Data Processing Method, Apparatus, Device and Readable Storage Medium

Abstract

The present application discloses a data processing method, apparatus, device and readable storage medium. The method includes: obtaining the travel characteristic data of a target user within a time period T t and the travel characteristic data within a time period T t‑1 ; the time period T t‑1 is the previous time period of the time period T t ; t is a positive integer greater than 1; according to the travel characteristic data within the time period T t and the travel characteristic data within the time period T t‑1 , predicting the predicted travel credit evaluation value of the target user within the time period T t ; obtaining the travel credit value of the target user within the time period T t‑1 , and determining the travel credit value of the target user within the time period T t‑1 according to the travel credit value within the time period T t and the predicted travel credit evaluation value within the time period T t . The present application is applied to the transportation field. By adopting the present application, the travel credit of users can be accurately evaluated, thereby improving the quality of the ride service.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a data processing method, apparatus, device, and readable storage medium. Background Art

[0002] Currently, taking a taxi has become a daily routine for people. In the taxi business, drivers increasingly need a reliable standard to understand the quality of passengers, so as not to fear losses in the taxi business; at the same time, passengers also need a reliable standard to prove their quality, so that they can obtain the recognition and trust of the taxi platform and drivers more simply and quickly, and thus can further obtain discounts given by the taxi platform.

[0003] It can be seen that in the taxi business, credit rating of passengers is an extremely important content. If there is a travel credit evaluation system for passengers, it will surely play a role in restricting and standardizing the behavior quality of passengers in the taxi business, thereby reducing behaviors such as unreasonable default and malicious ordering by passengers, and further bringing beneficial improvements to the social civilized environment and production efficiency. Currently, for determining the credit rating of passengers, it is only determined by relying on the number of order cancellations of passengers. If the number of order cancellations of a passenger is too high, the passenger's taxi service will be directly suspended. This method that only relies on the number of order cancellations of passengers is difficult to accurately evaluate user credit, resulting in low accuracy in identifying user credit and affecting the passenger's ride service. Summary of the Invention

[0004] Embodiments of this application provide a data processing method, apparatus, device, and readable storage medium, which can accurately evaluate the travel credit of users, thereby improving the quality of the ride service.

[0005] On the one hand, embodiments of this application provide a data processing method, including:

[0006] Obtain the travel feature data of a target user within a time period T t and the travel feature data within a time period T t-1 ; the time period T t-1 is the previous time period of the time period T t ; t is a positive integer greater than 1;

[0007] According to the travel feature data within the time period T t and the travel feature data within the time period T t-1 , predict the predicted travel credit evaluation value of the target user within the time period T t ;

[0008] Obtain the travel credit value of the target user within the time period T t-1 According to the time period Tt-1 The in - journey credit value within it and the time period T t The predicted in - journey credit evaluation value within it, to determine the in - journey credit value of the target user within the time period T t The in - journey credit value within it; the time period T t The in - journey credit value within it is used to determine the resources consumed by the target user's journey for the ride service within the time period T t The in - journey credit value within it, used to jointly determine with the predicted in - journey credit evaluation value within the time period T t The in - journey credit value within it, for jointly determining with the predicted in - journey credit evaluation value within the time period T t+1 The in - journey credit value of the target user within the time period T t+1 The in - journey credit value within it; the time period T t+1 is the time period T t The next time period of the time period T; the time period T t+1 The predicted in - journey credit evaluation value within it is based on the journey characteristic data of the target user within the time period T t+1 The journey characteristic data within it, and the journey characteristic data within the time period T t determined by the journey characteristic data within it.

[0009] An embodiment of the present application provides a data processing device on the one hand, including:

[0010] A data acquisition module, configured to acquire the journey characteristic data of the target user within the time period T t The journey characteristic data within it, and the journey characteristic data within the time period T t-1 The time period T t-1 is the time period T t The previous time period of the time period T; t is a positive integer greater than 1;

[0011] A data prediction module, configured to predict the predicted in - journey credit evaluation value of the target user within the time period T t Based on the journey characteristic data within the time period T and the journey characteristic data within the time period T t-1 The predicted in - journey credit evaluation value of the target user within the time period T t within it;

[0012] A credit value determination module, configured to acquire the in - journey credit value of the target user within the time period T t-1 within it;

[0013] The credit value determination module is further configured to, according to the in - journey credit value within the time period T t-1 and the predicted in - journey credit evaluation value within the time period T t Determine the in - journey credit value of the target user within the time period T t within it; the time period T t The in - journey credit value within it is used to determine the resources consumed by the target user's journey for the ride service within the time period T t within it; the time period T t The in - journey credit value within it, used to jointly determine with the time period T t+1The predicted travel credit evaluation value in the time period T determines the target user t+1 The credit value of the trip within the time period T t+1 is the time period T t The next time period; time period T t+1 The predicted trip credit evaluation value in the time period T is based on the target user t+1 The trip characteristic data within the time period T t Determined by the trip characteristic data within.

[0014] In one embodiment, the data prediction module includes:

[0015] Data input unit, used to input time period T t The trip feature data within the time period T is input into the credit assessment model; the credit assessment model is based on t-1 The trip characteristic data within the time period T t-1 The historical itinerary credit labels within the time period T are used to train the sample credit assessment model together; t-1 Historical trip credit tags within the time period T t-1 Determined by the number of historical defaults in the trip characteristics data within the

[0016] The data prediction unit is used to obtain the credit assessment model related to the time period T t-1 Associated model parameters, obtain the parameter transposed matrix corresponding to the model parameters;

[0017] The data prediction unit is also used to obtain the time period T t The feature matrix corresponding to the travel feature data in the time period T is obtained by performing matrix multiplication of the feature matrix and the parameter transpose matrix. t The credit assessment value of the predicted journey within.

[0018] In one embodiment, the credit value determination module includes:

[0019] Weight acquisition unit, used to obtain time period T t-1 The first weight parameter corresponding to the trip credit value within, and the time period T t A second weight parameter corresponding to the predicted trip credit assessment value within;

[0020] The calculation unit is used to convert the time period T t-1 The trip credit value in is multiplied by the first weight parameter to obtain a first calculated trip credit value;

[0021] The computing unit is also used to convert the time period T t The predicted trip credit evaluation value in is multiplied by the second weight parameter to obtain a second calculated trip credit value;

[0022] The operation unit is further configured to add the first operation trip credit value and the second operation trip credit value to obtain the trip credit value of the target user within the time period T. t within the time period T.

[0023] In one embodiment, the data processing device further includes:

[0024] The blockchain module is configured to obtain a hash function and encrypt the trip credit value within the time period T based on the hash function to obtain an encrypted trip credit value; t within the time period T.

[0025] The blockchain module is further configured to obtain the user identifier corresponding to the target user and generate a target block according to the user identifier and the encrypted trip credit value;

[0026] The blockchain module is further configured to upload the target block to the blockchain.

[0027] In one embodiment, the data processing device further includes:

[0028] The request receiving module is configured to receive a ride service request sent by the target terminal within the time period T; the target terminal is the terminal corresponding to the target user; t within the time period T.

[0029] The consumption data determining module is configured to obtain the trip credit value within the time period T in the blockchain according to the ride service request, and determine the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type according to the trip credit value within the time period T; t within the time period T. t The consumption data determining module is further configured to determine both the ride vehicle type and the ride consumption data as the trip consumption resources of the target user for the ride service, and send the trip consumption resources to the target terminal.

[0030] The consumption data determining module is further configured to determine both the ride vehicle type and the ride consumption data as the trip consumption resources of the target user for the ride service, and send the trip consumption resources to the target terminal.

[0031] In one embodiment, the data processing device further includes:

[0032] The matching module is configured to match the trip credit value within the time period T with a credit value threshold; t within the time period T.

[0033] The information sending module is configured to, if the trip credit value within the time period T is less than the credit value threshold, generate a permission prompt message and send the permission prompt message to the target terminal; the permission prompt message is used to prompt that the trip credit value of the target user within the time period T does not meet the ride condition and the target user does not have the permission to execute the ride service; t within the time period T. t The information sending module is configured to, if the trip credit value within the time period T is less than the credit value threshold, generate a permission prompt message and send the permission prompt message to the target terminal; the permission prompt message is used to prompt that the trip credit value of the target user within the time period T does not meet the ride condition and the target user does not have the permission to execute the ride service;

[0034] The step execution module is configured to, if the time period Tt If the trip credit value within is greater than or equal to the credit value threshold, then execute according to the time period T t Steps of determining the type of the vehicle taken by the target user based on the trip credit value within, and the ride consumption data pointed to by the vehicle type taken.

[0035] In one embodiment, the consumption data determination module includes:

[0036] A table acquisition unit for acquiring a vehicle type mapping table; the vehicle type mapping table includes a mapping relationship between a first configured trip credit value interval and a configured vehicle type; one first configured trip credit value interval corresponds to one configured vehicle type;

[0037] A type determination unit for using the time period T t The first configured trip credit value interval corresponding to the trip credit value within is determined as the first target trip credit value interval;

[0038] The type determination unit is further configured to determine the configured vehicle type corresponding to the first target trip credit value interval in the vehicle type mapping table as the vehicle type taken;

[0039] A consumption data determination unit for determining the ride consumption data according to the trip credit value within the time period T t and the vehicle type taken.

[0040] In one embodiment, the consumption data determination unit is further specifically configured to acquire a discount coefficient mapping table; the discount coefficient mapping table includes a mapping relationship between a second configured trip credit value interval and a configured discount coefficient; one second configured trip credit value interval corresponds to one configured discount coefficient;

[0041] The consumption data determination unit is further specifically configured to use the time period T t The second configured trip credit value interval corresponding to the trip credit value within is determined as the second target trip credit value interval;

[0042] The consumption data determination unit is further specifically configured to determine the configured discount coefficient corresponding to the second target trip credit value interval in the discount coefficient mapping table as the target discount coefficient;

[0043] The consumption data determination unit is further specifically configured to acquire the initial ride consumption data corresponding to the vehicle type taken, and multiply the initial ride consumption data by the target discount coefficient to obtain the ride consumption data.

[0044] In one embodiment, the data processing device further includes:

[0045] A label construction module for acquiring the trip feature data of the target user within the time period T t-1 within, and the time period Tt-1 The historical default times in the trip feature data within;

[0046] The label construction module is further configured to construct the historical trip credit label of the target user within the time period T according to the historical default times; t-1 within;

[0047] The model training module is used to train the sample credit evaluation model according to the trip feature data within the time period T and the historical trip credit label within the time period T, and obtain the credit evaluation model. t-1 and the historical trip credit label within the time period T, t-1 to obtain a credit evaluation model.

[0048] In one embodiment, the label construction module includes:

[0049] The times acquisition unit is configured to acquire the total number of user defaults of at least two historical users within the time period T; the at least two historical users are users who have taken a ride within the time period T; the at least two historical users include the target user; t-1 within; t-1 within;

[0050] The times acquisition unit is further configured to determine the number of users corresponding to the at least two historical users, and determine the average number of default times within the time period T according to the total number of user defaults and the number of users; t-1 within;

[0051] The label construction unit is configured to determine the historical trip credit label of the target user within the time period T according to the historical default times and the average number of default times; t-1 within.

