Order matching method and system of service platform

Abstract

The invention provides an order matching method and system for a service platform, and the method comprises the steps: obtaining user order demand information (including travel, service and resource demands) and service provision information (including service travel, service and resource provision information) in a tourism service platform, carrying out the demand feature extraction of the user order demand information, and obtaining a user preference feature set; providing feature extraction is carried out on the service providing information to obtain a server capability feature set, then feature association processing is carried out on the service providing information and the server capability feature set to generate a demand capability association matrix, and an order service matching degree parameter is calculated based on the matrix to represent the degree that the service providing information meets the user order demand information; and finally, generating an order matching scheme according to the matching degree parameter and sending the order matching scheme to a user interface for display, thereby improving order matching accuracy and efficiency, and satisfying individual demands of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital service, in particular to an order matching method and system of a service platform. BACKGROUND

[0002] In the current rapid development of the tourism service industry, the tourism service platform has become an important bridge connecting users and service providers. However, the existing tourism service platform has many deficiencies in order matching. On the one hand, when obtaining user order demand information and service provider information, the traditional platform often only lists the information simply, lacking systematic classification of the information. For example, for user itinerary demand information, only the departure place and destination may be recorded, while key details such as travel mode preference and stay time preference are ignored; for service provider itinerary provision information, only the range of the itinerary that can be provided is roughly stated, without details of the specific time arrangement and itinerary details.

[0003] On the other hand, in feature extraction, the existing technology usually only focuses on single-dimensional features, such as only considering the user's price preference for accommodation, while ignoring multi-aspect preference features such as itinerary, service, and the corresponding ability features of service providers. This results in an inability to comprehensively and accurately measure the degree of fit between user demand and service provision in the matching process. Moreover, the traditional platform uses simple algorithms such as weighted summation to calculate the matching degree, without deeply mining the internal correlation between user preference features and service provider ability features, resulting in inaccurate matching results that cannot meet the increasingly diverse and personalized tourism needs of users, and affecting the service efficiency of service providers and the overall operation effect of the platform. SUMMARY

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present application, the embodiments of the present application provide an order matching method of a service platform, which comprises: obtaining user order demand information and service provision information in a tourism service platform, the user order demand information comprising user itinerary demand information, user service demand information and user resource demand information, and the service provision information comprising service provider itinerary provision information, service provider service provision information and service provider resource provision information; performing demand feature extraction processing on the user order demand information to obtain a user preference feature set, the user preference feature set comprising itinerary preference features, service preference features and resource preference features; performing provision feature extraction processing on the service provision information to obtain a service provider ability feature set, the service provider ability feature set comprising itinerary provision ability features, service provision ability features and resource provision ability features; perform feature correlation processing on the user preference feature set and the service provider capability feature set to generate a demand-capability correlation matrix, each element in the demand-capability correlation matrix being used to represent a correlation degree between one user preference feature in the user preference feature set and one service provider capability feature in the service provider capability feature set; perform matching degree calculation processing on the user order demand information and the service providing information based on the demand-capability correlation matrix to obtain an order-service matching degree parameter, the order-service matching degree parameter being used to represent a degree to which the service providing information satisfies the user order demand information; generate an order matching scheme according to the order-service matching degree parameter, and send the order matching scheme to a user interface of the tourism service platform for display.

[0005] In still another aspect, the embodiment of the present application further provides an order matching system of a service platform, comprising a processor, a machine readable storage medium, the machine readable storage medium being connected with the processor, the machine readable storage medium being used to store programs, instructions or codes, and the processor being used to execute the programs, instructions or codes in the machine readable storage medium to realize the above method.

[0006] Based on the above aspects, the embodiment of the present application comprehensively acquires user order demand information and service providing information in a tourism service platform, classifies the same, covers user itinerary, service, resource demand and corresponding service provider providing information, extracts demand features of the user order demand information to obtain a user preference feature set containing itinerary, service and resource preference features, extracts providing features of the service providing information to obtain a service provider capability feature set, realizes deep mining of multi-dimensional features of users and service providers, generates a demand-capability correlation matrix through feature correlation processing, can clearly present a correlation degree between user preference features and service provider capability features, accurately grasps a matching relationship between the two from a micro level, performs matching degree calculation based on the demand-capability correlation matrix to obtain an order-service matching degree parameter which can scientifically and accurately represent a degree to which service providing information satisfies user order demand information, finally generates an order matching scheme according to the matching degree parameter and displays the same on a user interface, greatly improves the accuracy and efficiency of order matching, effectively meets user individualized demand, and improves service effect of service providers and overall operation quality of the platform. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is an execution flow schematic diagram of the order matching method of the service platform provided by the embodiment of the present application.

[0008] Figure 2 is a schematic diagram of exemplary hardware and software components of the order matching system of the service platform provided by the embodiment of the present application. DETAILED DESCRIPTION

[0009] The application will be described in detail below with reference to the accompanying drawings, Figure 1 is a flowchart of the order matching method of the service platform provided by an embodiment of the application, and the order matching method of the service platform will be described in detail below.

[0010] Step S110: Obtain user order demand information and service providing information in the tourism service platform, the user order demand information including user itinerary demand information, user service demand information and user resource demand information, and the service providing information including service provider itinerary providing information, service provider service providing information and service provider resource providing information.

[0011] In this embodiment, the user order demand information and the service providing information can be extracted from the database and related storage modules of the tourism service platform. The user order demand information covers various demands of the user for tourism services submitted on the platform, wherein the user itinerary demand information relates to travel arrangement, such as departure place, destination, passing place and itinerary theme in a specific time period; the user service demand information includes requirements for services in the tourism process, such as whether a guide service or a translation service is needed and service standards; and the user resource demand information is the requirement for tourism resources, such as hotel type, room quantity, vehicle type and quantity, etc.

[0012] The service providing information is the available tourism service content published by the service provider on the platform, the service provider itinerary providing information including available itinerary time period, covered departure place, passing place, destination and itinerary theme type, etc.; the service provider service providing information covering available service types, such as guide, translation, catering reservation, etc., and service standards and providing modes, such as whole-process accompanying or phased service, etc.; and the service provider resource providing information including available resource types, such as hotel, vehicle, scenic spot ticket, etc., and resource quantity and quality, etc.

[0013] In step S110, data collection and data authorization permission strictly follow relevant laws and regulations. Before obtaining the user order demand information, the tourism service platform will clearly inform the user of the scope, purpose, use and storage period of data collection through user registration agreement, privacy policy and other documents, including the collection method and use scenario of personal related data such as user itinerary demand information, service demand information and resource demand information. When the user submits an order demand on the platform, the user needs to actively check the authorization option of agreeing to data collection and use, and the authorization behavior is recorded and archived in written form (electronic agreement), so as to ensure that the user clearly knows and voluntarily authorizes the platform to process his / her personal data. Without the explicit authorization of the user, the platform will not collect any user information arbitrarily. For service providing information, the platform requires service providers to submit legal business qualification certificates when registering and sign a data providing authorization agreement, stating that the provided service information and related data are true, legal, and do not involve infringement of third-party rights, and authorizing the platform to process and display these information as necessary. During data collection, the collection range is strictly limited, and only data directly related to the tourism service order is collected, without collecting sensitive information unrelated to the service. For the collected user ID card number, contact information and other core sensitive data, except for the necessary steps such as identity verification and order confirmation, desensitization processing is performed to remove the identification that can directly identify the user's identity. The platform establishes a data access permission management mechanism, only authorized staff can access related data when performing their duties, and the access behavior is traceable throughout the process. At the same time, the data collection and authorization process is regularly audited, and third-party institutions are invited to assess the legality of data processing activities to ensure compliance with legal requirements. If the laws and regulations are updated, the platform will adjust the data collection and authorization permission mechanism in a timely manner to maintain compliance.

