Resource matching method and system for performing credit evaluation according to multi-dimensional data

Abstract

The invention relates to a resource matching method and system for credit evaluation according to multi-dimensional data, and the method comprises the steps: determining the transaction preference of a user and a recycler through the historical recovery record information of the user and the recycler, and determining the user credit of the user through the basic credit information and the historical recovery record of the user; and the credit of the recoverer is determined through historical recovery records and evaluation information of the recoverer. And finally, matching the user and the recoverer based on the transaction preference and credit. The method is applied to a recovery platform, two transaction parties are matched by using transaction preferences and credit, the consistency of transaction demands and credit levels of the two parties can be ensured to the greatest extent, and better experience is brought to transaction users with high credit levels.

Description

Technical Field

[0001] The present invention relates to the field of information management, and in particular to a resource matching method and system for credit evaluation based on multi-dimensional data. Background Art

[0002] For recycling resource platforms, the valuation of recyclables is generally assessed by recyclers based on the information reported by customers. Therefore, the customer's credit information is very important for the valuation of recyclables and the subsequent recycling process.

[0003] In the prior art, the valuation of recyclables is generally based on the information reported by the customer. After recycling, the recycler will conduct an appraisal and make a payment. However, in this process, if the appraisal result is significantly different from the information reported by the customer, the final payment will be significantly different from the valuation, causing customer dissatisfaction or wasting recycling costs. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a resource matching method and system for credit evaluation based on multi-dimensional data to solve the problems in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: The resource matching method for credit evaluation based on multi-dimensional data of the present invention comprises the steps of: Obtain the user's historical recycling records and basic credit information, and obtain the recycler's historical recycling records and evaluation information, where the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; Determine transaction preferences of users and recyclers based on historical recycling records; Based on the basic credit information and historical recycling records of the user, the recycling credit of the user is evaluated to obtain the initial credit of the user, and based on the historical recycling records and evaluation information of the recycler, the recycling credit of the recycler is evaluated to obtain the initial credit of the recycler; the initial credit of the user is corrected using the initial credit of the recycler to obtain the user credit, and the initial credit of the recycler is corrected using the initial credit of the user to obtain the recycler credit; When conducting a recycling transaction, the user and the recycler are matched based on the transaction preference, the user credit and the recycler credit.

[0006] In one embodiment of the present application, determining the transaction preference of the user and the recycler based on the historical recycling records includes: Count the number of recycling businesses in historical recycling records; For users whose recycling business quantity is less than or equal to a preset value, obtaining user information, and determining the user's transaction preference based on the user information and a preference recommendation model, wherein the preference recommendation model is obtained by training an artificial neural network with training data labeled with preferences, and the training data includes user information; For recyclers and users whose recycling business volume is greater than a preset value, the preferred category, preferred price range and preferred transaction duration range of the recycler or user are determined based on each recycling business in the historical recycling records.

[0007] In one embodiment of the present application, the preferred type, preferred price range, and preferred transaction duration range of the recycler or user are determined based on each recycling business in the historical recycling record, including: Extract the type of items in each recycling transaction , Evaluation Price , payment price and transaction duration ,in, It is the recycling business serial number; The highest frequency Item types as the preferred categories of recyclers or users; Calculate the valuation price for each recycling business , payment price Average price , and calculate the average value of multiple recycling transactions The average and standard deviation , based on the average and the standard deviation Construct the preferred price segments of recyclers or users ,in, is a first range adjustment parameter; Calculate the transaction time for each recycling business The average and standard deviation , based on the average and the standard deviation Construct the preferred transaction time range of recyclers or users ,in, Adjust the parameters for the second range.

[0008] In one embodiment of the present application, a user's recycling credit is evaluated based on the user's basic credit information and historical recycling records to obtain the user's initial credit, including: Determining the recycling business quantity from the historical recycling records of the user; When the recycling business quantity is less than or equal to a preset value, the basic credit information is used as the user's evaluation information; When the number of recycling services is greater than a preset value, the evaluation price of each recycling service in the user's historical recycling records is calculated. and payment price Deviation rate ,in ; The deviation rate The recycling business that is greater than the preset threshold is marked as the first target recycling business, and the user's initial credit is calculated based on the number of the first target recycling business. , where the initial credit The mathematical expression is: ; In the formula, is the basic credit score corresponding to the basic credit information, is the first scale parameter, is the second scale parameter, is the third scale parameter, The number of recycling services in the user's historical recycling records. The number of recovery businesses for the first goal.