[0052] In one embodiment, the label construction unit is further specifically configured to match the historical default times with the average number of default times;

[0053] The label construction unit is further specifically configured to, if the historical default times are greater than or equal to the average number of default times, determine the first numerical label as the historical trip credit label of the target user within the time period T; the first numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is an abnormal status; t-1 within;

[0054] The label construction unit is further specifically configured to, if the historical default times are less than the average number of default times, determine the second numerical label as the historical trip credit label of the target user within the time period T; the second numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is a normal status. t-1 within.

[0055] In one embodiment, the model training module includes:

[0056] A model input unit for inputting travel feature data within a time period T t-1 into a sample credit assessment model, and predicting a predicted travel credit assessment value of a target user within the time period T t-1 through sample model parameters in the sample credit assessment model and the travel feature data within the time period T t-1 ;

[0057] A loss value determination unit for determining a model loss value according to the predicted travel credit assessment value within the time period T t-1 and the historical travel credit label within the time period T t-1 ;

[0058] A model adjustment unit for training and adjusting the sample model parameters according to the model loss value to obtain model parameters, and determining the sample credit assessment model including the model parameters as a credit assessment model.

[0059] One aspect of the embodiments of the present application provides a computer device, including: a processor and a memory;

[0060] The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method in the embodiments of the present application.

[0061] One aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program, where the computer program includes program instructions, and when the program instructions are executed by a processor, the method in the embodiments of the present application is executed.

[0062] One aspect of the present application provides a computer program product or a computer program, where the computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in one aspect of the embodiments of the present application.

[0063] In the embodiments of the present application, the predicted travel credit assessment value of the target user within the time period T t-1 can be predicted through the travel feature data of the target user within the time period T t and the travel feature data within the time period T t ; Subsequently, the travel credit value of the target user within the time period T t-1 can be obtained, and according to the predicted travel credit assessment value within the time period T t and the travel credit value within the time period T t-1 , the travel credit value of the target user within the time period T t can be determined; and based on the time period T tThe target trip credit value within can be used to calculate and determine the resources consumed by the target user for the ride service during the time period T. t Within, the resources consumed by the target user for the ride service can be calculated. It can be seen that in the ride service of this application, based on the trip feature data of the target user in the previous time period and the trip feature data in this time period, the travel credit of the target user in this time period can be accurately evaluated to obtain an accurate predicted trip credit evaluation value. Subsequently, based on the trip credit value in the previous time period and the predicted trip credit evaluation value in this time period, an accurate trip credit value of the target user in this time period can be obtained. Furthermore, based on this trip credit value, the resources consumed by the target user for the ride service can be determined (for example, the higher the target trip credit value, the better the vehicle type allocated to the target user). It should be understood that by accurately evaluating the travel credit of users through the trip feature data of users, this application can improve the binding force of users' standardized behaviors in the ride service, encourage users to travel civilizedly and creditably, thereby improving the quality of the ride service. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0065] Figure 1 is a network architecture diagram provided by an embodiment of the present application;

[0066] Figures 2a - 2b is a schematic diagram of a user ride scenario provided by an embodiment of the present application;

[0067] Figure 3 is a flowchart of a data processing method provided by an embodiment of the present application;

[0068] Figure 4 is a schematic diagram of a block structure provided by an embodiment of the present application;

[0069] Figure 5 is a flowchart of another data processing method provided by an embodiment of the present application;

[0070] Figure 6 is a schematic diagram of a system process provided by an embodiment of the present application;

[0071] Figure 7 is a schematic diagram of the structure of a data processing device provided by an embodiment of the present application;

[0072] Figure 8It is a schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0073] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0074] The present application relates to the field of artificial intelligence. For the convenience of understanding, the following will elaborate on artificial intelligence and its related technical concepts.

[0075] Artificial Intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, and is a theory, method, technology, and application system that can perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines, enabling the machines to have the functions of perception, reasoning, and decision-making.

[0076] Artificial intelligence technology is an interdisciplinary subject involving a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0077] The solution provided by the embodiment of the present application belongs to machine learning (ML) under the field of artificial intelligence.

[0078] Machine Learning (ML) is an interdisciplinary subject involving multiple fields such as probability theory, statistics, approximation theory, convex analysis, and algorithm complexity theory. It specifically studies how a computer simulates or implements human learning behaviors to acquire new knowledge or skills, and reorganizes the existing knowledge structure to continuously improve its own performance. Machine learning is the core of artificial intelligence and the fundamental way to make a computer intelligent. Its applications cover all fields of artificial intelligence. Machine learning and deep learning usually include technologies such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and rote learning.

[0079] Please refer to Figure 1 , which is a schematic diagram of a network architecture provided by an embodiment of the present application. Blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. It is mainly used to sort data in chronological order, encrypt it into a ledger, making it tamper-proof and forgery-proof, and at the same time, data verification, storage, and update can be carried out. Essentially, blockchain is a decentralized database, and each node in this database stores an identical blockchain. The blockchain network divides nodes into core nodes, data nodes, and light nodes. Among them, core nodes are responsible for the consensus of the entire blockchain network, that is, core nodes are consensus nodes in the blockchain network; data nodes are responsible for synchronizing the ledger information of core nodes, that is, synchronizing the latest block data; light nodes belong to business nodes and are responsible for synchronizing business-related block data from data nodes.

[0080] For the process of writing transaction data into the ledger in the blockchain network, it can be that the client sends transaction data to a data node or a light node, and then this transaction data is passed between data nodes or light nodes in the blockchain network in a relay manner until the consensus node receives this transaction data. The consensus node then packages this transaction data into a block, conducts consensus with other consensus nodes. After the consensus is passed, the block carrying this transaction data is written into the ledger.

[0081] Among them, it can be understood that the blockchain system may include smart contracts. In the blockchain system, a smart contract can be understood as a piece of code that can be understood and executed by each node (including consensus nodes) in the blockchain, and can execute any logic and obtain results. Users can initiate a transaction business request through the client to call the smart contracts already deployed on the blockchain. Subsequently, the data nodes or light nodes on the blockchain can send this transaction business request to the consensus nodes, and each consensus node on the blockchain can run this smart contract respectively. It should be understood that the blockchain may include one or more smart contracts, and these smart contracts can be distinguished by identity document (ID) or name. In the transaction business request initiated by the client, the ID or name of the smart contract can also be carried to specify the smart contract that the blockchain needs to run. If the smart contract specified by the client is a contract that needs to read data, each consensus node will access the local ledger to read data. Finally, each consensus node will verify whether the execution results are consistent with each other (that is, conduct consensus). If they are consistent, the execution results can be stored in their respective local ledgers and the execution results can be returned to the client.

[0082] Such as Figure 1As shown, the network architecture may include a core node (consensus node) cluster 1000, a data node or a light node cluster 100, and a user terminal (client) cluster 10. The core node cluster 1000 may include at least two core nodes, and the light node 100 may include at least two data nodes. As Figure 1 shown, the core node cluster 1000 may include core nodes 1000a, 1000b, …, 1000n. The light node 100 may specifically include light nodes 100a, 100b, …, 100n. The user terminal cluster 10 may specifically include user terminals 10a, 10b, …, 10n.

[0083] As Figure 1 shown, the user terminals 10a, 10b, …, 10n may be respectively network-connected to the light nodes 100a, 100b, …, 100n, so that the user terminals can perform data interaction with the light nodes through the network connection; the light nodes 100a, 100b, …, 100n may be respectively network-connected to the core nodes 1000a, 1000b, …, 1000n, so that the light nodes can perform data interaction with the core nodes through the network connection; the light nodes 100a, 100b, …, 100n are connected to each other, so that data interaction can be performed between the light nodes, and the core nodes 1000a, 1000b, …, 1000n are connected to each other, so that data interaction can be performed between the core nodes.

[0084] It can be understood that, as Figure 1 shown, each user terminal may be installed with a target application. When the target application runs on each user terminal, each user terminal can obtain relevant information of the user. Among them, the target application may include an application with functions of processing data information such as displaying text, images, audio, and video. For example, the application may be an application supporting navigation and ride-hailing functions, such as a map application, a ticket booking application, a food ordering application, a logistics distribution application, etc. The application can be used for the user to navigate, take a taxi, etc.; and the user terminal can obtain the user's user information, taxi information, etc. through the application. Among them, the application may be an independent application or an embedded application integrated in a certain client (such as a social client, an educational client, and a multimedia client, etc.), which is not limited here.

[0085] For ease of understanding, embodiments of the present application may be in Figure 1Select one user terminal from the multiple user terminals shown as the target user terminal. The user terminal may include, but is not limited to, intelligent terminals with multimedia data processing functions (such as video data playback function, music data playback function, text data playback function), such as smart phones, tablet computers, laptop computers, desktop computers, smart TVs, smart speakers, desktop computers, smart watches, intelligent voice interaction devices, smart home appliances, vehicle terminals, etc. For example, in the embodiments of the present application, Figure 1 The user terminal 100a shown can be used as the target user terminal, and a target application with the data information processing function can be integrated in the target user terminal. At this time, the target user terminal can realize data interaction with the data node cluster 100 through the service data platform corresponding to the target application.

[0086] For example, when the target user uses the target application (such as a map application) in the target user terminal within a certain period of time, the target user can input a certain location in the target application and select to take a taxi to that location. Correspondingly, this period of time can be called time period T t , which can also be called the time period to be measured. The target user terminal can obtain the travel characteristic data of the target user within this time period (i.e., within time period T t ), and the travel characteristic data within this time period can be called the travel characteristic data to be measured. Subsequently, the target user terminal can send the travel characteristic data to be measured to a certain data node in the data node cluster 100. Taking the data node 100a as an example, the target user terminal can send the travel characteristic data to be measured to the data node 100a, and the data node 100a can send the travel characteristic data to be measured to a certain core node in the core node cluster 1000. Taking the core node 1000a as an example, the data node 100a can send the travel characteristic data to be measured to the core node 1000a. Further, the core node 1000a can determine the travel credit value of the target user within the time period T t based on the travel characteristic data to be measured, and upload the travel credit value within the time period T t to the blockchain to which it belongs.

[0087] The core node 1000a can return the travel credit value within the time period T t to the target user terminal, and the target user terminal can determine the travel consumption resources of the target user for this ride service according to the travel credit value within the time period T t . The travel consumption resources may include vehicle brand type, vehicle driver, taxi fare, etc. For example, if the travel credit value within the time period T t is higher than a certain threshold, when receiving the ride request of the target user within the time period T t , it can be based on the time period Tt The trip credit value within t assigns a better vehicle brand type to the target user, assigns a driver with a higher credit, and offers a discount on the taxi fare for the target user. Among them, for the trip characteristic data to be measured (i.e., the time period T t The trip characteristic data within t ), it is determined that the target user's trip credit value within the time period T t The specific implementation method of the trip credit value within t can be seen in the description of the corresponding embodiment in the following Figure 3 section.

[0088] Optionally, it can be understood that after the target user terminal obtains the trip characteristic data of the target user within a certain time period (which can be called the time period T t ), it can first determine the trip credit value of the target user within the time period T based on the trip characteristic data to be measured; subsequently, the target user terminal can then send the trip credit value within the time period T t to the data node 100a, and the data node 100a sends it to the core node 1000a; the core node 1000a uploads the trip credit value within the time period T t to the blockchain it belongs to, so as to ensure the authenticity and security of the trip credit value within the time period T t . t

[0089] It can be understood that the method provided in the embodiments of the present invention can be executed by a computer device, and the computer device includes but is not limited to a user terminal or a server. The nodes in the embodiments of the present invention can be computer devices.