[0014] Step S120: performing demand feature extraction processing on the user order demand information to obtain a user preference feature set, the user preference feature set including a travel preference feature, a service preference feature, and a resource preference feature.

[0015] After obtaining the user order demand information, key feature items are extracted from the text, data and other contents thereof. These key feature items form a user preference feature set, wherein the travel preference feature reflects the user's preference in travel arrangement, the service preference feature embodies the user's preference for services, and the resource preference feature shows the user's preference for resources.

[0016] Step S121: performing travel feature analysis processing on the user travel demand information to extract a travel time feature, a travel location feature and a travel type feature in the user travel demand information, and combining the travel time feature, the travel location feature and the travel type feature to form a travel preference feature.

[0017] The travel feature analysis processing is performed on the user travel demand information, and the features related to time, location and type are extracted from the information, which specifically reflect the user's preference in travel, and are combined to form a travel preference feature.

[0018] Step S1211: performing text word segmentation processing on the user travel demand information to decompose the user travel demand information into a plurality of travel text words.

[0019] The user itinerary demand information is usually presented in text form, such as "plan to start from location X, pass through location Y, and go to location Z, and have a historical and cultural theme tour, participate in historical site visit and folk experience activities, and the itinerary distance is within a certain range".

[0020] The above text is segmented into multiple itinerary text words such as "plan", "in", "specific time period", "from", "location X", "start", "pass through", "location Y", "go to", "location Z", "have", "a", "historical and cultural", "theme", "tour", "on the way", "participate", "historical site visit", "and", "folk experience", "activity", "itinerary", "distance", "within", "a certain range" by using a dictionary-based segmentation method combined with a professional dictionary in the tourism field.

[0021] Step S1212: Perform part-of-speech tagging on the multiple itinerary text words to identify words representing time, words representing location, and words representing type.

[0022] After obtaining the multiple itinerary text words, a statistical-based machine learning model such as a Hidden Markov Model (HMM) is used to perform part-of-speech tagging on each word. The machine learning model is trained on a large amount of annotated corpus and can determine the part-of-speech of a word based on its context information.

[0023] In the above example, after part-of-speech tagging, "specific time period" is identified as a word representing time, "location X", "location Y", and "location Z" are identified as words representing location, and "historical and cultural theme", "historical site visit", "folk experience", and "a certain range" are identified as words representing type.

[0024] Step S1213: Extract itinerary time features from the words representing time, including itinerary start time, itinerary end time, and itinerary duration.

[0025] Extract itinerary time features from the identified words representing time. For the word "specific time period", further determine the specific time point and duration in combination with other related descriptions in the user order demand information. For example, if the text also mentions "the itinerary is expected to start at the beginning of the month and end at the middle of the month", the itinerary start time is a specific date at the beginning of the month, the itinerary end time is a specific date in the middle of the month, and the itinerary duration is the number of days between the start time and the end time.

[0026] Step S1214: Extract itinerary location features from the words representing location, including itinerary start location, itinerary passing location, and itinerary destination location.

[0027] Extract itinerary location features from words representing locations. "Location X" is explicitly the departure point of the itinerary, "Location Y" is a location along the route, and "Location Z" is the destination. If the text provides more detailed descriptions of these locations, such as "Location X is a central square in a city," "Location Y is the entrance to an ancient town," or "Location Z is a mountain resort," then this detailed information is included in the corresponding itinerary location features.

[0028] Step S1215: Extract trip type features from the vocabulary representing types, the trip type features including trip theme type, trip activity type and trip distance type.

[0029] Extract itinerary type features from the vocabulary indicating type. "Historical and cultural theme" is identified as the itinerary theme type; "visiting historical sites" and "experiencing folk customs" belong to the itinerary activity type; "a certain range" combined with the specific context is identified as the itinerary distance type, such as medium distance range.

[0030] Step S1216: Combine the trip time feature, the trip location feature, and the trip type feature according to a preset feature combination rule to form a trip preference feature that includes time dimension, location dimension, and type dimension.

[0031] According to the preset feature combination rules, the trip time feature, trip location feature, and trip type feature are combined. For example, first, the trip start time, trip end time, and trip duration are arranged by time dimension; then, the trip departure point, trip route points, and trip destination are arranged by location dimension; finally, the trip theme type, trip activity type, and trip distance type are arranged by type dimension. The combination forms a multi-dimensional trip preference feature.

[0032] Step S1217: Perform feature verification processing on the combined trip preference features to ensure that the trip preference features can accurately reflect the trip preferences in the user's trip demand information.

[0033] The combined trip preference features undergo feature verification processing. By comparing the extracted trip preference features with the original user trip demand information, it is checked for any missing or incorrect feature items. If a feature item is found to be inconsistent with the original information, such as an error in calculating the trip duration, the feature item is re-extracted and combined until the trip preference features accurately reflect the trip preferences in the user trip demand information.

[0034] Step S122: Perform service feature parsing processing on the user service demand information, extract service type features, service standard features and service method features from the user service demand information, and combine the service type features, the service standard features and the service method features to form service preference features.

[0035] The user service demand information is analyzed to obtain service feature. The user service demand information can be "hope to obtain professional guide service during the travel, and require the guide to have rich historical and cultural knowledge, and the service mode is full- accompany".

[0036] First, the text is segmented to obtain the words "hope", "in", "travel", "process", "get", "professional", "guide", "service", "require", "guide", "have", "rich", "historical and cultural", "knowledge", "service", "mode", "full- accompany".

[0037] Then, the part-of-speech tagging is performed to identify the words "guide service" representing the service type, "professional" and "have rich historical and cultural knowledge" representing the service standard, and "full- accompany" representing the service mode.

[0038] From these words, the service type feature is extracted as guide service, the service standard feature is extracted as professional and having rich historical and cultural knowledge, and the service mode feature is extracted as full- accompany.

[0039] According to the preset combination rule, the service type feature, the service standard feature and the service mode feature are combined to form a service preference feature, which contains information of three dimensions of service type, service standard and service mode.

[0040] Step S123: performing resource feature analysis processing on the user resource demand information, extracting resource type feature, resource quantity feature and resource quality feature in the user resource demand information, and combining the resource type feature, the resource quantity feature and the resource quality feature to form a resource preference feature.

[0041] The user resource demand information is analyzed to obtain resource feature. The user resource demand information can be "need to book two three-star hotels and rent one comfortable car".

[0042] The text is segmented to obtain the words "need", "book", "three-star", "hotel", "two", "rent", "comfortable", "car", "one".

[0043] After part-of-speech tagging, the words "hotel" and "car" representing resource type, "two" and "one" representing resource quantity, and "three-star" and "comfortable" representing resource quality are identified.

[0044] The resource type feature is extracted as hotel and car, the resource quantity feature is extracted as two hotels and one car, and the resource quality feature is extracted as three-star hotel and comfortable car.