[0009] In one embodiment of the present application, a recycling credit evaluation is performed on a recycler based on the recycler's historical recycling records and evaluation information to obtain the recycler's initial credit, including: Calculate the assessed price of each recycling business in the recycling company's historical recycling records and payment price Deviation rate ,in ; and based on the pre-built emotion recognition model, perform emotion recognition on each evaluation text in the evaluation information to obtain the recognition result of each evaluation text , wherein the recognition results include positive, neutral and negative, and the emotion recognition model is obtained by training an artificial neural network based on training data with emotion states labeled in advance, is the serial number of the evaluation text; The deviation rate The recycling business with a value greater than a preset threshold is marked as a second target recycling business, and based on the number of the second target recycling business and the recognition result of each evaluation text Calculating a recycler's initial credit , where the recycler’s initial credit The mathematical expression is: ; In the formula, is the initial credit score set. is the fourth scale parameter, is the number of recycling businesses in the recycler's historical recycling records, The number of recovered businesses for the second goal, identifying the results When positive, , recognition results When it is neutral, , recognition results When negative, .

[0010] In one embodiment of the present application, the initial credit of the user is corrected using the initial credit of the recycler to obtain the user credit, including: Screen out initial credit Target merchants below the preset credit threshold; Remove the first target recycling business that exists in the target merchant, and re-use formula (1) to calculate the user's credit score to obtain the first credit score; The first credit scores of all users are normalized to obtain user credit.

[0011] In one embodiment of the present application, the initial credit of the recycler is corrected using the initial credit of the user to obtain the credit of the recycler, including: Screen out initial credit Target users below the preset credit threshold; Remove the second target recycling business with target users, and re-use formula (2) to calculate the credit score of the recycler to obtain the second credit score; The second credit scores of all recyclers are normalized to obtain the recycler credit.

[0012] In one embodiment of the present application, matching a user and a recycler based on the transaction preference, the user credit, and the recycler credit includes: Calculating the preference matching degree between the current user and each recycler based on the transaction preference; and selecting multiple recyclers with the highest matching degree as target recyclers; The user credit interval of the current user is determined, and a target recycler within the interval is used as a matching recycler for the current user, wherein the credit score is pre-divided into a plurality of intervals.

[0013] In one embodiment of the present application, the preference matching degree between the user and each recycler is calculated based on the transaction preference, including: Determine the number of shared preferences that the user has with each recycler , Preferred price overlap rate Overlap rate with preferred transaction duration , the preference price overlap rate is the ratio of the length of the overlapping price segment to the length of the preferred price segment, and the preferred transaction duration overlap rate is the ratio of the length of the overlapping time segment to the length of the preferred transaction segment, is the recycler serial number; The number of common preference categories , the overlap rate of the preferred prices Overlap rate with the preferred transaction duration Perform weighted summation to obtain the preference matching degree between the user and each recycler , the preference matching degree The mathematical expression is: ; In the formula, is the first weight, is the second weight, The third weight.

[0014] This application also provides a resource matching system for credit evaluation based on multi-dimensional data, including: An acquisition module is used to acquire the user's historical recycling records and basic credit information, and to acquire the recycler's historical recycling records and evaluation information, wherein the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; A preference analysis module for determining the transaction preferences of users and recyclers based on historical recycling records; A credit analysis module, used to evaluate the recycling credit of the user based on the user's basic credit information and historical recycling records to obtain the user's initial credit, and to evaluate the recycling credit of the recycler based on the recycler's historical recycling records and evaluation information to obtain the recycler's initial credit; to modify the user's initial credit using the recycler's initial credit to obtain the user's credit, and to modify the recycler's initial credit using the user's credit to obtain the recycler's credit; A matching module is used to match the user and the recycler based on the transaction preference, the user credit and the recycler credit when performing a recycling transaction.

[0015] The beneficial effects of the present invention are as follows: the resource matching method and system for credit evaluation based on multi-dimensional data of the present invention determines the transaction preferences of users and recyclers through the historical recycling record information of users and merchants, determines the user credit of users through the basic credit information and historical recycling records of users, and determines the credit of recyclers through the historical recycling records and evaluation information of recyclers. Finally, users and recyclers are matched based on transaction preferences and credit. This application is used in a recycling platform, and transaction preferences and credit are used to match transaction parties, which can maximize the consistency of the transaction needs and credit levels of both parties, and bring a better experience to transaction users with high credit levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 It is an application scenario diagram of a resource matching method for credit evaluation based on multi-dimensional data shown in an embodiment of the present application; Figure 2 is a flow chart of a resource matching method for credit evaluation based on multi-dimensional data shown in an embodiment of the present application; Figure 3 A schematic diagram of a matching process in an embodiment of the present application; Figure 4 is a structural diagram of a resource matching system for performing credit evaluation based on multi-dimensional data in one embodiment of the present application; Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0018] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.

