Network service platform intelligent matching method, system, device and storage medium

Abstract

The application provides a network service platform intelligent matching method, system, device and storage medium, the method comprises the following steps: receiving a service request sent by a user terminal; obtaining user information corresponding to the user terminal from a user management server; selecting multiple network service platforms as alternative network service platforms according to the type of the service request; obtaining matching conditions corresponding to the alternative network service platforms from a platform management server; selecting one network service platform from the alternative network service platforms as a matching network service platform according to the matching conditions and the user information; and pushing the service request and the user information to the matching network service platform. By adopting the scheme of the application, intelligent matching between a service platform and a user is realized, the efficiency of selecting a service platform by the user is improved, and the probability of successful service establishment is further improved.

Description

Technical Field

[0001] This invention relates to the field of Internet data processing technology, and in particular to a method, system, device and storage medium for intelligent matching of network service platforms. Background Technology

[0002] With the rapid development of internet technology, the types and models of online services provided through this technology are also increasing, allowing users to apply for and obtain many online services without leaving their homes. Corresponding to each type of online service, numerous online platforms are also emerging, offering users more and more choices.

[0003] In existing technologies, when choosing a service platform, users need to manually search for relevant information about various platforms online and then make a selection. This requires users to perform a large amount of data queries and human judgment, making the process very complex, time-consuming, and labor-intensive. Another approach might involve third-party service providers manually selecting and recommending service platforms to users, which is also very time-consuming and labor-intensive.

[0004] Furthermore, for some types of online services, after a user applies for a service online, the service platform will review the request. Therefore, there may be cases where the request is accepted and the contract is successfully concluded, or cases where the request fails but the contract is successfully concluded. Different service platforms may also have different review requirements. Whether the user manually selects a service platform or a third-party staff member manually selects and recommends a service platform, it is impossible to perfectly match the user with the most suitable platform, thus significantly impacting the user experience. Summary of the Invention

[0005] To address the problems in the existing technology, the present invention aims to provide a method, system, device, and storage medium for intelligent matching of network service platforms, thereby realizing intelligent matching between service platforms and users, improving the efficiency of users in selecting service platforms, and further increasing the probability of successful service establishment.

[0006] This invention provides an intelligent matching method for a network service platform, the method comprising the following steps:

[0007] Received a service request from the user terminal;

[0008] Obtain user information corresponding to the user terminal from the user management server;

[0009] Multiple network service platforms are selected as alternative network service platforms based on the type of the service request.

[0010] The matching conditions corresponding to the candidate network service platforms are obtained from the platform management server, which is configured to manage the matching conditions of each network service platform.

[0011] Based on the matching criteria and the user information, select one network service platform from the candidate network service platforms as the matching network service platform;

[0012] The service request and the user information are pushed to the matching network service platform.

[0013] Optionally, the matching conditions include preset matching conditions and platform feature vectors. Selecting a network service platform from the candidate network service platforms based on the matching conditions and the user information as the matching network service platform includes the following steps:

[0014] The attribute values ​​of the first user attribute and the attribute values ​​of the second user attribute are determined based on the user information.

[0015] From the candidate network service platforms, select the network service platform whose attribute value of the first user attribute meets the corresponding preset matching conditions as the pre-selected network service platform. The preset matching conditions include the attribute value requirements corresponding to the first user attribute.

[0016] Obtain the platform feature vectors of each of the pre-selected network service platforms;

[0017] The user feature vector is determined based on the attribute values ​​of the second user attribute.

[0018] The matching degree between the user and each of the pre-selected network service platforms is calculated based on the user feature vector and the platform feature vector.

[0019] Select the pre-selected network service platform with the highest matching degree as the matching network service platform.

[0020] Optionally, the platform feature vector includes the successful contracting feature vector and the failed contracting feature vector of the pre-selected network service platform. The successful contracting feature vector includes the first attribute value feature vector corresponding to the second user attribute, and the failed contracting feature vector includes the second attribute value feature vector corresponding to the second user attribute.

[0021] Optionally, the method further includes the following steps:

[0022] The collected successful contracting data and failed contracting data are added to the successful contracting dataset and the failed contracting dataset, respectively;

[0023] Extract successful contracting feature vectors from the successful contracting data within a preset time period;

[0024] Extract the contract failure feature vector from the contract failure data within the preset time period.

[0025] Optionally, the successful contract data includes the user attribute value of the second user attribute corresponding to the successful contract, and the extraction of the successful contract feature vector includes the following steps:

[0026] The number of times each user attribute value corresponding to each second user attribute appears in the successful contract signing data within a preset time period is counted.

[0027] The attribute value that appears most frequently for each second attribute is taken as the first attribute value corresponding to that second attribute;

[0028] The feature values ​​corresponding to the first attribute values ​​of each user's second attribute are combined to obtain the successful contract feature vector;

[0029] The contract failure data includes the user attribute values ​​of the second user attribute corresponding to the contract failure. The extraction of the contract failure feature vector includes the following steps:

[0030] The number of times each user attribute value corresponding to each second user attribute appears in the contract failure data within a preset time period is counted.