[0045] The features are combined according to the combination rule to form a resource preference feature, which contains information of three dimensions of resource type, resource quantity and resource quality.

[0046] Step S124: The trip preference feature, the service preference feature and the resource preference feature are subjected to feature standardization and integration processing to form a user preference feature set containing trip dimension, service dimension and resource dimension.

[0047] The trip preference feature, the service preference feature and the resource preference feature are subjected to feature standardization and integration processing. The Min-Max standardization method is adopted to map the numerical range of each feature into the same interval, for example, all feature values are converted to between 0 and 1.

[0048] For the time feature in the trip preference feature, if the original time is in days, the range is 1-10 days, and the numerical value is converted to between 0 and 1 through the standardization formula; for non-numeric features such as location feature and type feature, the one-hot encoding method is adopted for processing, which is converted to a numeric feature.

[0049] The standardized trip preference feature, the service preference feature and the resource preference feature are integrated in the order of trip dimension, service dimension and resource dimension to form a user preference feature set, which is a multi-dimensional feature combination and comprehensively reflects the user's preferences in trip, service and resource.

[0050] Step S130: The service provider information is subjected to service feature extraction processing to obtain a service provider capability feature set, which includes trip providing capability feature, service providing capability feature and resource providing capability feature.

[0051] After obtaining the service provider information, the service feature extraction processing is performed. Through corresponding algorithms and rules, key features are extracted from the service provider information, which form a service provider capability feature set. The trip providing capability feature reflects the service provider's ability in trip arrangement, the service providing capability feature embodies the service provider's ability to provide services, and the resource providing capability feature demonstrates the service provider's ability to provide resources.

[0052] Step S131: The service provider trip providing information is subjected to trip providing capability analysis processing to extract the trip providing time feature, the trip providing location feature and the trip providing type feature in the service provider trip providing information, and the trip providing time feature, the trip providing location feature and the trip providing type feature are combined to form the trip providing capability feature.

[0053] The service provider itinerary providing information is parsed to obtain itinerary providing capability. The service provider itinerary providing information can be "a historical and cultural theme itinerary can be arranged in the first half of each month, starting from location A, passing through location B, and going to location C."

[0054] The text is segmented to obtain the words "can", "in", "each month", "the", "first half of the month", "arrange", "itinerary", "can", "from", "location A", "start", "pass through", "location B", "go to", "location C", "provide", "historical and cultural", "theme", "itinerary", and "itinerary".

[0055] After part-of-speech tagging, the words "first half of each month" representing the providing time, "location A", "location B", and "location C" representing the providing location, and "historical and cultural theme" representing the providing type are identified.

[0056] From these words, the itinerary providing time feature is extracted as the first half of each month, the itinerary providing location feature includes the starting location A, the passing-through location B, and the destination location C, and the itinerary providing type feature is the historical and cultural theme.

[0057] According to the preset feature combination rule, the features are combined to form the itinerary providing capability feature, which includes information of providing time, providing location, and providing type in three dimensions.

[0058] For example, step S1311: text segmentation processing is performed on the service provider itinerary providing information to divide the service provider itinerary providing information into multiple itinerary providing text words.

[0059] The service provider itinerary providing information is in text form, such as "a natural scenery theme itinerary can be arranged from location D, passing through location E, and going to location F in the first two months of each quarter."

[0060] Using a dictionary-based segmentation method, combined with a professional dictionary in the tourism field, the text is segmented to obtain multiple itinerary providing text words such as "can", "in", "each quarter", "the", "first two months", "arrange", "from", "location D", "start", "pass through", "location E", "go to", "location F", "natural scenery", "theme", and "itinerary".

[0061] Step S1312: part-of-speech tagging is performed on the multiple itinerary providing text words to identify words representing providing time, words representing providing location, and words representing providing type.

[0062] The HMM is used to perform part-of-speech tagging on the text words of the multiple itineraries. In the above example, "the first two months of each quarter" is identified as a word indicating a time of provision, "location D", "location E", and "location F" are identified as words indicating a location of provision, and "natural landscape theme" is identified as a word indicating a type of provision.

[0063] Step S1313: extracting an itinerary provision time feature from the word indicating a time of provision, the itinerary provision time feature including an itinerary provision start time, an itinerary provision end time, and an itinerary provision duration.

[0064] The itinerary provision time feature is extracted from the word "the first two months of each quarter" indicating a time of provision. The itinerary provision start time is the first day of the first month of each quarter, the itinerary provision end time is the last day of the second month of each quarter, and the itinerary provision duration is the total number of days of the two months.

[0065] Step S1314: extracting an itinerary provision location feature from the word indicating a location of provision, the itinerary provision location feature including an itinerary provision departure location, an itinerary provision passing location, and an itinerary provision destination location.

[0066] The itinerary provision location feature is extracted from the words "location D", "location E", and "location F" indicating a location of provision. "Location D" is the itinerary provision departure location, "location E" is the itinerary provision passing location, and "location F" is the itinerary provision destination location. If there is a more detailed description, such as "location D is a train station square", the detailed information is included in the itinerary provision departure location feature.

[0067] Step S1315: extracting an itinerary provision type feature from the word indicating a type of provision, the itinerary provision type feature including an itinerary provision theme type, an itinerary provision activity type, and an itinerary provision distance type.

[0068] The itinerary provision type feature is extracted from the word "natural landscape theme" indicating a type of provision. The itinerary provision theme type is a natural landscape theme. In combination with other descriptions in the service provider itinerary provision information, if it is mentioned that "mountain climbing and picnic activities can be arranged along the way, and the itinerary distance is within a certain range", the itinerary provision activity type is mountain climbing and picnic, and the itinerary provision distance type is the certain range.

[0069] Step S1316: combining the itinerary provision time feature, the itinerary provision location feature, and the itinerary provision type feature according to a preset feature combination rule to form an itinerary provision capability feature including a provision time dimension, a provision location dimension, and a provision type dimension.

[0070] According to the preset characteristic combination rule, the itinerary providing start time, the itinerary providing end time, and the itinerary providing duration in the itinerary providing time feature are arranged first, the itinerary providing departure location, the itinerary providing passing location, and the itinerary providing destination location in the itinerary providing location feature are arranged second, and the itinerary providing theme type, the itinerary providing activity type, and the itinerary providing distance type in the itinerary providing type feature are arranged last, to form the itinerary providing ability feature by combination.

[0071] In step S132, the service providing ability analysis processing is performed on the service provider service providing information, the service providing type feature, the service providing standard feature, and the service providing mode feature in the service provider service providing information are extracted, and the service providing type feature, the service providing standard feature, and the service providing mode feature are combined to form the service providing ability feature.

[0072] The service providing ability analysis processing is performed on the service provider service providing information. The service provider service providing information can be "professional translation service can be provided, and the translator needs to be proficient in multiple languages, and the service mode is on-call".

[0073] After the text is segmented, the words "can", "provide", "four-star", "hotel", "three", "luxury", "bus", and "two" are obtained.

[0074] After the part-of-speech tagging, the word "translation service" representing the service providing type, the words "professional" and "proficient in multiple languages" representing the service providing standard, and the word "on-call" representing the service providing mode are identified.

[0075] The service providing type feature is extracted as translation service, the service providing standard feature is extracted as professional and proficient in multiple languages, and the service providing mode feature is extracted as on-call, to form the service providing ability feature by combination.