[0019] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.

[0020] Figure 1 is an application scenario diagram of a resource matching method for credit evaluation based on multidimensional data shown in an embodiment of the present application, such as Figure 1 As shown, the present application is applied to an online trading platform, and both the user 110 and the recycler 120 conduct transactions on the website of the online trading platform. In a typical case, the recycler 120 recycles the resources of the user 110 in the name of the platform. The user 110 uploads the item information to the online trading platform, and the recycler 120 makes an estimate based on the item information. After the online completion, the user 110 mails the item to the recycler 120, and the recycler 120 makes the final payment after the physical identification. In this process, if the difference between the valuation and the final payment price is too large, it will lead to conflicts between the two parties. It may even cause user loss. Therefore, the present application matches the recycler 120 and the user 110 based on transaction preferences and credit to reduce the above situation. The specific process is as follows.

[0021] Figure 2 is a flow chart of a resource matching method for credit evaluation based on multi-dimensional data shown in an embodiment of the present application, such as Figure 2 As shown: the resource matching method for credit evaluation based on multi-dimensional data in this embodiment may include steps S210 to S240: S210, obtaining the user's historical recycling records and basic credit information, and obtaining the recycler's historical recycling records and evaluation information, wherein the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; In this application, if the user is a new user who has just registered and has no historical recovery record, the user's basic credit information is obtained using the authorization of the external platform.

[0022] S220, determining the transaction preference of the user and the recycler based on the historical recycling records; In this application, the transaction preferences of users and recyclers can be the types of traded items, price ranges, transaction duration, etc. These data can reflect the preferences of users or recyclers in past recycling business. In the subsequent process, if users and recyclers with similar preferences are matched, the transaction rate will be greatly improved and the experience of both parties will be optimized.

[0023] In this embodiment, the process of determining the transaction preference includes: S221, counting the number of recycling businesses in historical recycling records; S222, for a user whose recycling business quantity is less than or equal to a preset value, obtaining user information, and determining the user's transaction preference based on the user information and a preference recommendation model, wherein the preference recommendation model is obtained by training an artificial neural network with training data labeled with preferences, and the training data includes the user information; For users, if the number of recycling businesses in historical recycling records is small and the user's transaction preferences cannot be inferred from the records, this application uses a prediction model to recommend the user's transaction preferences. Specifically, the user's male, age, job and other information are input into the preference recommendation model to obtain the transaction preferences.

[0024] The construction process of the preference recommendation model includes: Acquire sample data, wherein the sample data includes user information; Label the sample data with information such as the type of transaction item, price range, transaction duration, etc., to obtain training data; The artificial neural network is trained using the training data and combined with the gradient descent method to obtain a preference recommendation model.

[0025] S223, for recyclers and users whose recycling business quantity is greater than a preset value, determining the preferred category, preferred price range and preferred transaction duration range of the recycler or user based on each recycling business in the historical recycling records.

[0026] For users and recyclers with sufficient historical records, the transaction preferences of recyclers and users are found from each recycling business in the historical recycling records, including: S2231, extract the type of items in each recycling business , Evaluation Price , payment price and transaction duration ,in, It is the recycling business serial number; S2232, for the highest frequency Item types as the preferred categories of recyclers or users; Specifically, 3 to 5 types of items that appear the most times are selected as preferred categories. If there are less than 3 types, all types can be selected as preferred categories.

[0027] S2233, calculate the evaluation price of each recycling business , payment price Average price , and calculate the average value of multiple recycling transactions The average and standard deviation , based on the average and the standard deviation Construct the preferred price segments of recyclers or users ,in, is a first range adjustment parameter; S2234, calculate the transaction time of each recycling business The average and standard deviation , based on the average and the standard deviation Construct the preferred transaction time range of recyclers or users ,in, Adjust the parameters for the second range.