[0090] For ease of understanding, please refer to Figures 2a - 2b Figures 2a - 2b which is a schematic diagram of a user's ride scenario provided in an embodiment of the present application. Among them, as Figures 2a - 2b shown, the user terminal 20a can be any user terminal in the user terminal cluster corresponding to the above Figure 1 embodiment, for example, the user terminal is the user terminal 10a; as Figures 2a - 2b shown, the blockchain node can be any core node in the core node cluster corresponding to the above Figure 1 embodiment, such as the core node is the core node 1000b.

[0091] As Figure 2a ​​As shown, when user a uses user terminal 20a, the user can search for a navigation route from the current location to location A through a target application (such as a navigation application) installed in user terminal 20a; user terminal 20a can correspondingly display the route to location A and the distance to location A. At the same time, user terminal 20a can also display a taxi control, and user a can click on this taxi control to hail a taxi. It should be understood that the embodiments of the present application can regularly calculate the trip credit value of the user (including user a), and calculate the resources consumed by the user in the taxi service (riding service) based on this trip credit value.

[0092] The embodiments of the present application calculate the trip credit value of the user based on the trip feature data of the user in each period (each time period for calculating the trip credit value). For example, taking the calculation of the user's trip credit value once every month as an example, if the time period from January 1, 2021 to January 31, 2021 is a time period for calculating the trip credit value, then the time period from February 1, 2021 to February 28, 2021 is the next time period for calculating the trip credit value. If the time when user a clicks the taxi control is February 10, 2021, then the time period in which this taxi-hailing time is located is from February 1, 2021 to February 28, 2021. It is necessary to obtain the trip feature data of user a in this time period from February 1, 2021 to February 28, 2021 (because the current time is February 10, 2021, so it is actually the trip feature data of user a in the time period from February 1, 2021 to February 10, 2021). Based on this trip feature data, the trip credit value of user a in the time period from February 1, 2021 to February 10, 2021 can be calculated. Thus, based on this trip credit value, the resources consumed by user a for the riding service (taxi service) can be determined.

[0093] As described above, as Figure 2a shown, after user a clicks the taxi control, user terminal 20a can correspondingly respond to this trigger operation of user a, obtain the trigger timestamp of this trigger operation of user a, and obtain the time period in which this trigger timestamp is located. The time period in which this trigger timestamp is located can be determined as the time period to be measured (which can also be called time period T t ). Further, user terminal 20a can obtain the trip feature data of user a within this time period to be measured. The trip feature data within this time period to be measured can be called the trip feature data to be measured; subsequently, user terminal 20a can send this trip feature data to be measured to the blockchain node.

[0094] Further, the blockchain node may input the to-be-tested trip feature data into the credit assessment model, and the credit assessment model may output the predicted trip credit assessment value of the target user during the to-be-tested time period. Subsequently, the blockchain node may obtain the block 2001 associated with user a from the blockchain 200, and the trip credit value of user a during the historical time period (the time period preceding the to-be-tested time period, which may also be referred to as time period T t-1 ; if the to-be-tested time period is from February 1, 2021 to February 28, 2021 as described above, then the historical time period may be from January 1, 2021 to January 31, 2021) is stored in the block 2001, and the blockchain node may obtain the trip credit value of user a stored in the block 2001 during time period T t-1 . Further, according to the trip credit value of user a during time period T t-1 and the predicted trip credit assessment value of user a during the to-be-tested time period (time period T t ), the blockchain node may determine the trip credit value of user a during the to-be-tested time period. Among them, the above credit assessment model may be trained based on the trip feature data of user a during the historical time period (time period T t-1 ). For the specific way of obtaining the credit assessment model by training the model, reference may be made to the description in the subsequent Figure 5 corresponding embodiment; for the specific implementation manner of determining the trip credit value during time period T t-1 according to the trip credit value during time period T t and the predicted trip credit assessment value during time period T t , reference may be made to the description in the subsequent Figure 3 corresponding embodiment.

[0095] Further, as Figure 2b shown, the blockchain node may generate the block 2002 according to the trip credit value during the time period T t and upload the block 2002 to the blockchain 200. It should be understood that the blockchain node may determine the resources consumed by user a for the trip for the ride service according to the trip credit value during the time period T t . Taking the resources consumed by the trip including the vehicle brand (vehicle type) and the taxi fare as an example, if the trip credit value during the time period T t is greater than the threshold, a better vehicle brand (vehicle type) may be allocated to user a, and at the same time, user a may be given a certain discount. For example, as Figure 2b shown, the trip credit value of user a during time period T tThe trip credit value in is 98, and the trip credit value 98 is greater than the threshold value 75. Then the vehicle types corresponding to the trip credit value 98 can be obtained as vehicle type 1, vehicle type 2, and vehicle type 3, and the discount coefficient corresponding to the trip credit value 98 can also be obtained as 20%. The initial taxi fare 1 corresponding to vehicle type 1 can be obtained. According to the initial taxi fare 1 and the discount coefficient 20%, it can be determined that the taxi fare required for user a to use vehicle type 1 is 11 yuan; similarly, the initial taxi fare 2 corresponding to vehicle type 2 can be obtained. According to the initial taxi fare 2 and the discount coefficient 20%, it can be determined that the taxi fare required for user a to use vehicle type 2 is 15 yuan; similarly, the initial taxi fare 3 corresponding to vehicle type 3 can be obtained. According to the initial taxi fare 3 and the discount coefficient 20%, it can be determined that the taxi fare required for user a to use vehicle type 3 is 13 yuan. Then the travel consumption resources of user a for the ride-hailing service may include {vehicle type 1: 11 yuan; vehicle type 2: 15 yuan; vehicle type 3: 13 yuan}, and the blockchain node may return the travel consumption resources to the user terminal 20a.

[0096] Furthermore, the user terminal 20a may display the resources consumed by the trip in its display interface. At the same time, the user terminal 20a may also display a simultaneous call control in the display interface. If the user a clicks on the simultaneous call control, vehicles of vehicle type 1, vehicle type 2, and vehicle type 3 may be called simultaneously. After successfully calling a vehicle, the user a may ride in the vehicle.

[0097] It should be understood that the present application can improve the restraint on users' standardized behavior in ride-hailing services by accurately evaluating users' travel credit through their travel feature data in each time period, and can encourage users to travel in a civilized and credit-based manner, thereby improving the quality of ride-hailing services.

[0098] For further information, see Figure 3 , Figure 3 is a flow chart of a data processing method provided by an embodiment of the present application. The method may be performed by a user terminal (for example, the above Figure 1 Any user terminal in the user terminal cluster shown, such as user terminal 100b), can also be executed by a blockchain node (for example, the above Figure 1 The method may be executed by any core node in the core node cluster shown, such as core node 1000b), or may be executed by a user terminal and a core node together. For ease of understanding, this embodiment takes the method executed by the above core node as an example for explanation. The method may include at least the following steps S101-S103:

[0099] Step S101: Obtain the target user in time period T tThe travel feature data within, and within the time period T t-1 The travel feature data within; the time period T t-1 Is the previous time period of the time period T t ; t is a positive integer greater than 1.

[0100] In this application, the travel credit value of the target user can be calculated regularly. For example, it can be calculated once every week, once every month, once every two months, once every six months, once every year, etc. Taking calculating the travel credit value of the target user once every month as an example, each period for calculating the target user can be from January 1, 2021 to January 31, 2021, from February 1, 2021 to February 28 (or 29), 2021, from March 1, 2021 to March 31, 2021, and so on. Each period for calculating the target user can be used as a time period, and the time period T t Can be the next time period after the travel credit value has been calculated, and the time period T t-1 Can be the last time period after the travel credit value has been calculated. For example, if the travel credit values of the target user from January 1, 2021 to January 31, 2021, from February 1, 2021 to February 28 (or 29), 2021, and from March 1, 2021 to March 31, 2021 have been calculated, then from March 1, 2021 to March 31, 2021 can be understood as the last time period after the travel credit value of the target user has been calculated, and this from March 1, 2021 to March 31, 2021 can be called the time period T t-1 , and the next time period after from March 1, 2021 to March 31, 2021, that is, from April 1, 2021 to April 30, 2021, can be called the time period T t . This time period T t Can also be called the time period to be measured, and this time period T t-1 Can also be called the previous historical time period of the time period to be measured.

[0101] It can be understood that this application can calculate the travel credit value of the target user jointly according to the travel feature data of the target user in the time period T t (that is, the time period to be measured), and the travel feature data in the time period T t-1 . Among them, the travel feature data of the target user in the time period T t Can be called the to-be-measured travel feature data, and the travel feature data of the target user in the time period T t Can be called the to-be-measured travel feature data, and the travel feature data of the target user in the time period T t-1The trip feature data therein can be called historical trip feature data. Among them, the trip feature data of the target user in each time period may include the travel feature information of the target user in each time period. The travel feature information may include the account information of the target user in the Electronic Toll Collection (ETC) system (such as, account status information, account balance information, average recharge amount, overdue amount, overdue duration, etc.), the riding information of the target user (such as, taxi-taking frequency, cancellation frequency, cancellation reason information, reserved number of passengers when taking a taxi, actual number of passengers when getting on the vehicle, taxi fare for each time, vehicle replacement information, etc.), the transaction information of the target user for the riding service (taxi service) (such as, delayed payment amount, delayed payment frequency, delayed payment duration and other delayed payment information; coupon amount used, coupon clicked for use, coupon cancelled for use, coupon expiration information and other coupon usage information), the trip status information of the target user for the taxi service (such as, the target user modifies the trip information during the driving of the riding service, late arrival information, driver cancels the trip information, etc.), the driver's rating information for the target user, and so on.

[0102] Then obviously the trip feature data of the target user in time period T t and time period T t-1 can also include the above travel feature information of the target user in time period T t therein.

[0103] Step S102, according to the trip feature data in time period T t and the trip feature data in time period T t-1 predict the predicted trip credit evaluation value of the target user in time period T t therein.

[0104] In this application, for predicting the predicted trip credit evaluation value of the target user in time period T t according to the trip feature data in time period T t-1 and the trip feature data in time period T t the specific implementation method can be: input the trip feature data in time period T t into the credit evaluation model; among them, the credit evaluation model is obtained by jointly training the sample credit evaluation model based on the trip feature data in time period T t-1 and the historical trip credit labels in time period T t-1 ; the historical trip credit labels in this time period T t-1 are determined based on the historical default times in the trip feature data in time period T t-1 ; subsequently, the value in the credit evaluation model corresponding to time period T t-1Associated model parameters are obtained, and the parameter transpose matrix corresponding to the model parameters is acquired. Subsequently, the travel feature data within the time period T can be obtained. t The feature matrix corresponding to the travel feature data within it is obtained, and the feature matrix is multiplied by the parameter transpose matrix through matrix multiplication, and then the predicted travel credit assessment value (travel credit score) of the target user within the time period T can be obtained. t within can be obtained.