[0031] The attribute value that appears most frequently for each second attribute is taken as the second attribute value corresponding to that second attribute;

[0032] The feature values ​​corresponding to the second attribute values ​​of each user's second attribute are combined to obtain the contract failure feature vector.

[0033] Optionally, combining the feature values ​​corresponding to the first attribute values ​​of each of the user's second attributes includes the following steps:

[0034] Calculate the similarity cij between the attribute name bj of the j-th second attribute and the attribute name ai of the i-th first attribute, where j∈(1,n), i∈(1,m), m is the number of categories of the first attribute, and n is the number of categories of the second attribute.

[0035] The first attribute with the highest similarity to the j-th second attribute is taken as its similar first attribute;

[0036] Obtain the priority order of each of the first attributes from the preset matching conditions;

[0037] The priority order of the second attribute is determined based on the priority order of the similar first attributes corresponding to each second attribute.

[0038] The additional coefficient of the first attribute value of the second attribute is determined according to the priority ranking of the second attribute. The higher the priority ranking, the larger the corresponding additional coefficient value.

[0039] The first attribute value of the second attribute is multiplied by the corresponding additional coefficient, and then combined to obtain the successful contracting feature vector.

[0040] Optionally, determining the priority order of the second attributes based on the priority order of the similar first attributes corresponding to each second attribute includes the following steps:

[0041] Based on the priority sorting of the similar first attributes corresponding to each second attribute, the initial priority value dj of the j-th second attribute is determined, wherein the higher the priority of the similar first attribute corresponding to the second attribute, the larger the initial priority value dj of the second attribute.

[0042] Record the similarity cjmax between the j-th second attribute and its similar first attribute;

[0043] Multiply the initial priority value dj of the j-th second attribute by cjmax to obtain the priority order value of the j-th second attribute;

[0044] The second attributes are sorted by priority from highest to lowest according to the priority value of the j-th second attribute.

[0045] Optionally, calculating the matching degree between the user and each of the pre-selected network service platforms includes the following steps:

[0046] The user feature vector, the successful contract feature vector, and the failed contract feature vector are combined and input into the trained matching degree calculation model to obtain the matching degree output by the matching degree calculation model.

[0047] Optionally, the method further includes training the matching degree calculation model using the following steps:

[0048] Query the successful contract data of each of the aforementioned network service platforms, and calculate the time difference Δt1 between the user request time and the contract time in each successful contract data;

[0049] For each of the aforementioned network service platforms, a preset number of successful contract signing data with the smallest time difference Δt1 are selected. The attribute value of the user's second attribute in the successful contract signing data is used as the user feature vector and combined with the successful contract signing feature vector and the failed contract signing feature vector of the network service platform to obtain the first feature vector.

[0050] The first feature vector is marked as having the highest matching degree and then added to the training set;

[0051] Query the contract failure data of each of the aforementioned network service platforms, and calculate the time difference Δt2 between the user request time and the request rejection time in each contract failure data;

[0052] For each of the network service platforms, a preset number of contract failure data with the smallest time difference Δt2 are selected. The attribute value of the user's second attribute in the contract failure data is used as the user feature vector and combined with the contract success feature vector and contract failure feature vector of the network service platform to obtain the second feature vector.

[0053] The second feature vector is marked as having the lowest matching degree and then added to the training set.

[0054] Optionally, calculating the matching degree between the user and each of the pre-selected network service platforms includes the following steps:

[0055] Calculate the first similarity x between the user feature vector and the successful contract feature vector;

[0056] Calculate the second similarity y between the user feature vector and the contract failure feature vector;

[0057] The matching degree between the user and each of the pre-selected network service platforms is calculated as x*k1-y*k2, where k1 and k2 are preset coefficients.

[0058] This invention also provides an intelligent matching system for a network service platform, applied to the aforementioned intelligent matching method for a network service platform. The system includes:

[0059] The communication and interaction module is used to receive service requests sent by user terminals and push the service requests and user information to the matching network service platform.

[0060] The information query module is used to obtain user information corresponding to user terminals from the user management server;

[0061] The platform query module is used to select multiple network service platforms as alternative network service platforms according to the type of the service request, and obtain the matching conditions corresponding to the alternative network service platforms from the platform management server. The platform management server is configured to manage the matching conditions of each network service platform.

[0062] The platform matching module is used to select one network service platform from the candidate network service platforms as the matching network service platform based on the matching conditions and the user information.

[0063] This invention also provides an intelligent matching device for a network service platform, comprising:

[0064] processor;

[0065] A memory in which executable instructions of the processor are stored;

[0066] The processor is configured to execute the steps of the network service platform intelligent matching method by executing the executable instructions.