[0028] Then extract the reference range of price and duration. Taking price as an example, price data includes evaluation price. , payment price , in this application, the evaluation price is calculated , payment price Average price The average of multiple average prices and standard deviation Can form corresponding preferred price segments The same applies to transaction duration.

[0029] S230, evaluating the recycling credit of the user based on the basic credit information and historical recycling records of the user to obtain the initial credit of the user, and evaluating the recycling credit of the recycler based on the historical recycling records and evaluation information of the recycler to obtain the initial credit of the recycler; using the initial credit of the recycler to correct the initial credit of the user to obtain the user credit, and using the initial credit of the user to correct the initial credit of the recycler to obtain the recycler credit; In this application, there are two reasons for the difference between the evaluation price and the payment price: either the information submitted by the user is incorrect, or the recycler deliberately lowers the price. Therefore, either the user is dishonest or the recycler is dishonest. This application conducts credit evaluation based on the above analysis, including: (1) User initial credit S2301, determining the number of recycling services from the historical recycling records of the user; S2302, when the recycling business quantity is less than or equal to a preset value, using the basic credit information as the user's evaluation information; First, determine whether there are enough recycling business in the user's historical recycling records. If the number is small, then convert the basic credit information obtained through authorization in the previous article into the corresponding credit evaluation score in this application. Specifically, you can multiply the credit evaluation score of the external system by a multiple to convert it into the credit evaluation score in this application.

[0030] S2303, when the number of recycling services is greater than a preset value, calculating the evaluation price of each recycling service in the historical recycling records of the user and payment price Deviation rate ,in ; If the quantity is sufficient, then calculate the evaluation price in each transaction and payment price Deviation rate Since it is impossible to determine whether the price deviation is caused by the customer or the merchant at the beginning, it is generally believed that the responsibility for the record with large deviation is on the side of the party, and it will be corrected in the subsequent process. Therefore, the evaluation price of each recycling business is first calculated. and payment price Deviation rate .

[0031] S2304, the deviation rate The recycling business that is greater than the preset threshold is marked as the first target recycling business, and the user's initial credit is calculated based on the number of the first target recycling business. , where the initial credit The mathematical expression is: ; In the formula, is the basic credit score corresponding to the basic credit information, is the first scale parameter, is the second scale parameter, is the third scale parameter, The number of recycling services in the user's historical recycling records. The number of recovery businesses for the first goal.

[0032] The setting principle of formula (1) is to screen out the number of first target recycling businesses with large deviations, and each time a first target recycling business appears, the initial credit Subtract points, the subtracted points are Furthermore, considering users with different amounts of data, if users with a relatively small amount of initial data cannot actually reflect their true credit situation through a small amount of data, a single business will deduct a large amount of points, which will have a greater impact on the credit score. Therefore, a weighted value based on the number of businesses is constructed, that is, , the larger the amount of data a user has, the greater the credit deduction for a single first-target recycling business, taking into account the bonus points for non-target businesses , the final score can be kept within a reasonable range. Users with less data will not have their scores too low due to a small amount of target recycling services.

[0033] (2) Initial credit of recycler S2311, calculate the evaluation price of each recycling business in the historical recycling records of the recycler and payment price Deviation rate ,in ; and based on the pre-built emotion recognition model, perform emotion recognition on each evaluation text in the evaluation information to obtain the recognition result of each evaluation text , wherein the recognition results include positive, neutral and negative, and the emotion recognition model is obtained by training an artificial neural network based on training data with emotion states labeled in advance, is the serial number of the evaluation text; This application uses deep learning models (such as convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), Transformer, etc.) to encode and classify text. These models can automatically learn complex features in text and improve the accuracy of sentiment analysis.

[0034] S2312, the deviation rate The recycling business with a value greater than a preset threshold is marked as a second target recycling business, and based on the number of the second target recycling business and the recognition result of each evaluation text Calculating a recycler's initial credit , where the recycler’s initial credit The mathematical expression is: ; In the formula, is the initial credit score set. is the fourth scale parameter, is the number of recycling businesses in the recycler's historical recycling records, The number of recovered businesses for the second goal, identifying the results When positive, , recognition results When it is neutral, , recognition results When negative, .

[0035] The principle of formula (2) is the same as that of formula (1), except that an emotional state score of the evaluation text is added, so that credit information can be extracted from the merchant's evaluation information.

[0036] (3) User credit correction S2321, screen out initial credit Target merchants below the preset credit threshold; S2322, removing the first target recycling business existing in the target merchant, and re-using formula (1) to calculate the user's credit score to obtain a first credit score; S2323, normalize the first credit scores of all users to obtain user credit.