[0105] It should be understood that the travel feature data of the target user within the time period T t-1 includes the ride information of the target user within the time period T t-1 and the ride information of the target user within the time period T t-1 includes the number of canceled taxi rides of the target user within the time period T t-1 Then, the number of canceled taxi rides of the target user within the time period T t-1 can be referred to as the historical default times. First, the historical default times in the travel feature data within the time period T t-1 are obtained. Based on the historical default times, the historical travel credit label of the target user within the time period T t-1 can be determined. Based on the travel feature data within the time period T t-1 and the historical travel credit label within the time period T t-1 the sample credit assessment model can be trained to obtain the credit assessment model.

[0106] The above sample credit assessment model can be an initialized supervised machine learning model, such as a logistic regression model, a support vector machine (Support Vector Machine, SVM) model, a decision tree model, a random forest model, etc.; based on the travel feature data within the time period T t-1 and the travel credit label within the time period T t-1 the sample credit assessment model can be jointly trained to obtain a credit assessment model that can be used to predict the predicted travel credit assessment value of the target user within the time period T t within. Among them, for determining the historical travel credit label of the target user within the time period T t-1 based on the historical default times, and for jointly training the sample credit assessment model according to the travel feature data and the historical travel credit label within the time period T t-1 The specific implementation methods can be referred to the descriptions in the subsequent Figure 5 corresponding embodiments.

[0107] Among them, the specific method for predicting the predicted travel credit assessment value of the target user within the time period T t can be shown as the following formula (1):

[0108]

[0109] Among them, W (t-1) can be used to characterize the model parameters in the credit evaluation model obtained after training the sample credit evaluation model based on the trip feature data in the (t-1)th period (time period T t-1 ); (W (t-1) ) T W that can be used to characterize the model parameters (t-1) transpose matrix of (i.e., ); X (t) can be used to characterize the to-be-trip feature data in the tth period (time period T t ); (i.e., ); S t can be used to characterize the trip credit value of the target user in the tth period.

[0110] Step S103, obtain the trip credit value of the target user within the time period T t-1 , and determine the trip credit value of the target user within the time period T t-1 according to the trip credit value within the time period T t and the predicted trip credit evaluation value within the time period T t ; the trip credit value within the time period T t is used to determine the trip consumption resources of the target user for the ride service within the time period T t ; the trip credit value within the time period T t is used to jointly determine the trip credit value of the target user within the time period T t+1 with the predicted trip credit evaluation value within the time period T t+1 ; the time period T t+1 is the next time period of the time period T t ; the predicted trip credit evaluation value within the time period T t+1 is determined based on the trip feature data of the target user within the time period T t+1 , and the trip feature data within the time period T t .

[0111] In this application, to ensure the authenticity and security of the trip credit value of the target user in each time period, after calculating the trip credit value of the target user in each time period, the trip credit value can be uploaded to the blockchain. Then the trip credit value of the target user within the time period T t-1 will also be stored in the blockchain. Then, after calculating the predicted trip credit evaluation value of the target user within the time period T t , the trip credit value of the target user stored in the blockchain within the time period T t-1 can be obtained, and according to the trip credit value within this time period T t-1 and the trip credit value within this time period Tt The predicted trip credit evaluation value within it can be jointly used to determine the trip credit value of the target user within the time period T t within it.

[0112] And for the trip credit value within the time period T t-1 and the predicted trip credit evaluation value within the time period T t to jointly determine the trip credit value of the target user within the time period T t The specific implementation method can be as follows: The first weight parameter corresponding to the trip credit value within the time period T t-1 and the second weight parameter corresponding to the predicted trip credit evaluation value within the time period T t can be obtained; the trip credit value within the time period T t-1 can be multiplied by the first weight parameter to obtain the first operation trip credit value; the predicted trip credit evaluation value within the time period T t can be multiplied by the second weight parameter to obtain the second operation trip credit value; the first operation trip credit value and the second operation trip credit value are added together to obtain the trip credit value of the target user within the time period T t within it.

[0113] It can be understood that the first weight parameter and the second weight parameter can be artificially specified values. For example, both the first weight parameter and the second weight parameter can be set to 1. Then, when the predicted trip credit evaluation value within the time period T t is obtained using the credit evaluation model, the predicted trip credit evaluation value within the time period T t can be directly added to the trip credit value within the time period T t-1 to obtain the trip credit value of the target user within the time period T t within it. Optionally, the first weight parameter and the second weight parameter can also be parameters obtained through machine learning training.

[0114] It can be understood that after determining the trip credit value of the target user within the time period T t , the trip credit value within the time period T t can be uploaded to the blockchain. Thus, when calculating the trip credit value of the target user in the next time period of the time period T t (such as the time period T t+1 ), the trip credit value of the time period T t can be obtained from the blockchain, and the trip credit value of the next time period can be calculated and determined based on the target trip credit value. Among them, the specific implementation method for uploading the trip credit value within the time period T t to the blockchain can be as follows: A hash function can be obtained, and based on the hash function for the time period T tEncrypt the travel credit value within to obtain the encrypted travel credit value; subsequently, the user identifier corresponding to the target user can be obtained, and a target block can be generated based on the user identifier and the encrypted travel credit value; the target block can be chained to the blockchain, thus completing the process of chaining to the blockchain.

[0115] It should be noted that the travel credit value of the target user in each time period can be used to calculate and determine the resources consumed by the target user for the travel business (taxi business) during the corresponding time period (such as resources such as taxi fares, taxi discounts, vehicle brand type information, driver information, etc.); and if there is a taxi demand at a certain timestamp within a certain time period to be measured for the target user (such as time period T t )), then the time period composed of the start time of the time period to be measured to this timestamp can be used as a sub-time period to be measured. Because the time period after this timestamp belongs to the future time period and the target user does not have travel feature data yet, the travel feature data to be measured of the target user within the time period to be measured is actually the travel feature data of the target user within this sub-time period to be measured. Then, the travel credit value calculated based on the travel feature data within this sub-time period to be measured corresponds to this sub-time period to be measured. At this time, because this sub-time period to be measured belongs to the time period to be measured, this travel credit value can of course be called the travel credit value within the time period to be measured, and the travel credit value corresponding to this sub-time period to be measured can also be chained to the blockchain; however, when the timestamp reaches the maximum timestamp corresponding to the time period to be measured (such as time period T t ), all the travel feature data of the target user within this time period to be measured can be obtained again, and the total travel credit value of the target user within this time period to be measured (which can also be called the travel credit value within the time period to be measured) can be calculated. Subsequently, this total travel credit value can be chained to the blockchain, and when calculating the travel credit value of the next time period within the time period to be measured (such as time period T t+1 ), this total travel credit value within the time period to be measured can be used for calculation and determination, rather than using the travel credit value corresponding to the above sub-time period to be measured for calculation and determination.

[0116] For example, the historical time period (time period T t-1 ) is from May 1, 2021 to May 31, 2021, and the travel credit value corresponding to the historical time period is 88; the time period to be measured (time period T t) is from June 1, 2021 to June 30, 2021, and the current time and date of the target user is June 15, 2021. June 16, 2021 and subsequent dates are future dates that have not yet arrived. Then, when the target user has a taxi-hailing demand on June 15, 2021, after the blockchain node receives the taxi-hailing request (riding service request) sent by the target user through its corresponding target terminal, it can obtain the travel feature data of the target user within the period from June 1, 2021 to June 15, 2021, and use this travel feature data as the to-be-tested travel feature data. The period from June 1, 2021 to June 15, 2021 is the to-be-tested sub-period; subsequently, based on the travel credit value 88 within the above-mentioned time period T t-1 and the to-be-tested travel feature data within the period from June 1, 2021 to June 15, 2021, jointly determine the travel credit value of the target user within the period from June 1, 2021 to June 15, 2021, and calculate and determine the travel consumption resources of the target user for this riding service based on this travel credit value.

[0117] It should be understood that the travel credit value of the target user within the period from June 1, 2021 to June 15, 2021 can be uploaded to the blockchain to ensure the authenticity and security of this travel credit value; when the time reaches June 15, 2021, the travel feature data of the target user within the period from June 1, 2021 to June 30, 2021 can be obtained again and used as the to-be-tested travel feature data; subsequently, based on the travel feature data within the period from June 1, 2021 to June 30, 2021, calculate and determine the target travel credit value (i.e., the total travel credit value) of the target user within the period from June 1, 2021 to June 30, 2021, and upload the total travel credit value of the target user within the period from June 1, 2021 to June 30, 2021 to the blockchain. At the same time, when calculating and determining the travel credit value of the target user within the period from July 1, 2021 to July 31, 2021, calculate and determine the travel credit value of the target user within the period from July 1, 2021 to July 31, 2021 based on the total travel credit value of the target user within the period from June 1, 2021 to June 30, 2021.

[0118] As can be seen from the above, the travel credit value of the target user within each time period can be used to calculate and determine the travel consumption resources of the target user for the riding service (taxi-hailing service) within its corresponding time period. Then, the travel credit value of the target user within the time period T t can also be used to calculate and determine the travel credit value of the target user within the time period T tResources consumed during a trip for the ride-hailing service. Among them, the resources consumed during the trip may include ride-hailing fees, ride-hailing discounts, vehicle information, driver information, vehicle type brands, etc. It should be understood that this application can provide a discount standard, that is, corresponding discount methods and vehicle allocation methods can be configured according to the target trip credit value of the target user. In a feasible way, the target user with a higher travel credit score (target trip credit value) can obtain more discounts (and can also obtain better vehicle brand types and drivers with higher scores); while the target user with a lower travel credit score (target trip credit value) obtains lower discounts or even no discounts (or increased taxi fares), and at the same time, a better vehicle brand type or a driver with a higher score will not be allocated to him. It should be understood that by means of discounting based on the target trip credit value, it is possible to encourage passengers to travel civilly and with credit.

[0119] For ease of understanding, the following will take the resources consumed during the trip including vehicle type and taxi fare as an example to elaborate on the specific method of calculating and determining the resources consumed during the trip for the ride-hailing service according to the trip credit value of the target user within the time period T t within the time period T t for the ride-hailing service. The specific method can be: within the time period T t receive a ride-hailing service request sent by the target terminal; among them, the target terminal can be the terminal corresponding to the target user; according to the ride-hailing service request, obtain the trip credit value within the time period T t in the blockchain, and determine the ride-hailing vehicle type of the target user and the ride-hailing consumption data (which can be understood as taxi fare) pointed to by the ride-hailing vehicle type according to the trip credit value within the time period T t Subsequently, both the ride-hailing vehicle type and the ride-hailing consumption data can be determined as the resources consumed during the trip for the ride-hailing service of the target user, and the resources consumed during the trip can be sent to the target terminal.

[0120] Among them, it should be understood that if the trip credit value of the target user within the time period T t is too low, then the taxi-taking permission of the target user can be cancelled, and the target user does not have the qualification to take a taxi within this time period T t to warn the target user to travel with credit and civilly. The specific method can be: match the trip credit value within the time period T t with the credit value threshold; if the trip credit value within the time period T t is less than the credit value threshold, then a permission prompt message can be generated and sent to the target terminal; among them, the permission prompt message is used to prompt the target user that the trip credit value within the time period T t does not meet the taxi-taking conditions, and the target user does not have the permission to execute the ride-hailing service; and if the time period T tIf the trip credit value within is greater than or equal to the credit value threshold, the above steps of determining the vehicle type for the target user's ride and the ride consumption data corresponding to the vehicle type according to the time period T can be executed. t within to determine the vehicle type for the target user's ride and the ride consumption data corresponding to the vehicle type.