[0076] In step S133, the resource providing ability analysis processing is performed on the service provider resource providing information, the resource providing type feature, the resource providing quantity feature, and the resource providing quality feature in the service provider resource providing information are extracted, and the resource providing type feature, the resource providing quantity feature, and the resource providing quality feature are combined to form the resource providing ability feature.

[0077] The resource providing ability analysis processing is performed on the service provider resource providing information. The service provider resource providing information can be "three four-star hotels and two luxury buses can be provided".

[0078] After the text is segmented, the words "can", "provide", "four-star", "hotel", "three", "luxury", "bus", and "two" are obtained.

[0079] After the part-of-speech tagging, the words "hotel" and "bus" representing the resource providing type, the words "three" and "two" representing the resource providing quantity, and the words "four-star" and "luxury" representing the resource providing quality are identified.

[0080] The resource providing type features are extracted as hotel and bus, the resource providing quantity features are extracted as three hotels and two buses, and the resource providing quality features are extracted as four-star hotel and luxury bus, which are combined to form the resource providing capability features.

[0081] Step S134: The trip providing capability features, the service providing capability features, and the resource providing capability features are standardized and integrated to form a service provider capability feature set containing trip providing dimension, service providing dimension, and resource providing dimension.

[0082] The trip providing capability features, the service providing capability features, and the resource providing capability features are standardized and integrated. The same standardization method as processing the user preference feature set is adopted, i.e., Min-Max standardization, which maps the numerical range of each feature to the same interval. For non-numeric features, one-hot encoding is also used to convert them to numeric features.

[0083] The integration process is performed in the order of trip providing dimension, service providing dimension, and resource providing dimension. The standardized trip providing capability features, service providing capability features, and resource providing capability features are arranged and combined in sequence to form the service provider capability feature set. This service provider capability feature set comprehensively reflects the service provider's capabilities in trip providing, service providing, and resource providing. Each dimension's features are standardized to ensure comparability between different features.

[0084] Step S140: The user preference feature set and the service provider capability feature set are associated to generate a demand-capability association matrix, where each element represents the association degree between a user preference feature in the user preference feature set and a service provider capability feature in the service provider capability feature set.

[0085] After obtaining the user preference feature set and the service provider capability feature set, the feature association process is performed. By analyzing the internal relationship between the features in the two sets, the association degree between each user preference feature and each service provider capability feature is determined, and these association degrees are represented in the form of a matrix to form the demand-capability association matrix.

[0086] Step S141: Determine the number of user preference features in the user preference feature set and the number of service provider capability features in the service provider capability feature set.

[0087] The number of user preference features in the user preference feature set is counted. The user preference feature set includes journey preference features, service preference features and resource preference features, each of which includes multiple sub-features, for example, the journey preference features include journey time features, journey location features and journey type features, etc. The total number of all the sub-features is counted and recorded as U.

[0088] Similarly, the number of service provider capability features in the service provider capability feature set is counted. The service provider capability feature set includes journey provision capability features, service provision capability features and resource provision capability features, each of which also includes multiple sub-features. The total number of all the sub-features is counted and recorded as S.

[0089] Step S142: According to the number of user preference features and the number of service provider capability features, an initial association matrix is constructed, the number of rows of the initial association matrix is the same as the number of user preference features, and the number of columns of the initial association matrix is the same as the number of service provider capability features.

[0090] According to the number U of user preference features and the number S of service provider capability features, an initial association matrix with U rows and S columns is constructed. All element values in the initial association matrix are set to 0, and the rows of the initial association matrix correspond to each user preference feature in the user preference feature set, and the columns correspond to each service provider capability feature in the service provider capability feature set.

[0091] Step S143: For each user preference feature in the user preference feature set, the association degree value between the user preference feature and each service provider capability feature in the service provider capability feature set is calculated in turn.

[0092] For the first user preference feature in the user preference feature set, the association degree value calculation is performed in turn with each service provider capability feature in the service provider capability feature set. After the calculation is completed, the same operation is performed on the second user preference feature in the user preference feature set, and so on, until the association degree value calculation between all user preference features and all service provider capability features is completed.

[0093] Step S1431: The feature attribute description of the user preference feature and the feature attribute description of the service provider capability feature are obtained.

[0094] The feature attribute description of the user preference feature is extracted, which is a specific description of the user preference feature. For example, the attribute description of the journey time feature may be "hope to travel during the early to middle of the month".

[0095] At the same time, the feature attribute description of the service provider capability feature is extracted, for example, the attribute description of the journey provision time feature may be "can arrange a journey in the first half of each month".

[0096] Step S1432: Comparing the feature attribute description of the user preference feature and the feature attribute description of the service provider capability feature, determining the attribute matching items and the attribute difference items between them.

[0097] Comparing the above two feature attribute descriptions, there is an overlapping time period between "from the beginning of the month to the middle of the month" and "the first half of each month", which is the attribute matching item; and the time period in "from the beginning of the month to the middle of the month" that exceeds "the first half of each month" and the part in "the first half of each month" that may not be covered by "from the beginning of the month to the middle of the month" is the attribute difference item.

[0098] Step S1433: According to the number of attribute matching items and the number of attribute difference items, calculating the attribute matching rate, which is the ratio of the number of attribute matching items to the sum of the number of attribute matching items and the number of attribute difference items.

[0099] The number of attribute matching items is counted as M, and the number of attribute difference items is counted as N. The attribute matching rate is calculated by M divided by (M plus N), and the result is the attribute matching rate.

[0100] Step S1434: Based on the attribute matching rate, combining a preset attribute weight coefficient, the basic correlation degree value between the user preference feature and the service provider capability feature is calculated.

[0101] A attribute weight coefficient is preset, which is determined according to the importance of the attribute, for example, the time attribute is more important in the itinerary arrangement, and a higher weight coefficient can be set, which is denoted as W. The basic correlation degree value is the attribute matching rate multiplied by W.

[0102] Step S1435: Adjusting the basic correlation degree value, according to the importance degree coefficient of the user preference feature and the importance degree coefficient of the service provider capability feature, the basic correlation degree value is weighted to obtain the final correlation degree value.

[0103] The importance degree coefficient of the user preference feature is denoted as Pu, which reflects the importance of the user preference feature in the overall user preference, and the higher the importance, the larger the coefficient. The importance degree coefficient of the service provider capability feature is denoted as Ps, which reflects the importance of the service provider capability feature in the overall service provider capability. The final correlation degree value is the basic correlation degree value multiplied by Pu and then multiplied by Ps.

[0104] Step S144: Fill the calculated correlation degree value into the corresponding position in the initial correlation matrix to generate a demand capability correlation matrix containing the correlation degree values of all user preference features and service provider capability features.

[0105] The calculated association degree value between each user preference feature and each service provider capability feature is filled into the corresponding row and column position in the initial association matrix. After all are filled, the initial association matrix is converted into the demand-capability association matrix, which fully presents the association degree between all user preference features and service provider capability features.

[0106] Step S150: Based on the demand-capability association matrix, the user order demand information and the service providing information are matched to obtain an order-service matching degree parameter, which is used to represent the degree to which the service providing information meets the user order demand information.

[0107] Using the association degree value in the demand-capability association matrix, through a series of calculation steps, an order-service matching degree parameter that can represent the degree to which the service providing information meets the user order demand information is obtained.