[0067] This invention also provides a computer-readable storage medium for storing a program, which, when executed, implements the steps of the intelligent matching method for the network service platform.

[0068] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure.

[0069] The intelligent matching method, system, device, and storage medium for the network service platform provided by this invention have the following advantages:

[0070] This invention solves the problems in the prior art by achieving intelligent matching between the service platform and the user based on the matching conditions of the service platform and the user information of the user sending the service request. This improves the efficiency of users in selecting service platforms and further increases the probability of successful service establishment. It avoids the time-consuming and laborious process of users manually querying data for selection and reduces the situation where users need to repeatedly apply for services due to unsuccessful applications, thus greatly improving the user experience. Attached Figure Description

[0071] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings.

[0072] Figure 1 This is a flowchart of an intelligent matching method for a network service platform according to an embodiment of the present invention;

[0073] Figure 2 This is a schematic diagram of the structure of an intelligent matching system for a network service platform according to an embodiment of the present invention;

[0074] Figure 3 This is a flowchart illustrating the matching conditions of an updated network service platform according to an embodiment of the present invention;

[0075] Figure 4 This is a schematic diagram of a filtering network service platform according to an embodiment of the present invention;

[0076] Figure 5 This is a flowchart of a selection and matching network service platform according to an embodiment of the present invention;

[0077] Figure 6 This is a flowchart of obtaining platform feature vectors according to an embodiment of the present invention;

[0078] Figure 7This is a flowchart illustrating the calculation of the matching degree between a user and a network service platform according to an embodiment of the present invention;

[0079] Figure 8 This is a schematic diagram of an intelligent matching device for a network service platform according to an embodiment of the present invention;

[0080] Figure 9 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. Detailed Implementation

[0081] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0082] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0083] like Figure 1 As shown, in order to solve the above-mentioned technical problems, this embodiment of the invention provides an intelligent matching method for a network service platform, the method comprising the following steps:

[0084] S100: Received a service request sent by a user terminal; here, the user terminal is a terminal device used by the user to connect to the network, including but not limited to mobile phones, tablets, laptops, etc.

[0085] S200: Obtain user information corresponding to the user terminal from the user management server, wherein the user management server is configured to manage various aspects of user information, such as the user's name, location, age, occupation, etc.

[0086] S300: Select multiple network service platforms as alternative network service platforms according to the type of the service request, that is, the selected alternative network service platforms are consistent with the type of service requested by the user;

[0087] S400: Obtain the matching conditions corresponding to the alternative network service platforms from the platform management server. The platform management server is configured to manage information of each network service platform, such as the service type, matching conditions, and service duration of each service platform.

[0088] S500: Select a network service platform from the candidate network service platforms according to the matching conditions and the user information, and use it as the matching network service platform;

[0089] S600: Push the service request and the user information to the matching network service platform, thereby realizing automatic matching of the network service platform and automatic forwarding of the service request.

[0090] Therefore, the present invention first receives a service request sent by a user through a user terminal in step S100, queries user information in step S200, selects a network service platform corresponding to the service type in step S300, collects information from the service platform in step S400, uses the user information and service platform information for matching in the subsequent step S500, and automatically sends the service request to the matched network service platform in step S600 after the matching is completed, thereby realizing automatic intelligent matching of network service platforms, improving network service efficiency and user experience.

[0091] like Figure 2 As shown, this embodiment of the invention also provides an intelligent matching system M100 for a network service platform, applied to the intelligent matching method for the network service platform. The system includes:

[0092] The communication interaction module M110 is used to receive service requests sent by the user terminal M200 and push the service requests and user information to the matching network service platform M300.

[0093] The information query module M120 is used to obtain user information corresponding to the user terminal from the user management server M400;

[0094] The platform query module M130 is used to select multiple network service platforms as alternative network service platforms according to the type of the service request, and obtain the matching conditions corresponding to the alternative network service platforms from the platform management server M500. The platform management server is configured to manage the matching conditions of each network service platform.

[0095] The platform matching module M140 is used to select one network service platform from the candidate network service platforms as the matching network service platform based on the matching conditions and the user information.

[0096] This invention first receives a service request sent by a user through a user terminal via a communication interaction module M110. User information can be retrieved via an information query module M120, and information from a network service platform M200 is collected via a platform query module M130. The user information and service platform information are then used for matching by a platform matching module M140. After matching is complete, the communication interaction module M110 automatically sends the service request to the matched network service platform M200, thereby achieving automatic and intelligent matching of network service platforms, improving network service efficiency and user experience.