[0121] Further, after the trip credit value of the target user within the time period T t is greater than the credit value threshold, the vehicle type for the target user's ride and the ride consumption data corresponding to the vehicle type can be determined according to the trip credit value within the time period T. The specific method can be as follows: A vehicle type mapping table can be obtained. Among them, the vehicle type mapping table can include the mapping relationship between the first configured trip credit value interval and the configured vehicle type. One first configured trip credit value interval corresponds to one configured vehicle type. Subsequently, the first configured trip credit value interval corresponding to the trip credit value within the time period T t can be determined as the first target trip credit value interval. The configured vehicle type corresponding to the first target trip credit value interval in the vehicle type mapping table can be determined as the vehicle type for the ride. The ride consumption data can be determined according to the trip credit value within the time period T t and the vehicle type for the ride. t The specific method of determining the ride consumption data according to the trip credit value within the time period T and the vehicle type for the ride can be as follows: A discount coefficient mapping table can be obtained. Among them, the discount coefficient mapping table includes the mapping relationship between the second configured trip credit value interval and the configured discount coefficient. One second configured trip credit value interval corresponds to one configured discount coefficient. The second configured trip credit value interval corresponding to the trip credit value within the time period T

[0122] can be determined as the second target trip credit value interval. The configured discount coefficient corresponding to the second target trip credit value interval in the discount coefficient mapping table can be determined as the target discount coefficient. Subsequently, the initial ride consumption data corresponding to the vehicle type for the ride can be obtained, and the initial ride consumption data can be multiplied by the target discount coefficient to obtain the final ride consumption data. t The specific method of determining the ride consumption data according to the trip credit value within the time period T and the vehicle type for the ride can be as follows: A discount coefficient mapping table can be obtained. Among them, the discount coefficient mapping table includes the mapping relationship between the second configured trip credit value interval and the configured discount coefficient. One second configured trip credit value interval corresponds to one configured discount coefficient. The second configured trip credit value interval corresponding to the trip credit value within the time period T t can be determined as the second target trip credit value interval. The configured discount coefficient corresponding to the second target trip credit value interval in the discount coefficient mapping table can be determined as the target discount coefficient. Subsequently, the initial ride consumption data corresponding to the vehicle type for the ride can be obtained, and the initial ride consumption data can be multiplied by the target discount coefficient to obtain the final ride consumption data.

[0123] It should be understood that the above target user can be understood as a passenger in the ride-hailing service, and the target user can also be a driver in the ride-hailing service. The solution provided in this application can also regularly calculate the travel credit score (trip credit value) of the driver. When the target user is a driver, the above trip feature data may include the driver's account information in the ETC, the driver's travel information (such as, passenger-carrying frequency, cancellation frequency, cancellation reason information, etc.), the driver's transaction information for the ride-hailing service (such as, amount of additional fees, frequency of additional fees, etc.), the driver's trip status information for the taxi-hailing service (such as, information on extended routes during driving, modified trip information, additional passenger information, late arrival information, cancelled trip information, passenger-cancelled trip information, etc.), the passenger's rating information for the driver, and so on. This application can also adopt the above method to calculate and determine the trip credit value of the driver in each time period based on the trip feature data of the driver in each time period. And this trip credit value can be used to determine whether the driver is eligible to grab an order for the taxi-hailing service for the passenger (only when the driver's trip credit value is relatively high can the driver be eligible to grab an order); when a taxi-hailing request from a passenger is obtained, the taxi-hailing order of this passenger can be preferentially assigned to the driver with a relatively high trip credit value.

[0124] In the embodiment of this application, the predicted trip credit evaluation value of the target user in time period T can be obtained through the trip feature data of the target user in time period T t-1 and the trip feature data in time period T t ; subsequently, the trip credit value of the target user in time period T can be obtained, and based on the predicted trip credit evaluation value in time period T t and the trip credit value in time period T t-1 , the trip credit value of the target user in time period T t can be determined; and based on the target trip credit value in time period T t-1 , the trip credit value of the target user in time period T t can be calculated and determined; and based on the target trip credit value in time period T t , the trip credit value of the target user in time period T tThe travel consumption resources for the ride-hailing service within the period. It can be seen that in the ride-hailing service, the present application can accurately evaluate the travel credit of the target user in the current time period based on the travel characteristic data of the target user in the previous time period and the travel characteristic data of the current time period, and obtain an accurate predicted travel credit evaluation value; subsequently, the accurate travel credit value of the target user in the current time period can be obtained based on the travel credit value in the previous time period and the predicted travel credit evaluation value in the current time period, and further the travel consumption resources of the target user for the ride-hailing service can be determined based on the travel credit value (for example, the higher the target travel credit value, the better the vehicle type allocated to the target user). It should be understood that the present application can improve the binding force of the user's standardized behavior in the ride-hailing service by accurately evaluating the user's travel credit through the user's travel characteristic data, and can encourage users to travel in a civilized and credit-based manner, thereby improving the quality of the ride-hailing service.

[0125] To understand the specific process of obtaining data from the blockchain and uploading data to the blockchain, please refer to Figure 4 , Figure 4 It is a schematic diagram of a block structure provided in an embodiment of the present application. It should be understood that the time period to be tested (time period T t ) can be understood as Figure 4 The t period is shown, while the time period T t-1 It can be understood as Figure 4 The t-1 period shown; the itinerary feature data of period t-1 can be used to train the sample credit assessment model to obtain the credit assessment model of period t, and the credit assessment model of period t and the itinerary feature data of period t can be used to calculate and determine the travel credit score (trip credit value) of the target user in period t. Similarly, the itinerary feature data of period t-2 can be used to train the sample credit assessment model to obtain the credit assessment model of period t-1, and the credit assessment model of period t-1 and the itinerary feature data of period t-1 can be used to calculate and determine the travel credit score (trip credit value) of the target user in period t-1. Based on the travel credit score of period t, block 40b can be generated; based on the travel credit score of period t-1, block 40a can be generated.

[0126] like Figure 4 As shown, each block in the blockchain can contain the hash value of all the information of the previous block (i.e. Figure 4(The parent block hash value shown), the information of each block (including block 40a and block 40b) may include: block identity (Identity document, ID), parent block hash value, timestamp, nonce, travel credit score. After calculating and determining the travel credit score in the (t - 1)th period, block 40a can be generated based on the travel credit score in the (t - 1)th period. Subsequently, the hash algorithm can be used to encrypt block 40a, and a private key corresponding to the target user can be generated. The private key can be sent to the target terminal corresponding to the target user, and the target terminal can decrypt block 40a based on the private key to view the travel credit score in block 40a.

[0127] At the same time, the block hash value of block 40a can be passed as the parent block hash value to the next block node (i.e., the block node in the tth period). When calculating the travel credit score in the tth period, the public key technology can be used to verify the signature of the block hash value of block 40a to verify the authenticity of the data. Using the public key technology, the travel credit score in block 40a can be obtained. According to the travel credit score in block 40a, the credit evaluation model in the tth period, and the travel feature data in the tth period, the travel credit score in the tth period can be jointly determined, and block 40b can be generated based on the travel credit score. Similarly, the hash algorithm can be used to encrypt block 40b, and a private key corresponding to the target user can be generated. The private key can be sent to the target terminal corresponding to the target user, and the target terminal can decrypt block 40b based on the private key to view the travel credit score in block 40b. At the same time, the block hash value of block 40b can be passed as the parent block hash value to the next block node (i.e., the block node in the (t + 1)th period).

[0128] In the embodiment of the present application, the travel feature data of the target user in time period T t-1 and the travel feature data in time period T t can be used to predict the predicted travel credit evaluation value of the target user in time period T t ; Subsequently, the travel credit value of the target user in time period T t-1 can be obtained. According to the predicted travel credit evaluation value in time period T t and the travel credit value in time period T t-1 , the travel credit value of the target user in time period T t can be determined; and based on the target travel credit value in time period T t , the travel credit value of the target user in time period T tResources consumed during the trip for the ride-hailing service. It can be seen that in the ride-hailing service of this application, based on the trip feature data of the target user in the previous time period and the trip feature data in this time period, the travel credit of the target user in this time period can be accurately evaluated to obtain an accurate predicted trip credit evaluation value. Subsequently, based on the trip credit value in the previous time period and the predicted trip credit evaluation value in this time period, the trip credit value of the target user in this time period can be accurately obtained, and further, based on this trip credit value, the resources consumed by the target user for the ride-hailing service can be determined (for example, the higher the target trip credit value, the better the vehicle type allocated to the target user). It should be understood that by accurately evaluating the travel credit of users through the trip feature data of users, this application can improve the binding force of users' standardized behaviors in the ride-hailing service, encourage users to travel civilizedly and with credit, thereby improving the quality of the ride-hailing service.

[0129] Further, please refer to Figure 5 , Figure 5 which is a schematic flowchart of a model training method provided by an embodiment of this application. This method can be executed by a user terminal (for example, any user terminal in the user terminal cluster shown above Figure 1 , such as user terminal 100b), or by a blockchain node (for example, any core node in the core node cluster shown above Figure 1 , such as core node 1000b), or jointly by a user terminal and a core node. For ease of understanding, this embodiment is described by taking this method as being executed by the above core node as an example. Among them, this method can at least include the following steps S201 - step S203:

[0130] Step S201, obtain the trip feature data of the target user within time period T t-1 , and the historical default times in the trip feature data within time period T t-1 .

[0131] In this application, for the specific interpretations of the trip feature data and the historical default times within time period T t-1 , time period T t-1 , reference can be made to the descriptions in the corresponding embodiments above Figure 3 , and details will not be elaborated here.

[0132] Step S202, construct the historical trip credit label of the target user within time period T t-1 according to the historical default times.

[0133] In this application, for constructing the historical trip credit label of the target user within time period T t-1The specific implementation method of the historical trip credit label within can be: at least two historical users can be obtained within time period T t-1 the total number of user defaults within; where at least two historical users are users who have taken a ride within time period T t-1 ; and at least two historical users include the target user; subsequently, the number of users corresponding to at least two historical users can be determined, and based on the total number of user defaults and the number of users, the average number of defaults within time period T t-1 can be determined; based on the historical number of defaults and the average number of defaults, the historical trip credit label of the target user within time period T t-1 can be determined.