[0108] Step S151: Obtain the preference weight value of each user preference feature in the user preference feature set and the capability weight value of each service provider capability feature in the service provider capability feature set.

[0109] Each user preference feature in the user preference feature set is assigned a preference weight value, which is determined according to the importance of the feature to the user. The higher the preference weight value, the more important the feature to the user. The sum of the preference weight values of all user preference features is 1.

[0110] Similarly, each service provider capability feature in the service provider capability feature set is assigned a capability weight value, which is determined according to the degree of advantage of the service provider in that capability feature. The higher the capability weight value, the more obvious the advantage of the feature. The sum of the capability weight values of all service provider capability features is 1.

[0111] Step S152: According to the preference weight value and the capability weight value, the association degree value in the demand-capability association matrix is weighted to obtain a weighted demand-capability association matrix.

[0112] For each element in the demand-capability association matrix, i.e. the association degree value, it is multiplied by the preference weight value of the corresponding user preference feature and the capability weight value of the corresponding service provider capability feature to obtain a weighted association degree value. After all elements are updated, a weighted demand-capability association matrix is formed.

[0113] Step S153: The weighted demand-capability association matrix is processed in the row direction to obtain the total association degree value corresponding to each user preference feature.

[0114] In the weighted demand-capability correlation matrix, sum all the element values in each row to obtain the total correlation degree value of the user preference feature corresponding to the row.

[0115] Step S154: Perform column-wise summation processing on the weighted demand-capability correlation matrix to obtain the total correlation degree value corresponding to each service provider capability feature.

[0116] In the weighted demand-capability correlation matrix, sum all the element values in each column to obtain the total correlation degree value of the service provider capability feature corresponding to the column.

[0117] Step S155: Sum all the total correlation degree values of the user preference features to obtain the total user preference correlation degree value, and sum all the total correlation degree values of the service provider capability features to obtain the total service provider capability correlation degree value.

[0118] Add all the total correlation degree values of the user preference features obtained in step S153 to obtain the total user preference correlation degree value, denoted as T1.

[0119] Add all the total correlation degree values of the service provider capability features obtained in step S154 to obtain the total service provider capability correlation degree value, denoted as T2.

[0120] Step S156: Calculate the order-service matching degree parameter based on the total user preference correlation degree value and the total service provider capability correlation degree value. The order-service matching degree parameter is the ratio of the product of the total user preference correlation degree value and the total service provider capability correlation degree value to the sum of the two.

[0121] The calculation method of the order-service matching degree parameter is (T1 multiplied by T2) divided by (T1 plus T2), and the result is the order-service matching degree parameter.

[0122] Step S160: Generate an order matching scheme based on the order-service matching degree parameter and send the order matching scheme to the user interface of the tourism service platform for display.

[0123] According to the size of the order-service matching degree parameter, determine whether to generate an order matching scheme, and send the generated scheme to the user interface of the tourism service platform for the user to view.

[0124] Step S161: Obtain a preset order matching threshold and compare the order-service matching degree parameter with the order matching threshold.

[0125] An order matching threshold is obtained from a profile of the travel service platform or a related storage area, and the order matching threshold is a criterion for determining whether the service providing information and the user order demand information match. The calculated order service matching degree parameter is compared with the order matching threshold.

[0126] Step S162: When the order service matching degree parameter is greater than or equal to the order matching threshold, it is determined that the service providing information and the user order demand information match successfully, and a preliminary order matching scheme is generated based on the service providing information.

[0127] If the order service matching degree parameter is greater than or equal to the order matching threshold, it indicates that the service providing information can meet the user order demand information, and a preliminary order matching scheme is generated based on the service providing information. The preliminary order matching scheme includes preliminary information such as itinerary arrangement, service content, and resource allocation, for example, specific time arrangement of the itinerary, list of service items provided, types and quantities of resources equipped, and the like.

[0128] Step S163: When the order service matching degree parameter is less than the order matching threshold, it is determined that the service providing information and the user order demand information do not match, and the process returns to the step of obtaining the service providing information, to reacquire new service providing information and perform matching degree calculation.

[0129] If the order service matching degree parameter is less than the order matching threshold, it indicates that the service providing information cannot meet the user order demand information, and the process returns to step S110 to reacquire new content from the service providing information, and then re-performs feature extraction, association processing, and matching degree calculation according to the above steps until a service providing information that matches successfully is found.

[0130] Step S164: The preliminary order matching scheme is subjected to scheme optimization processing, and the itinerary arrangement, service content, and resource allocation in the preliminary order matching scheme are adjusted according to the user preference feature set and the service provider ability feature set.

[0131] Step S1641: The itinerary arrangement in the preliminary order matching scheme is adjusted according to the itinerary preference feature and the itinerary providing ability feature, and the order of itinerary times and the connection between itinerary locations are optimized.

[0132] The order of itinerary times in the preliminary order matching scheme is adjusted according to the user's requirements for time and location in the itinerary preference feature and the service provider's available time and location arrangement in the itinerary providing ability feature, to ensure that the itinerary time meets the user's preferences and is within the service provider's available time range. At the same time, the connection between the itinerary locations is optimized to reduce unnecessary travel time and make the itinerary smoother.

[0133] Step S1642: According to the service preference feature and the service providing capability feature, the service content in the preliminary order matching scheme is adjusted, the service items meeting the user's service demand are added, and the service items not meeting the user's service demand are reduced.

[0134] According to the user's requirements for service type, standard and method in the service preference feature, and the service content that the service provider can provide in the service providing capability feature, the service items that the user needs but does not contain in the preliminary order matching scheme are added, and the service items that the user does not need are deleted, so that the service content is more in line with the user's demand.

[0135] Step S1643: According to the resource preference feature and the resource providing capability feature, the resource configuration in the preliminary order matching scheme is adjusted, and the resource allocation quantity and resource use sequence are optimized.

[0136] Combined with the user's requirements for resource type, quantity and quality in the resource preference feature, and the resource situation that the service provider can provide in the resource providing capability feature, the resource configuration in the preliminary order matching scheme is adjusted. For example, the quantity of a certain type of resource needed by the user is increased, and the use sequence of the resource is adjusted to improve the resource utilization efficiency.

[0137] Step S1644: The adjusted itinerary arrangement, service content and resource configuration are comprehensively evaluated, and the comprehensive satisfaction parameter of the scheme after adjustment is calculated.

[0138] A comprehensive evaluation index system is established, which includes itinerary rationality, service fitting degree, resource adaptability and the like. According to these indexes, the adjusted itinerary arrangement, service content and resource configuration are scored, and the scores are weighted calculated according to the preset weight to obtain the comprehensive satisfaction parameter.

[0139] Step S1645: When the comprehensive satisfaction parameter is greater than the preset satisfaction threshold, it is determined that the optimized preliminary order matching scheme meets the requirements, otherwise, the adjustment of the itinerary arrangement, service content and resource configuration is re-performed until the comprehensive satisfaction parameter is greater than the preset satisfaction threshold.

[0140] The comprehensive satisfaction parameter is compared with the preset satisfaction threshold. If the comprehensive satisfaction parameter is greater than the threshold, it means that the optimized preliminary order matching scheme meets the requirements; if it is less than the threshold, return to step S1641 to step S1643 to re-adjust the itinerary arrangement, service content and resource configuration, and perform comprehensive evaluation again until the comprehensive satisfaction parameter is greater than the preset satisfaction threshold.