[0037] After obtaining the initial credit score of the merchant, we can roughly screen out the target merchants with lower credit, then remove the businesses that have been deducted points in the previous article from the target businesses, and re-update the user credit. In this way, the businesses that affect the real credit evaluation are eliminated, and the credit score is updated through formula (1).

[0038] (4) Credit correction of recyclers S2331, screen out initial credit Target users below the preset credit threshold; S2332, removing the second target recycling business that exists in the target user, and re-using formula (2) to calculate the credit score of the recycler to obtain a second credit score; S2333, normalizing the second credit scores of all recyclers to obtain the recycler credits.

[0039] The principle of revising the credit of recyclers is similar. After obtaining the initial credit score of the user, we can roughly screen out the target users with low credit, then remove the businesses that were deducted in the previous article from the target businesses, and re-update the credit of the recyclers. In this way, the businesses that affect the real credit evaluation are eliminated, and the credit score is updated through formula (2).

[0040] S240, when performing a recycling transaction, matching the user and the recycler based on the transaction preference, the user credit, and the recycler credit.

[0041] Finally, transaction preferences and user credit are used for matching. Matching users and merchants based on credit scores and transaction preferences can further improve the accuracy of matching. Merchants can more easily find users who meet their requirements, and users can also more easily find merchants who meet their needs. At the same time, the difference between the evaluation price and the payment price in the recycling business is reduced to avoid user dissatisfaction caused by large price differences.

[0042] Figure 3 FIG. 1 is a schematic diagram of a matching process in an embodiment of the present application. Figure 3 As shown, matching the user and the recycler based on the transaction preference, the user credit and the recycler credit includes: S241, calculating the preference matching degree between the current user and each recycler based on the transaction preference; and selecting multiple recyclers with the highest matching degree as target recyclers; First, the current user's target recycler is determined through transaction preferences, including: S2411, determine the number of common preference categories between the user and each recycler , Preferred price overlap rate Overlap rate with preferred transaction duration , the preference price overlap rate is the ratio of the length of the overlapping price segment to the length of the preferred price segment, and the preferred transaction duration overlap rate is the ratio of the length of the overlapping time segment to the length of the preferred transaction segment, is the recycler serial number; S2412, the number of the common preference categories , the overlap rate of the preferred prices Overlap rate with the preferred transaction duration Perform weighted summation to obtain the preference matching degree between the user and each recycler , the preference matching degree The mathematical expression is: ; In the formula, is the first weight, is the second weight, The third weight.

[0043] In this application, the number of common preference categories , Preferred price overlap rate Overlap rate with preferred transaction duration As the criterion for preference matching, the weighted sum is taken to obtain the matching degree. The higher the matching degree, the higher the similarity of transaction preferences between the merchant and the user. In the subsequent transaction process, the higher the similarity of transaction preferences, the higher the transaction rate and transaction experience.

[0044] S242, determining the interval to which the user credit of the current user belongs, and using a target recycler within the interval as a matching recycler for the current user, wherein the credit score is pre-divided into a plurality of intervals.

[0045] After obtaining target recyclers with similar transaction preferences, the matching recyclers in the credit range of the current user are matched. If the current user has a higher credit, then the recycler with higher credit is matched. Otherwise, the recycler with clear credit is matched. This can bring better recycling business experience to users with higher credit, and can also screen high-quality customers for recyclers with higher credit. It promotes the virtuous cycle development of the recycling platform.

[0046] The resource matching method of the present invention for credit evaluation based on multidimensional data determines the transaction preferences of users and recyclers through the historical recycling record information of users and merchants, determines the user credit of the user through the basic credit information and historical recycling records of the user, and determines the credit of the recycler through the historical recycling records and evaluation information of the recycler. Finally, the user and the recycler are matched based on the transaction preference and credit. This application is used in the recycling platform, and the transaction preferences and credit are used to match the transaction parties, which can maximize the consistency of the transaction needs and credit levels of both parties, and bring a better experience to transaction users with high credit levels.