[0097] In this embodiment, the matching conditions include preset matching conditions and platform feature vectors. The preset matching conditions are generally conditions for approval service requests pre-set by the online service platform and sent to the platform management server. For example, some service platforms focusing on serving teenagers are set to provide services only to users in a certain age group, some service platforms focusing on women's health-related services are set to provide services only to female users, and some service platforms currently serving users in a specific region are set to match users whose current location or registered residence is in a specified region. The platform feature vector is a platform feature vector representing the contract-contracting tendency of the online service platform, obtained by analyzing the platform's historical service data. After pre-selecting candidate online service platforms through preset matching conditions, a secondary selection can be performed based on the platform feature vector to improve the user's contract-contracting success rate and reduce the additional burden on users and online service platforms due to contract failures.

[0098] like Figure 3 As shown, the matching conditions are stored in the platform management server M500. The platform management server M500 is configured to update the preset matching conditions after receiving new matching conditions from the network service platform M300. The intelligent matching system M100 extracts new platform feature vectors based on the historical service data of each network service platform M300 at preset intervals. The platform management server M500 is further configured to update the stored platform feature vectors after receiving new platform feature vectors from the intelligent matching system M100.

[0099] The following example illustrates how users can apply for online loan services. Here, each online service platform represents a different online loan channel. Currently, when applying for an online loan, users can do so directly through a third-party platform. The platform's staff manually selects and recommends loan channels to the user. For example, if a user purchases a course through an online education platform, they can pay the tuition through a loan. In this case, the online education platform's staff will call the user to recommend loan channels for them to choose from. This method is not only time-consuming and labor-intensive, but it also doesn't guarantee a suitable loan channel. If the user's conditions don't match the requirements of the loan channel, the success rate of the agreement is low, placing a significant processing burden on the user, the loan channel platform, and the online education platform.

[0100] like Figure 4 As shown, this invention automatically and intelligently filters online service platforms for users based on matching conditions, mainly in two steps. First, based on the service request type being online loan services, loan service platforms in region A are filtered out (12 loan service platforms are used as an example here). Then, a first pre-selection is performed based on preset matching conditions to obtain loan service platforms in region B (6 loan service platforms are used as an example here). This ensures that the mandatory preset matching conditions are met and also reduces the number of loan service platforms to be calculated for matching degree in the subsequent second calculation, reducing the amount of calculation and improving matching efficiency. Then, after the second step of calculating the matching degree, the optimal matching loan service platform in region C is obtained.

[0101] like Figure 5 As shown, in this embodiment, step S500, selecting a network service platform from the candidate network service platforms as the matching network service platform based on the matching conditions and the user information, includes the following steps:

[0102] S510: Determine the attribute values ​​of the first user attribute and the attribute values ​​of the second user attribute based on the user information. The first user attribute is a user attribute that corresponds to the user attribute value requirements in the preset matching conditions. The second user attribute is a user attribute selected for the matching degree calculation in the second step. There are multiple first user attributes and multiple second user attributes, and the first user attribute and the second user attribute may overlap.

[0103] S520: Select a network service platform from the candidate network service platforms whose attribute value of the first user attribute meets the corresponding preset matching conditions, and use it as a pre-selected network service platform. The preset matching conditions include the attribute value requirements corresponding to the first user attribute.

[0104] This is the first step in matching: pre-selecting based on the user's first user attribute value and preset matching conditions to narrow down the service platform range for the second step of calculating the matching degree.

[0105] For example, if user A initiates a loan request, its first user attributes include user age, gender, region, type of course purchased, credit rating, and loan amount requested. If a loan platform A's preset matching conditions include age group requirements and region requirements, and user A's age meets the loan platform A's age group requirements and its region meets the loan platform A's region requirements, and other attributes not required by the loan platform A are considered to meet the requirements, then the loan platform A is considered a pre-selected online service platform.

[0106] For example, if the default matching conditions of loan platform B include credit rating requirements and a maximum loan amount, and user A's requested loan amount exceeds the maximum loan amount requested by loan platform B, then loan platform B is considered not to be a pre-selected online service platform.

[0107] S530: Obtain the platform feature vectors of each of the pre-selected network service platforms;

[0108] S540: Determine a user feature vector based on the attribute values ​​of the second user attribute, wherein each value in the user feature vector may correspond to a feature value of the second user attribute.

[0109] S550: Calculate the matching degree between the user and each of the pre-selected network service platforms based on the user feature vector and the platform feature vector;

[0110] S560: Select the pre-selected network service platform with the highest matching degree as the matching network service platform.

[0111] Therefore, this embodiment matches users and network service platforms in two steps: using preset matching conditions and platform feature vectors obtained through historical data analysis. This automatically matches the most suitable network service platform for the user and significantly improves the success rate of contract signing. The invention first selects candidate network service platforms from all network service platforms based on the type of service request. Then, it selects pre-selected network service platforms from the candidate platforms based on preset matching conditions. Finally, it selects a matching network service platform from the pre-selected network service platforms based on platform feature vectors and user feature vectors, thereby matching the network service platform that best meets the user's needs.