[0141] Step S165: Determine the optimized preliminary order matching scheme as the final order matching scheme, and format the order matching scheme to generate order matching scheme display information meeting the display requirements of the user interface.

[0142] The optimized preliminary order matching scheme determined through comprehensive evaluation is determined as the final order matching scheme. The scheme is formatted, for example, the font, size, and layout of the text are adjusted, necessary icons and separators are added, and the like, so as to meet the display requirements of the user interface of the tourism service platform, and order matching scheme display information is generated.

[0143] Step S166: Send the order matching scheme display information to the user interface of the tourism service platform, and control the user interface to display the order matching scheme display information in a preset display manner.

[0144] The order matching scheme display information is sent to the user interface of the tourism service platform through a data transmission protocol. The user interface presents the order matching scheme display information to the user in a preset display manner, such as page display, module display, and the like, so that the user can clearly and intuitively view the contents of the order matching scheme.

[0145] For example, the method can further include: Step S210: Collect the set of user preference features, the set of service provider capability features, the demand-capability correlation matrix, the order service matching degree parameter, and the corresponding order matching scheme to form a historical order matching data set.

[0146] After each order matching is completed, the set of user preference features, the set of service provider capability features, the demand-capability correlation matrix, the order service matching degree parameter, and the corresponding order matching scheme generated in the matching process are collected, and these data are stored in a designated database to gradually accumulate to form a historical order matching data set.

[0147] Step S211: Perform data cleaning processing on the historical order matching data set, and extract a training sample from the cleaned historical order matching data set, the training sample including sample input data and sample label data, the sample input data being the set of user preference features and the set of service provider capability features, and the sample label data being the order service matching degree parameter.

[0148] The historical order matching data set is subjected to data cleaning processing to remove repeated data, data with excessive missing values, and abnormal data. For example, for a set of user preference features with some missing feature values, if the missing proportion exceeds a preset threshold, the data is removed; for an order service matching degree parameter that deviates from the normal range, it is identified as abnormal data and deleted.

[0149] Extract training samples from the cleaned historical order matching data set, each training sample containing sample input data and sample label data, the sample input data consisting of a set of user preference features and a set of service provider capability features, and the sample label data being the corresponding order service matching degree parameter.

[0150] Step S310: Construct a neural network model containing an input layer, a hidden layer and an output layer, the input layer being used to receive the sample input data, the hidden layer including a feature interaction layer and an attention mechanism layer, the feature interaction layer being used to perform interactive feature extraction processing on the set of user preference features and the set of service provider capability features, the attention mechanism layer being used to perform importance weight allocation processing on the interactive features obtained by the interactive feature extraction processing, and the output layer being used to output the order service matching degree prediction parameter.

[0151] A neural network model is constructed, which consists of an input layer, a hidden layer and an output layer. The number of neurons in the input layer matches the feature dimension of the sample input data, which can receive the sample input data and pass it to the hidden layer.

[0152] The hidden layer contains a feature interaction layer, an attention mechanism layer and a fully connected layer. The feature interaction layer extracts interactive features from the input set of user preference features and the set of service provider capability features by setting multiple neurons, and realizes the combination and conversion of features through the connection weights between neurons to generate interactive features.

[0153] The attention mechanism layer contains neurons corresponding to the number of interactive features, each neuron corresponding to an interactive feature, and determines the importance weight of each interactive feature by calculation to weight the interactive features, so that the model pays more attention to important interactive features.

[0154] The fully connected layer consists of multiple neurons, which receive the features processed by the attention mechanism layer, perform nonlinear transformation through a nonlinear activation function, and generate high-level abstract features.

[0155] The output layer contains a neuron that receives the high-level abstract features output by the fully connected layer and outputs the order service matching degree prediction parameter through a linear activation function.

[0156] Step S311: input the training sample into the neural network model for model training processing, adjust the parameters of the neural network model, so that the difference between the order service matching degree prediction parameter and the sample label data meets the preset condition, and obtain a trained order matching prediction model.

[0157] Step S3111: dividing the training samples into a training set, a validation set, and a test set, the training set being used for model parameter learning, the validation set being used for model hyperparameter adjustment, and the test set being used for model performance evaluation.

[0158] The training samples are divided into a training set, a validation set, and a test set according to a preset ratio, such as 7:2:1. The training set contains most of the training samples and is used for the model to learn the parameter law during the training process; the validation set is used to evaluate the model performance during the model training process, and assists in adjusting the hyperparameters of the model, such as the learning rate and the number of hidden layer neurons; and the test set is used to finally evaluate the generalization ability and performance of the model after the model training is completed.

[0159] Step S3112: inputting the sample input data of the training set into the input layer of the neural network model, performing element-by-element multiplication and addition operations on the user preference feature set and the service provider capability feature set through the feature interaction layer of the hidden layer to generate preliminary interaction features, calculating the attention weight values of each feature in the preliminary interaction features through the attention mechanism layer of the hidden layer, and performing weighted sum processing on the preliminary interaction features according to the attention weight values to obtain weighted interaction features.

[0160] The sample input data of the training set is input into the input layer of the neural network model, and the input layer transmits the sample input data to the feature interaction layer of the hidden layer. After receiving the user preference feature set and the service provider capability feature set, the feature interaction layer performs element-by-element multiplication operation on the corresponding features in the two feature sets to obtain a group of product features, and performs element-by-element addition operation on the corresponding features in the two feature sets to obtain a group of sum features. The product features and the sum features are combined to form preliminary interaction features.

[0161] The preliminary interaction features are transmitted to the attention mechanism layer, which determines the attention weight values of each preliminary interaction feature by calculating the correlation of each preliminary interaction feature with the overall feature set, and the sum of the attention weight values is 1. Then, according to the attention weight values of each preliminary interaction feature, the preliminary interaction features are processed by weighted sum to obtain weighted interaction features, which highlight the important preliminary interaction feature information.

[0162] Step S3113: inputting the weighted interaction features into the fully connected layer of the hidden layer for nonlinear transformation processing to generate high-level abstract features, and inputting the high-level abstract features into the output layer to output the order service matching degree prediction parameters through the linear activation function of the output layer.

[0163] The weighted interaction features are input to a fully connected layer of a hidden layer. Each neuron in the fully connected layer is connected to all neurons of the previous layer, linearly combines the weighted interaction features through preset connection weights, and then performs nonlinear transformation processing through a nonlinear activation function (such as a ReLU function) to map the low-dimensional features to a high-dimensional space, generate high-level abstract features, and the high-level abstract features can more profoundly express the complex relationships between the features.

[0164] The high-level abstract features are input to an output layer. The output layer processes the high-level abstract features through a linear activation function to convert them into order service matching degree prediction parameters. The order service matching degree prediction parameters reflect the prediction results of the model on the matching degree of the user order demand information and the service providing information in the training sample.

[0165] Step S3114: Calculate the loss value between the order service matching degree prediction parameter and the sample label data of the training set. The loss value is calculated using a mean square error loss function.

[0166] The sample label data of the training set, i.e., the corresponding order service matching degree parameter, is obtained. The order service matching degree prediction parameter output by the neural network model is compared with the sample label data. The loss value between the two is calculated using a mean square error loss function. The calculation method of the mean square error loss function is as follows: first, calculate the difference between the order service matching degree prediction parameter and the sample label data of each sample; then, square the difference; finally, calculate the average of the squared differences of all samples to obtain the loss value.