[0047] like Figure 4 As shown, the present application also provides a resource matching system for credit evaluation based on multi-dimensional data, including: An acquisition module is used to acquire the user's historical recycling records and basic credit information, and to acquire the recycler's historical recycling records and evaluation information, wherein the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; A preference analysis module for determining the transaction preferences of users and recyclers based on historical recycling records; A credit analysis module, used to evaluate the recycling credit of the user based on the user's basic credit information and historical recycling records to obtain the user's initial credit, and to evaluate the recycling credit of the recycler based on the recycler's historical recycling records and evaluation information to obtain the recycler's initial credit; to modify the user's initial credit using the recycler's initial credit to obtain the user's credit, and to modify the recycler's initial credit using the user's credit to obtain the recycler's credit; A matching module is used to match the user and the recycler based on the transaction preference, the user credit and the recycler credit when performing a recycling transaction.

[0048] The resource matching system of the present invention, which performs credit evaluation based on multi-dimensional data, determines the transaction preferences of users and recyclers through the historical recycling record information of users and merchants, determines the user credit of users through the basic credit information and historical recycling records of users, and determines the credit of recyclers through the historical recycling records and evaluation information of recyclers. Finally, users and recyclers are matched based on transaction preferences and credit. This application is used in a recycling platform, and transaction preferences and credit are used to match transaction parties, which can maximize the consistency of transaction needs and credit levels of both parties, and bring a better experience to transaction users with high credit levels.

[0049] Figure 5 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0050] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0051] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0052] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0053] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier, which carries a computer-readable computer program. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0054] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0055] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0056] Another aspect of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the above method. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0057] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in each of the above embodiments.

[0058] The above embodiments are only preferred embodiments for fully illustrating the present application, and the protection scope of the present application is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present application is within the protection scope of the present application.

Claims

1. A resource matching method for credit evaluation based on multi-dimensional data, characterized in that: Includes steps: Obtain the user's historical recycling records and basic credit information, and obtain the recycler's historical recycling records and evaluation information, where the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; Determine transaction preferences of users and recyclers based on historical recycling records; Based on the basic credit information and historical recycling records of the user, the recycling credit of the user is evaluated to obtain the initial credit of the user, and based on the historical recycling records and evaluation information of the recycler, the recycling credit of the recycler is evaluated to obtain the initial credit of the recycler; the initial credit of the user is corrected using the initial credit of the recycler to obtain the user credit, and the initial credit of the recycler is corrected using the initial credit of the user to obtain the recycler credit; When conducting a recycling transaction, the user and the recycler are matched based on the transaction preference, the user credit and the recycler credit.

2. The resource matching method for credit evaluation based on multidimensional data according to claim 1, characterized in that: Determine transaction preferences of users and recyclers based on historical recycling records, including: Count the number of recycling businesses in historical recycling records; For users whose recycling business quantity is less than or equal to a preset value, obtaining user information, and determining the user's transaction preference based on the user information and a preference recommendation model, wherein the preference recommendation model is obtained by training an artificial neural network with training data labeled with preferences, and the training data includes user information; For recyclers and users whose recycling business volume is greater than a preset value, the preferred category, preferred price range and preferred transaction duration range of the recycler or user are determined based on each recycling business in the historical recycling records.

3. The resource matching method for credit evaluation based on multi-dimensional data according to claim 1, characterized in that: Determine the preferred category, preferred price range and preferred transaction duration range of the recycler or user based on each recycling business in the historical recycling records, including: Extract the type of items in each recycling transaction , Evaluation Price , payment price and transaction duration ,in, It is the recycling business serial number; The highest frequency Item types as the preferred categories of recyclers or users; Calculate the valuation price for each recycling business , payment price Average price , and calculate the average value of multiple recycling transactions The average and standard deviation , based on the average and the standard deviation Construct the preferred price segments of recyclers or users ,in, is a first range adjustment parameter; Calculate the transaction time for each recycling business The average and standard deviation , based on the average and the standard deviation Construct the preferred transaction time range of recyclers or users ,in, Adjust the parameters for the second range.

4. The resource matching method for credit evaluation based on multi-dimensional data according to claim 1, characterized in that: Based on the user's basic credit information and historical recycling records, the user's recycling credit is evaluated to obtain the user's initial credit, including: Determining the recycling business quantity from the historical recycling records of the user; When the recycling business quantity is less than or equal to a preset value, the basic credit information is used as the user's evaluation information; When the number of recycling services is greater than a preset value, the evaluation price of each recycling service in the user's historical recycling records is calculated. and payment price Deviation rate ,in ; The deviation rate The recycling business that is greater than the preset threshold is marked as the first target recycling business, and the user's initial credit is calculated based on the number of the first target recycling business. , where the initial credit The mathematical expression is: ； In the formula, is the basic credit score corresponding to the basic credit information, is the first scale parameter, is the second scale parameter, is the third scale parameter, The number of recycling services in the user's historical recycling records. The number of recovery businesses for the first goal.