[0112] In this embodiment, the platform feature vector includes a successful contract formation feature vector and a failed contract formation feature vector of the pre-selected network service platform. The successful contract formation feature vector includes a first attribute value feature vector corresponding to the second user attribute, and the failed contract formation feature vector includes a second attribute value feature vector corresponding to the second user attribute. The first attribute value feature vector corresponding to the second user attribute is obtained by analyzing the historical successful contract formation data of the pre-selected network service platform, and the second attribute value feature vector corresponding to the second user attribute is obtained by analyzing the historical failed contract formation data of the pre-selected network service platform.

[0113] like Figure 6 As shown, specifically, the intelligent matching method for the network service platform further includes obtaining the platform feature vector using the following steps:

[0114] S710: Collect newly generated contract success data and contract failure data from each network service platform within the most recent preset interval at preset intervals; the collection of contract success data and contract failure data can be obtained by directly communicating with each network service platform, or it can be obtained based on course order success data and course order failure data from third-party platforms such as online education platforms.

[0115] S720: Add the collected successful contracting data and failed contracting data to the successful contracting dataset and the failed contracting dataset, respectively;

[0116] S730: Extract the successful contracting feature vector from the successful contracting data within a preset time period from the successful contracting data dataset;

[0117] Considering that the contracting tendency of various online service platforms may change over time, such as the approval rate of a certain type of user being higher in the previous period, while the approval rate of another type of user may be higher in the current period, a preset time period is set here, such as the most recent month, two months, three months, etc., so as to ensure that the extracted contracting success feature vector is the latest feature vector representing the contracting tendency within this period.

[0118] S740: Extract the failure feature vector from the failure data within a preset time period from the successful contracting dataset. Similarly, the length of the preset time period can be selected as needed, such as the most recent month, two months, four months, six months, etc.

[0119] In this embodiment, the successful contract data includes the user attribute value of the second user attribute corresponding to the successful contract. Step S730, extracting the successful contract feature vector, includes the following steps:

[0120] The number of times each user attribute value corresponding to each second user attribute appears in the successful contract signing data within a preset time period is counted.

[0121] The attribute value that appears most frequently for each second attribute is taken as the first attribute value corresponding to that second attribute;

[0122] For example, for network service platform A, if 60 of its 100 successful contract signing records are from Shanghai, then the first attribute value of its region attribute is set to Shanghai; if 45 of its successful contract signing records are for individuals aged 25-40, 25 of its successful contract signing records are for individuals aged 41-60, 15 of its successful contract signing records are for individuals under 25, and 15 of its successful contract signing records are for individuals over 60, then the first attribute value of its age attribute is set to 25-40.

[0123] The feature values ​​corresponding to the first attribute values ​​of each user's second attribute are combined to obtain the successful contract feature vector;

[0124] For example, for age, the characteristic value is set as follows: below 25 years old, the characteristic value is 1; 25-40 years old, the characteristic value is 2; 41-60 years old, the characteristic value is 3; and above 60 years old, the characteristic value is 4.

[0125] The contract failure data includes the user attribute values ​​of the second user attribute corresponding to the contract failure. In step S740, the contract failure feature vector is extracted, including the following steps:

[0126] The number of times each user attribute value corresponding to each second user attribute appears in the contract failure data within a preset time period is counted.

[0127] The attribute value that appears most frequently for each second attribute is taken as the second attribute value corresponding to that second attribute. The determination of the second attribute value here is similar to the method of determining the first attribute value of the second attribute in step S730 above, except that the object of the count is the contract failure data.

[0128] Failure to conclude a contract here includes situations where the online service platform rejects the user's service request after reviewing it, thus failing to conclude a contract.

[0129] The feature values ​​corresponding to the second attribute values ​​of each user's second attribute are combined to obtain the contract failure feature vector.

[0130] In this embodiment, combining the feature values ​​corresponding to the first attribute values ​​of each of the user's second attributes includes the following steps:

[0131] Calculate the similarity cij between the attribute name bj of the j-th second attribute and the attribute name ai of the i-th first attribute, where j∈(1,n), i∈(1,m), m is the number of categories of the first attribute, and n is the number of categories of the second attribute. Here, the similarity can be the similarity between the word vectors of the attribute names of the two attributes (Euclidean distance, cosine similarity, etc.), or it can be the similarity between two attributes pre-set in the intelligent matching system. If a second attribute and a first attribute are exactly the same, the similarity between the two attribute values ​​is set to 1. If the two are not exactly the same, their similarity is a value less than 1 and greater than or equal to 0.

[0132] The first attribute with the highest similarity to the j-th second attribute is taken as its similar first attribute;

[0133] Obtain the priority order of each of the first attributes from the preset matching conditions;

[0134] The priority order of the second attribute is determined based on the priority order of the similar first attributes corresponding to each second attribute.

[0135] The additional coefficient of the first attribute value of the second attribute is determined according to the priority ranking of the second attribute. The higher the priority ranking, the larger the corresponding additional coefficient value. Here, the additional coefficient can be determined according to a preset mapping relationship table between the ranking position and the additional coefficient.

