder card is generated according to the target itinerary characteristic information corresponding to other persons.

9. A device for processing travel mails, characterized in that: include: An extraction unit is used to extract target trip feature information according to the target email information, wherein the target trip feature information includes: target transportation mode features, target trip node features and / or target association features of the target transportation mode and the target trip node; A generating unit is used to generate target trip reminder information according to the target trip characteristic information.

10. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are used by the processor to execute the method for processing travel emails as described in any one of claims 1 to 8 when the processor is running.

Images