5. The resource matching method for credit evaluation based on multi-dimensional data according to claim 4, characterized in that: The recycling credit of the recycler is evaluated based on the recycler's historical recycling records and evaluation information to obtain the recycler's initial credit, including: Calculate the assessed price of each recycling business in the recycling company's historical recycling records and payment price Deviation rate ,in ; and based on the pre-built emotion recognition model, perform emotion recognition on each evaluation text in the evaluation information to obtain the recognition result of each evaluation text , wherein the recognition results include positive, neutral and negative, and the emotion recognition model is obtained by training an artificial neural network based on training data with emotion states labeled in advance, is the serial number of the evaluation text; The deviation rate The recycling business with a value greater than a preset threshold is marked as a second target recycling business, and based on the number of the second target recycling business and the recognition result of each evaluation text Calculating a recycler's initial credit , where the recycler’s initial credit The mathematical expression is: ； In the formula, is the initial credit score set. is the fourth scale parameter, is the number of recycling businesses in the recycler's historical recycling records, The number of recovered businesses for the second goal, identifying the results When positive, , recognition results When it is neutral, , recognition results When negative, .

6. The resource matching method for credit evaluation based on multi-dimensional data according to claim 5, characterized in that: The initial credit of the user is modified using the initial credit of the recycler to obtain the user credit, including: Screen out initial credit Target merchants below the preset credit threshold; Remove the first target recycling business that exists in the target merchant, and re-use formula (1) to calculate the user's credit score to obtain the first credit score; The first credit scores of all users are normalized to obtain user credit.

7. The resource matching method for credit evaluation based on multi-dimensional data according to claim 6, characterized in that: The initial credit of the recycler is modified by using the initial credit of the user to obtain the credit of the recycler, including: Screen out initial credit Target users below the preset credit threshold; Remove the second target recycling business with target users, and re-use formula (2) to calculate the credit score of the recycler to obtain the second credit score; The second credit scores of all recyclers are normalized to obtain the recycler credit.

8. The resource matching method for credit evaluation based on multi-dimensional data according to claim 5, characterized in that: Matching the user and the recycler based on the transaction preference, the user credit and the recycler credit includes: Calculating the preference matching degree between the current user and each recycler based on the transaction preference; and selecting multiple recyclers with the highest matching degree as target recyclers; The user credit interval of the current user is determined, and a target recycler within the interval is used as a matching recycler for the current user, wherein the credit score is pre-divided into a plurality of intervals.

9. The resource matching method for credit evaluation based on multi-dimensional data according to claim 8, characterized in that: Calculating the preference matching degree between the user and each recycler based on the transaction preference, including: Determine the number of shared preferences that the user has with each recycler , Preferred price overlap rate Overlap rate with preferred transaction duration , the preference price overlap rate is the ratio of the length of the overlapping price segment to the length of the preferred price segment, and the preferred transaction duration overlap rate is the ratio of the length of the overlapping time segment to the length of the preferred transaction segment, is the recycler serial number; The number of common preference categories , the overlap rate of the preferred prices Overlap rate with the preferred transaction duration Perform weighted summation to obtain the preference matching degree between the user and each recycler , the preference matching degree The mathematical expression is: ； In the formula, is the first weight, is the second weight, The third weight.

10. A resource matching system for credit evaluation based on multi-dimensional data, characterized in that: include: An acquisition module is used to acquire the user's historical recycling records and basic credit information, and to acquire the recycler's historical recycling records and evaluation information, wherein the historical recycling records include the number of recycling businesses, item types, evaluation prices, payment prices, and transaction duration; A preference analysis module for determining the transaction preferences of users and recyclers based on historical recycling records; A credit analysis module, used to evaluate the recycling credit of the user based on the user's basic credit information and historical recycling records to obtain the user's initial credit, and to evaluate the recycling credit of the recycler based on the recycler's historical recycling records and evaluation information to obtain the recycler's initial credit; to modify the user's initial credit using the recycler's initial credit to obtain the user's credit, and to modify the recycler's initial credit using the user's credit to obtain the recycler's credit; A matching module is used to match the user and the recycler based on the transaction preference, the user credit and the recycler credit when performing a recycling transaction.

Images