[0136] The first attribute value of the second attribute is multiplied by the corresponding additional coefficient, and then combined to obtain the successful contracting feature vector.

[0137] Therefore, in this embodiment, an additional coefficient value is further determined based on the similarity between each user's second attribute and each first attribute, as well as the priority ranking of each first attribute. This allows different second attributes to have different levels of importance, which is reflected by the additional coefficient value. The larger the additional coefficient value, the greater the role the second attribute plays in subsequently calculating the matching degree between the user and the online service platform. Thus, by cleverly combining the second and first attributes, this invention can significantly improve the accuracy of matching users with online service platforms, further enhance the matching degree between users and online service platforms, and achieve a more accurate prediction of the online service platform's contractual tendency, thereby increasing the contract success rate.

[0138] Furthermore, the combination of the feature values ​​corresponding to the second attribute values ​​of each user's second attribute can also be achieved by multiplying the second attribute values ​​of the second attribute by their corresponding additional coefficients and then combining them to obtain the contract failure feature vector.

[0139] In this embodiment, determining the priority order of the second attributes based on the priority order of the similar first attributes corresponding to each second attribute includes the following steps:

[0140] Based on the priority sorting of the similar first attributes corresponding to each second attribute, the initial priority value dj of the j-th second attribute is determined. The higher the priority of the similar first attribute corresponding to the second attribute, the larger the initial priority value dj of the second attribute. The initial priority value can be determined according to a pre-set mapping table between sorting position and initial priority value.

[0141] Record the similarity cjmax between the j-th second attribute and its similar first attribute;

[0142] Multiply the initial priority value dj of the j-th second attribute by cjmax to obtain the priority order value of the j-th second attribute;

[0143] The priority of the second attribute is sorted from high to low based on the priority value of the j-th second attribute, thereby realizing the comprehensive determination of the priority order of the second attribute by combining the priority order of the first attribute related to the second attribute and the similarity value between the second attribute and the first attribute.

[0144] In this embodiment, step S550, calculating the matching degree between the user and each of the pre-selected network service platforms, includes the following steps:

[0145] The user feature vector, the successful contract feature vector, and the failed contract feature vector are combined and input into the trained matching degree calculation model to obtain the matching degree output by the matching degree calculation model.

[0146] The matching degree calculation model here can be a neural network model built based on deep learning, such as a convolutional neural network model. The neural network model is trained using a pre-collected and labeled training set of matching degrees until the loss function is less than a preset threshold, thus obtaining a trained matching degree calculation model. The input of the matching degree calculation model is an input feature vector obtained by combining the user feature vector, the successful contract feature vector, and the failed contract feature vector. The output is a matching degree value or a matching degree level.

[0147] like Figure 7 As shown, in this embodiment, the intelligent matching method of the network service platform further includes step S800: training the matching degree calculation model. Specifically, step S800 includes the following steps:

[0148] S810: Query the successful contract data of each of the aforementioned network service platforms, and calculate the time difference Δt1 between the user request time and the contract time in each successful contract data;

[0149] S820: For each of the network service platforms, select a preset number of successful contract data with the smallest time difference Δt1, and use the attribute value of the user's second attribute in the successful contract data as the user feature vector. Combine the successful contract feature vector and the failed contract feature vector of the network service platform to obtain the first feature vector.

[0150] S830: After marking the first feature vector as the highest matching degree, add it to the training set, for example, set the highest matching degree to 1; here, the user request corresponding to the first feature vector is the feature vector with the shortest approval time and successful contract signing, which can reflect the approval tendency of the network service platform;

[0151] S840: Query the contract failure data of each of the network service platforms, and calculate the time difference Δt2 between the user request time and the request rejection time in each contract failure data;

[0152] S850: For each of the network service platforms, select a preset number of contract failure data with the smallest time difference Δt2, and use the attribute value of the user's second attribute in the contract failure data as the user feature vector. Combine the user feature vector with the contract success feature vector and the contract failure feature vector of the network service platform to obtain a second feature vector. The user request corresponding to the second feature vector is the feature vector with the shortest approval time and successful contract, which can reflect the approval tendency of the network service platform.

[0153] S860: Mark the second feature vector as the lowest matching degree and add it to the training set, for example, set the lowest matching degree to 0.

[0154] In another alternative implementation, after obtaining the user feature vector and platform feature vector, vector similarity can be used to calculate the similarity between the user and the network service platform. Specifically, in this implementation, step S550, calculating the matching degree between the user and each of the pre-selected network service platforms, includes the following steps:

[0155] Calculate the first similarity x between the user feature vector and the successful contract feature vector;

[0156] Calculate the second similarity y between the user feature vector and the contract failure feature vector;

[0157] The matching degree between the user and each of the pre-selected network service platforms is calculated as x*k1-y*k2, where k1 and k2 are preset coefficients.