[0134] Among them, the specific method for determining the historical trip credit label of the target user within time period T based on the historical number of defaults and the average number of defaults can be: the historical number of defaults and the average number of defaults can be matched; if the historical number of defaults is greater than or equal to the average number of defaults, the first numerical label can be determined as the historical trip credit label of the target user within time period T t-1 ; where the first numerical label is used to represent that the trip credit status of the target user within time period T t-1 is an abnormal status; and if the historical number of defaults is less than the average number of defaults, the second numerical label can be determined as the historical trip credit label of the target user within time period T t-1 ; where the second numerical label is used to represent that the trip credit status of the target user within time period T t-1 is a normal status. t-1

[0135] It should be understood that the above at least two historical users are users who have taken a taxi within time period T t-1 (i.e., all passengers within time period T t-1 ); the number of cancellation times of the trip that occurred among these passengers can be obtained, and this number is the above total number of user defaults. For example, user a cancelled a trip within time period T t-1 , user b cancelled a trip within time period T t-1 , and user c cancelled a trip within time period T t-1 , then the total number of user defaults can be 3. Based on the total number of cancellation times of all passengers' trips and the number of all passengers, the average number of cancelled trips within time period T t-1 (i.e., the average number of defaults) can be determined. And if the number of cancellation times (historical number of defaults) of the target user is greater than or equal to this average number of cancelled trips, the historical trip credit label of this target user can be marked as 0 (i.e., the first numerical label); and if the number of cancellation times of the target user is less than this average number of cancelled trips, the historical trip credit label of this target user can be marked as 1 (i.e., the second numerical label).​

[0136] Step S203: According to the trip feature data within time period T t-1 and the historical trip credit labels within time period T t-1 train the sample credit evaluation model to obtain a credit evaluation model.

[0137] In this application, for training the sample credit evaluation model according to the trip feature data within time period T t-1 and the historical trip credit labels within time period T t-1 to obtain a credit evaluation model, the specific implementation manner may be: input the trip feature data within time period T t-1 into the sample credit evaluation model. Through the sample model parameters in the sample credit evaluation model and the trip feature data within time period T t-1 the predicted trip credit evaluation value of the target user within time period T can be predicted; according to the predicted trip credit evaluation value within time period T t-1 and the historical trip credit labels, the model loss value can be determined; according to the model loss value, the sample model parameters can be trained and adjusted to obtain model parameters, and the sample credit evaluation model including the model parameters can be determined as the credit evaluation model. t-1 It should be understood that if the model loss value does not meet the model convergence condition, the sample model parameters can be adjusted based on the model loss value; if the model loss value meets the model convergence condition, no further training adjustment is required, and the sample model parameters when the model convergence condition is met are determined as the final model parameters, and the sample credit evaluation model including the model parameters is determined as the final credit evaluation model.

[0138] It should be understood that if the model loss value does not meet the model convergence condition, the sample model parameters can be adjusted based on the model loss value; if the model loss value meets the model convergence condition, no further training adjustment is required, and the sample model parameters when the model convergence condition is met are determined as the final model parameters, and the sample credit evaluation model including the model parameters is determined as the final credit evaluation model.

[0139] In the embodiment of this application, training the credit evaluation model through the trip feature data within time period T t-1 can enable the credit evaluation model to accurately predict the predicted trip credit evaluation value corresponding to time period T, and further, based on the accurate predicted trip credit evaluation value within time period T t the trip credit value within time period T can be obtained. Further, based on this trip credit value, the resources consumed by the target user for the ride service can be determined (for example, the higher the target trip credit value, the better the vehicle type allocated for the target user). It should be understood that this application can accurately evaluate the travel credit of users through the trip feature data of users, improve the binding force of users' standardized behaviors in the ride service, encourage users to travel civilizedly and with credit, and thus improve the quality of the ride service. t the trip credit value within time period T can be obtained. Further, based on this trip credit value, the resources consumed by the target user for the ride service can be determined (for example, the higher the target trip credit value, the better the vehicle type allocated for the target user). It should be understood that this application can accurately evaluate the travel credit of users through the trip feature data of users, improve the binding force of users' standardized behaviors in the ride service, encourage users to travel civilizedly and with credit, and thus improve the quality of the ride service. t the trip credit value within time period T can be obtained. Further, based on this trip credit value, the resources consumed by the target user for the ride service can be determined (for example, the higher the target trip credit value, the better the vehicle type allocated for the target user). It should be understood that this application can accurately evaluate the travel credit of users through the trip feature data of users, improve the binding force of users' standardized behaviors in the ride service, encourage users to travel civilizedly and with credit, and thus improve the quality of the ride service.

[0140] Further, please refer to Figure 6, Figure 6 It is a schematic diagram of a system process provided by an embodiment of the present application.

[0141] As Figure 6 shown, the process may include the following steps S301 - step S307:

[0142] Step S301, obtain the travel feature data within the time period T t-1 inside.

[0143] Step S302, construct the historical travel credit label within the time period T t-1 according to the travel feature data within the time period T. t-1 inside.

[0144] In the present application, for the specific implementation manners of steps S301 - step S302, reference may be made to the description of step S201 in the corresponding embodiment above, and details will not be elaborated here. Figure 4

[0145] Step S303, construct the training samples.

[0146] In the present application, the travel feature data within the time period T t-1 can be docked with the historical travel credit label within the time period T t-1 to obtain the initial sample data. The initial sample data can be divided into training samples and test samples according to a certain ratio. For example, the initial sample data can be divided into training samples (ratio 80%) and test samples (ratio 20%) according to the ratio of 8:2.

[0147] Step S304, input the training samples to train the sample credit evaluation model.

[0148] In the present application, the training samples can be input into the sample credit evaluation model to train the sample credit evaluation model, and thus the credit evaluation model can be obtained.

[0149] Step S305, predict the predicted travel credit evaluation value of the target user within the to - be - measured time period according to the credit evaluation model.

[0150] Step S306, determine the travel credit value of the target user within the time period T t according to the predicted travel credit evaluation value.

[0151] Step S307, determine the travel - consumed resources of the target user for the ride service according to the travel credit value within the time period T t inside.

[0152] Among them, for the specific implementation manners of steps S305 - step S307, reference may be made to the above Figure 3 ​The descriptions of steps S101 - S103 in the corresponding embodiments will not be elaborated here.

[0153] In the embodiments of the present application, the travel characteristic data of the target user in time period T t-1 and the travel characteristic data in time period T t can be used to predict the predicted travel credit evaluation value of the target user in time period T t Subsequently, the travel credit value of the target user in time period T t-1 can be obtained. Based on the predicted travel credit evaluation value in this time period T t and the travel credit value in this time period T t-1 the travel credit value of the target user in time period T t can be determined. Based on the target travel credit value in this time period T t the travel resource consumption of the target user for the ride service in time period T t can be calculated and determined. It can be seen that in the ride service of the present application, based on the travel characteristic data of the target user in the previous time period and the travel characteristic data of the current time period, the travel credit of the target user in the current time period can be accurately evaluated to obtain an accurate predicted travel credit evaluation value. Subsequently, based on the travel credit value in the previous time period and the predicted travel credit evaluation value in the current time period, the accurate travel credit value of the target user in the current time period can be obtained, and further, based on this travel credit value, the travel resource consumption of the target user for the ride service can be determined (for example, the higher the target travel credit value, the better the vehicle type allocated for the target user). It should be understood that by accurately evaluating the travel credit of the user through the travel characteristic data of the user, the present application can improve the binding force of the user's standardized behavior in the ride service, encourage the user to travel civilizedly and with credit, thereby improving the quality of the ride service.

[0154] Further, please refer to Figure 7 , Figure 7 which is a schematic structural diagram of a data processing device provided by an embodiment of the present application. The data processing device can be a computer program (including program code) running in a computer device. For example, the data processing device is an application software. The data processing device can be used to execute Figure 3 the method shown. As Figure 7 shown, the data processing device 1 can include: a data acquisition module 11, a data prediction module 12, and a credit value determination module 13.

[0155] The data acquisition module 11 is used to acquire the travel characteristic data of the target user in time period T t and the travel characteristic data in time period T t-1 Time period Tt-1 is the previous time period of time period T t ; t is a positive integer greater than 1;

[0156] The data prediction module 12 is used to predict the predicted trip credit evaluation value of the target user within the time period T t based on the trip feature data within the time period T t-1 and the trip feature data within the time period T t ;

[0157] The credit value determination module 13 is used to obtain the trip credit value of the target user within the time period T t-1 ;

[0158] The credit value determination module 13 is further used to determine the trip credit value of the target user within the time period T t-1 based on the trip credit value within the time period T t and the predicted trip credit evaluation value within the time period T t ; the trip credit value within the time period T t is used to determine the resources consumed by the target user for the trip service within the time period T t ; the trip credit value within the time period T t is used to jointly determine the trip credit value of the target user within the time period T t+1 with the predicted trip credit evaluation value within the time period T t+1 ; the time period T t+1 is the next time period of the time period T t ; the predicted trip credit evaluation value within the time period T t+1 is determined based on the trip feature data of the target user within the time period T t+1 and the trip feature data within the time period T t ;

[0159] Among them, for the specific implementation manners of the data acquisition module 11, the data prediction module 12, and the credit value determination module 13, reference can be made to the descriptions of steps S101 - S103 in the corresponding embodiments above Figure 3 , and details will not be elaborated here

[0160] Please refer to Figure 7 , the data prediction module 12 may include: a data input unit 121 and a data prediction unit 122

[0161] The data input unit 121 is used to input the trip feature data within the time period T t into the credit evaluation model; the credit evaluation model is based on the trip feature data within the time period T t-1 and the trip feature data within the time period T t-1The historical travel credit labels within are obtained by jointly training the sample credit assessment model; time period T t-1 The historical travel credit labels within are based on time period T t-1 Determined based on the historical default times in the travel feature data within;

[0162] The data prediction unit 122 is configured to obtain the model parameters associated with time period T in the credit assessment model and obtain the parameter transpose matrix corresponding to the model parameters; t-1 The data prediction unit 122 is further configured to obtain the feature matrix corresponding to the travel feature data within time period T, perform matrix multiplication processing on the feature matrix and the parameter transpose matrix, and obtain the predicted travel credit assessment value of the target user within time period T.

[0163] The data prediction unit 122 is further configured to obtain the feature matrix corresponding to the travel feature data within time period T, perform matrix multiplication processing on the feature matrix and the parameter transpose matrix, and obtain the predicted travel credit assessment value of the target user within time period T. t The data prediction unit 122 is further configured to obtain the feature matrix corresponding to the travel feature data within time period T, perform matrix multiplication processing on the feature matrix and the parameter transpose matrix, and obtain the predicted travel credit assessment value of the target user within time period T. t The predicted travel credit assessment value within.

[0164] Among them, the specific implementation manners of the data input unit 121 and the data prediction unit 122 can be referred to the description in step S102 of the corresponding embodiment above, and will not be elaborated here. Figure 3 The description in step S102 of the corresponding embodiment above, and will not be elaborated here.

[0165] Please refer to Figure 7 , the credit value determination module 13 may include: a weight acquisition unit 131 and an operation unit 132.

[0166] The weight acquisition unit 131 is configured to obtain the first weight parameter corresponding to the travel credit value within time period T, and the second weight parameter corresponding to the predicted travel credit assessment value within time period T; t-1 The weight acquisition unit 131 is configured to obtain the first weight parameter corresponding to the travel credit value within time period T, and the second weight parameter corresponding to the predicted travel credit assessment value within time period T; t The second weight parameter corresponding to the predicted travel credit assessment value within.

[0167] The operation unit 132 is configured to perform multiplication processing on the travel credit value within time period T and the first weight parameter to obtain the first operation travel credit value; t-1 The operation unit 132 is configured to perform multiplication processing on the travel credit value within time period T and the first weight parameter to obtain the first operation travel credit value;

[0168] The operation unit 132 is further configured to perform multiplication processing on the predicted travel credit assessment value within time period T and the second weight parameter to obtain the second operation travel credit value; t The operation unit 132 is further configured to perform multiplication processing on the predicted travel credit assessment value within time period T and the second weight parameter to obtain the second operation travel credit value;

[0169] The operation unit 132 is further configured to perform addition processing on the first operation travel credit value and the second operation travel credit value to obtain the travel credit value of the target user within time period T. t The travel credit value within.