[0167] Step S3115: Based on the loss value, use a gradient descent optimization algorithm to perform backpropagation update processing on the parameters of the neural network model to adjust the weight matrix of the feature interaction layer, the attention weight value of the attention mechanism layer, and the connection weight of the fully connected layer.

[0168] Based on the calculated loss value, the gradient descent optimization algorithm is used to adjust the parameters of the neural network model in the direction of reducing the loss value. Through the backpropagation algorithm, the partial derivatives of the loss value with respect to the weight matrix of the feature interaction layer, the attention weight value of the attention mechanism layer, and the connection weight of the fully connected layer, i.e., the gradients, are calculated. According to the direction and size of the gradient, update these parameters according to the preset learning rate, so that the loss value gradually decreases.

[0169] Step S3116: After completing a preset number of training rounds, input the sample input data of the validation set into the currently trained neural network model to calculate the validation order service matching degree prediction parameter, and calculate the validation loss value according to the validation order service matching degree prediction parameter and the sample label data of the validation set.

[0170] After each preset training round is completed, such as after 50 training rounds are completed, the sample input data of the validation set is input into the neural network model that is currently being trained, and the model outputs the validation order service matching degree prediction parameter after processing. The validation order service matching degree prediction parameter is compared with the sample label data of the validation set, and the same mean square error loss function as step S3114 is used to calculate the validation loss value.

[0171] Step S3117: When the validation loss value no longer decreases for a preset number of consecutive times, stop model training, and determine the current neural network model as the trained order matching prediction model.

[0172] The change of the validation loss value is continuously monitored. If the validation loss value no longer decreases for a preset number of consecutive times, such as 5 consecutive times, it indicates that the model has reached a good training state, and further training may cause overfitting. At this time, the model training is stopped, and the current neural network model is determined as the trained order matching prediction model.

[0173] Step S3118: The trained order matching prediction model is evaluated for performance using the test set, and the mean absolute error and the root mean square error of the model are calculated. When the mean absolute error and the root mean square error are both less than the corresponding preset error threshold, it is determined that the trained order matching prediction model meets the use requirements.

[0174] The sample input data of the test set is input into the trained order matching prediction model to obtain the test order service matching degree prediction parameter. The mean absolute error between the test order service matching degree prediction parameter and the sample label data of the test set is calculated, and the calculation method is the average value of the absolute values of the difference between all samples of the prediction parameter and the label data. The root mean square error is calculated, and the calculation method is the square root of the average value of the squares of the difference between all samples of the prediction parameter and the label data.

[0175] The mean absolute error is compared with the preset mean absolute error threshold, and the root mean square error is compared with the preset root mean square error threshold. When both are less than the corresponding preset error threshold, it indicates that the trained order matching prediction model has good prediction performance and generalization ability, and meets the use requirements.

[0176] Step S312: The trained order matching prediction model is deployed to the order matching system of the tourism service platform for assisting in order matching degree calculation processing.

[0177] The trained and use-required order matching prediction model is deployed to the order matching system of the travel service platform, in the order matching process, the user preference feature set and the service provider ability feature set are input into the model, the model outputs the order service matching degree prediction parameter, assists the order matching system to make the order matching decision, improves the efficiency and accuracy of the order matching.

[0178] Figure 2 An exemplary hardware and software components of the order matching system 100 of the service platform that can implement the idea of the present application are shown. For example, the processor 120 can be used in the order matching system 100 of the service platform, and used to execute the functions in the present application.

[0179] The order matching system 100 of the service platform can be a general server or a special-purpose server, both of which can be used to implement the order matching method of the service platform of the present application. Although only one server is shown in the present application, for the sake of convenience, the functions described in the present application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0180] For example, the order matching system 100 of the service platform can include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as a disk, a ROM, or a RAM, or any combination thereof. The order matching system 100 of the service platform can also include program instructions stored in the ROM, the RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The order matching system 100 of the service platform also includes an input / output (I / O) interface 150 between the computer and other input / output devices.

[0181] For the sake of illustration, only one processor is described in the order matching system 100 of the service platform. However, it should be noted that the order matching system 100 of the service platform in the present application can also include multiple processors, so the steps performed by one processor described in the present application can also be jointly performed or separately performed by multiple processors. For example, if the processor of the order matching system 100 of the service platform performs steps A and B, it should be understood that steps A and B can also be performed by two different processors together or separately in one processor. For example, a first processor performs step A, a second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0182] In addition, the embodiment of the present application further provides a readable storage medium, wherein computer executable instructions are preset in the readable storage medium, and when a processor executes the computer executable instructions, the order matching method of the service platform is realized.

[0183] It should be noted that, in order to simplify the expression of the present disclosure, and to help the understanding of one or more embodiments of the present application, in the foregoing description of the embodiments of the present application, various features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A method for order matching of a service platform, characterized in that, The method comprises: obtaining user order demand information and service provider information in a tourism service platform, the user order demand information comprising user itinerary demand information, user service demand information and user resource demand information, and the service provider information comprising service provider itinerary provision information, service provider service provision information and service provider resource provision information; performing demand feature extraction processing on the user order demand information to obtain a user preference feature set, the user preference feature set comprising itinerary preference features, service preference features and resource preference features; performing provision feature extraction processing on the service provider information to obtain a service provider capability feature set, the service provider capability feature set comprising itinerary provision capability features, service provision capability features and resource provision capability features; performing feature association processing on the user preference feature set and the service provider capability feature set to generate a demand-capability association matrix, each element in the demand-capability association matrix representing the degree of association between one user preference feature in the user preference feature set and one service provider capability feature in the service provider capability feature set; performing matching degree calculation processing on the user order demand information and the service provider information based on the demand-capability association matrix to obtain an order service matching degree parameter, the order service matching degree parameter representing the degree to which the service provider information satisfies the user order demand information; generating an order matching scheme according to the order service matching degree parameter and sending the order matching scheme to a user interface of the tourism service platform for display.

2. The order matching method of the service platform according to claim 1, characterized in that, The demand feature extraction processing on the user order demand information to obtain a user preference feature set, the user preference feature set comprising itinerary preference features, service preference features and resource preference features, comprises: performing itinerary feature analysis processing on the user itinerary demand information to extract itinerary time features, itinerary location features and itinerary type features from the user itinerary demand information, and combining the itinerary time features, the itinerary location features and the itinerary type features to form itinerary preference features; performing service feature analysis processing on the user service demand information to extract service type features, service standard features and service mode features from the user service demand information, and combining the service type features, the service standard features and the service mode features to form service preference features; performing resource feature analysis processing on the user resource demand information to extract resource type features, resource quantity features and resource quality features from the user resource demand information, and combining the resource type features, the resource quantity features and the resource quality features to form resource preference features; performing feature standardization and integration processing on the itinerary preference features, the service preference features and the resource preference features to form a user preference feature set comprising itinerary dimensions, service dimensions and resource dimensions.