[0158] This invention also provides a network service platform intelligent matching device, including a processor; a memory storing executable instructions of the processor; wherein the processor is configured to perform the steps of the network service platform intelligent matching method by executing the executable instructions.

[0159] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0160] The following reference Figure 8 To describe an electronic device 600 according to this embodiment of the present invention. Figure 8 The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0161] like Figure 8 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The combination of the electronic device 600 may include, but is not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform combinations (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0162] The storage unit stores program code that can be executed by the processing unit 610, causing the processing unit 610 to perform the steps described in the above-described section of this specification regarding the intelligent matching processing method for a network service platform, according to various exemplary embodiments of the present invention. For example, the processing unit 610 can perform actions such as... Figure 1 The steps shown. Specifically, the processing unit 610 executes... Figure 1 The specific execution methods for each step can be adopted from the specific implementation methods of the intelligent matching method of the network service platform described above, and will not be repeated here.

[0163] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only memory unit (ROM) 6203.

[0164] The storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0165] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0166] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0167] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steps of the intelligent matching method for the network service platform. In some possible implementations, various aspects of this invention can also be implemented as a program product comprising program code, which, when run on a terminal device, causes the terminal device to execute the steps described in the above-described intelligent matching processing method section of this specification according to various exemplary embodiments of the invention.

[0168] refer to Figure 9As shown, a program product 800 for implementing the above-described method according to an embodiment of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0169] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0170] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0171] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0172] In summary, compared with the prior art, the intelligent matching method, system, device, and storage medium for network service platforms provided by this invention have the following advantages:

[0173] This invention solves the problems in the prior art by achieving intelligent matching between the service platform and the user based on the matching conditions of the service platform and the user information of the user sending the service request. This improves the efficiency of users in selecting service platforms and further increases the probability of successful service establishment. It avoids the time-consuming and laborious process of users manually querying data for selection and reduces the situation where users need to repeatedly apply for services due to unsuccessful applications, thus greatly improving the user experience.

[0174] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A method for intelligent matching on a network service platform, characterized in that, Includes the following steps: Received a service request from the user terminal; Obtain user information corresponding to the user terminal from the user management server; Multiple network service platforms are selected as alternative network service platforms based on the type of the service request. The matching conditions corresponding to the candidate network service platforms are obtained from the platform management server, which is configured to manage the matching conditions of each network service platform. Based on the matching criteria and the user information, select one network service platform from the candidate network service platforms as the matching network service platform; The service request and the user information are pushed to the matching network service platform; The matching conditions include preset matching conditions and platform feature vectors. The platform feature vectors include successful contract formation feature vectors and failed contract formation feature vectors of the pre-selected network service platforms. The successful contract formation feature vectors include the first attribute value feature vector corresponding to the second user attribute, and the failed contract formation feature vectors include the second attribute value feature vector corresponding to the second user attribute. The step of selecting a network service platform from the candidate network service platforms based on the matching conditions and the user information as the matching network service platform includes the following steps: The values ​​of each attribute of the first user attribute and each attribute of the second user attribute are determined based on the user information, wherein there are multiple first user attributes and multiple second user attributes. From the candidate network service platforms, select the network service platform whose attribute value of the first user attribute meets the corresponding preset matching conditions as the pre-selected network service platform. The preset matching conditions include the attribute value requirements corresponding to the first user attribute. Obtain the platform feature vectors of each of the pre-selected network service platforms; The user feature vector is determined based on the attribute values ​​of the second user attribute. The matching degree between the user and each of the pre-selected network service platforms is calculated based on the user feature vector and the platform feature vector. Select the pre-selected network service platform with the highest matching degree as the matching network service platform.

2. The intelligent matching method for a network service platform according to claim 1, characterized in that, The method further includes the following steps: The collected successful contracting data and failed contracting data are added to the successful contracting dataset and the failed contracting dataset, respectively; Extract successful contracting feature vectors from the successful contracting data within a preset time period; Extract the contract failure feature vector from the contract failure data within the preset time period.

3. The intelligent matching method for a network service platform according to claim 2, characterized in that, The successful contract signing data includes the user attribute values ​​of the second user attribute corresponding to the successful contract signing. The extraction of the successful contract signing feature vector includes the following steps: The number of times each user attribute value corresponding to each second user attribute appears in the successful contract signing data within a preset time period is counted. The attribute value that appears most frequently for each second user attribute is taken as the first attribute value corresponding to that second user attribute; The feature values ​​corresponding to the first attribute values ​​of each second user attribute are combined to obtain the successful contract feature vector; The contract failure data includes the user attribute values ​​of the second user attribute corresponding to the contract failure. The extraction of the contract failure feature vector includes the following steps: The number of times each user attribute value corresponding to each second user attribute appears in the contract failure data within a preset time period is counted. The attribute value that appears most frequently for each second user attribute is taken as the second attribute value corresponding to that second user attribute; The feature values ​​corresponding to the second attribute values ​​of each second user attribute are combined to obtain the contract failure feature vector.