[0170] Among them, the specific implementation manners of the weight acquisition unit 131 and the operation unit 132 can be referred to the description in step S103 of the corresponding embodiment above, and will not be elaborated here. Figure 3 The description in step S103 of the corresponding embodiment above, and will not be elaborated here.

[0171] Please refer to Figure 7 , the data processing device 1 may further include: a blockchain uploading module 14.

[0172] The blockchain uploading module 14 is configured to obtain a hash function, encrypt the target trip credit value based on the hash function to obtain an encrypted trip credit value;

[0173] The blockchain uploading module 14 is further specifically configured to obtain a user identifier corresponding to the target user, and generate a target block according to the user identifier and the encrypted trip credit value;

[0174] The blockchain uploading module 14 is further specifically configured to upload the target block to the blockchain.

[0175] Among them, for the specific implementation manner of the blockchain uploading module 14, reference may be made to the description in step S103 in the corresponding embodiment above, which will not be elaborated here. Figure 3 The description in step S103 in the corresponding embodiment above, which will not be elaborated here.

[0176] Please refer to Figure 7 , the data processing device 1 may further include: a request receiving module 15 and a consumption data determining module 16.

[0177] The request receiving module 15 is configured to receive a ride service request sent by the target terminal within the time period T t ; the target terminal is the terminal corresponding to the target user;

[0178] The consumption data determining module 16 is configured to obtain the trip credit value within the time period T in the blockchain according to the ride service request, and determine the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type; t According to the trip credit value within the time period T t Determine the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type;

[0179] The consumption data determining module 16 is further configured to determine both the ride vehicle type and the ride consumption data as the trip consumption resources of the target user for the ride service, and send the trip consumption resources to the target terminal.

[0180] Among them, for the specific implementation manners of the request receiving module 15 and the consumption data determining module 16, reference may be made to the description in step S103 in the corresponding embodiment above, which will not be elaborated here. Figure 3 The description in step S103 in the corresponding embodiment above, which will not be elaborated here.

[0181] Please refer to Figure 7 , the data processing device 1 may further include: a matching module 17, an information sending module 18, and a step execution module 19.

[0182] The matching module 17 is configured to match the trip credit value within the time period T t with the credit value threshold;

[0183] An information sending module 18, configured to generate an authority prompt message and send the authority prompt message to a target terminal if the trip credit value within a time period T t is less than a credit value threshold; the authority prompt message is used to prompt that the trip credit value of the target user within the time period T t does not meet the riding condition, and the target user does not have the authority to execute the riding service;

[0184] A step execution module 19, configured to execute the step of determining the riding vehicle type of the target user according to the trip credit value within the time period T t if the trip credit value within the time period T t is greater than or equal to the credit value threshold, and the riding consumption data pointed to by the riding vehicle type.

[0185] Among them, for the specific implementation manners of the matching module 17, the information sending module 18, and the step execution module 19, reference can be made to the description in step S103 in the corresponding embodiment above Figure 3 , and details will not be described herein again.

[0186] Please refer to Figure 7 , the consumption data determination module 16 may include: a table acquisition unit 161, a type determination unit 162, and a consumption data determination unit 163.

[0187] The table acquisition unit 161 is configured to acquire a vehicle type mapping table; the vehicle type mapping table includes a mapping relationship between a first configured trip credit value interval and a configured vehicle type; one first configured trip credit value interval corresponds to one configured vehicle type;

[0188] The type determination unit 162 is configured to determine the first configured trip credit value interval corresponding to the trip credit value within the time period T t as the first target trip credit value interval;

[0189] The type determination unit 162 is further configured to determine the configured vehicle type corresponding to the first target trip credit value interval in the vehicle type mapping table as the riding vehicle type;

[0190] The consumption data determination unit 163 is configured to determine the riding consumption data according to the trip credit value within the time period T t and the riding vehicle type.

[0191] Among them, for the specific implementation manners of the table acquisition unit 161, the type determination unit 162, and the consumption data determination unit 163, reference can be made to the description in step S103 in the corresponding embodiment above Figure 3 , and details will not be described herein again.

[0192] In one embodiment, the consumption data determination unit 163 is further specifically configured to obtain a discount coefficient mapping table; the discount coefficient mapping table includes a mapping relationship between a second configured trip credit value interval and a configured discount coefficient; one second configured trip credit value interval corresponds to one configured discount coefficient;

[0193] The consumption data determination unit 163 is further specifically configured to use the travel credit value within the time period T t to determine the corresponding second configured trip credit value interval as the second target trip credit value interval;

[0194] The consumption data determination unit 163 is further specifically configured to determine the configured discount coefficient corresponding to the second target trip credit value interval in the discount coefficient mapping table as the target discount coefficient;

[0195] The consumption data determination unit 163 is further specifically configured to obtain the initial ride consumption data corresponding to the type of the ride vehicle, and multiply the initial ride consumption data by the target discount coefficient to obtain the ride consumption data.

[0196] Please refer to Figure 7 , the data processing device 1 may further include: a label construction module 21 and a model training module 22.

[0197] The label construction module 21 is configured to obtain the trip feature data of the target user within the time period T t-1 and the historical default times in the trip feature data within the time period T t-1 ;

[0198] The label construction module 21 is further configured to construct the historical trip credit label of the target user within the time period T t-1 according to the historical default times;

[0199] The model training module 22 is configured to train the sample credit evaluation model according to the trip feature data within the time period T t-1 and the historical trip credit label within the time period T t-1 to obtain a credit evaluation model.

[0200] Among them, for the specific implementation manners of the label construction module 21 and the model training module 22, reference may be made to the descriptions in steps S201 - S203 in the corresponding embodiment above, and details will not be repeated here. Figure 5

[0201] In one embodiment, the label construction module 21 may include: a times acquisition unit 211 and a label construction unit 212.

[0202] The times acquisition unit 211 is configured to obtain at least two historical users within the time period T t-1 ​The total number of user defaults within; at least two historical users are users who have taken rides within the time period T t-1 among them; at least two historical users include the target user;

[0203] The number acquisition unit 211 is further configured to determine the number of users corresponding to at least two historical users, and determine the time period T according to the total number of user defaults and the number of users t-1 The average number of defaults within;

[0204] The label construction unit 212 is configured to determine the historical trip credit label of the target user within the time period T according to the historical default number and the average number of defaults t-1 within.

[0205] Among them, for the specific implementation manners of the number acquisition unit 211 and the label construction unit 212, reference may be made to the description in step S202 in the foregoing Figure 5 corresponding embodiment, and details will not be described herein again.

[0206] In one embodiment, the label construction unit 212 is further specifically configured to match the historical default number with the average number of defaults;

[0207] The label construction unit 212 is further specifically configured to, if the historical default number is greater than or equal to the average number of defaults, determine the first numerical label as the historical trip credit label of the target user within the time period T t-1 within; the first numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is an abnormal status;

[0208] The label construction unit 212 is further specifically configured to, if the historical default number is less than the average number of defaults, determine the second numerical label as the historical trip credit label of the target user within the time period T t-1 within; the second numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is a normal status.

[0209] In one embodiment, the model training module 22 may include: a model input unit 221, a loss value determination unit 222, and a model adjustment unit 223.

[0210] The model input unit 221 is configured to input the trip feature data within the time period T t-1 into the sample credit evaluation model, and predict the predicted trip credit evaluation value of the target user within the time period T through the sample model parameters in the sample credit evaluation model and the trip feature data within the time period T t-1 within; t-1 within;

[0211] The loss value determination unit 222 is configured to, according to the time period Tt-1 the predicted trip credit evaluation value within and the time period T t-1 the historical trip credit labels within, and determine the model loss value;

[0212] The model adjustment unit 223 is configured to perform training and adjustment on the sample model parameters according to the model loss value to obtain model parameters, and determine the sample credit evaluation model including the model parameters as the credit evaluation model.

[0213] Among them, for the specific implementation manners of the model input unit 221, the loss value determination unit 222, and the model adjustment unit 223, reference may be made to the description in step S203 in the corresponding embodiment above, which will not be elaborated here. Figure 5 The description in step S203 in the corresponding embodiment above will not be elaborated here.

[0214] In the embodiment of the present application, the trip feature data of the target user in the time period T t-1 and the trip feature data in the time period T t can be used to predict the predicted trip credit evaluation value of the target user in the time period T t ; subsequently, the trip credit value of the target user in the time period T t-1 can be obtained, and based on the predicted trip credit evaluation value in the time period T t and the trip credit value in the time period T t-1 , the trip credit value of the target user in the time period T t can be determined; and based on the target trip credit value in the time period T t , the trip resource consumption of the target user for the ride service in the time period T t can be calculated and determined. It can be seen that in the ride service of the present application, based on the trip feature data of the target user in the previous time period and the trip feature data of the current time period, the travel credit of the target user in the current time period can be accurately evaluated to obtain an accurate predicted trip credit evaluation value; subsequently, based on the trip credit value in the previous time period and the predicted trip credit evaluation value in the current time period, the accurate trip credit value of the target user in the current time period can be obtained, and further, the trip resource consumption of the target user for the ride service can be determined based on this trip credit value (for example, the higher the target trip credit value, the better the vehicle type allocated to the target user). It should be understood that by accurately evaluating the travel credit of the user through the trip feature data of the user, the present application can improve the binding force of the user's standardized behavior in the ride service, encourage the user to travel civilizedly and with credit, and thus improve the quality of the ride service.

[0215] Furthermore, please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a computer device provided by an embodiment of the present application. As shown in Figure 8As shown above, the above-mentioned Figure 7 The data processing device 1 in the corresponding embodiment can be applied to the above-mentioned computer device 1000. The above-mentioned computer device 1000 may include: a processor 1001, a network interface 1004, and a memory 1005. In addition, the above-mentioned computer device 1000 further includes: a user interface 1003 and at least one communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. Among them, the user interface 1003 may include a display screen (Display) and a keyboard (Keyboard). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. Optionally, the memory 1005 may further be at least one storage device located far from the aforementioned processor 1001. As Figure 8 shown, the memory 1005, as a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a device control application program.

[0216] In Figure 8 the computer device 1000 shown, the network interface 1004 can provide network communication functions; while the user interface 1003 is mainly used to provide an input interface for users; and the processor 1001 can be used to call the device control application program stored in the memory 1005 to achieve:

[0217] Obtain the travel characteristic data of the target user within the time period T t and the travel characteristic data within the time period T t-1 ; the time period T t-1 is the previous time period of the time period T t ; t is a positive integer greater than 1;

[0218] According to the travel characteristic data within the time period T t and the travel characteristic data within the time period T t-1 , predict the predicted travel credit evaluation value of the target user within the time period T t ;

[0219] Obtain the travel credit value of the target user within the time period T t-1 , and according to the travel credit value within the time period T t-1 and the predicted travel credit evaluation value within the time period T t , determine the travel credit value of the target user within the time period T t ; the time period T tThe in-trip credit value is used to determine the resources consumed by the target user for the ride service within time period T t ; the in-trip credit value within time period T t is used to jointly determine the in-trip credit value of the target user within time period T t+1 together with the predicted in-trip credit evaluation value within time period T t+1 ; time period T t+1 is the next time period of time period T t ; the predicted in-trip credit evaluation value within time period T t+1 is determined based on the trip feature data of the target user within time period T t+1 and the trip feature data within time period T t .