3. The order matching method of the service platform according to claim 2, wherein, The trip feature analysis processing is performed on the user trip demand information, trip time features, trip location features and trip type features in the user trip demand information are extracted, the trip time features, the trip location features and the trip type features are combined to form trip preference features, and the trip preference features include: The text word segmentation processing is performed on the user trip demand information, and the user trip demand information is divided into a plurality of trip text words; The part-of-speech tagging processing is performed on the plurality of trip text words, and words representing time, words representing location and words representing type are identified; The trip time features are extracted from the words representing time, and the trip time features include trip start time, trip end time and trip duration; The trip location features are extracted from the words representing location, and the trip location features include trip departure location, trip passing location and trip destination location; The trip type features are extracted from the words representing type, and the trip type features include trip theme type, trip activity type and trip distance type; The trip time features, the trip location features and the trip type features are combined according to a preset feature combination rule to form trip preference features including time dimension, location dimension and type dimension; The feature verification processing is performed on the trip preference features formed by combination to ensure that the trip preference features can accurately reflect the trip preference in the user trip demand information.

4. The order matching method of the service platform according to claim 1, wherein, The service provider capability feature set is obtained by performing the service feature extraction processing on the service provider information, and the service feature extraction processing includes: The trip providing capability analysis processing is performed on the service provider trip information, trip providing time features, trip providing location features and trip providing type features in the service provider trip information are extracted, and the trip providing time features, the trip providing location features and the trip providing type features are combined to form trip providing capability features; The service providing capability analysis processing is performed on the service provider service information, service providing type features, service providing standard features and service providing mode features in the service provider service information are extracted, and the service providing type features, the service providing standard features and the service providing mode features are combined to form service providing capability features; The resource providing capability analysis processing is performed on the service provider resource information, resource providing type features, resource providing quantity features and resource providing quality features in the service provider resource information are extracted, and the resource providing type features, the resource providing quantity features and the resource providing quality features are combined to form resource providing capability features; The feature standardization integration processing is performed on the trip providing capability features, the service providing capability features and the resource providing capability features to form a service provider capability feature set including trip providing dimension, service providing dimension and resource providing dimension.

5. The order matching method of the service platform according to claim 1, wherein, The feature association processing is performed on the user preference feature set and the service provider capability feature set to generate a demand capability association matrix, and the feature association processing includes: determining a number of user preference features contained in the user preference feature set and a number of service provider capability features contained in the service provider capability feature set; constructing an initial correlation matrix according to the number of user preference features and the number of service provider capability features, a number of rows of the initial correlation matrix being the same as the number of user preference features, and a number of columns of the initial correlation matrix being the same as the number of service provider capability features; for each user preference feature in the user preference feature set, sequentially calculating a correlation degree value between the user preference feature and each service provider capability feature in the service provider capability feature set; filling the calculated correlation degree values into corresponding positions in the initial correlation matrix to generate a demand-capability correlation matrix containing correlation degree values between all user preference features and service provider capability features.

6. The order matching method of the service platform according to claim 5, wherein, The for each user preference feature in the user preference feature set, sequentially calculating a correlation degree value between the user preference feature and each service provider capability feature in the service provider capability feature set, includes: obtaining a feature attribute description of the user preference feature and a feature attribute description of the service provider capability feature; comparing the feature attribute description of the user preference feature and the feature attribute description of the service provider capability feature to determine attribute matching items and attribute difference items therebetween; calculating an attribute matching rate according to the number of attribute matching items and the number of attribute difference items, the attribute matching rate being a ratio of the number of attribute matching items to a sum of the number of attribute matching items and the number of attribute difference items; calculating a basic correlation degree value between the user preference feature and the service provider capability feature based on the attribute matching rate and in combination with a preset attribute weight coefficient; adjusting the basic correlation degree value, weighting the basic correlation degree value according to an importance degree coefficient of the user preference feature and an importance degree coefficient of the service provider capability feature to obtain a final correlation degree value.

7. The order matching method of the service platform according to claim 1, wherein, The based on the demand-capability correlation matrix, performing matching degree calculation processing on the user order demand information and the service provision information to obtain an order-service matching degree parameter, includes: obtaining preference weight values of each user preference feature in the user preference feature set and capability weight values of each service provider capability feature in the service provider capability feature set; performing weighting processing on correlation degree values in the demand-capability correlation matrix according to the preference weight values and the capability weight values to obtain a weighted demand-capability correlation matrix; performing row direction summation processing on the weighted demand-capability correlation matrix to obtain total correlation degree values corresponding to each user preference feature; performing column direction summation processing on the weighted demand-capability correlation matrix to obtain total correlation degree values corresponding to each service provider capability feature; performing summation processing on the total correlation degree values corresponding to all user preference features to obtain a user preference total correlation degree value, and performing summation processing on the total correlation degree values corresponding to all service provider capability features to obtain a service provider capability total correlation degree value; According to the user preference total correlation degree value and the service provider capability total correlation degree value, an order service matching degree parameter is calculated, which is the ratio of the product of the user preference total correlation degree value and the service provider capability total correlation degree value to the sum of the two.

8. The order matching method of the service platform according to claim 1, wherein, The order matching scheme is generated according to the order service matching degree parameter, and the order matching scheme is sent to the user interface of the tourism service platform for display, which includes: A preset order matching threshold is obtained, and the order service matching degree parameter is compared with the order matching threshold; When the order service matching degree parameter is greater than or equal to the order matching threshold, it is determined that the service providing information and the user order demand information are matched successfully, and a preliminary order matching scheme is generated based on the service providing information; When the order service matching degree parameter is less than the order matching threshold, it is determined that the service providing information and the user order demand information are matched unsuccessfully, and the step of obtaining service providing information is returned to, new service providing information is re-obtained and matching degree calculation is performed; The preliminary order matching scheme is optimized, and the user preference feature set and the service provider capability feature set are adjusted to adjust the itinerary arrangement, service content and resource allocation in the preliminary order matching scheme; The optimized preliminary order matching scheme is determined as the final order matching scheme, the order matching scheme is formatted, and order matching scheme display information meeting the user interface display requirements is generated; The order matching scheme display information is sent to the user interface of the tourism service platform, and the user interface is controlled to display the order matching scheme display information in a preset display manner.

9. The order matching method of the service platform according to claim 8, characterized in that, The preliminary order matching scheme is optimized, and the user preference feature set and the service provider capability feature set are adjusted to adjust the itinerary arrangement, service content and resource allocation in the preliminary order matching scheme, which includes: According to the itinerary preference feature and the itinerary providing capability feature, the itinerary arrangement in the preliminary order matching scheme is adjusted to optimize the itinerary time sequence and itinerary location connection; According to the service preference feature and the service providing capability feature, the service content in the preliminary order matching scheme is adjusted to increase service items meeting the user service demand and reduce service items not meeting the user service demand; According to the resource preference feature and the resource providing capability feature, the resource allocation in the preliminary order matching scheme is adjusted to optimize the resource allocation quantity and resource use sequence; The adjusted itinerary arrangement, service content and resource allocation are comprehensively evaluated, and a comprehensive satisfaction parameter after scheme adjustment is calculated; When the comprehensive satisfaction parameter is greater than a preset satisfaction threshold, it is determined that the optimized preliminary order matching scheme meets the requirements, otherwise, the adjustment of the itinerary arrangement, service content and resource allocation is re-performed until the comprehensive satisfaction parameter is greater than the preset satisfaction threshold.

10. An order matching system of a service platform, characterized in that, The order matching system of the service platform comprises a processor and a memory, the memory is connected with the processor, the memory is used for storing programs, instructions or codes, and the processor is used for executing the programs, instructions or codes in the memory to realize the order matching method of the service platform according to any one of claims 1-9.

Images