4. The intelligent matching method for a network service platform according to claim 3, characterized in that, The step of combining the feature values ​​corresponding to the first attribute values ​​of each second user attribute includes the following steps: Calculate the similarity cij between the attribute name bj of the j-th second user attribute and the attribute name ai of the i-th first user attribute, where j∈(1,n), i∈(1,m), m is the number of categories of first user attributes, and n is the number of categories of second user attributes. The first user attribute with the highest similarity to the j-th second user attribute is taken as its first similarity attribute; Obtain the priority order of each of the first user attributes from the preset matching conditions; The priority order of the second user attributes is determined based on the priority order of the similar first attributes corresponding to each second user attribute. The additional coefficient of the first attribute value corresponding to the second user attribute is determined according to the priority ranking of the second user attribute. The higher the priority ranking, the larger the corresponding additional coefficient value. After multiplying the first attribute value corresponding to the second user attribute by the corresponding additional coefficient, the resulting combination yields the successful contract feature vector.

5. The intelligent matching method for a network service platform according to claim 4, characterized in that, The step of determining the priority order of the second user attributes based on the priority order of the similar first attributes corresponding to each second user attribute includes the following steps: Based on the priority sorting of the similar first attributes corresponding to each second user attribute, the initial priority value dj of the j-th second user attribute is determined, wherein the higher the priority of the similar first attribute corresponding to the second user attribute, the larger the initial priority value dj of the second user attribute. Record the similarity cjmax between the j-th second user attribute and its similar first attribute; Multiply the initial priority value dj of the j-th second user attribute by cjmax to obtain the priority order value of the j-th second user attribute; The second user attributes are prioritized and sorted from highest to lowest according to the priority value of the j-th second user attribute.

6. The intelligent matching method for a network service platform according to claim 1, characterized in that, The process of calculating the matching degree between the user and each of the pre-selected network service platforms includes the following steps: The user feature vector, the successful contract feature vector, and the failed contract feature vector are combined and input into the trained matching degree calculation model to obtain the matching degree output by the matching degree calculation model.

7. The intelligent matching method for a network service platform according to claim 6, characterized in that, The method further includes training the matching degree calculation model using the following steps: Query the successful contract data of each of the aforementioned network service platforms, and calculate the time difference Δt1 between the user request time and the contract time in each successful contract data; For each of the aforementioned network service platforms, a preset number of successful contracting data with the smallest time difference Δt1 are selected. The attribute value of the second user attribute in the successful contracting data is used as the user feature vector and combined with the successful contracting feature vector and the failed contracting feature vector of the network service platform to obtain the first feature vector. The first feature vector is marked as having the highest matching degree and then added to the training set; Query the contract failure data of each of the aforementioned network service platforms, and calculate the time difference Δt2 between the user request time and the request rejection time in each contract failure data; For each of the network service platforms, a preset number of contract failure data with the smallest time difference Δt2 are selected, and the attribute value of the second user attribute in the contract failure data is used as the user feature vector. This is then combined with the contract success feature vector and the contract failure feature vector of the network service platform to obtain the second feature vector. The second feature vector is marked as having the lowest matching degree and then added to the training set.

8. The intelligent matching method for a network service platform according to claim 6, characterized in that, The process of calculating the matching degree between the user and each of the pre-selected network service platforms includes the following steps: Calculate the first similarity x between the user feature vector and the successful contract feature vector; Calculate the second similarity y between the user feature vector and the contract failure feature vector; The matching degree between the user and each of the pre-selected network service platforms is calculated as x. k1-y k2, where k1 and k2 are preset coefficients.

9. An intelligent matching system for a network service platform, characterized in that, The intelligent matching method for network service platforms applied to any one of claims 1 to 8, the system comprising: The communication and interaction module is used to receive service requests sent by user terminals and push the service requests and user information to the matching network service platform. The information query module is used to obtain user information corresponding to user terminals from the user management server; The platform query module is used to select multiple network service platforms as alternative network service platforms according to the type of the service request, and obtain the matching conditions corresponding to the alternative network service platforms from the platform management server. The platform management server is configured to manage the matching conditions of each network service platform. The platform matching module is used to select one network service platform from the candidate network service platforms as the matching network service platform based on the matching conditions and the user information.

10. A network service platform intelligent matching device, characterized in that, include: processor; A memory in which executable instructions of the processor are stored; The processor is configured to execute the steps of the network service platform intelligent matching method according to any one of claims 1 to 8 by executing the executable instructions.

11. A computer-readable storage medium for storing a program, characterized in that, When the program is executed, it implements the steps of the intelligent matching method for the network service platform as described in any one of claims 1 to 8.

Images