[0220] It should be understood that the computer device 1000 described in the embodiments of the present application can execute the description of the data processing method in the corresponding embodiments mentioned above Figure 3 or Figure 5 ; it can also execute the description of the data processing device 1 in the corresponding embodiments mentioned above Figure 7 , which will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either.

[0221] In addition, it should be noted here that: the embodiments of the present application also provide a computer-readable storage medium, and the computer program executed by the computer device 1000 for data processing mentioned above is stored in the above computer-readable storage medium, and the above computer program includes program instructions. When the above processor executes the above program instructions, it can execute the description of the above data processing method in the corresponding embodiments mentioned above Figure 3 or Figure 5 , so it will not be elaborated here. In addition, the description of the beneficial effects of using the same method will not be elaborated either. For the technical details not disclosed in the embodiments of the computer-readable storage medium involved in the present application, please refer to the description of the method embodiments of the present application.

[0222] The above computer-readable storage medium may be the data processing device provided in any of the foregoing embodiments or the internal storage unit of the above computer device, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store the data that has been output or is to be output.

[0223] In one aspect of the present application, there is provided a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in one aspect of the embodiments of the present application.

[0224] The terms "first", "second", etc. in the description and claims of the embodiments of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or modules, but optionally further includes steps or modules not listed, or optionally further includes other step units inherent to these processes, methods, devices, products or equipment.

[0225] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0226] The method and related devices provided by the embodiments of the present application are described with reference to the method flowcharts and / or structural schematic diagrams provided by the embodiments of the present application. Specifically, each process and / or block of the method flowchart and / or structural schematic diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general computer, a special computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or structural schematic Figure 1 diagrams, or in multiple blocks.

[0227] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or structural schematic Figure 1 diagrams, or in multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one process or multiple processes and / or structural schematic diagrams, or in multiple blocks.

[0228] The foregoing disclosure is only for the preferred embodiments of the present application, and of course cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A data processing method, characterized in that, including: Obtain the travel feature data of the target user within the time period T t and the travel feature data within the time period T t-1 ; the time period T t-1 is the previous time period of the time period T t ; t is a positive integer greater than 1; Input the travel feature data within the time period T t into the credit assessment model; the credit assessment model is obtained by jointly training a sample credit assessment model based on the travel feature data within the time period T t-1 and the historical travel credit labels within the time period T t-1 ; the historical travel credit labels within the time period T t-1 are determined based on the historical default times in the travel feature data within the time period T t-1 ; obtain the model parameters associated with the time period T t-1 in the credit assessment model, and the parameter transpose matrix corresponding to the model parameters; obtain the feature matrix corresponding to the travel feature data within the time period T t , perform matrix multiplication on the feature matrix and the parameter transpose matrix to obtain the predicted travel credit assessment value of the target user within the time period T t ; Get the target user in the time period T t-1 The credit value of the trip within the time period T t-1 The credit value of the trip within the time period T t The predicted travel credit evaluation value within the time period T determines the target user t The travel credit value within the time period T t The travel credit value within the time period T is used to determine the target user t The time period T is the time period for the trip consumption of the ride service. t The credit value of the trip within the time period T t+1 The predicted travel credit evaluation value in the time period T jointly determines the target user t+1 The travel credit value within the time period T t+1 is the time period T t The next time period of the t+1 The predicted travel credit evaluation value within the time period T is based on the target user t+1 The trip characteristic data within the time period T t Determined by the trip characteristic data within.

2. The method according to claim 1, characterized in that, Based on the trip credit value within the said time period T t-1 and the predicted trip credit evaluation value within the said time period T t to determine the trip credit value of the target user within the said time period T t includes: Obtain the travel credit value within the time period T t-1 The first weight parameter corresponding to the travel credit value within the time period T, and t The second weight parameter corresponding to the predicted travel credit evaluation value within the time period T; Multiply the trip credit value within the time period T t-1 by the first weight parameter to obtain a first calculated trip credit value; Multiply the predicted travel credit assessment value within the time period T t by the second weight parameter to obtain a second calculated travel credit value; Add the first operation trip credit value and the second operation trip credit value to obtain the trip credit value of the target user within the time period T. t ​ 3. The method according to claim 1, characterized in that, The method further includes: Obtain a hash function, and encrypt the trip credit value within the time period T based on the hash function to obtain an encrypted trip credit value; t ​ obtaining a user identifier corresponding to the target user, and generating a target block according to the user identifier and the encrypted trip credit value; uploading the target block to a blockchain.

4. The method according to claim 3, characterized in that, The method further includes: During the time period T t receive a ride service request sent by the target terminal; the target terminal is the terminal corresponding to the target user; Obtain the time period T in the blockchain according to the ride service request, and determine the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type based on the trip credit value within the time period T t within the trip credit value, and according to the trip credit value within the time period T t determine the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type; determining both the vehicle type of the ride and the consumption data of the ride as the trip consumption resources of the target user for the ride service, and sending the trip consumption resources to the target terminal.

5. The method according to claim 4, wherein The method further includes: Match the trip credit value within the time period T t with the credit value threshold; If the travel credit value within the time period T t is less than the credit value threshold, a permission prompt message is generated and sent to the target terminal; the permission prompt message is used to prompt the target user that the travel credit value within the time period T t does not meet the ride condition, and the target user does not have the permission to execute the ride service; If the trip credit value within the time period T t is greater than or equal to the credit value threshold, then perform the step of determining the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type according to the trip credit value within the time period T t ​ 6. The method according to claim 5, wherein Determining the ride vehicle type of the target user and the ride consumption data pointed to by the ride vehicle type according to the travel credit value within the time period T t including: obtaining a vehicle type mapping table; the vehicle type mapping table includes a mapping relationship between a first configured trip credit value range and a configured vehicle type; one first configured trip credit value range corresponds to one configured vehicle type; Determine the first configured trip credit value interval corresponding to the trip credit value within the time period T t as the first target trip credit value interval; determining the configured vehicle type corresponding to the first target trip credit value range in the vehicle type mapping table as the vehicle type of the ride; Based on the trip credit value within the time period T t determine the ride consumption data according to the type of the ride vehicle.

7. The method according to claim 6, wherein Determining the ride consumption data according to the trip credit value within the said time period T t includes: obtaining a discount coefficient mapping table; the discount coefficient mapping table includes a mapping relationship between a second configured trip credit value range and a configured discount coefficient; one second configured trip credit value range corresponds to one configured discount coefficient; Determine the second configured trip credit value interval corresponding to the trip credit value within the time period T t as the second target trip credit value interval; determining the configured discount coefficient corresponding to the second target trip credit value range in the discount coefficient mapping table as the target discount coefficient; obtaining the initial consumption data of the ride corresponding to the vehicle type of the ride, and multiplying the initial consumption data of the ride by the target discount coefficient to obtain the consumption data of the ride.

8. The method according to claim 1, characterized in that The training process of the credit evaluation model includes: Obtain the travel feature data of the target user within the time period T t-1 and the historical default times in the travel feature data within the time period T t-1 ; Construct the historical trip credit label of the target user within the time period T according to the number of historical defaults t-1 therein; According to the travel feature data within the time period T t-1 and the historical travel credit labels within the time period T t-1 train the sample credit assessment model to obtain the credit assessment model.

9. The method according to claim 8, wherein Construct the historical trip credit label of the target user within the time period T according to the historical default times, including: t-1 ​ Obtain the total number of user defaults of at least two historical users within the time period T t-1 ; The at least two historical users are users who have taken rides within the time period T t-1 ; The at least two historical users include the target user Determine the number of users corresponding to the at least two historical users, and determine the default frequency mean within the time period T according to the total number of user defaults and the number of users. t-1 The average number of defaults within it; Determine the historical trip credit label of the target user within the time period T according to the historical default times and the average default times t-1 therein 10. The method according to claim 9, characterized in that, Determining the historical trip credit label of the target user within the time period T according to the historical default times and the average default times t-1 includes: matching the historical number of defaults with the average number of defaults; If the number of historical defaults is greater than or equal to the average number of defaults, then determine the first numerical label as the historical trip credit label of the target user within the time period T t-1 ; the first numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is an abnormal status; If the number of historical defaults is less than the average number of defaults, the second numerical label is determined as the historical trip credit label of the target user within the time period T t-1 ; the second numerical label is used to characterize that the trip credit status of the target user within the time period T t-1 is in a normal state.

11. The method according to claim 8, characterized in that Based on the travel characteristic data within the time period T t-1 and the historical travel credit tags within the time period T t-1 train the sample credit evaluation model to obtain the credit evaluation model, including: Input the travel feature data within the time period T t-1 into the sample credit assessment model. Through the sample model parameters in the sample credit assessment model and the travel feature data within the time period T t-1 , predict the predicted travel credit assessment value of the target user within the time period T t-1 ; According to the predicted trip credit evaluation value within the time period T t-1 and the historical trip credit label within the time period T t-1 to determine the model loss value; training and adjusting the sample model parameters according to the model loss value to obtain model parameters, and determining the sample credit evaluation model including the model parameters as the credit evaluation model.

12. A data processing device, characterized in that, including: A data acquisition module, configured to acquire the travel feature data of a target user within a time period T t and the travel feature data within a time period T t-1 ; the time period T t-1 is the previous time period of the time period T t ; t is a positive integer greater than 1; A data prediction module for inputting the trip feature data within the time period T t into a credit assessment model; the credit assessment model is obtained by jointly training a sample credit assessment model based on the trip feature data within the time period T t-1 and the historical trip credit labels within the time period T t-1 ; the historical trip credit labels within the time period T t-1 are determined based on the historical default times in the trip feature data within the time period T t-1 ; obtain the model parameters associated with the time period T t-1 in the credit assessment model, and the parameter transpose matrix corresponding to the model parameters; obtain the feature matrix corresponding to the trip feature data within the time period T t , multiply the feature matrix by the parameter transpose matrix, and obtain the predicted trip credit assessment value of the target user within the time period T t ; The credit value determination module is used to obtain the target user's credit value in the time period T t-1 The credit value of the trip within the time period T t-1 The credit value of the trip within the time period T t The predicted travel credit evaluation value within the time period T determines the target user t The travel credit value within the time period T t The travel credit value within the time period T is used to determine the target user t The time period T is the time period for the trip consumption of the ride service. t The credit value of the trip within the time period T t+1 The predicted travel credit evaluation value in the time period T jointly determines the target user t+1 The travel credit value within the time period T t+1 is the time period T t The next time period of the t+1 The predicted travel credit evaluation value within the time period T is based on the target user t+1 The trip characteristic data within the time period T t Determined by the trip characteristic data within.

13. A computer device, characterized in that, including: a processor, a memory, and a network interface; the processor is connected to the memory and the network interface, wherein the network interface is used to provide network communication functions, the memory is used to store program codes, and the processor is used to call the program codes to execute the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1-11 is executed.

Images